From 945aa1e2b90401fb5ab7571663078809970933b7 Mon Sep 17 00:00:00 2001 From: Jason Jafari Date: Sat, 15 Jun 2024 18:46:19 -0400 Subject: [PATCH] chore: bump version to 1.0.13 --- .gitignore | 1 + Readme.md | 8 + helpers/__init__.py | 17 + mlModelSaver/__init__.py | 104 +- mlModelSaver/mlModelSaver.py | 67 - .../.ipynb_checkpoints/001-checkpoint.ipynb | 284 ++ .../Advance_regression-checkpoint.ipynb | 1906 ++++++++ .../Untitled-checkpoint.ipynb | 6 + notebooks/001.ipynb | 284 ++ notebooks/Readme.md | 4 + notebooks/Untitled.ipynb | 170 + notebooks/wip/Advance_regression.ipynb | 1906 ++++++++ notebooks/wip/Advance_regression2.ipynb | 2742 ++++++++++++ notebooks/wip/Advance_regression3.ipynb | 701 +++ .../Evaluating_Binary_Classification.ipynb | 1361 ++++++ notebooks/wip/Gym.xlsx | Bin 0 -> 30987 bytes notebooks/wip/KNN.ipynb | 1708 ++++++++ notebooks/wip/KNN_adjusted.ipynb | 2308 ++++++++++ ..._Probability_and_logistic_Regression.ipynb | 1785 ++++++++ ...lity_and_logistic_Regression_holdout.ipynb | 3289 ++++++++++++++ notebooks/wip/Linear_regression_example.ipynb | 3837 +++++++++++++++++ package.json | 2 +- pytests/test_mlModelSaver.py | 27 +- requirements.txt | 96 + setup.py | 2 +- 25 files changed, 22536 insertions(+), 79 deletions(-) create mode 100644 helpers/__init__.py delete mode 100644 mlModelSaver/mlModelSaver.py create mode 100644 notebooks/.ipynb_checkpoints/001-checkpoint.ipynb create mode 100644 notebooks/.ipynb_checkpoints/Advance_regression-checkpoint.ipynb create mode 100644 notebooks/.ipynb_checkpoints/Untitled-checkpoint.ipynb create mode 100644 notebooks/001.ipynb create mode 100644 notebooks/Readme.md create mode 100644 notebooks/Untitled.ipynb create mode 100644 notebooks/wip/Advance_regression.ipynb create mode 100644 notebooks/wip/Advance_regression2.ipynb create mode 100644 notebooks/wip/Advance_regression3.ipynb create mode 100644 notebooks/wip/Evaluating_Binary_Classification.ipynb create mode 100644 notebooks/wip/Gym.xlsx create mode 100644 notebooks/wip/KNN.ipynb create mode 100644 notebooks/wip/KNN_adjusted.ipynb create mode 100644 notebooks/wip/Linear_Probability_and_logistic_Regression.ipynb create mode 100644 notebooks/wip/Linear_Probability_and_logistic_Regression_holdout.ipynb create mode 100644 notebooks/wip/Linear_regression_example.ipynb diff --git a/.gitignore b/.gitignore index 298ccf1..7c5d855 100644 --- a/.gitignore +++ b/.gitignore @@ -10,3 +10,4 @@ build/ node_modules ~~ +~~* \ No newline at end of file diff --git a/Readme.md b/Readme.md index e1cf7c5..0721709 100644 --- a/Readme.md +++ b/Readme.md @@ -35,4 +35,12 @@ python setup.py sdist bdist_wheel ## Push project ``` twine upload dist/* +``` + +## Run Jupyter notebooks +``` +export PYTHONPATH="${PYTHONPATH}:$(pwd)" +jupyter notebook \ + --notebook-dir="./notebooks" \ + --ip=0.0.0.0 --port=3225 ``` \ No newline at end of file diff --git a/helpers/__init__.py b/helpers/__init__.py new file mode 100644 index 0000000..0f43efb --- /dev/null +++ b/helpers/__init__.py @@ -0,0 +1,17 @@ +def add_constant_column(df): + """ + Adds a constant column 'const' with value 1 as the first column to the DataFrame. + + Parameters: + df (pd.DataFrame): Input DataFrame. + + Returns: + pd.DataFrame: DataFrame with the added constant column as the first column. + """ + # Create a new DataFrame to avoid modifying the original DataFrame + df_with_const = df.copy() + + # Add a constant column with value 1 + df_with_const.insert(0, 'const', 1) + + return df_with_const \ No newline at end of file diff --git a/mlModelSaver/__init__.py b/mlModelSaver/__init__.py index 7ab76cb..eb49465 100644 --- a/mlModelSaver/__init__.py +++ b/mlModelSaver/__init__.py @@ -1,2 +1,104 @@ -from mlModelSaver.mlModelSaver import MlModelSaver +import pickle +import json +import os + +from functools import partial + +def ensure_directory_exists(directory_path): + """ + Ensure that the specified directory exists. If it doesn't, create it. + + Parameters: + directory_path (str): The path of the directory to ensure exists. + """ + os.makedirs(directory_path, exist_ok=True) + + +def check_file_exists(file_path): + """ + Check if the specified file exists. + + Parameters: + file_path (str): The path of the file to check. + + Returns: + bool: True if the file exists, False otherwise. + """ + if os.path.isfile(file_path): + print(f"File '{file_path}' exists.") + return True + else: + print(f"File '{file_path}' does not exist.") + return False + + +supportedModels = { + "sm.OLS": { + "supported": True + } +} + +supportedDataType = { + "int": { + "supported": True + }, + "float": { + "supported": True + }, + "binary":{ + "supported": True + } +} + +def default_transformer(x): + return x + + +def mlModelSavePredict(self, df, typeOfPredict = 'normal'): + dfAfterTransformation = self.mlModelSaverTransformer(df) + output = [] + outputsName = self.mlModelSaverConfig.get("outputs", [{"name": "result"}]) + outputsName = [item["name"] for item in outputsName] + if typeOfPredict == 'normal': + results = self.predict(dfAfterTransformation) + for value in results: + output.append({ + outputsName[0]: value, + }) + return output + +class MlModelSaver: + + cachedModels = {} + + def __init__(self, config): + self.baseRelativePath = config.get('baseRelativePath', '.') + self.modelsFolder = f'{self.baseRelativePath}/{config.get('modelsFolder', '~~modelsFolder')}' + ensure_directory_exists(self.modelsFolder) + + + + def showSupportedModels(self): + supported_keys = [key for key, value in supportedModels.items() if value.get('supported')] + return supported_keys + + def exportModel(self, model, config): + transformer = config.get("transformer", default_transformer) + model.mlModelSaverTransformer = transformer + if "transformer" in config: + del config["transformer"] + model.mlModelSaverConfig = config + isModelSupporter = supportedModels.get( + config.get("modelType", ''), + {} + ).get("supported", False) + if not isModelSupporter: + raise ValueError(f'only {self.showSupportedModels()} are supported and {config.get("modelType", '')} is not supported') + modelName = model.mlModelSaverConfig['modelName'] + model.mlModelSavePredict = partial(mlModelSavePredict, model) + filename = f'{self.modelsFolder}/{modelName}.pkl' + pickle.dump(model, open(filename, 'wb')) + loaded_model = pickle.load(open(filename, 'rb')) + self.cachedModels[loaded_model.mlModelSaverConfig.get("modelName")] = loaded_model + return loaded_model diff --git a/mlModelSaver/mlModelSaver.py b/mlModelSaver/mlModelSaver.py deleted file mode 100644 index fd455ee..0000000 --- a/mlModelSaver/mlModelSaver.py +++ /dev/null @@ -1,67 +0,0 @@ -import pickle -import json - -supportedModels = { - "sm.OLS": { - "supported": True - } -} - -supportedDataType = { - "int": { - "supported": True - }, - "float": { - "supported": True - }, - "binary":{ - "supported": True - } -} - -class MlModelSaver: - - def __init__(self, config): - self.baseRelativePath = config.get('baseRelativePath', '.') - self.modelsFolder = config.get('modelsFolder', '~~modelsFolder') - - def showSupportedModels(self): - supported_keys = [key for key, value in supportedModels.items() if value.get('supported')] - return supported_keys - - def exportModel(self, model, config): - model.mlModelSaverConfig = config - isModelSupporter = supportedModels.get( - config.get("modelType", ''), - {} - ).get("supported", False) - if not isModelSupporter: - raise ValueError(f'only {self.showSupportedModels()} are supported and {config.get("modelType", '')} is not supported') - print(model.mlModelSaverConfig) - # modelName = config['modelName'] - # modelsConfig[modelName] = {} - # modelsConfig[modelName]['name'] = modelName - # model = config['model'] - # inputs = config['inputs'] - # output = config['output'] - # transformers = config.get('transformers', []) - # description = config['description'] - # modelsConfig[modelName]['description'] = description - # modelsConfig[modelName]['inputs'] = inputs - # if len(transformers) > 0: - # modelsConfig[modelName]['transformers'] = transformers - # modelsConfig[modelName]['output'] = output - # modelType = config.get('modelType', '') - # modelsConfig[modelName]['modelType'] = modelType - # if hasattr(model, 'customMetrics'): - # customMetrics = model.customMetrics - # modelsConfig[modelName]['customMetrics'] = customMetrics - # else: - # pass - # filename = f'{baseRelativePath}/models/{modelName}' - # pickle.dump(model, open(filename, 'wb')) - # with open(f'{baseRelativePath}/models/configs.json', "w") as outputFile: - # json.dump(modelsConfig, outputFile, indent = 4) - - # loaded_model = pickle.load(open(filename, 'rb')) - # return loaded_model \ No newline at end of file diff --git a/notebooks/.ipynb_checkpoints/001-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/001-checkpoint.ipynb new file mode 100644 index 0000000..592e13c --- /dev/null +++ b/notebooks/.ipynb_checkpoints/001-checkpoint.ipynb @@ -0,0 +1,284 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "ZbwpTMgRjUMS", + "outputId": "7fca63af-b277-4dad-bc59-44ad128cb10a" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalesTemperatureAdvertisingDiscount
01723533155.0
11985442255.0
245786584010.0
349745677020.0
465894737520.0
\n", + "
" + ], + "text/plain": [ + " Sales Temperature Advertising Discount\n", + "0 17235 33 15 5.0\n", + "1 19854 42 25 5.0\n", + "2 45786 58 40 10.0\n", + "3 49745 67 70 20.0\n", + "4 65894 73 75 20.0" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "from mlModelSaver import MlModelSaver\n", + "from helpers import add_constant_column\n", + "\n", + "mowersDf = pd.read_excel('https://www.dropbox.com/scl/fi/y2rktyoqb8rrshrnlpvw1/Mowers.xlsx?rlkey=e5bi1d8sx5hml4ylfkjv7cryh&dl=1')\n", + "mowersDf.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "SPmxr6rde0Od" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm\n", + "# Your answer" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "4jjcJF3SfX-h", + "outputId": "dac6566b-1320-48ca-db70-712d4a7ff82b" + }, + "outputs": [], + "source": [ + "modelPredictSaleByTemperatureAdvertisingDiscount = sm.OLS(\n", + " mowersDf[\"Sales\"],\n", + " add_constant_column(mowersDf[[\"Temperature\", \"Advertising\", \"Discount\"]])\n", + ")\n", + "modelPredictSaleByTemperatureAdvertisingDiscountFit = modelPredictSaleByTemperatureAdvertisingDiscount.fit()\n", + "# print(modelPredictSaleByTemperatureAdvertisingDiscountFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from mlModelSaver import MlModelSaver\n", + "mlModelSaverInstance = MlModelSaver({\n", + " \"baseRelativePath\": \"..\",\n", + " \"modelsFolder\": \"~~tmp/testModels\"\n", + "})\n", + "\n", + "loadedModel = mlModelSaverInstance.exportModel(\n", + " modelPredictSaleByTemperatureAdvertisingDiscountFit,\n", + " {\n", + " \"modelName\": \"modelPredictSaleByTemperatureAdvertisingDiscountFit\",\n", + " \"description\": \"modelPredictSaleByTemperatureAdvertisingDiscountFit\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"Temperature\",\n", + " \"type\": \"float\",\n", + " },\n", + " {\n", + " \"name\": \"Advertising\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"Discount\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"transformer\": add_constant_column,\n", + " \"outputs\": [\n", + " {\n", + " \"name\": \"Sales\",\n", + " \"type\": \"float\"\n", + " }\n", + " ]\n", + " }\n", + ")\n", + "loadedModel" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "testData = [{\n", + " 'Temperature': 42,\n", + " 'Advertising': 15,\n", + " 'Discount': 5\n", + "}]\n", + "\n", + "# Create a DataFrame from the dictionary\n", + "testDf = pd.DataFrame(testData)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 19590.46727\n", + "dtype: float64" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "modelPredictSaleByTemperatureAdvertisingDiscountFit.predict( add_constant_column(testDf))\n" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[{'Sales': 19590.467270313893}]" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "loadedModel.mlModelSavePredict(testDf)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4YoK17TkeGCw" + }, + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/.ipynb_checkpoints/Advance_regression-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Advance_regression-checkpoint.ipynb new file mode 100644 index 0000000..57b33f6 --- /dev/null +++ b/notebooks/.ipynb_checkpoints/Advance_regression-checkpoint.ipynb @@ -0,0 +1,1906 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "xwFyEsosINqT" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "pKewSQysItJ-" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "id": "Lz-DyAtNWsJR" + }, + "outputs": [], + "source": [ + "# Download Dataset from https://www.dropbox.com/scl/fi/zt2vtwhpz8ndblsxqdqx1/Salary_MIS.xlsx?rlkey=2uk6m7m9w90isv6zsynhhhpyv&st=gxumjns5&dl=1\n", + "# and add it to colab" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "id": "6rRHygNBIpgA" + }, + "outputs": [], + "source": [ + "sallaryMisDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/zt2vtwhpz8ndblsxqdqx1/Salary_MIS.xlsx?rlkey=2uk6m7m9w90isv6zsynhhhpyv&st=gxumjns5&dl=1\")" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "id": "0zM8FGMJXJ70" + }, + "outputs": [], + "source": [ + "# sallaryMisDf = pd.read_excel(\"./Salary_MIS.xlsx\")" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "wsIgDGYcXT_z" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatistics
0723.5310
1662.8610
2723.6900
3633.2400
4653.2100
...............
115663.2700
116632.8610
117783.0411
118642.9900
119663.6500
\n", + "

120 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics\n", + "0 72 3.53 1 0\n", + "1 66 2.86 1 0\n", + "2 72 3.69 0 0\n", + "3 63 3.24 0 0\n", + "4 65 3.21 0 0\n", + ".. ... ... ... ...\n", + "115 66 3.27 0 0\n", + "116 63 2.86 1 0\n", + "117 78 3.04 1 1\n", + "118 64 2.99 0 0\n", + "119 66 3.65 0 0\n", + "\n", + "[120 rows x 4 columns]" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "id": "nw2BHv7PmpVU" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(120, 4)" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "id": "mWaKOoGvmrE8" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatistics
count120.000000120.000000120.000000120.000000
mean69.8750003.2427500.3166670.341667
std6.5945770.4938340.4671270.476257
min53.0000002.4100000.0000000.000000
25%65.7500002.8050000.0000000.000000
50%70.0000003.2800000.0000000.000000
75%73.2500003.6925001.0000001.000000
max88.0000003.9800001.0000001.000000
\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics\n", + "count 120.000000 120.000000 120.000000 120.000000\n", + "mean 69.875000 3.242750 0.316667 0.341667\n", + "std 6.594577 0.493834 0.467127 0.476257\n", + "min 53.000000 2.410000 0.000000 0.000000\n", + "25% 65.750000 2.805000 0.000000 0.000000\n", + "50% 70.000000 3.280000 0.000000 0.000000\n", + "75% 73.250000 3.692500 1.000000 1.000000\n", + "max 88.000000 3.980000 1.000000 1.000000" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "w-fAHOgMmyH5" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(120, 4)" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "id": "MDlD1b-aY4Yc" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
constGPAMISStatistics
01.03.5310
11.02.8610
21.03.6900
31.03.2400
41.03.2100
...............
1151.03.2700
1161.02.8610
1171.03.0411
1181.02.9900
1191.03.6500
\n", + "

120 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " const GPA MIS Statistics\n", + "0 1.0 3.53 1 0\n", + "1 1.0 2.86 1 0\n", + "2 1.0 3.69 0 0\n", + "3 1.0 3.24 0 0\n", + "4 1.0 3.21 0 0\n", + ".. ... ... ... ...\n", + "115 1.0 3.27 0 0\n", + "116 1.0 2.86 1 0\n", + "117 1.0 3.04 1 1\n", + "118 1.0 2.99 0 0\n", + "119 1.0 3.65 0 0\n", + "\n", + "[120 rows x 4 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sm.add_constant(sallaryMisDf[[\"GPA\", \"MIS\", \"Statistics\"]])" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "id": "MjFUWOq2m6P3" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(sallaryMisDf[[\"GPA\", \"MIS\", \"Statistics\"]])\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "id": "3yteijRmnabA" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatisticsFit = salaryBasedOnGpaMisStatistics.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatisticsFit\",\n", + " \"model\": salaryBasedOnGpaMisStatisticsFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics for sallaryMisDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "id": "adXMPcPPndd1" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.795\n", + "Model: OLS Adj. R-squared: 0.790\n", + "Method: Least Squares F-statistic: 150.3\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 8.35e-40\n", + "Time: 01:24:53 Log-Likelihood: -300.92\n", + "No. Observations: 120 AIC: 609.8\n", + "Df Residuals: 116 BIC: 621.0\n", + "Df Model: 3 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 44.0072 1.860 23.662 0.000 40.324 47.691\n", + "GPA 6.6227 0.569 11.649 0.000 5.497 7.749\n", + "MIS 6.6071 0.595 11.098 0.000 5.428 7.786\n", + "Statistics 6.7309 0.591 11.391 0.000 5.561 7.901\n", + "==============================================================================\n", + "Omnibus: 1.144 Durbin-Watson: 2.164\n", + "Prob(Omnibus): 0.564 Jarque-Bera (JB): 0.758\n", + "Skew: -0.172 Prob(JB): 0.685\n", + "Kurtosis: 3.182 Cond. No. 24.4\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatisticsFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "id": "H5PP4w6epEwm" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatistics
0723.5310
1662.8610
2723.6900
3633.2400
4653.2100
...............
115663.2700
116632.8610
117783.0411
118642.9900
119663.6500
\n", + "

120 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics\n", + "0 72 3.53 1 0\n", + "1 66 2.86 1 0\n", + "2 72 3.69 0 0\n", + "3 63 3.24 0 0\n", + "4 65 3.21 0 0\n", + ".. ... ... ... ...\n", + "115 66 3.27 0 0\n", + "116 63 2.86 1 0\n", + "117 78 3.04 1 1\n", + "118 64 2.99 0 0\n", + "119 66 3.65 0 0\n", + "\n", + "[120 rows x 4 columns]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "id": "jgXOZuY4ocyq" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatisticsmisXStatisticsmisXStatistics1
0723.531000.0
1662.861000.0
2723.690000.0
3633.240000.0
4653.210000.0
.....................
115663.270000.0
116632.861000.0
117783.041111.0
118642.990000.0
119663.650000.0
\n", + "

120 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics misXStatistics misXStatistics1\n", + "0 72 3.53 1 0 0 0.0\n", + "1 66 2.86 1 0 0 0.0\n", + "2 72 3.69 0 0 0 0.0\n", + "3 63 3.24 0 0 0 0.0\n", + "4 65 3.21 0 0 0 0.0\n", + ".. ... ... ... ... ... ...\n", + "115 66 3.27 0 0 0 0.0\n", + "116 63 2.86 1 0 0 0.0\n", + "117 78 3.04 1 1 1 1.0\n", + "118 64 2.99 0 0 0 0.0\n", + "119 66 3.65 0 0 0 0.0\n", + "\n", + "[120 rows x 6 columns]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.transformers import transformersDict\n", + "sallaryMisDf[\"misXStatistics\"] = sallaryMisDf[\"MIS\"] * sallaryMisDf[\"Statistics\"]\n", + "# sallaryMisDf['misXStatistics1'] = sallaryMisDf.apply(lambda row: row['MIS'] * row['Statistics'], axis=1)\n", + "sallaryMisDf['misXStatistics1'] = sallaryMisDf.apply(transformersDict.get('MIS_X_Statistics'), axis=1)\n", + "\n", + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "id": "FwXG9Q54pbne" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"misXStatistics1\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "id": "w7hob-54phqv" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit = salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction MIS * Statistics for sallaryMisDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"misXStatistics\",\n", + " \"transformer\": \"MIS_X_Statistics\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "NMNYYAespkAn" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.810\n", + "Model: OLS Adj. R-squared: 0.803\n", + "Method: Least Squares F-statistic: 122.2\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.87e-40\n", + "Time: 01:24:53 Log-Likelihood: -296.63\n", + "No. Observations: 120 AIC: 603.3\n", + "Df Residuals: 115 BIC: 617.2\n", + "Df Model: 4 \n", + "Covariance Type: nonrobust \n", + "===================================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "-----------------------------------------------------------------------------------\n", + "const 44.0993 1.803 24.464 0.000 40.529 47.670\n", + "GPA 6.7109 0.552 12.162 0.000 5.618 7.804\n", + "MIS 5.3250 0.725 7.343 0.000 3.889 6.761\n", + "Statistics 5.5350 0.704 7.861 0.000 4.140 6.930\n", + "misXStatistics1 3.4915 1.196 2.918 0.004 1.122 5.861\n", + "==============================================================================\n", + "Omnibus: 0.396 Durbin-Watson: 2.073\n", + "Prob(Omnibus): 0.820 Jarque-Bera (JB): 0.109\n", + "Skew: -0.013 Prob(JB): 0.947\n", + "Kurtosis: 3.146 Cond. No. 24.4\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "id": "ZnQnXfdRv7dP" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatisticsmisXStatisticsmisXStatistics1misXGpa
0723.531000.03.53
1662.861000.02.86
2723.690000.00.00
3633.240000.00.00
4653.210000.00.00
........................
115663.270000.00.00
116632.861000.02.86
117783.041111.03.04
118642.990000.00.00
119663.650000.00.00
\n", + "

120 rows × 7 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics misXStatistics misXStatistics1 misXGpa\n", + "0 72 3.53 1 0 0 0.0 3.53\n", + "1 66 2.86 1 0 0 0.0 2.86\n", + "2 72 3.69 0 0 0 0.0 0.00\n", + "3 63 3.24 0 0 0 0.0 0.00\n", + "4 65 3.21 0 0 0 0.0 0.00\n", + ".. ... ... ... ... ... ... ...\n", + "115 66 3.27 0 0 0 0.0 0.00\n", + "116 63 2.86 1 0 0 0.0 2.86\n", + "117 78 3.04 1 1 1 1.0 3.04\n", + "118 64 2.99 0 0 0 0.0 0.00\n", + "119 66 3.65 0 0 0 0.0 0.00\n", + "\n", + "[120 rows x 7 columns]" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# sallaryMisDf['misXGpa'] = sallaryMisDf.apply(lambda row: row['MIS'] * row['GPA'], axis=1)\n", + "sallaryMisDf['misXGpa'] = sallaryMisDf.apply(transformersDict.get('MIS_X_GPA'), axis=1)\n", + "\n", + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "id": "6CjgMmDAwEPw" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXGpa = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"misXGpa\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "id": "VmYH7tHmwMzm" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_misXGpa.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXGpa for sallaryMisDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"misXGpa\",\n", + " \"transformer\": \"MIS_X_GPA\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "id": "rL8pX5dTwP8H" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.795\n", + "Model: OLS Adj. R-squared: 0.788\n", + "Method: Least Squares F-statistic: 111.8\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.11e-38\n", + "Time: 01:24:53 Log-Likelihood: -300.91\n", + "No. Observations: 120 AIC: 611.8\n", + "Df Residuals: 115 BIC: 625.8\n", + "Df Model: 4 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 44.1653 2.307 19.142 0.000 39.595 48.736\n", + "GPA 6.5737 0.709 9.278 0.000 5.170 7.977\n", + "MIS 6.1605 3.873 1.591 0.114 -1.511 13.832\n", + "Statistics 6.7350 0.594 11.330 0.000 5.558 7.912\n", + "misXGpa 0.1381 1.184 0.117 0.907 -2.206 2.483\n", + "==============================================================================\n", + "Omnibus: 1.114 Durbin-Watson: 2.167\n", + "Prob(Omnibus): 0.573 Jarque-Bera (JB): 0.727\n", + "Skew: -0.167 Prob(JB): 0.695\n", + "Kurtosis: 3.185 Cond. No. 57.3\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "id": "z-idrSTJwi90" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatisticsmisXStatisticsmisXStatistics1misXGpastatisticsXGpa
0723.531000.03.530.00
1662.861000.02.860.00
2723.690000.00.000.00
3633.240000.00.000.00
4653.210000.00.000.00
...........................
115663.270000.00.000.00
116632.861000.02.860.00
117783.041111.03.043.04
118642.990000.00.000.00
119663.650000.00.000.00
\n", + "

120 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics misXStatistics misXStatistics1 misXGpa \\\n", + "0 72 3.53 1 0 0 0.0 3.53 \n", + "1 66 2.86 1 0 0 0.0 2.86 \n", + "2 72 3.69 0 0 0 0.0 0.00 \n", + "3 63 3.24 0 0 0 0.0 0.00 \n", + "4 65 3.21 0 0 0 0.0 0.00 \n", + ".. ... ... ... ... ... ... ... \n", + "115 66 3.27 0 0 0 0.0 0.00 \n", + "116 63 2.86 1 0 0 0.0 2.86 \n", + "117 78 3.04 1 1 1 1.0 3.04 \n", + "118 64 2.99 0 0 0 0.0 0.00 \n", + "119 66 3.65 0 0 0 0.0 0.00 \n", + "\n", + " statisticsXGpa \n", + "0 0.00 \n", + "1 0.00 \n", + "2 0.00 \n", + "3 0.00 \n", + "4 0.00 \n", + ".. ... \n", + "115 0.00 \n", + "116 0.00 \n", + "117 3.04 \n", + "118 0.00 \n", + "119 0.00 \n", + "\n", + "[120 rows x 8 columns]" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# sallaryMisDf['statisticsXGpa'] = sallaryMisDf.apply(lambda row: row['Statistics'] * row['GPA'], axis=1)\n", + "sallaryMisDf['statisticsXGpa'] = sallaryMisDf.apply(transformersDict.get('GPA_X_Statistics'), axis=1)\n", + "\n", + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "id": "im61d1RUwpQJ" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpa = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"statisticsXGpa\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "id": "WZ9eNcnMwvB3" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpa.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXGpa for statisticsXGpa\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"statisticsXGpa\",\n", + " \"transformer\": \"GPA_X_Statistics\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "id": "P5MFMA4NwzcE" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.803\n", + "Model: OLS Adj. R-squared: 0.796\n", + "Method: Least Squares F-statistic: 116.9\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.44e-39\n", + "Time: 01:24:53 Log-Likelihood: -298.78\n", + "No. Observations: 120 AIC: 607.6\n", + "Df Residuals: 115 BIC: 621.5\n", + "Df Model: 4 \n", + "Covariance Type: nonrobust \n", + "==================================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "----------------------------------------------------------------------------------\n", + "const 41.2856 2.267 18.215 0.000 36.796 45.775\n", + "GPA 7.4828 0.701 10.674 0.000 6.094 8.871\n", + "MIS 6.5400 0.588 11.118 0.000 5.375 7.705\n", + "Statistics 14.5988 3.891 3.752 0.000 6.892 22.306\n", + "statisticsXGpa -2.3890 1.168 -2.045 0.043 -4.703 -0.075\n", + "==============================================================================\n", + "Omnibus: 0.348 Durbin-Watson: 2.118\n", + "Prob(Omnibus): 0.840 Jarque-Bera (JB): 0.149\n", + "Skew: -0.079 Prob(JB): 0.928\n", + "Kurtosis: 3.068 Cond. No. 59.1\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "id": "gJGNzwfdw-mg" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpa = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"misXStatistics\",\n", + " \"misXGpa\",\n", + " \"statisticsXGpa\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "NPGVE5cFxW-q" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpa.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXStatistics, misXGpa, statisticsXGpa\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"misXStatistics\",\n", + " \"transformer\": \"MIS_X_Statistics\"\n", + " },\n", + " {\n", + " \"name\": \"misXGpa\",\n", + " \"transformer\": \"MIS_X_GPA\"\n", + " },\n", + " {\n", + " \"name\": \"statisticsXGpa\",\n", + " \"transformer\": \"GPA_X_Statistics\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "id": "qRpqQP9LxaO-" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.815\n", + "Model: OLS Adj. R-squared: 0.805\n", + "Method: Least Squares F-statistic: 83.09\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 4.15e-39\n", + "Time: 01:24:53 Log-Likelihood: -294.81\n", + "No. Observations: 120 AIC: 603.6\n", + "Df Residuals: 113 BIC: 623.1\n", + "Df Model: 6 \n", + "Covariance Type: nonrobust \n", + "==================================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "----------------------------------------------------------------------------------\n", + "const 41.7092 2.481 16.809 0.000 36.793 46.625\n", + "GPA 7.4604 0.769 9.708 0.000 5.938 8.983\n", + "MIS 5.1669 3.757 1.375 0.172 -2.276 12.610\n", + "Statistics 12.6641 3.923 3.229 0.002 4.893 20.435\n", + "misXStatistics 3.3076 1.204 2.747 0.007 0.922 5.693\n", + "misXGpa 0.0512 1.158 0.044 0.965 -2.243 2.345\n", + "statisticsXGpa -2.1451 1.158 -1.853 0.066 -4.439 0.148\n", + "==============================================================================\n", + "Omnibus: 0.398 Durbin-Watson: 2.028\n", + "Prob(Omnibus): 0.820 Jarque-Bera (JB): 0.148\n", + "Skew: 0.067 Prob(JB): 0.928\n", + "Kurtosis: 3.108 Cond. No. 63.5\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/.ipynb_checkpoints/Untitled-checkpoint.ipynb b/notebooks/.ipynb_checkpoints/Untitled-checkpoint.ipynb new file mode 100644 index 0000000..363fcab --- /dev/null +++ b/notebooks/.ipynb_checkpoints/Untitled-checkpoint.ipynb @@ -0,0 +1,6 @@ +{ + "cells": [], + "metadata": {}, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/001.ipynb b/notebooks/001.ipynb new file mode 100644 index 0000000..592e13c --- /dev/null +++ b/notebooks/001.ipynb @@ -0,0 +1,284 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "ZbwpTMgRjUMS", + "outputId": "7fca63af-b277-4dad-bc59-44ad128cb10a" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalesTemperatureAdvertisingDiscount
01723533155.0
11985442255.0
245786584010.0
349745677020.0
465894737520.0
\n", + "
" + ], + "text/plain": [ + " Sales Temperature Advertising Discount\n", + "0 17235 33 15 5.0\n", + "1 19854 42 25 5.0\n", + "2 45786 58 40 10.0\n", + "3 49745 67 70 20.0\n", + "4 65894 73 75 20.0" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "from mlModelSaver import MlModelSaver\n", + "from helpers import add_constant_column\n", + "\n", + "mowersDf = pd.read_excel('https://www.dropbox.com/scl/fi/y2rktyoqb8rrshrnlpvw1/Mowers.xlsx?rlkey=e5bi1d8sx5hml4ylfkjv7cryh&dl=1')\n", + "mowersDf.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "SPmxr6rde0Od" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm\n", + "# Your answer" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "4jjcJF3SfX-h", + "outputId": "dac6566b-1320-48ca-db70-712d4a7ff82b" + }, + "outputs": [], + "source": [ + "modelPredictSaleByTemperatureAdvertisingDiscount = sm.OLS(\n", + " mowersDf[\"Sales\"],\n", + " add_constant_column(mowersDf[[\"Temperature\", \"Advertising\", \"Discount\"]])\n", + ")\n", + "modelPredictSaleByTemperatureAdvertisingDiscountFit = modelPredictSaleByTemperatureAdvertisingDiscount.fit()\n", + "# print(modelPredictSaleByTemperatureAdvertisingDiscountFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from mlModelSaver import MlModelSaver\n", + "mlModelSaverInstance = MlModelSaver({\n", + " \"baseRelativePath\": \"..\",\n", + " \"modelsFolder\": \"~~tmp/testModels\"\n", + "})\n", + "\n", + "loadedModel = mlModelSaverInstance.exportModel(\n", + " modelPredictSaleByTemperatureAdvertisingDiscountFit,\n", + " {\n", + " \"modelName\": \"modelPredictSaleByTemperatureAdvertisingDiscountFit\",\n", + " \"description\": \"modelPredictSaleByTemperatureAdvertisingDiscountFit\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"Temperature\",\n", + " \"type\": \"float\",\n", + " },\n", + " {\n", + " \"name\": \"Advertising\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"Discount\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"transformer\": add_constant_column,\n", + " \"outputs\": [\n", + " {\n", + " \"name\": \"Sales\",\n", + " \"type\": \"float\"\n", + " }\n", + " ]\n", + " }\n", + ")\n", + "loadedModel" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "\n", + "testData = [{\n", + " 'Temperature': 42,\n", + " 'Advertising': 15,\n", + " 'Discount': 5\n", + "}]\n", + "\n", + "# Create a DataFrame from the dictionary\n", + "testDf = pd.DataFrame(testData)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 19590.46727\n", + "dtype: float64" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "modelPredictSaleByTemperatureAdvertisingDiscountFit.predict( add_constant_column(testDf))\n" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[{'Sales': 19590.467270313893}]" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "loadedModel.mlModelSavePredict(testDf)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4YoK17TkeGCw" + }, + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/Readme.md b/notebooks/Readme.md new file mode 100644 index 0000000..4ce4e63 --- /dev/null +++ b/notebooks/Readme.md @@ -0,0 +1,4 @@ +``` +pip install jupyterlab +pip install notebook +``` \ No newline at end of file diff --git a/notebooks/Untitled.ipynb b/notebooks/Untitled.ipynb new file mode 100644 index 0000000..988ac5a --- /dev/null +++ b/notebooks/Untitled.ipynb @@ -0,0 +1,170 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 7, + "id": "1a33d2cd-5d9f-40a6-bc28-5b2e8026226c", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ABC
0147
\n", + "
" + ], + "text/plain": [ + " A B C\n", + "0 1 4 7" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "\n", + "# Example DataFrame\n", + "data = {\n", + " 'A': [1, 2, 3],\n", + " 'B': [4, 5, 6],\n", + " 'C': [7, 8, 9]\n", + "}\n", + "df = pd.DataFrame(data)\n", + "\n", + "# Create a new DataFrame with only the first row using .iloc[0:1]\n", + "first_row_df = df.iloc[0:1]\n", + "first_row_df" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "51c38582-bccf-4e03-918f-9d65bbec1dda", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "New DataFrame with First Row:\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ABC
0147
\n", + "
" + ], + "text/plain": [ + " A B C\n", + "0 1 4 7" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Create a new DataFrame with only the first row using .head(1)\n", + "first_row_df = df.head(1)\n", + "\n", + "print(\"New DataFrame with First Row:\")\n", + "first_row_df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "664e8423-f560-4c23-8a94-242f8ec283cd", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/wip/Advance_regression.ipynb b/notebooks/wip/Advance_regression.ipynb new file mode 100644 index 0000000..57b33f6 --- /dev/null +++ b/notebooks/wip/Advance_regression.ipynb @@ -0,0 +1,1906 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "xwFyEsosINqT" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "pKewSQysItJ-" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "id": "Lz-DyAtNWsJR" + }, + "outputs": [], + "source": [ + "# Download Dataset from https://www.dropbox.com/scl/fi/zt2vtwhpz8ndblsxqdqx1/Salary_MIS.xlsx?rlkey=2uk6m7m9w90isv6zsynhhhpyv&st=gxumjns5&dl=1\n", + "# and add it to colab" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "id": "6rRHygNBIpgA" + }, + "outputs": [], + "source": [ + "sallaryMisDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/zt2vtwhpz8ndblsxqdqx1/Salary_MIS.xlsx?rlkey=2uk6m7m9w90isv6zsynhhhpyv&st=gxumjns5&dl=1\")" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "id": "0zM8FGMJXJ70" + }, + "outputs": [], + "source": [ + "# sallaryMisDf = pd.read_excel(\"./Salary_MIS.xlsx\")" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "wsIgDGYcXT_z" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatistics
0723.5310
1662.8610
2723.6900
3633.2400
4653.2100
...............
115663.2700
116632.8610
117783.0411
118642.9900
119663.6500
\n", + "

120 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics\n", + "0 72 3.53 1 0\n", + "1 66 2.86 1 0\n", + "2 72 3.69 0 0\n", + "3 63 3.24 0 0\n", + "4 65 3.21 0 0\n", + ".. ... ... ... ...\n", + "115 66 3.27 0 0\n", + "116 63 2.86 1 0\n", + "117 78 3.04 1 1\n", + "118 64 2.99 0 0\n", + "119 66 3.65 0 0\n", + "\n", + "[120 rows x 4 columns]" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "id": "nw2BHv7PmpVU" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(120, 4)" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "id": "mWaKOoGvmrE8" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatistics
count120.000000120.000000120.000000120.000000
mean69.8750003.2427500.3166670.341667
std6.5945770.4938340.4671270.476257
min53.0000002.4100000.0000000.000000
25%65.7500002.8050000.0000000.000000
50%70.0000003.2800000.0000000.000000
75%73.2500003.6925001.0000001.000000
max88.0000003.9800001.0000001.000000
\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics\n", + "count 120.000000 120.000000 120.000000 120.000000\n", + "mean 69.875000 3.242750 0.316667 0.341667\n", + "std 6.594577 0.493834 0.467127 0.476257\n", + "min 53.000000 2.410000 0.000000 0.000000\n", + "25% 65.750000 2.805000 0.000000 0.000000\n", + "50% 70.000000 3.280000 0.000000 0.000000\n", + "75% 73.250000 3.692500 1.000000 1.000000\n", + "max 88.000000 3.980000 1.000000 1.000000" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "w-fAHOgMmyH5" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(120, 4)" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "id": "MDlD1b-aY4Yc" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
constGPAMISStatistics
01.03.5310
11.02.8610
21.03.6900
31.03.2400
41.03.2100
...............
1151.03.2700
1161.02.8610
1171.03.0411
1181.02.9900
1191.03.6500
\n", + "

120 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " const GPA MIS Statistics\n", + "0 1.0 3.53 1 0\n", + "1 1.0 2.86 1 0\n", + "2 1.0 3.69 0 0\n", + "3 1.0 3.24 0 0\n", + "4 1.0 3.21 0 0\n", + ".. ... ... ... ...\n", + "115 1.0 3.27 0 0\n", + "116 1.0 2.86 1 0\n", + "117 1.0 3.04 1 1\n", + "118 1.0 2.99 0 0\n", + "119 1.0 3.65 0 0\n", + "\n", + "[120 rows x 4 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sm.add_constant(sallaryMisDf[[\"GPA\", \"MIS\", \"Statistics\"]])" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "id": "MjFUWOq2m6P3" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(sallaryMisDf[[\"GPA\", \"MIS\", \"Statistics\"]])\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "id": "3yteijRmnabA" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatisticsFit = salaryBasedOnGpaMisStatistics.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatisticsFit\",\n", + " \"model\": salaryBasedOnGpaMisStatisticsFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics for sallaryMisDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "id": "adXMPcPPndd1" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.795\n", + "Model: OLS Adj. R-squared: 0.790\n", + "Method: Least Squares F-statistic: 150.3\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 8.35e-40\n", + "Time: 01:24:53 Log-Likelihood: -300.92\n", + "No. Observations: 120 AIC: 609.8\n", + "Df Residuals: 116 BIC: 621.0\n", + "Df Model: 3 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 44.0072 1.860 23.662 0.000 40.324 47.691\n", + "GPA 6.6227 0.569 11.649 0.000 5.497 7.749\n", + "MIS 6.6071 0.595 11.098 0.000 5.428 7.786\n", + "Statistics 6.7309 0.591 11.391 0.000 5.561 7.901\n", + "==============================================================================\n", + "Omnibus: 1.144 Durbin-Watson: 2.164\n", + "Prob(Omnibus): 0.564 Jarque-Bera (JB): 0.758\n", + "Skew: -0.172 Prob(JB): 0.685\n", + "Kurtosis: 3.182 Cond. No. 24.4\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatisticsFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "id": "H5PP4w6epEwm" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatistics
0723.5310
1662.8610
2723.6900
3633.2400
4653.2100
...............
115663.2700
116632.8610
117783.0411
118642.9900
119663.6500
\n", + "

120 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics\n", + "0 72 3.53 1 0\n", + "1 66 2.86 1 0\n", + "2 72 3.69 0 0\n", + "3 63 3.24 0 0\n", + "4 65 3.21 0 0\n", + ".. ... ... ... ...\n", + "115 66 3.27 0 0\n", + "116 63 2.86 1 0\n", + "117 78 3.04 1 1\n", + "118 64 2.99 0 0\n", + "119 66 3.65 0 0\n", + "\n", + "[120 rows x 4 columns]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "id": "jgXOZuY4ocyq" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatisticsmisXStatisticsmisXStatistics1
0723.531000.0
1662.861000.0
2723.690000.0
3633.240000.0
4653.210000.0
.....................
115663.270000.0
116632.861000.0
117783.041111.0
118642.990000.0
119663.650000.0
\n", + "

120 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics misXStatistics misXStatistics1\n", + "0 72 3.53 1 0 0 0.0\n", + "1 66 2.86 1 0 0 0.0\n", + "2 72 3.69 0 0 0 0.0\n", + "3 63 3.24 0 0 0 0.0\n", + "4 65 3.21 0 0 0 0.0\n", + ".. ... ... ... ... ... ...\n", + "115 66 3.27 0 0 0 0.0\n", + "116 63 2.86 1 0 0 0.0\n", + "117 78 3.04 1 1 1 1.0\n", + "118 64 2.99 0 0 0 0.0\n", + "119 66 3.65 0 0 0 0.0\n", + "\n", + "[120 rows x 6 columns]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.transformers import transformersDict\n", + "sallaryMisDf[\"misXStatistics\"] = sallaryMisDf[\"MIS\"] * sallaryMisDf[\"Statistics\"]\n", + "# sallaryMisDf['misXStatistics1'] = sallaryMisDf.apply(lambda row: row['MIS'] * row['Statistics'], axis=1)\n", + "sallaryMisDf['misXStatistics1'] = sallaryMisDf.apply(transformersDict.get('MIS_X_Statistics'), axis=1)\n", + "\n", + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "id": "FwXG9Q54pbne" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"misXStatistics1\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "id": "w7hob-54phqv" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit = salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction MIS * Statistics for sallaryMisDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"misXStatistics\",\n", + " \"transformer\": \"MIS_X_Statistics\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "NMNYYAespkAn" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.810\n", + "Model: OLS Adj. R-squared: 0.803\n", + "Method: Least Squares F-statistic: 122.2\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.87e-40\n", + "Time: 01:24:53 Log-Likelihood: -296.63\n", + "No. Observations: 120 AIC: 603.3\n", + "Df Residuals: 115 BIC: 617.2\n", + "Df Model: 4 \n", + "Covariance Type: nonrobust \n", + "===================================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "-----------------------------------------------------------------------------------\n", + "const 44.0993 1.803 24.464 0.000 40.529 47.670\n", + "GPA 6.7109 0.552 12.162 0.000 5.618 7.804\n", + "MIS 5.3250 0.725 7.343 0.000 3.889 6.761\n", + "Statistics 5.5350 0.704 7.861 0.000 4.140 6.930\n", + "misXStatistics1 3.4915 1.196 2.918 0.004 1.122 5.861\n", + "==============================================================================\n", + "Omnibus: 0.396 Durbin-Watson: 2.073\n", + "Prob(Omnibus): 0.820 Jarque-Bera (JB): 0.109\n", + "Skew: -0.013 Prob(JB): 0.947\n", + "Kurtosis: 3.146 Cond. No. 24.4\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_misXStatisticsFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "id": "ZnQnXfdRv7dP" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatisticsmisXStatisticsmisXStatistics1misXGpa
0723.531000.03.53
1662.861000.02.86
2723.690000.00.00
3633.240000.00.00
4653.210000.00.00
........................
115663.270000.00.00
116632.861000.02.86
117783.041111.03.04
118642.990000.00.00
119663.650000.00.00
\n", + "

120 rows × 7 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics misXStatistics misXStatistics1 misXGpa\n", + "0 72 3.53 1 0 0 0.0 3.53\n", + "1 66 2.86 1 0 0 0.0 2.86\n", + "2 72 3.69 0 0 0 0.0 0.00\n", + "3 63 3.24 0 0 0 0.0 0.00\n", + "4 65 3.21 0 0 0 0.0 0.00\n", + ".. ... ... ... ... ... ... ...\n", + "115 66 3.27 0 0 0 0.0 0.00\n", + "116 63 2.86 1 0 0 0.0 2.86\n", + "117 78 3.04 1 1 1 1.0 3.04\n", + "118 64 2.99 0 0 0 0.0 0.00\n", + "119 66 3.65 0 0 0 0.0 0.00\n", + "\n", + "[120 rows x 7 columns]" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# sallaryMisDf['misXGpa'] = sallaryMisDf.apply(lambda row: row['MIS'] * row['GPA'], axis=1)\n", + "sallaryMisDf['misXGpa'] = sallaryMisDf.apply(transformersDict.get('MIS_X_GPA'), axis=1)\n", + "\n", + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "id": "6CjgMmDAwEPw" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXGpa = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"misXGpa\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "id": "VmYH7tHmwMzm" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_misXGpa.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXGpa for sallaryMisDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"misXGpa\",\n", + " \"transformer\": \"MIS_X_GPA\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "id": "rL8pX5dTwP8H" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.795\n", + "Model: OLS Adj. R-squared: 0.788\n", + "Method: Least Squares F-statistic: 111.8\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.11e-38\n", + "Time: 01:24:53 Log-Likelihood: -300.91\n", + "No. Observations: 120 AIC: 611.8\n", + "Df Residuals: 115 BIC: 625.8\n", + "Df Model: 4 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 44.1653 2.307 19.142 0.000 39.595 48.736\n", + "GPA 6.5737 0.709 9.278 0.000 5.170 7.977\n", + "MIS 6.1605 3.873 1.591 0.114 -1.511 13.832\n", + "Statistics 6.7350 0.594 11.330 0.000 5.558 7.912\n", + "misXGpa 0.1381 1.184 0.117 0.907 -2.206 2.483\n", + "==============================================================================\n", + "Omnibus: 1.114 Durbin-Watson: 2.167\n", + "Prob(Omnibus): 0.573 Jarque-Bera (JB): 0.727\n", + "Skew: -0.167 Prob(JB): 0.695\n", + "Kurtosis: 3.185 Cond. No. 57.3\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_misXGpaFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "id": "z-idrSTJwi90" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SalaryGPAMISStatisticsmisXStatisticsmisXStatistics1misXGpastatisticsXGpa
0723.531000.03.530.00
1662.861000.02.860.00
2723.690000.00.000.00
3633.240000.00.000.00
4653.210000.00.000.00
...........................
115663.270000.00.000.00
116632.861000.02.860.00
117783.041111.03.043.04
118642.990000.00.000.00
119663.650000.00.000.00
\n", + "

120 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " Salary GPA MIS Statistics misXStatistics misXStatistics1 misXGpa \\\n", + "0 72 3.53 1 0 0 0.0 3.53 \n", + "1 66 2.86 1 0 0 0.0 2.86 \n", + "2 72 3.69 0 0 0 0.0 0.00 \n", + "3 63 3.24 0 0 0 0.0 0.00 \n", + "4 65 3.21 0 0 0 0.0 0.00 \n", + ".. ... ... ... ... ... ... ... \n", + "115 66 3.27 0 0 0 0.0 0.00 \n", + "116 63 2.86 1 0 0 0.0 2.86 \n", + "117 78 3.04 1 1 1 1.0 3.04 \n", + "118 64 2.99 0 0 0 0.0 0.00 \n", + "119 66 3.65 0 0 0 0.0 0.00 \n", + "\n", + " statisticsXGpa \n", + "0 0.00 \n", + "1 0.00 \n", + "2 0.00 \n", + "3 0.00 \n", + "4 0.00 \n", + ".. ... \n", + "115 0.00 \n", + "116 0.00 \n", + "117 3.04 \n", + "118 0.00 \n", + "119 0.00 \n", + "\n", + "[120 rows x 8 columns]" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# sallaryMisDf['statisticsXGpa'] = sallaryMisDf.apply(lambda row: row['Statistics'] * row['GPA'], axis=1)\n", + "sallaryMisDf['statisticsXGpa'] = sallaryMisDf.apply(transformersDict.get('GPA_X_Statistics'), axis=1)\n", + "\n", + "sallaryMisDf" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "id": "im61d1RUwpQJ" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpa = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"statisticsXGpa\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "id": "WZ9eNcnMwvB3" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpa.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXGpa for statisticsXGpa\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"statisticsXGpa\",\n", + " \"transformer\": \"GPA_X_Statistics\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "id": "P5MFMA4NwzcE" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.803\n", + "Model: OLS Adj. R-squared: 0.796\n", + "Method: Least Squares F-statistic: 116.9\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.44e-39\n", + "Time: 01:24:53 Log-Likelihood: -298.78\n", + "No. Observations: 120 AIC: 607.6\n", + "Df Residuals: 115 BIC: 621.5\n", + "Df Model: 4 \n", + "Covariance Type: nonrobust \n", + "==================================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "----------------------------------------------------------------------------------\n", + "const 41.2856 2.267 18.215 0.000 36.796 45.775\n", + "GPA 7.4828 0.701 10.674 0.000 6.094 8.871\n", + "MIS 6.5400 0.588 11.118 0.000 5.375 7.705\n", + "Statistics 14.5988 3.891 3.752 0.000 6.892 22.306\n", + "statisticsXGpa -2.3890 1.168 -2.045 0.043 -4.703 -0.075\n", + "==============================================================================\n", + "Omnibus: 0.348 Durbin-Watson: 2.118\n", + "Prob(Omnibus): 0.840 Jarque-Bera (JB): 0.149\n", + "Skew: -0.079 Prob(JB): 0.928\n", + "Kurtosis: 3.068 Cond. No. 59.1\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_statisticsXGpaFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "id": "gJGNzwfdw-mg" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpa = sm.OLS(\n", + " sallaryMisDf[\"Salary\"],\n", + " sm.add_constant(\n", + " sallaryMisDf[[\n", + " \"GPA\",\n", + " \"MIS\",\n", + " \"Statistics\",\n", + " \"misXStatistics\",\n", + " \"misXGpa\",\n", + " \"statisticsXGpa\"\n", + " ]]\n", + " )\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "NPGVE5cFxW-q" + }, + "outputs": [], + "source": [ + "salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit = salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpa.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit\",\n", + " \"model\": salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit,\n", + " \"description\": \"Predict Salary based on GPA MIS Statistics and interaction misXStatistics, misXGpa, statisticsXGpa\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"GPA\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"MIS\",\n", + " \"type\": \"binary\"\n", + " },\n", + " {\n", + " \"name\": \"Statistics\",\n", + " \"type\": \"binary\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"misXStatistics\",\n", + " \"transformer\": \"MIS_X_Statistics\"\n", + " },\n", + " {\n", + " \"name\": \"misXGpa\",\n", + " \"transformer\": \"MIS_X_GPA\"\n", + " },\n", + " {\n", + " \"name\": \"statisticsXGpa\",\n", + " \"transformer\": \"GPA_X_Statistics\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Salary\",\n", + " \"type\": \"int\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "id": "qRpqQP9LxaO-" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Salary R-squared: 0.815\n", + "Model: OLS Adj. R-squared: 0.805\n", + "Method: Least Squares F-statistic: 83.09\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 4.15e-39\n", + "Time: 01:24:53 Log-Likelihood: -294.81\n", + "No. Observations: 120 AIC: 603.6\n", + "Df Residuals: 113 BIC: 623.1\n", + "Df Model: 6 \n", + "Covariance Type: nonrobust \n", + "==================================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "----------------------------------------------------------------------------------\n", + "const 41.7092 2.481 16.809 0.000 36.793 46.625\n", + "GPA 7.4604 0.769 9.708 0.000 5.938 8.983\n", + "MIS 5.1669 3.757 1.375 0.172 -2.276 12.610\n", + "Statistics 12.6641 3.923 3.229 0.002 4.893 20.435\n", + "misXStatistics 3.3076 1.204 2.747 0.007 0.922 5.693\n", + "misXGpa 0.0512 1.158 0.044 0.965 -2.243 2.345\n", + "statisticsXGpa -2.1451 1.158 -1.853 0.066 -4.439 0.148\n", + "==============================================================================\n", + "Omnibus: 0.398 Durbin-Watson: 2.028\n", + "Prob(Omnibus): 0.820 Jarque-Bera (JB): 0.148\n", + "Skew: 0.067 Prob(JB): 0.928\n", + "Kurtosis: 3.108 Cond. No. 63.5\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "print(salaryBasedOnGpaMisStatistics_Transfoms_misXStatistics_misXGpa_statisticsXGpaFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/wip/Advance_regression2.ipynb b/notebooks/wip/Advance_regression2.ipynb new file mode 100644 index 0000000..5d1f149 --- /dev/null +++ b/notebooks/wip/Advance_regression2.ipynb @@ -0,0 +1,2742 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "xwFyEsosINqT" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "pKewSQysItJ-" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "id": "Lz-DyAtNWsJR" + }, + "outputs": [], + "source": [ + "# Download Dataset from https://www.dropbox.com/scl/fi/v7c1c8a3cnncuv1fo28es/Wages.xlsx?rlkey=vli12nwph687hvn9jskgf73a1&st=s862pfm6&dl=1\n", + "# and add it to colab" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "id": "0zM8FGMJXJ70" + }, + "outputs": [], + "source": [ + "# wagesDf = pd.read_excel(\"./Wages.xlsx\")\n", + "wagesDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/v7c1c8a3cnncuv1fo28es/Wages.xlsx?rlkey=vli12nwph687hvn9jskgf73a1&st=s862pfm6&dl=1\")" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "wsIgDGYcXT_z", + "outputId": "ea121018-2592-4214-8f58-69fa61183858" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAge
017.541276
120.931061
212.94875
319.34638
424.121259
............
7525.641474
7638.772141
7721.871575
7827.542046
7923.661249
\n", + "

80 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age\n", + "0 17.54 12 76\n", + "1 20.93 10 61\n", + "2 12.94 8 75\n", + "3 19.34 6 38\n", + "4 24.12 12 59\n", + ".. ... ... ...\n", + "75 25.64 14 74\n", + "76 38.77 21 41\n", + "77 21.87 15 75\n", + "78 27.54 20 46\n", + "79 23.66 12 49\n", + "\n", + "[80 rows x 3 columns]" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "nw2BHv7PmpVU", + "outputId": "a3caf5ac-528c-4a56-d08a-801470d6bbb4" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "240" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "wagesDf.size" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "mWaKOoGvmrE8", + "outputId": "cda584b5-2ca4-4133-ee84-67ac1531929c" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAge
count80.00000080.00000080.000000
mean24.93050013.85000049.487500
std7.4799824.01610717.213473
min6.9300006.00000018.000000
25%19.14500010.00000034.750000
50%24.98000014.00000051.000000
75%30.57250017.00000065.250000
max43.44000022.00000077.000000
\n", + "
" + ], + "text/plain": [ + " Wage Educ Age\n", + "count 80.000000 80.000000 80.000000\n", + "mean 24.930500 13.850000 49.487500\n", + "std 7.479982 4.016107 17.213473\n", + "min 6.930000 6.000000 18.000000\n", + "25% 19.145000 10.000000 34.750000\n", + "50% 24.980000 14.000000 51.000000\n", + "75% 30.572500 17.000000 65.250000\n", + "max 43.440000 22.000000 77.000000" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "wagesDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "w-fAHOgMmyH5", + "outputId": "4fc1e799-4d23-42f4-9947-a2ee7ccef909" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(80, 3)" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "wagesDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "H15Y1sg61e5Z" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "id": "-4_3Xd1i1cPa", + "outputId": "c78650e1-2817-4a19-fce3-95f81ac3945b" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "fig1 = plt.figure(\n", + " figsize=(8, 8)\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 472 + }, + "id": "RmM8cJp41hSB", + "outputId": "d6e2108c-97c7-41c5-b551-7fd2da0c8c77" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plt.scatter(\n", + " wagesDf[\"Educ\"],\n", + " wagesDf[\"Wage\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "\n", + "plt.title('Education Level vs. Wage with OLS Regression')\n", + "plt.xlabel('Education Level(yr)')\n", + "plt.ylabel('Wage K')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "uonOqiSW14Qq", + "outputId": "ffde8bb6-939e-49a5-ad29-269381731c58" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Wage R-squared: 0.607\n", + "Model: OLS Adj. R-squared: 0.602\n", + "Method: Least Squares F-statistic: 120.4\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.75e-17\n", + "Time: 01:26:13 Log-Likelihood: -236.64\n", + "No. Observations: 80 AIC: 477.3\n", + "Df Residuals: 78 BIC: 482.0\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 4.8341 1.906 2.537 0.013 1.040 8.628\n", + "Educ 1.4510 0.132 10.975 0.000 1.188 1.714\n", + "==============================================================================\n", + "Omnibus: 2.125 Durbin-Watson: 1.728\n", + "Prob(Omnibus): 0.346 Jarque-Bera (JB): 1.975\n", + "Skew: -0.380 Prob(JB): 0.373\n", + "Kurtosis: 2.873 Cond. No. 52.3\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "wageEduModel = sm.OLS(\n", + " wagesDf[\"Wage\"],\n", + " sm.add_constant(wagesDf[\"Educ\"])\n", + ")\n", + "wageEduModelFit = wageEduModel.fit()\n", + "print(wageEduModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"wageEduModelFit\",\n", + " \"model\": wageEduModelFit,\n", + " \"description\": \"Predict Wage based on Educ for wagesDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Educ\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Wage\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "lLQzN2F42WHI", + "outputId": "5dd9b463-f7ef-49de-f0e8-a1b12d4ec5a6" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAgepredictedWage1
017.54127622.246147
120.93106119.344145
212.9487516.442142
319.3463813.540139
424.12125922.246147
...............
7525.64147425.148150
7638.77214135.305160
7721.87157526.599152
7827.54204633.854159
7923.66124922.246147
\n", + "

80 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age predictedWage1\n", + "0 17.54 12 76 22.246147\n", + "1 20.93 10 61 19.344145\n", + "2 12.94 8 75 16.442142\n", + "3 19.34 6 38 13.540139\n", + "4 24.12 12 59 22.246147\n", + ".. ... ... ... ...\n", + "75 25.64 14 74 25.148150\n", + "76 38.77 21 41 35.305160\n", + "77 21.87 15 75 26.599152\n", + "78 27.54 20 46 33.854159\n", + "79 23.66 12 49 22.246147\n", + "\n", + "[80 rows x 4 columns]" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedWage1 = wageEduModelFit.predict(sm.add_constant(wagesDf[\"Educ\"]))\n", + "wagesDf['predictedWage1'] = predictedWage1\n", + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 472 + }, + "id": "yszN-fZr2TZU", + "outputId": "83ea553f-eab8-4f9e-a043-d5e9bc8b06c0" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "\n", + "plt.scatter(\n", + " wagesDf[\"Educ\"],\n", + " wagesDf[\"Wage\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.plot(\n", + " wagesDf[\"Educ\"],\n", + " wagesDf[\"predictedWage1\"],\n", + " color='red',\n", + " label='OLS Regression - predictedWage1'\n", + ")\n", + "plt.title('Educ Level vs. Wage with OLS Regression')\n", + "plt.xlabel('Educ Level(yr)')\n", + "plt.ylabel('Wage K')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 472 + }, + "id": "olxdwpKV3GMJ", + "outputId": "ad1876d2-c303-4a27-b808-bb9bde58ea9a" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plt.scatter(\n", + " wagesDf[\"Age\"],\n", + " wagesDf[\"Wage\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "\n", + "plt.title('Age vs. Wage with OLS Regression')\n", + "plt.xlabel('Age')\n", + "plt.ylabel('Wage K')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "LMhx9bzJ3d7a", + "outputId": "75532a8c-df8f-4299-bfca-371489f2081b" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Wage R-squared: 0.022\n", + "Model: OLS Adj. R-squared: 0.009\n", + "Method: Least Squares F-statistic: 1.718\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 0.194\n", + "Time: 01:26:14 Log-Likelihood: -273.12\n", + "No. Observations: 80 AIC: 550.2\n", + "Df Residuals: 78 BIC: 555.0\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 21.7740 2.548 8.544 0.000 16.701 26.847\n", + "Age 0.0638 0.049 1.311 0.194 -0.033 0.161\n", + "==============================================================================\n", + "Omnibus: 0.180 Durbin-Watson: 1.914\n", + "Prob(Omnibus): 0.914 Jarque-Bera (JB): 0.372\n", + "Skew: 0.016 Prob(JB): 0.830\n", + "Kurtosis: 2.667 Cond. No. 160.\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "wageAgeModel = sm.OLS(\n", + " wagesDf[\"Wage\"],\n", + " sm.add_constant(wagesDf[\"Age\"])\n", + ")\n", + "wageAgeModelFit = wageAgeModel.fit()\n", + "print(wageAgeModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"wageAgeModelFit\",\n", + " \"model\": wageAgeModelFit,\n", + " \"description\": \"Predict Wage based on Age for wagesDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Age\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Wage\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "eLEY_vB-3oVw", + "outputId": "4938f031-77f3-44bf-ee37-cfc3f27fa7e4" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAgepredictedWage1predictedWage2
017.54127622.24614726.621568
120.93106119.34414525.664811
212.9487516.44214226.557784
319.3463813.54013924.197784
424.12125922.24614725.537243
..................
7525.64147425.14815026.494001
7638.77214135.30516024.389135
7721.87157526.59915226.557784
7827.54204633.85415924.708054
7923.66124922.24614724.899405
\n", + "

80 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age predictedWage1 predictedWage2\n", + "0 17.54 12 76 22.246147 26.621568\n", + "1 20.93 10 61 19.344145 25.664811\n", + "2 12.94 8 75 16.442142 26.557784\n", + "3 19.34 6 38 13.540139 24.197784\n", + "4 24.12 12 59 22.246147 25.537243\n", + ".. ... ... ... ... ...\n", + "75 25.64 14 74 25.148150 26.494001\n", + "76 38.77 21 41 35.305160 24.389135\n", + "77 21.87 15 75 26.599152 26.557784\n", + "78 27.54 20 46 33.854159 24.708054\n", + "79 23.66 12 49 22.246147 24.899405\n", + "\n", + "[80 rows x 5 columns]" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedWage2 = wageAgeModelFit.predict(sm.add_constant(wagesDf[\"Age\"]))\n", + "wagesDf['predictedWage2'] = predictedWage2\n", + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 718 + }, + "id": "9tHJPDGt3sjK", + "outputId": "0ed44935-aafa-4acd-d757-f128227fdc69" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "plt.figure(\n", + " figsize=(8, 8)\n", + ")\n", + "\n", + "plt.scatter(\n", + " wagesDf[\"Age\"],\n", + " wagesDf[\"Wage\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.plot(\n", + " wagesDf[\"Age\"],\n", + " wagesDf[\"predictedWage2\"],\n", + " color='red',\n", + " label='OLS Regression - predictedWage2'\n", + ")\n", + "plt.title('Age. Wage with OLS Regression')\n", + "plt.xlabel('Age')\n", + "plt.ylabel('Wage K')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "v4CvzLau4TZ6", + "outputId": "24667a49-768a-4063-d97d-a36f3067d430" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAgepredictedWage1predictedWage2agePower2
017.54127622.24614726.6215685776.0
120.93106119.34414525.6648113721.0
212.9487516.44214226.5577845625.0
319.3463813.54013924.1977841444.0
424.12125922.24614725.5372433481.0
.....................
7525.64147425.14815026.4940015476.0
7638.77214135.30516024.3891351681.0
7721.87157526.59915226.5577845625.0
7827.54204633.85415924.7080542116.0
7923.66124922.24614724.8994052401.0
\n", + "

80 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age predictedWage1 predictedWage2 agePower2\n", + "0 17.54 12 76 22.246147 26.621568 5776.0\n", + "1 20.93 10 61 19.344145 25.664811 3721.0\n", + "2 12.94 8 75 16.442142 26.557784 5625.0\n", + "3 19.34 6 38 13.540139 24.197784 1444.0\n", + "4 24.12 12 59 22.246147 25.537243 3481.0\n", + ".. ... ... ... ... ... ...\n", + "75 25.64 14 74 25.148150 26.494001 5476.0\n", + "76 38.77 21 41 35.305160 24.389135 1681.0\n", + "77 21.87 15 75 26.599152 26.557784 5625.0\n", + "78 27.54 20 46 33.854159 24.708054 2116.0\n", + "79 23.66 12 49 22.246147 24.899405 2401.0\n", + "\n", + "[80 rows x 6 columns]" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.transformers import transformersDict\n", + "# wagesDf['agePower2'] = wagesDf.apply(lambda row: row['Age'] * row['Age'], axis=1)\n", + "wagesDf['agePower2'] = wagesDf.apply(transformersDict.get('AGE_POWER_2'), axis=1)\n", + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "id": "d7cn8Io05ebq" + }, + "outputs": [], + "source": [ + "wagesDf = wagesDf.sort_values(by=\"Age\")" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Vr9zmJ7L4lEg", + "outputId": "bac52dd3-0455-40a8-fb08-63154aad18b6" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Wage R-squared: 0.400\n", + "Model: OLS Adj. R-squared: 0.385\n", + "Method: Least Squares F-statistic: 25.72\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 2.79e-09\n", + "Time: 01:26:14 Log-Likelihood: -253.53\n", + "No. Observations: 80 AIC: 513.1\n", + "Df Residuals: 77 BIC: 520.2\n", + "Df Model: 2 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -14.4664 5.569 -2.598 0.011 -25.556 -3.376\n", + "Age 1.7567 0.246 7.150 0.000 1.267 2.246\n", + "agePower2 -0.0173 0.002 -6.976 0.000 -0.022 -0.012\n", + "==============================================================================\n", + "Omnibus: 2.225 Durbin-Watson: 2.070\n", + "Prob(Omnibus): 0.329 Jarque-Bera (JB): 2.224\n", + "Skew: 0.370 Prob(JB): 0.329\n", + "Kurtosis: 2.652 Cond. No. 2.74e+04\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 2.74e+04. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "wageAgePower2Model = sm.OLS(\n", + " wagesDf[\"Wage\"],\n", + " sm.add_constant(wagesDf[[\"Age\", \"agePower2\"]])\n", + ")\n", + "wageAgePower2ModelFit = wageAgePower2Model.fit()\n", + "print(wageAgePower2ModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"wageAgePower2ModelFit\",\n", + " \"model\": wageAgePower2ModelFit,\n", + " \"description\": \"Predict Wage based on Age quadradic for wagesDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Age\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"agePower2\",\n", + " \"transformer\": \"AGE_POWER_2\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Wage\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "qefCiN4F4yHq", + "outputId": "1c35de4e-79b7-41fa-c25d-334062439bd6" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAgepredictedWage1predictedWage2agePower2predictedWage3
6925.13161828.05015322.922107324.011.536003
2712.39131923.69714922.985891361.012.651138
626.9362113.54013923.113459441.014.777375
6018.11142125.14815023.113459441.014.777375
2816.37122222.24614723.177243484.015.788477
........................
4828.95207533.85415926.5577845625.019.752807
7721.87157526.59915226.5577845625.019.752807
6715.38127622.24614726.6215685776.018.891302
017.54127622.24614726.6215685776.018.891302
5010.3197717.89314326.6853525929.017.995120
\n", + "

80 rows × 7 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age predictedWage1 predictedWage2 agePower2 \\\n", + "69 25.13 16 18 28.050153 22.922107 324.0 \n", + "27 12.39 13 19 23.697149 22.985891 361.0 \n", + "62 6.93 6 21 13.540139 23.113459 441.0 \n", + "60 18.11 14 21 25.148150 23.113459 441.0 \n", + "28 16.37 12 22 22.246147 23.177243 484.0 \n", + ".. ... ... ... ... ... ... \n", + "48 28.95 20 75 33.854159 26.557784 5625.0 \n", + "77 21.87 15 75 26.599152 26.557784 5625.0 \n", + "67 15.38 12 76 22.246147 26.621568 5776.0 \n", + "0 17.54 12 76 22.246147 26.621568 5776.0 \n", + "50 10.31 9 77 17.893143 26.685352 5929.0 \n", + "\n", + " predictedWage3 \n", + "69 11.536003 \n", + "27 12.651138 \n", + "62 14.777375 \n", + "60 14.777375 \n", + "28 15.788477 \n", + ".. ... \n", + "48 19.752807 \n", + "77 19.752807 \n", + "67 18.891302 \n", + "0 18.891302 \n", + "50 17.995120 \n", + "\n", + "[80 rows x 7 columns]" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedWage3 = wageAgePower2ModelFit.predict(sm.add_constant(wagesDf[[\"Age\", \"agePower2\"]]))\n", + "wagesDf['predictedWage3'] = predictedWage3\n", + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 718 + }, + "id": "MgtSumSS4v-w", + "outputId": "3a38bcec-2dfb-4304-bdac-f4fab159606c" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "plt.figure(\n", + " figsize=(8, 8)\n", + ")\n", + "\n", + "plt.scatter(\n", + " wagesDf[\"Age\"],\n", + " wagesDf[\"Wage\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.plot(\n", + " wagesDf[\"Age\"],\n", + " wagesDf[\"predictedWage2\"],\n", + " color='red',\n", + " label='OLS Regression - predictedWage2'\n", + ")\n", + "\n", + "plt.plot(\n", + " wagesDf[\"Age\"],\n", + " wagesDf[\"predictedWage3\"],\n", + " color='green',\n", + " label='OLS Regression - predictedWage3'\n", + ")\n", + "plt.title('Age. Wage with OLS Regression')\n", + "plt.xlabel('Age')\n", + "plt.ylabel('Wage K')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "IdnsnYWW8vW6", + "outputId": "4f29d91f-bc51-4068-b4c6-52360a206857" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAgepredictedWage1predictedWage2agePower2predictedWage3
6925.13161828.05015322.922107324.011.536003
2712.39131923.69714922.985891361.012.651138
626.9362113.54013923.113459441.014.777375
6018.11142125.14815023.113459441.014.777375
2816.37122222.24614723.177243484.015.788477
........................
4828.95207533.85415926.5577845625.019.752807
7721.87157526.59915226.5577845625.019.752807
6715.38127622.24614726.6215685776.018.891302
017.54127622.24614726.6215685776.018.891302
5010.3197717.89314326.6853525929.017.995120
\n", + "

80 rows × 7 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age predictedWage1 predictedWage2 agePower2 \\\n", + "69 25.13 16 18 28.050153 22.922107 324.0 \n", + "27 12.39 13 19 23.697149 22.985891 361.0 \n", + "62 6.93 6 21 13.540139 23.113459 441.0 \n", + "60 18.11 14 21 25.148150 23.113459 441.0 \n", + "28 16.37 12 22 22.246147 23.177243 484.0 \n", + ".. ... ... ... ... ... ... \n", + "48 28.95 20 75 33.854159 26.557784 5625.0 \n", + "77 21.87 15 75 26.599152 26.557784 5625.0 \n", + "67 15.38 12 76 22.246147 26.621568 5776.0 \n", + "0 17.54 12 76 22.246147 26.621568 5776.0 \n", + "50 10.31 9 77 17.893143 26.685352 5929.0 \n", + "\n", + " predictedWage3 \n", + "69 11.536003 \n", + "27 12.651138 \n", + "62 14.777375 \n", + "60 14.777375 \n", + "28 15.788477 \n", + ".. ... \n", + "48 19.752807 \n", + "77 19.752807 \n", + "67 18.891302 \n", + "0 18.891302 \n", + "50 17.995120 \n", + "\n", + "[80 rows x 7 columns]" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 430 + }, + "id": "o_JsGSTW8hWt", + "outputId": "f93023b4-5034-4810-cafd-cd3e43bb8978" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fig = plt.figure()\n", + "ax = plt.axes(projection =\"3d\")\n", + "\n", + "# Creating plot\n", + "ax.scatter3D(\n", + " wagesDf[\"Age\"],\n", + " wagesDf[\"Educ\"],\n", + " wagesDf[\"Wage\"],\n", + " color = \"green\"\n", + ")\n", + "plt.title(\"Cost,Grad -> Wage\")\n", + "ax.set_xlabel('Age')\n", + "ax.set_ylabel('Educ')\n", + "ax.set_zlabel('Wage')\n", + "\n", + "# show plot\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "3eA8WZha8aGL", + "outputId": "954bd6db-78bd-41cd-e425-1b838ba7db98" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Wage R-squared: 0.619\n", + "Model: OLS Adj. R-squared: 0.609\n", + "Method: Least Squares F-statistic: 62.47\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 7.57e-17\n", + "Time: 01:26:14 Log-Likelihood: -235.42\n", + "No. Observations: 80 AIC: 476.8\n", + "Df Residuals: 77 BIC: 484.0\n", + "Df Model: 2 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 2.6381 2.366 1.115 0.268 -2.074 7.350\n", + "Age 0.0472 0.031 1.541 0.127 -0.014 0.108\n", + "Educ 1.4410 0.131 10.981 0.000 1.180 1.702\n", + "==============================================================================\n", + "Omnibus: 1.999 Durbin-Watson: 0.932\n", + "Prob(Omnibus): 0.368 Jarque-Bera (JB): 1.721\n", + "Skew: -0.359 Prob(JB): 0.423\n", + "Kurtosis: 2.977 Cond. No. 245.\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "wageAgeEduModel1 = sm.OLS(\n", + " wagesDf[\"Wage\"],\n", + " sm.add_constant(wagesDf[[\"Age\", \"Educ\"]])\n", + ")\n", + "wageAgeEduModel1Fit = wageAgeEduModel1.fit()\n", + "print(wageAgeEduModel1Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"wageAgeEduModel1\",\n", + " \"model\": wageAgeEduModel1,\n", + " \"description\": \"Predict Wage based on Age and Educ for wagesDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Age\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"Educ\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Wage\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "g7H5sriP89MI", + "outputId": "aeaded50-79e3-4ba4-cbb0-b0c4eaf492df" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAgepredictedWage1predictedWage2agePower2predictedWage3predictedWage4
6925.13161828.05015322.922107324.011.53600326.543357
2712.39131923.69714922.985891361.012.65113822.267494
626.9362113.54013923.113459441.014.77737512.274758
6018.11142125.14815023.113459441.014.77737523.802849
2816.37122222.24614723.177243484.015.78847720.967998
...........................
4828.95207533.85415926.5577845625.019.75280734.996187
7721.87157526.59915226.5577845625.019.75280727.791130
6715.38127622.24614726.6215685776.018.89130223.515267
017.54127622.24614726.6215685776.018.89130223.515267
5010.3197717.89314326.6853525929.017.99512019.239405
\n", + "

80 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age predictedWage1 predictedWage2 agePower2 \\\n", + "69 25.13 16 18 28.050153 22.922107 324.0 \n", + "27 12.39 13 19 23.697149 22.985891 361.0 \n", + "62 6.93 6 21 13.540139 23.113459 441.0 \n", + "60 18.11 14 21 25.148150 23.113459 441.0 \n", + "28 16.37 12 22 22.246147 23.177243 484.0 \n", + ".. ... ... ... ... ... ... \n", + "48 28.95 20 75 33.854159 26.557784 5625.0 \n", + "77 21.87 15 75 26.599152 26.557784 5625.0 \n", + "67 15.38 12 76 22.246147 26.621568 5776.0 \n", + "0 17.54 12 76 22.246147 26.621568 5776.0 \n", + "50 10.31 9 77 17.893143 26.685352 5929.0 \n", + "\n", + " predictedWage3 predictedWage4 \n", + "69 11.536003 26.543357 \n", + "27 12.651138 22.267494 \n", + "62 14.777375 12.274758 \n", + "60 14.777375 23.802849 \n", + "28 15.788477 20.967998 \n", + ".. ... ... \n", + "48 19.752807 34.996187 \n", + "77 19.752807 27.791130 \n", + "67 18.891302 23.515267 \n", + "0 18.891302 23.515267 \n", + "50 17.995120 19.239405 \n", + "\n", + "[80 rows x 8 columns]" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedWage4 = wageAgeEduModel1Fit.predict(\n", + " sm.add_constant(wagesDf[[\"Age\", \"Educ\"]])\n", + ")\n", + "wagesDf['predictedWage4'] = predictedWage4\n", + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 430 + }, + "id": "B6uSr6jt9H9v", + "outputId": "9ee4d99e-7b65-46ae-d61d-08abe262057d" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Extracting coefficients\n", + "intercept = wageAgeEduModel1Fit.params['const']\n", + "coefAge = wageAgeEduModel1Fit.params['Age']\n", + "coefEduc = wageAgeEduModel1Fit.params['Educ']\n", + "\n", + "# Create 3D grid for plotting\n", + "ageRange = np.linspace(wagesDf['Age'].min(), wagesDf['Age'].max(), 100)\n", + "educRange = np.linspace(wagesDf['Educ'].min(), wagesDf['Educ'].max(), 100)\n", + "ageGrid, educGrid = np.meshgrid(ageRange, educRange)\n", + "\n", + "# Calculate predicted Wage for each combination of Age and Educ\n", + "wagePredictEq = intercept + coefAge * ageGrid + coefEduc * educGrid\n", + "\n", + "\n", + "\n", + "\n", + "fig = plt.figure()\n", + "ax = plt.axes(projection =\"3d\")\n", + "\n", + "# Scatter plot of the actual data points\n", + "ax.scatter(wagesDf['Age'], wagesDf['Educ'], wagesDf['Wage'], color='blue', label='Actual Wage')\n", + "\n", + "# Plotting the fitted plane\n", + "ax.plot_surface(ageGrid, educGrid, wagePredictEq, color='red', alpha=0.5, label='Fitted Plane')\n", + "\n", + "# Labeling axes\n", + "ax.set_xlabel('Age')\n", + "ax.set_ylabel('Educ')\n", + "ax.set_zlabel('Wage')\n", + "\n", + "\n", + "\n", + "plt.title('Age and Educ vs. Wage with Fitted Plane')\n", + "\n", + "# Rotating the plot\n", + "# ax.view_init(elev=45, azim=45) # Set the elevation and azimuth angles\n", + "plt.show()\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "FcfLUqqc-AUb", + "outputId": "641a5fe0-840a-410d-a7dc-b574a32cbdc2" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Wage R-squared: 0.832\n", + "Model: OLS Adj. R-squared: 0.826\n", + "Method: Least Squares F-statistic: 125.7\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 2.18e-29\n", + "Time: 01:26:14 Log-Likelihood: -202.56\n", + "No. Observations: 80 AIC: 413.1\n", + "Df Residuals: 76 BIC: 422.7\n", + "Df Model: 3 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -22.7219 3.023 -7.517 0.000 -28.742 -16.701\n", + "Age 1.3500 0.134 10.077 0.000 1.083 1.617\n", + "Educ 1.2540 0.090 13.990 0.000 1.075 1.432\n", + "agePower2 -0.0133 0.001 -9.840 0.000 -0.016 -0.011\n", + "==============================================================================\n", + "Omnibus: 3.000 Durbin-Watson: 1.979\n", + "Prob(Omnibus): 0.223 Jarque-Bera (JB): 2.884\n", + "Skew: 0.031 Prob(JB): 0.236\n", + "Kurtosis: 3.928 Cond. No. 2.79e+04\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 2.79e+04. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "wageAgePower2EducModel = sm.OLS(\n", + " wagesDf[\"Wage\"],\n", + " sm.add_constant(wagesDf[[\"Age\", \"Educ\", \"agePower2\"]])\n", + ")\n", + "wageAgePower2EducModelFit = wageAgePower2EducModel.fit()\n", + "print(wageAgePower2EducModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"wageAgePower2EducModelFit\",\n", + " \"model\": wageAgePower2EducModelFit,\n", + " \"description\": \"Predict Wage based on Age quadradic and Educ for wagesDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Age\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"Educ\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"agePower2\",\n", + " \"transformer\": \"AGE_POWER_2\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Wage\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "id": "8yE7of2c-Mb-", + "outputId": "a240051f-99af-410b-aa53-a65147f0f885" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
WageEducAgepredictedWage1predictedWage2agePower2predictedWage3predictedWage4predictedWage5
6925.13161828.05015322.922107324.011.53600326.54335717.325188
2712.39131923.69714922.985891361.012.65113822.26749414.420408
626.9362113.54013923.113459441.014.77737512.2747587.276959
6018.11142125.14815023.113459441.014.77737523.80284917.308629
2816.37122222.24614723.177243484.015.78847720.96799815.577878
..............................
4828.95207533.85415926.5577845625.019.75280734.99618728.672466
7721.87157526.59915226.5577845625.019.75280727.79113022.402672
6715.38127622.24614726.6215685776.018.89130223.51526717.979211
017.54127622.24614726.6215685776.018.89130223.51526717.979211
5010.3197717.89314326.6853525929.017.99512019.23940513.529107
\n", + "

80 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " Wage Educ Age predictedWage1 predictedWage2 agePower2 \\\n", + "69 25.13 16 18 28.050153 22.922107 324.0 \n", + "27 12.39 13 19 23.697149 22.985891 361.0 \n", + "62 6.93 6 21 13.540139 23.113459 441.0 \n", + "60 18.11 14 21 25.148150 23.113459 441.0 \n", + "28 16.37 12 22 22.246147 23.177243 484.0 \n", + ".. ... ... ... ... ... ... \n", + "48 28.95 20 75 33.854159 26.557784 5625.0 \n", + "77 21.87 15 75 26.599152 26.557784 5625.0 \n", + "67 15.38 12 76 22.246147 26.621568 5776.0 \n", + "0 17.54 12 76 22.246147 26.621568 5776.0 \n", + "50 10.31 9 77 17.893143 26.685352 5929.0 \n", + "\n", + " predictedWage3 predictedWage4 predictedWage5 \n", + "69 11.536003 26.543357 17.325188 \n", + "27 12.651138 22.267494 14.420408 \n", + "62 14.777375 12.274758 7.276959 \n", + "60 14.777375 23.802849 17.308629 \n", + "28 15.788477 20.967998 15.577878 \n", + ".. ... ... ... \n", + "48 19.752807 34.996187 28.672466 \n", + "77 19.752807 27.791130 22.402672 \n", + "67 18.891302 23.515267 17.979211 \n", + "0 18.891302 23.515267 17.979211 \n", + "50 17.995120 19.239405 13.529107 \n", + "\n", + "[80 rows x 9 columns]" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedWage5 = wageAgePower2EducModelFit.predict(\n", + " sm.add_constant(wagesDf[[\"Age\", \"Educ\", \"agePower2\"]])\n", + ")\n", + "wagesDf['predictedWage5'] = predictedWage5\n", + "wagesDf" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 430 + }, + "id": "iKJ_cPMm-bKj", + "outputId": "2040b352-e2ac-498d-cfc7-5988b1b859f1" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Extracting coefficients\n", + "intercept2 = wageAgePower2EducModelFit.params['const']\n", + "coefAge2 = wageAgePower2EducModelFit.params['Age']\n", + "coefEduc2 = wageAgePower2EducModelFit.params['Educ']\n", + "coefAgePower22 = wageAgePower2EducModelFit.params['agePower2']\n", + "\n", + "# Create 3D grid for plotting\n", + "ageRange = np.linspace(wagesDf['Age'].min(), wagesDf['Age'].max(), 100)\n", + "educRange = np.linspace(wagesDf['Educ'].min(), wagesDf['Educ'].max(), 100)\n", + "ageGrid, educGrid = np.meshgrid(ageRange, educRange)\n", + "\n", + "# Calculate predicted Wage for each combination of Age and Educ\n", + "wagePredictEq2 = intercept2 + coefAge2 * ageGrid + coefEduc2 * educGrid + coefAgePower22 * ageGrid * ageGrid\n", + "\n", + "\n", + "\n", + "\n", + "fig = plt.figure()\n", + "ax = plt.axes(projection =\"3d\")\n", + "\n", + "# Scatter plot of the actual data points\n", + "ax.scatter(wagesDf['Age'], wagesDf['Educ'], wagesDf['Wage'], color='blue', label='Actual Wage')\n", + "\n", + "\n", + "\n", + "# Plotting the fitted plane\n", + "ax.plot_surface(ageGrid, educGrid, wagePredictEq2, color='green', alpha=0.5, label='Fitted Plane')\n", + "\n", + "# Labeling axes\n", + "ax.set_xlabel('Age')\n", + "ax.set_ylabel('Educ')\n", + "ax.set_zlabel('Wage')\n", + "\n", + "\n", + "\n", + "plt.title('Age and Educ vs. Wage with Fitted Plane')\n", + "\n", + "# Rotating the plot\n", + "# ax.view_init(elev=45, azim=45) # Set the elevation and azimuth angles\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 430 + }, + "id": "g8HsfNtZ_FNl", + "outputId": "18a36a34-2711-49fd-a86a-3bdd4ce5bb24" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Extracting coefficients\n", + "intercept2 = wageAgePower2EducModelFit.params['const']\n", + "coefAge2 = wageAgePower2EducModelFit.params['Age']\n", + "coefEduc2 = wageAgePower2EducModelFit.params['Educ']\n", + "coefAgePower22 = wageAgePower2EducModelFit.params['agePower2']\n", + "\n", + "# Create 3D grid for plotting\n", + "ageRange = np.linspace(wagesDf['Age'].min(), wagesDf['Age'].max(), 100)\n", + "educRange = np.linspace(wagesDf['Educ'].min(), wagesDf['Educ'].max(), 100)\n", + "ageGrid, educGrid = np.meshgrid(ageRange, educRange)\n", + "\n", + "# Calculate predicted Wage for each combination of Age and Educ\n", + "wagePredictEq2 = intercept2 + coefAge2 * ageGrid + coefEduc2 * educGrid + coefAgePower22 * ageGrid * ageGrid\n", + "\n", + "\n", + "\n", + "\n", + "fig = plt.figure()\n", + "ax = plt.axes(projection =\"3d\")\n", + "\n", + "# Scatter plot of the actual data points\n", + "ax.scatter(wagesDf['Age'], wagesDf['Educ'], wagesDf['Wage'], color='blue', label='Actual Wage')\n", + "\n", + "# Plotting the fitted plane\n", + "ax.plot_surface(ageGrid, educGrid, wagePredictEq, color='red', alpha=0.5, label='Fitted Plane')\n", + "\n", + "\n", + "# Plotting the fitted plane\n", + "ax.plot_surface(ageGrid, educGrid, wagePredictEq2, color='green', alpha=0.5, label='Fitted Plane')\n", + "\n", + "# Labeling axes\n", + "ax.set_xlabel('Age')\n", + "ax.set_ylabel('Educ')\n", + "ax.set_zlabel('Wage')\n", + "\n", + "\n", + "\n", + "plt.title('Age and Educ vs. Wage with Fitted Plane')\n", + "\n", + "# Rotating the plot\n", + "# ax.view_init(elev=45, azim=45) # Set the elevation and azimuth angles\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/wip/Advance_regression3.ipynb b/notebooks/wip/Advance_regression3.ipynb new file mode 100644 index 0000000..aabd9d6 --- /dev/null +++ b/notebooks/wip/Advance_regression3.ipynb @@ -0,0 +1,701 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "xwFyEsosINqT" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "pKewSQysItJ-" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Lz-DyAtNWsJR" + }, + "outputs": [], + "source": [ + "# Download Dataset from https://www.dropbox.com/scl/fi/bkcdp9tpqqh6dfr6phtt8/AnnArbor.xlsx?rlkey=0agfqwc7f0kt7oqb3e2h6q3qs&dl=1\n", + "# and add it to colab" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "0zM8FGMJXJ70" + }, + "outputs": [], + "source": [ + "# annArborDf = pd.read_excel(\"./AnnArbor.xlsx\")\n", + "annArborDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/bkcdp9tpqqh6dfr6phtt8/AnnArbor.xlsx?rlkey=0agfqwc7f0kt7oqb3e2h6q3qs&dl=1\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "t0LUca0Myqw5", + "outputId": "249ab087-895f-4fa6-993e-e8dd50ef87c1" + }, + "outputs": [], + "source": [ + "annArborDf" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "GQRNPIeyy6ub", + "outputId": "00211933-f2b1-40c6-d9cf-187560ffa305" + }, + "outputs": [], + "source": [ + "annArborDf.size" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "yumMybniy85d" + }, + "outputs": [], + "source": [ + "annArborDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "aspq6hoPy_xZ", + "outputId": "96892272-a1d5-400e-a177-6c96746619d8" + }, + "outputs": [], + "source": [ + "annArborDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "z_hVTvPrzYJr" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "id": "pIniVuaIzaaZ", + "outputId": "6a061f6a-8bff-42c0-d705-0c2bd06eb5ff" + }, + "outputs": [], + "source": [ + "# Plotting\n", + "fig1 = plt.figure(\n", + " figsize=(8, 8)\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "VHdpDE7o42Pf", + "outputId": "ac876802-b6d1-4926-d069-0532ee9e7a0b" + }, + "outputs": [], + "source": [ + "plt.scatter(\n", + " annArborDf[\"Beds\"],\n", + " annArborDf[\"Rent\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('Beds')\n", + "plt.ylabel('Rent')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "knAa4W9R47rZ", + "outputId": "81359d91-03b7-4f70-c381-c88172f800a9" + }, + "outputs": [], + "source": [ + "plt.scatter(\n", + " annArborDf[\"Baths\"],\n", + " annArborDf[\"Rent\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('Baths')\n", + "plt.ylabel('Rent')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "dOnWJbFOzczV", + "outputId": "c6d6b86b-dd85-45d1-b543-928441c11dc4" + }, + "outputs": [], + "source": [ + "plt.scatter(\n", + " annArborDf[\"Sqft\"],\n", + " annArborDf[\"Rent\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('Sqft')\n", + "plt.ylabel('Rent')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "alIhUPPUzvli", + "outputId": "8ed14c4b-a596-49ac-912a-0dcb4145df89" + }, + "outputs": [], + "source": [ + "rentSqftModel1 = sm.OLS(\n", + " annArborDf[\"Rent\"],\n", + " sm.add_constant(annArborDf[[\"Sqft\"]])\n", + ")\n", + "rentSqftModel1Fit = rentSqftModel1.fit()\n", + "print(rentSqftModel1Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"rentSqftModel1Fit\",\n", + " \"model\": rentSqftModel1Fit,\n", + " \"description\": \"Predict Rent based on Sqft for annArborDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Sqft\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Rent\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "S-AyfiLN0Due", + "outputId": "aacd248d-5a72-4ce0-ab0a-048f30d398ca" + }, + "outputs": [], + "source": [ + "predictedRent1 = rentSqftModel1Fit.predict(sm.add_constant(annArborDf[\"Sqft\"]))\n", + "annArborDf['predictedRent1'] = predictedRent1\n", + "annArborDf" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "9ouX-mzz4sl-" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 454 + }, + "id": "L55GN8hZ4wXi", + "outputId": "712ace2c-5a04-48e0-acf0-cc42430f2aa9" + }, + "outputs": [], + "source": [ + "plt.scatter(\n", + " annArborDf[\"Rent\"],\n", + " annArborDf[\"Sqft\"],\n", + " color='blue',\n", + " alpha=0.5,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "intercept = rentSqftModel1Fit.params['const']\n", + "sqFtSlope = rentSqftModel1Fit.params['Sqft']\n", + "x_values = np.linspace(500, 4500, 200)\n", + "y_values = intercept + sqFtSlope * x_values\n", + "\n", + "plt.plot(\n", + " x_values,\n", + " y_values,\n", + " color='red',\n", + " label='rentSqftModel1Fit - predictedRent1'\n", + ")\n", + "plt.xlabel('Sqft')\n", + "plt.ylabel('Rent')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "swSVnmy44Ddg", + "outputId": "251afab3-0563-4eb7-e23a-b526238c7584" + }, + "outputs": [], + "source": [ + "rentBedsBathsSqftModel = sm.OLS(\n", + " annArborDf[\"Rent\"],\n", + " sm.add_constant(annArborDf[[\"Beds\", \"Baths\", \"Sqft\"]])\n", + ")\n", + "rentBedsBathsSqftModelFit = rentBedsBathsSqftModel.fit()\n", + "print(rentBedsBathsSqftModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"rentBedsBathsSqftModelFit\",\n", + " \"model\": rentBedsBathsSqftModelFit,\n", + " \"description\": \"Predict Rent based on Beds,Baths,Sqft for annArborDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Beds\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Baths\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Sqft\",\n", + " \"type\": \"float\"\n", + " }\n", + " \n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Rent\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "6lKEw7Wt57Px" + }, + "outputs": [], + "source": [ + "import math" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 1000 + }, + "id": "da3o51IG5u7r", + "outputId": "abe849ba-7689-468c-f327-b183c4d3f70a" + }, + "outputs": [], + "source": [ + "from functions.transformers import transformersDict\n", + "# annArborDf['log(Sqft)'] = annArborDf.apply(lambda row: math.log(row['Sqft']), axis=1)\n", + "annArborDf['log(Sqft)'] = annArborDf.apply(transformersDict.get('Sqft_log'), axis=1)\n", + "annArborDf" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "lYYrtI0O5lSG", + "outputId": "6a980e88-5630-4e5e-f887-875ab5f1d748" + }, + "outputs": [], + "source": [ + "rentBedsBathsLogSqftModel= sm.OLS(\n", + " annArborDf[\"Rent\"],\n", + " sm.add_constant(annArborDf[[\"Beds\", \"Baths\", \"log(Sqft)\"]])\n", + ")\n", + "rentBedsBathsLogSqftModelFit = rentBedsBathsLogSqftModel.fit()\n", + "print(rentBedsBathsLogSqftModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"rentBedsBathsLogSqftModelFit\",\n", + " \"model\": rentBedsBathsLogSqftModelFit,\n", + " \"description\": \"Predict Rent based on Beds,Baths,log(Sqft) for annArborDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Beds\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Baths\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Sqft\",\n", + " \"type\": \"float\"\n", + " }\n", + " \n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"log(Sqft)\",\n", + " \"transformer\": \"Sqft_log\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Rent\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "amUWG6386dyn" + }, + "outputs": [], + "source": [ + "annArborDf['log(Rent)'] = annArborDf.apply(lambda row: math.log(row['Rent']), axis=1)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "LxcjPBLn6iAq", + "outputId": "f827bc12-0083-4fb9-ea95-53a58cc0999b" + }, + "outputs": [], + "source": [ + "rentSqftModel4 = sm.OLS(\n", + " annArborDf[\"log(Rent)\"],\n", + " sm.add_constant(annArborDf[[\"Beds\", \"Baths\", \"Sqft\"]])\n", + ")\n", + "rentSqftModel4Fit = rentSqftModel4.fit()\n", + "print(rentSqftModel4Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "WM5h3QnN60IY", + "outputId": "56dd02c1-b8a8-4fcc-951f-676d574e6a62" + }, + "outputs": [], + "source": [ + "logRentBedsBathsLogSqftModel = sm.OLS(\n", + " annArborDf[\"log(Rent)\"],\n", + " sm.add_constant(annArborDf[[\"Beds\", \"Baths\", \"log(Sqft)\"]])\n", + ")\n", + "logRentBedsBathsLogSqftModelFit = logRentBedsBathsLogSqftModel.fit()\n", + "print(logRentBedsBathsLogSqftModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"logRentBedsBathsLogSqftModelFit\",\n", + " \"model\": logRentBedsBathsLogSqftModelFit,\n", + " \"description\": \"Predict log(Rent) based on Beds,Baths,log(Sqft) for annArborDf\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Beds\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Baths\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Sqft\",\n", + " \"type\": \"float\"\n", + " }\n", + " \n", + " ],\n", + " \"transformers\":[\n", + " {\n", + " \"name\": \"log(Sqft)\",\n", + " \"transformer\": \"Sqft_log\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"log(Rent)\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "1PHrUcM6694a", + "outputId": "7b463d70-25d1-4073-bf7e-4e93f31c5fb2" + }, + "outputs": [], + "source": [ + "rentSqftModel6 = sm.OLS(\n", + " annArborDf[\"log(Rent)\"],\n", + " sm.add_constant(annArborDf[[\"Beds\", \"log(Sqft)\"]])\n", + ")\n", + "rentSqftModel6Fit = rentSqftModel6.fit()\n", + "print(rentSqftModel6Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 430 + }, + "id": "BybWTp_k7hzc", + "outputId": "335b1499-534c-47d2-bdb6-7c0f3b456160" + }, + "outputs": [], + "source": [ + "# plt.scatter(\n", + "# annArborDf[\"Sqft\"],\n", + "# annArborDf[\"Rent\"],\n", + "# color='blue',\n", + "# alpha=0.9,\n", + "# label='Data Points - scatter',\n", + "# )\n", + "\n", + "plt.scatter(\n", + " annArborDf[\"log(Sqft)\"],\n", + " annArborDf[\"Rent\"],\n", + " color='red',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "# plt.scatter(\n", + "# annArborDf[\"log(Sqft)\"],\n", + "# annArborDf[\"log(Rent)\"],\n", + "# color='Green',\n", + "# alpha=0.9,\n", + "# label='Data Points - scatter',\n", + "# )\n", + "\n", + "# plt.scatter(\n", + "# annArborDf[\"Sqft\"],\n", + "# annArborDf[\"log(Rent)\"],\n", + "# color='Yellow',\n", + "# alpha=0.9,\n", + "# label='Data Points - scatter',\n", + "# )\n", + "\n", + "\n", + "\n", + "# plt.xlabel('Sqft')\n", + "plt.ylabel('Rent')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/wip/Evaluating_Binary_Classification.ipynb b/notebooks/wip/Evaluating_Binary_Classification.ipynb new file mode 100644 index 0000000..9294f9a --- /dev/null +++ b/notebooks/wip/Evaluating_Binary_Classification.ipynb @@ -0,0 +1,1361 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "-iRvitW_mOmI" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "ZTL4F90RnqNA" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "id": "fK4vZwBPnA5z" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
RecordSpamRecipientsHyperlinksCharacters
01019147
12015158
231131188
341171168
45015187
..................
495496015297
496497020572
4974981411152
4984991161174
499500113232
\n", + "

500 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Record Spam Recipients Hyperlinks Characters\n", + "0 1 0 19 1 47\n", + "1 2 0 15 1 58\n", + "2 3 1 13 11 88\n", + "3 4 1 17 11 68\n", + "4 5 0 15 1 87\n", + ".. ... ... ... ... ...\n", + "495 496 0 15 2 97\n", + "496 497 0 20 5 72\n", + "497 498 1 41 11 52\n", + "498 499 1 16 11 74\n", + "499 500 1 13 2 32\n", + "\n", + "[500 rows x 5 columns]" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "spamDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/v24mmhg5hmefmnv99uqsy/Spam.xlsx?rlkey=iq7exnueq84sy7y2b8ud70mp0&dl=1\")\n", + "spamDf" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "id": "AgPRgw9TnYLJ" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(2500, (500, 5))" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "spamDf.size, spamDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "id": "zqcLaMdZoasO" + }, + "outputs": [], + "source": [ + "from sklearn.model_selection import train_test_split" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "Y_JGlYFloXHm" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "((350, 5), (150, 5))" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Split the dataset into training and testing sets\n", + "trainSet, testSet = train_test_split(\n", + " spamDf,\n", + " test_size=0.3,\n", + " random_state=1,\n", + " stratify=spamDf['Spam']\n", + ")\n", + "trainSet.shape, testSet.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "id": "P8pFCQgIpAu3" + }, + "outputs": [], + "source": [ + "# Fit the logistic regression model\n", + "features = ['Recipients', 'Hyperlinks', 'Characters']\n", + "xTrain = trainSet[features]\n", + "yTrain = trainSet['Spam'].astype(int)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "id": "6sHvxFpspMKh" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.430522\n", + " Iterations 6\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 350\n", + "Model: Logit Df Residuals: 346\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3784\n", + "Time: 15:05:50 Log-Likelihood: -150.68\n", + "converged: True LL-Null: -242.40\n", + "Covariance Type: nonrobust LLR p-value: 1.606e-39\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -4.3440 0.757 -5.741 0.000 -5.827 -2.861\n", + "Recipients 0.1071 0.035 3.083 0.002 0.039 0.175\n", + "Hyperlinks 0.5803 0.059 9.833 0.000 0.465 0.696\n", + "Characters -0.0132 0.006 -2.154 0.031 -0.025 -0.001\n", + "==============================================================================\n" + ] + } + ], + "source": [ + "spamBasedOnRecipientsHyperlinksCharactersLogitModel = sm.Logit(\n", + " yTrain,\n", + " sm.add_constant(xTrain)\n", + ")\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit = spamBasedOnRecipientsHyperlinksCharactersLogitModel.fit()\n", + "print(spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "5YbGrnLcp4EK" + }, + "outputs": [], + "source": [ + "predict1 = spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.predict(sm.add_constant(testSet[features]))\n", + "testSet['predict1'] = predict1\n", + "sumTable = pd.DataFrame({'A': testSet['Spam'], 'Prob': testSet['predict1']})\n", + "sumTable.to_csv(\"ROC.csv\", index=True)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "id": "nnM895bnYFuU" + }, + "outputs": [], + "source": [ + "sumTable1 = pd.DataFrame({'A': testSet['Spam'], 'Prob': testSet['predict1']})" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "id": "N0GKRfOerVZk" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AProbP
18600.7396331
42300.0791930
36910.7128011
28310.8384281
26610.7892401
............
15610.8505761
5400.1800120
32200.3769420
31400.0404720
29600.1020760
\n", + "

150 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " A Prob P\n", + "186 0 0.739633 1\n", + "423 0 0.079193 0\n", + "369 1 0.712801 1\n", + "283 1 0.838428 1\n", + "266 1 0.789240 1\n", + ".. .. ... ..\n", + "156 1 0.850576 1\n", + "54 0 0.180012 0\n", + "322 0 0.376942 0\n", + "314 0 0.040472 0\n", + "296 0 0.102076 0\n", + "\n", + "[150 rows x 3 columns]" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Make predictions based on probability threshold of 0.5\n", + "testSet['predictions'] = (testSet['predict1'] > 0.5).astype(int)\n", + "sumTable1['P'] = testSet['predictions']\n", + "sumTable1" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "id": "xlQk7hqYsHwL" + }, + "outputs": [], + "source": [ + "from sklearn.metrics import accuracy_score, recall_score, precision_score, roc_auc_score, roc_curve" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "id": "7FS8w-2ysIlk" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 0.78\n" + ] + } + ], + "source": [ + "# Calculate accuracy\n", + "accuracy = accuracy_score(sumTable1['A'], sumTable1['P'])\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics = {}\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['accuracy'] = accuracy\n", + "print(f'Accuracy: {spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['accuracy']}')" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "id": "yuSL_r7AsYT3" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Recall: 0.7532467532467533\n" + ] + } + ], + "source": [ + "# Calculate recall\n", + "recall = recall_score(sumTable1['A'], sumTable1['P'])\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['recall'] = recall\n", + "print(f'Recall: {recall}')" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "id": "NicDWx4esa9G" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Precision: 0.8055555555555556\n" + ] + } + ], + "source": [ + "# Calculate precision\n", + "precision = precision_score(sumTable1['A'], sumTable1['P'])\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['precision'] = precision\n", + "print(f'Precision: {precision}')" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "id": "SgxhSyW-spz7" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Sensitivity: 0.7532467532467533\n", + "Specificity: 0.8082191780821918\n" + ] + } + ], + "source": [ + "# Sensitivity and Specificity (Sensitivity is same as recall)\n", + "sensitivity = recall\n", + "specificity = sum((sumTable1['A'] == 0) & (sumTable1['P'] == 0)) / sum(sumTable1['A'] == 0)\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['sensitivity'] = sensitivity\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['specificity'] = specificity\n", + "print(f'Sensitivity: {sensitivity}')\n", + "print(f'Specificity: {specificity}')" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "id": "Y4Bufrh8tPIp" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "F1 Score: 0.778523489932886\n" + ] + } + ], + "source": [ + "# Calculate F1 Score\n", + "f1Score = 2 * (precision * recall) / (precision + recall)\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['f1Score'] = f1Score\n", + "print(f'F1 Score: {f1Score}')" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "id": "7NS_N1R_tcf9" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "AUC: 0.8305461661626046\n" + ] + } + ], + "source": [ + "# Plot ROC curve\n", + "fpr, tpr, _ = roc_curve(testSet['Spam'], testSet['predict1'])\n", + "roc_auc = roc_auc_score(testSet['Spam'], testSet['predict1'])\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics['roc_auc'] = roc_auc\n", + "# Calculate AUC\n", + "print(f'AUC: {roc_auc}')\n" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "id": "OZLGYNGpuGWY" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "1K-2SMbUt90Z" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "plt.figure()\n", + "plt.plot(fpr, tpr, color='darkorange', lw=2, label=f'ROC curve (area = {roc_auc:.2f})')\n", + "plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')\n", + "plt.xlim([0.0, 1.0])\n", + "plt.ylim([0.0, 1.05])\n", + "plt.xlabel('False Positive Rate')\n", + "plt.ylabel('True Positive Rate')\n", + "plt.title('Receiver Operating Characteristic')\n", + "plt.legend(loc=\"lower right\")\n", + "plt.show()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
RecordSpamRecipientsHyperlinksCharacters
01019147
12015158
231131188
341171168
45015187
\n", + "
" + ], + "text/plain": [ + " Record Spam Recipients Hyperlinks Characters\n", + "0 1 0 19 1 47\n", + "1 2 0 15 1 58\n", + "2 3 1 13 11 88\n", + "3 4 1 17 11 68\n", + "4 5 0 15 1 87" + ] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# KFold\n", + "from sklearn.model_selection import KFold\n", + "# Initialize KFold\n", + "# k=2\n", + "# k=5\n", + "k=10\n", + "kf = KFold(n_splits=k, shuffle=True, random_state=55)\n", + "spamDf.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.460658\n", + " Iterations 6\n", + "expr=1\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3343\n", + "Time: 15:23:34 Log-Likelihood: -207.30\n", + "converged: True LL-Null: -311.38\n", + "Covariance Type: nonrobust LLR p-value: 7.258e-45\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -4.0452 0.691 -5.857 0.000 -5.399 -2.691\n", + "Recipients 0.1205 0.035 3.407 0.001 0.051 0.190\n", + "Hyperlinks 0.5087 0.047 10.832 0.000 0.417 0.601\n", + "Characters -0.0123 0.005 -2.405 0.016 -0.022 -0.002\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.458531\n", + " Iterations 6\n", + "expr=2\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3383\n", + "Time: 15:23:34 Log-Likelihood: -206.34\n", + "converged: True LL-Null: -311.85\n", + "Covariance Type: nonrobust LLR p-value: 1.759e-45\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.7954 0.651 -5.835 0.000 -5.070 -2.520\n", + "Recipients 0.0955 0.031 3.036 0.002 0.034 0.157\n", + "Hyperlinks 0.5174 0.047 10.961 0.000 0.425 0.610\n", + "Characters -0.0126 0.005 -2.451 0.014 -0.023 -0.003\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.459673\n", + " Iterations 6\n", + "expr=3\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3365\n", + "Time: 15:23:34 Log-Likelihood: -206.85\n", + "converged: True LL-Null: -311.76\n", + "Covariance Type: nonrobust LLR p-value: 3.205e-45\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.5764 0.692 -5.172 0.000 -4.932 -2.221\n", + "Recipients 0.0957 0.037 2.578 0.010 0.023 0.169\n", + "Hyperlinks 0.5080 0.047 10.921 0.000 0.417 0.599\n", + "Characters -0.0153 0.005 -2.954 0.003 -0.025 -0.005\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.452198\n", + " Iterations 6\n", + "expr=4\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3476\n", + "Time: 15:23:34 Log-Likelihood: -203.49\n", + "converged: True LL-Null: -311.92\n", + "Covariance Type: nonrobust LLR p-value: 9.609e-47\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -4.0845 0.673 -6.068 0.000 -5.404 -2.765\n", + "Recipients 0.1071 0.034 3.176 0.001 0.041 0.173\n", + "Hyperlinks 0.5174 0.047 10.997 0.000 0.425 0.610\n", + "Characters -0.0112 0.005 -2.152 0.031 -0.021 -0.001\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.456077\n", + " Iterations 6\n", + "expr=5\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3407\n", + "Time: 15:23:34 Log-Likelihood: -205.23\n", + "converged: True LL-Null: -311.28\n", + "Covariance Type: nonrobust LLR p-value: 1.033e-45\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.7435 0.657 -5.695 0.000 -5.032 -2.455\n", + "Recipients 0.1010 0.033 3.026 0.002 0.036 0.166\n", + "Hyperlinks 0.5043 0.046 11.030 0.000 0.415 0.594\n", + "Characters -0.0124 0.005 -2.361 0.018 -0.023 -0.002\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.449368\n", + " Iterations 6\n", + "expr=6\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3512\n", + "Time: 15:23:34 Log-Likelihood: -202.22\n", + "converged: True LL-Null: -311.70\n", + "Covariance Type: nonrobust LLR p-value: 3.360e-47\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.9098 0.694 -5.635 0.000 -5.270 -2.550\n", + "Recipients 0.1211 0.036 3.363 0.001 0.051 0.192\n", + "Hyperlinks 0.5235 0.048 10.982 0.000 0.430 0.617\n", + "Characters -0.0172 0.005 -3.297 0.001 -0.028 -0.007\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.455797\n", + " Iterations 6\n", + "expr=7\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3415\n", + "Time: 15:23:34 Log-Likelihood: -205.11\n", + "converged: True LL-Null: -311.47\n", + "Covariance Type: nonrobust LLR p-value: 7.501e-46\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.7370 0.671 -5.573 0.000 -5.051 -2.423\n", + "Recipients 0.1079 0.034 3.193 0.001 0.042 0.174\n", + "Hyperlinks 0.5177 0.047 10.908 0.000 0.425 0.611\n", + "Characters -0.0153 0.005 -2.941 0.003 -0.026 -0.005\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.445224\n", + " Iterations 6\n", + "expr=8\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3572\n", + "Time: 15:23:34 Log-Likelihood: -200.35\n", + "converged: True LL-Null: -311.70\n", + "Covariance Type: nonrobust LLR p-value: 5.249e-48\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.7848 0.667 -5.677 0.000 -5.092 -2.478\n", + "Recipients 0.1079 0.033 3.243 0.001 0.043 0.173\n", + "Hyperlinks 0.5328 0.048 11.053 0.000 0.438 0.627\n", + "Characters -0.0162 0.005 -3.070 0.002 -0.027 -0.006\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.461358\n", + " Iterations 6\n", + "expr=9\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3338\n", + "Time: 15:23:34 Log-Likelihood: -207.61\n", + "converged: True LL-Null: -311.63\n", + "Covariance Type: nonrobust LLR p-value: 7.718e-45\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.7859 0.659 -5.741 0.000 -5.078 -2.493\n", + "Recipients 0.1045 0.032 3.224 0.001 0.041 0.168\n", + "Hyperlinks 0.5039 0.046 10.879 0.000 0.413 0.595\n", + "Characters -0.0133 0.005 -2.574 0.010 -0.023 -0.003\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.467026\n", + " Iterations 6\n", + "expr=10\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Spam No. Observations: 450\n", + "Model: Logit Df Residuals: 446\n", + "Method: MLE Df Model: 3\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3258\n", + "Time: 15:23:34 Log-Likelihood: -210.16\n", + "converged: True LL-Null: -311.70\n", + "Covariance Type: nonrobust LLR p-value: 9.141e-44\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -3.8264 0.669 -5.716 0.000 -5.138 -2.514\n", + "Recipients 0.1148 0.035 3.319 0.001 0.047 0.183\n", + "Hyperlinks 0.5033 0.047 10.821 0.000 0.412 0.594\n", + "Characters -0.0151 0.005 -2.921 0.003 -0.025 -0.005\n", + "==============================================================================\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_38981/1702950247.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n" + ] + } + ], + "source": [ + "check = kf.split(spamDf)\n", + "check\n", + "experiment = 1\n", + "# Loop through each fold\n", + "# Initialize variables to store results\n", + "accuracies = []\n", + "\n", + "for train_index, val_index in check:\n", + " # Split the data\n", + " trainSet, valSet = spamDf.iloc[train_index], spamDf.iloc[val_index]\n", + "\n", + " # Fit the model\n", + "\n", + " trainModel = sm.Logit(\n", + " trainSet[\"Spam\"],\n", + " sm.add_constant(trainSet[['Recipients', 'Hyperlinks', 'Characters']])\n", + " )\n", + " trainModelFit = trainModel.fit()\n", + "\n", + " # Predict on the validation set\n", + " val_predictions = trainModelFit.predict(sm.add_constant(valSet[['Recipients', 'Hyperlinks', 'Characters']]))\n", + " valSet['val_predictions'] = val_predictions\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['Spam'] == row['yHatCross'] else 0, axis=1)\n", + " accuracy = (np.sum(valSet['isCrossCorrect']) / len(valSet['yHatCross'])) * 100\n", + " accuracies.append(accuracy)\n", + "\n", + "\n", + " # Print summary for each fold (optional)\n", + " print(f'expr={experiment}')\n", + " experiment = experiment +1\n", + " print(trainModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average accuracies across all folds: 78.8\n" + ] + }, + { + "data": { + "text/plain": [ + "([82.0, 78.0, 82.0, 74.0, 80.0, 78.0, 78.0, 68.0, 80.0, 88.0], None)" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "accuracies, print(f\"Average accuracies across all folds: {sum(accuracies) /len(accuracies)}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'accuracy': 0.78,\n", + " 'recall': 0.7532467532467533,\n", + " 'precision': 0.8055555555555556,\n", + " 'sensitivity': 0.7532467532467533,\n", + " 'specificity': 0.8082191780821918,\n", + " 'f1Score': 0.778523489932886,\n", + " 'roc_auc': 0.8305461661626046,\n", + " 'k-fold5': {'k': 5,\n", + " 'accuracies': [80.0, 78.0, 80.0, 73.0, 84.0],\n", + " 'accuracyAvg': 79.0},\n", + " 'k-fold10': {'k': 10,\n", + " 'accuracies': [82.0, 78.0, 82.0, 74.0, 80.0, 78.0, 78.0, 68.0, 80.0, 88.0],\n", + " 'accuracyAvg': 78.8},\n", + " 'k-fold2': {'k': 2, 'accuracies': [76.0, 78.8], 'accuracyAvg': 77.4}}" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics[f'k-fold{k}'] = {\n", + " \"k\": k,\n", + " \"accuracies\": accuracies,\n", + " \"accuracyAvg\": sum(accuracies) /len(accuracies)\n", + " \n", + "}\n", + "spamBasedOnRecipientsHyperlinksCharactersLogitModelFit.customMetrics" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 63, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"spamBasedOnRecipientsHyperlinksCharactersLogitModelFit\",\n", + " \"model\": spamBasedOnRecipientsHyperlinksCharactersLogitModelFit,\n", + " \"description\": \"spamDf Logit with hold out\",\n", + " \"modelType\": \"sm.Logit\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Recipients\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Hyperlinks\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Characters\",\n", + " \"type\": \"int\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Spam_probibility\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/wip/Gym.xlsx b/notebooks/wip/Gym.xlsx new file mode 100644 index 0000000000000000000000000000000000000000..a5c5399a83803f683870e6e0f4df451f52f9a185 GIT binary patch literal 30987 zcmeFY^;eZq_b*C^bhp4JBsYz8Z(14=*fblY8$?Q^*>s2?9TFnlol?>go0JAA0qMFA z@Ao}poIB3_56D-ONg>Kcmo$0h`=A4NqGO`z^p5v=lBa?1Sp3k_pV1J;p73YGyB0VbVD+^b&SVI+A zNxzZ18USTmise7$I%b~#)Wr6@0~ooK4pOX=>kRU8i|IHu^g zNW@o_{*wNzuJRL}L2ehJtX(;BNj1a>u1M9mBlSDyqxRRLAd7?xf0ZkRxNd1T!d3Bv zJ>Nj~q@Rf)OioG%I{l>Zl7;{SH_@}yUqy}Y>L$I5pRgO@YQ350TLKC;TKjCz3|RF(+pV+)vR zmOEe266#ThpehBm2i^@YE=$Dz8DzXz7c7SplZrDn_=s4KOT<=xd~kJF>q5>x-K3=WH1`o^16-t$po z*x?yrcl)|1c*HMp-LJQqleI6a88A8B(wFKNa+rKmevzE1lA(Eyje8v~l};ESer$;T zjl6-|>?Kc}dk3+R2F{ehDMqM7kG#!0Q}br~7g$!WRXC_Yc6~J1ViNP`#ThhJ1xX=2 z^$s`fwjbpzgFCujzf~bmg84wKOV9H&{%AK{Ed*cVR5Oj5WXUEyYuO{`JDg2wgvVRg zTW(I+oj9IQEy;zElc>~@`ukvv|E-Bso$8sQdq)1EhLy)-_hslS{w;2jrTUk4j}J>; z=IK~UC#EWS-M6qi?9YLWmxLOGuL1`z)FRV@F3rVN{)h{#$^@rT#$_>B9W_TKUSYkm z9La%b-=UThntpbh8aZVk3KN~7yGt$_w-&E3C%xbbYI{VcdoF)Ip5b;FQKLuJYm9;X zjx?Fte$l0T=o+JL+fV9qEzJN%gLxCx>&|NEr>cIh%#Eeal<%s!F(%?4RFYJ@HC+aY zZBp<)fy8F${T&hAxFM*l_*YC=#7vP+@8E5Q)Zzl9hI=v-5*8wQ7Up9Aj0CL5B1{5` z>yXjSX5MZ&)0A~$%?PdY4-60QV0KtTC#Ffdhp-*Ay51Qmmf=pRc|D`Sq%;g(kZnBG zeG&0IWweX+AQyp#9v4i!C`2n=g}YkK&E#&$>Gnb;^QQ@!)%hOwqayNiVlLWFyJ(n7 zXd4l;ac|n+404aDU}{W?&s~=(2TSKWgBZ~o(Yn3e$XM=2qTw{f4dUHyDNTeQ63h8J z-&tLsjjjo@)I?0>mi6%B>wkG}6QA54xK6nAB8tXzVE8y97;ax@#dHegX4pk%X%qTvQ}+ep4qdxAtqPjN#&-nL zOq@{R3`OB2=f-i@e6+hWB{xJt_s!0OCa?7lpc*PjxzQRh7ppa+>D~$awB&De=t-C% z8pRpVlM*WuFy>+LsO7+o5BPIa%_%r4ec}H4@ej`bm*%K#Pj(aOAt5cdp&(HLD)C?3 z_jn6~d3x~t=MUeL1IWxWskCWK%sNKhl*S5h**_S+r0qR5=jvBJ`p7U85dW(oEb*6y z+5;up^)Vtse7T*zqW-f9>dy$<*JNKtw`~&p*UugYp!-Y9^K|V{G0jmc(VHV_uI}(v%9;I#hebm+uqxpm4Nf@)s_3Z?VP|%`o~_E z$A^dB&WF1lpX0#m^|x!qIi2s%cFY2=M_fAYPIp`$?~Vo7y!$?lx`^UAz&O6t;_D8<&E}i%5^z?C$8S#&%QV)EGk32zB@vA|%Yxm>Fk5?m= z@t-;+Zp(x2(|F7}{BIA7Km9un`j&2Yf7;vH8Sr>RaMfITy*gK9cl&GhuDN<^6*2!% zT0OUR^Y=?<;N!A^%fsbq&bG_!YUj_+_jeDl+nJW2v%7Dr$0O5~54&rFrgfryJcHAB2Hm&BshnTXo3)EdJUra{blzQmdpX`27`Q?|eP-o% zKm2g$m7jGlDrsEV;d?u>xO#uld)pc0rk*et_qcVqzaxCldfz>eb7g-sUfD3Zu{$w7 z@aFE&XT+uRZt;ZT?&8s~&LX#;gu7!_*v81efPDG|oG0Ei=+6ybp0m&W%tgIbW!A$I z^w#12p={J|&P+r~TGA^h$0fJ2qhP?geRzMkf$vU0udty1L;{CMZ& zIH)zJvcXQKa-qQs^*z~~)zA?pDPGXSTvzAa{$_``otcxaQe}oGX`GUDQ8Dk;-FR^J zQCN1z!q=diZ>*B-(MLJYZ+6D<=mJQ^ZtTB=|0_GZrw!Za#bw9sv3+a_YPyYowEyz{ z{mk~bnSwD%M@RJH*T)M3N&j=6u)zOWMflQ;q)-3Wcc%ESrZk;#-7Vkm84<7g`hVI` zsrV7muUb1y|1NT*a4lWbi1w{`-S!_m$$a*>p=RnXl^6t_`5LK|Gcg+zAXP8EGl!-Y z79CpLn;=I1`G?8&P%+46wc$&>w_ScH3$>{d872QZoT^3KF4H2S>HQS>Q3h3o> z%)yK#T39J@dxqQHj|#@OiH3gq^sKzOhk|yTjE>a(ypiy7Qv(AM$2G|?$u(${<)}zD zW(A|hHWxH!^iO|7uf%6g?Q*JOUnIAq9pqngbOt{2AD_QoX!e|-&aSIiU(gJ>*zsSG z{9J&H`<2jrN0rp!hnqD~zqNH`+2Tn4;a;uycvUK!uo=^RLjO79_j47AjzXVki(-y+&R3+K|L`DPw8glv|G3m?IH5 z`-)r&9^S9f7;fC2aubeVU}TGYeU@dfBfRDFG6n7wt3_#OjSX#t_q*pI`!?IixH=0} zDKBYR@hjIs^0$w#=z18=8;FNKX)}kgiBp$2Pk|D`1bTI_tw%-1LL3;3ZXI7j&3qaH ztUt&a5pY;IQibtFCS?_T+ds%sSl7X}8Wq9k9@7m7kE=))U7rA<)f5pAX1GB+T^W-9 zN$^M8yohViwdHhkq@o*SsNipi)Hz~mr4Eg~GJ5*-6z98bp3ph#8kObUpRRw z3rP@0E$B4;)w5H@XO2OjkQ+x~L0)B=jQXd;77_qdYcD{8T9EN~k1KN<>XoRP0jnQh7}kG2)Hnz=SUt>^aqH+gwH zzH5M6?Zuz$XfaiNx;ZO@&Qe6UEq@7oA5i*N3#x33iZ87Ry`});a3)&OHEQQbbZo`o zq(XdSTZA+@Z^xj9{6eVGE>`5JiusYT;60nOb8BzEiTJtx`bqME79t))6yExWg%C=d z_GL~BKymtU@_!nYfbY>m>PS|f3}ax$v|xTIo*Qag`>Tf`z}k-`=0C4Pev5|(eOcQa z)=lc{exXVUh+su->6RD6OF)I1vJljwO1Y?{#2=Z|5z+Exh8)9!zQdsBjX)feU#xu6 zMehE3_{E=`_r_6Hw`_5;OSihHzxFJK-A_g%Q#Xe9pxMmia}X8@wWu6 z#wPOw$KY&%Fw94fN24iK<-v9{ikOpRkxc#BUF{vFUB2C*ciAVCnQVpzD&)uZTuA_Ak+?GNzg+h;QOC$3XRN;}d9uh>KfKpT zHedG-Fer+Ja|(PbfWgf7INILpS|&3>xIM_H%}=XkG!Ui*qKDjA&H`Gb)3u|@1_cqChC4-%>K6L$tiVL@n6rOM{lq4-6L>X}<=_g4BV9{1nbUwhP8QUGvgl}RZ! z^z;(Cs=^Zgk@j@D>P9xi?i^ZE3p}ua?se6F#`Xk4*dU}@%WYw@8I3%tT2JRSl}D^l zXm`ylLuwDJsDeuS073cr#ln)_hVS>5n+yKE?N57>Ky~fh8)nEMU?Q4ol}8r!0i_DS zOmV+hYrh=Sf_-Poi7C^-I6y-SH}&R|E@kbGRMO7virD zo9TD^PF(j(#zD@m-GW$}UTGFA3Y58L?plj;Yh~tSXG!VHE&VE=wuvY!cSZJ=1ZfrgJ_p`&bprW7wOd0Onu{HwDa6dJ`ZhY3}I64&FW^UC%5uX zP^?{hW?;qDn+4aAK{G~m{!6x^TYTBx=?r3quPS(ci<%&GBJOB;6HPx2HVnQXVkiEz zrFh!(sv6}|UXETbpbQ_e<^RGGq7$!{7ypicYQw=@$GL)4Y_U{5IUzN}-k(rQ>V|Fy zF*|UsKwOrxykT#|te_lAgn}PAhC_Q8+KO!3%8@La^hN^jw_6YgQx+Qu>ZP-s$?h9Q za1x<#(zZMMMXVd6mRD5B!SHYVl~uB9Ql)0nJDG=xsNgzS5N*0Lt!PuIs&$^q0{7em zqm?(7p2fc))+s3Lm7PZ+eHy?l?uSOkXwWEaILs}Kjzo_u&-)>9RU z%~xzMOuzS%C23GlAxbMXMHrSwQwYfzWXT>>*j19|&K(y2F@~5S|Ho<(%c%`v&6h45 zp9{%pE8Wcu$f@KGHEJ$JmURva=!#Ho3g<8w*`Yt*^Zbn^mbHi^6$g>5ttiRV zE@tm$&wn(;N~|EIl%j~x;#LM*oa&LH0{SYZnxPM6L!e=2Q-&tiB%>$^_clG+FzJ#7 zs~#ow@1QT5;&;S>*3_p;CBtOwTecKcQ4CQbP_Y|iQqc5A%EX7))}Zh{{L}M;&pHq_ z_I*UTRT)+pE86bCA4%4XLb|}-&?VFLaET=BKT~PbT7jeQy&v&cCqPbcRrMt7--KBd zbICbfPJ4F;#Px5b#^6)k1n-CrPlR~?%#w`ZR|_SYCV5k`hz*@^ICc?y<><;ELmctW z2WC0T$S2%^I`7g&-W<$AfG=Zur#?s$o%iLw=9@WHiCSE zoQdZj$Aszdlk2*97}dTq)`pfj|6Mzfqc_&{+xkJ$EXf`II|;iCOqsB(5H9=vqll38 z;Qe#6aafHmYr8^2R>HDwbFDy5(pNiB+R-f*)t+XVR@msvNd)6(;5D|0`>avy6fmho zHC3j2d>aI=7i6OS@fh5LjAB+sUwuf#dKXs18TJ(-7L)Rpl_Zjh_*>o|Aztf&HH$O$ zgVYbK(+O|o^ebt0+vc}WT>efq8i<|Xm9moPwa)}QMjclv=a^zU@*_)urcuf;><5K? zRwp%k7}9>Tl3+0}Y&np{Y`R&nN`==wZ}f~j8{k-&XLLvH7y-IJ+q zp7=ICf+f?l!PrkYXBJL;U`;)xQF0VeF9^HTD0PrJjG&I*d}wP@WX&2DIaTRM{zc-W z90n=pcj!vIHF>Tm)urYc#YEK)6IYRrGBew&aT%0O&$WMzQ`6oU4q5UR78$zNeoo$k zi5Nxa3Z*1tSCrRYSP!Eah6v_e2bVGMqQ&_^5+?*?H3(Z z6PANW>Q9>&_IzlCz!t@RY^`EOZ{2~DwP}rkcL?&R-lY_vS&-i5+8=~C9tXMb>EYXGZTa>l zP6rl?88!N9d(um(5lue_OAho|pOKRyqt*ex08CtUUBo+tB)m6%qK3QBjzO9nn9n1}|(~Er|S} z(SEswyObMF@{dUGKGwF<=E=U{P{sX(O-OE-kY`VvIo1$L&dOe@k5aAPS2UOwfkGi# z)N{QSNSZb}(4S9w5iaow`%nHf%8uymUN&ZpE!K0lU)*8bp{0cPN^l(q|vJ5xIfc}Tv{d0x%ukP3r{CL>hdgm{* zhu*rm#g7(m=tfQP6BSMIP-+S3`P3kw6QJ^87M&46g?cTrT;(0dN7yy5>?c8Z?t6Whr_mRb^JGIGldsm_(vhg^>~ba=vrg#OjpQb%&<59zF7|@- z?}TlJ4~2Y{UD9*^>|xg|n@)h1;{;uS6US46Nf@|LRP&djwTo2KDbpyGR9|#34#GZ` z&6K1#(RSBLKc3U2k%s+Tv&%ZI)nh48M@Y&SLf))x6Ay3IjY%p-sa?iD2xS>0Gvq@e zXFRaC+yUntLbGfpIDwG-m=9_Bm_Z}8bu<9@Y;efdl&$SvTY8i_Tx2knX;ng@Sxbn7 zN=w7T?gvIs;9GDaRAXP_M_1||Wx+!~X;am;UW-(kGPu~QCB2ZtSAIASyegCvxZD!z zp8mz_`PP2otG^VUfeivwwjCm=oQ?ix37c~IAHq`()jN{+GHEil9^Cof{|sz6FHLA& zCDfKO)%vs2A%Oj*iK$sH%3tRDzb{R--!*+~0?x%?K9e%=f3>G9Nh1=>&04AdATL^1 z?Ul~<2I#giG@B*)!r9V*xg-UebUNO+EwN`lpnsvreu1YA z7BJ+#CyK6V{g4mgNX=AZOPdx0kDyf#M$4waZ}}J+=#z#$3W}F+U6)zp12#M?wM-(5_oG^dwr@OWJ+*b;X4lu9&7xkB_jC9Mh250UqgVTm8 zLmE{f8J)Gx@aOZJjIlr?hPtm42B2nI+RAP}sWKgM8N_{^zAaH)DNDi#ZUS5#r{wFv zoWPp)sjV=jBcoTd&a!C84CoA{Ork&cY~Msarz01VNuKK0K}Ab($QKBcowXKe%{LRy zIilVs9sqF10*&$$Bni2&?(-KZ;T)`w9!$kcrYRA$fMDW-7}+t39SNA9qT~4@+Pz>e z;_zrFQsow|__|p-HDW+Y%V<-75*LxmKLO%)1HO0Dq50*llPae&jHxzP4j4s10I-$% zPgUvEyx~}l9mh0S9ih&phy1stYzm}m-myD z#NW|;pOmBBoXR8kOis7yps4HN<{3C&>hHuD7?Ap{gX%NcA^%E^THV)LtGJqb&*yfV zDYv@5?{-ncAZ7J7!_FbHF=_|yMZ+)*8^{hnf42LdklI(~T_BAuolP1!s7;B^n^)Hi z4z2pvKO8Qa(cDD8Z~P#^C6{HJyzYlM2qvs6W3TfQFoN~A5Y{{XZ83AG*o&G&O~n1M z=Q_}mKc-Y;M{Cw|{x>(OlxgX?sZvn+8Cd$*5rlg&-UOU=`@u319kmQe+-6WX01N(( zXl9qAF>MPl+;EP1g_PxEyGhXfY#$V*Idj&ne^;41ARDX354(TcDyc!iJ-yq0GAcME z2b$Q0(2Q|FwTsXOHUE@P!qNAQmPN=aiovx6_|voiyUV5!xfuEy$wtx2wb8=k-K?|C zpZo*lKwGBwo|Pzzjxvm#-N#I>nbwP>z=K{-@{;J+>E^nS`jj3x54z1b99Fi1Lh@_< zLZM1|vIW>Tf|;U>`sVk64w$(+RM!l9lRu;mv`?dl=bvCw%?!kOTf_q}i~)$Bzhn*f z=~g!)?;7F1;QfggEFj8xZ-lHb;O2P|60;f_Spc>08AJNM%SMnRJb`#Eo%k=w#(nRn z(pYrN>G{v%bP*lXpYr4Bqs1n+*c<#IwfP}2jR)>_c(#`rpGF7D-Q|myR=n^=Wurdq>vDUd#M@FZ0Rkk$WNcTJr=~Fph zA8}YdbP7)edy7A$KA!|No@Nsb-PV{wDMjt>PPLn$1W-BrfSUdfwSH&($(uG5go?XoJ(ue(xVRGn8;R>zHYH5rw%Bd zQh}pCHwh*KGbjK!I~j`k1I>MQls4812Y>^xq=XR(Gyr)eJ7$}k8k0@V_I??lH2*ZO z9&G!-;bOXb5cv3kyc(?l?Z5a&9bJPr2L#5OQ!sjEPO-sv6W}i}k;N$gbIos%CkRLa zAb_gO=4emi%g&l3qb6Ku6ZI_wlWP3NdIQ^5DL>1C=w&t_v!KrrWZA!~-X=w6Qus(> z!%44Hfe#DGn^9Q@AkGVnt(b=F6H}CkE|DD7J zWm*|DoC~-aD=Nd{6p}Fg3wQQYWpJY2fpuQ8go8c1DE#3S`E#%70xumGP*@PvUTO5 zm`70d31i|~NbT2sQK!YNU5XlSnlF||UYQTGXM=6Y81p89nqV4L6InWy7DW`Zb$t^{ zNY&@Mc+NGb&F|NBBUf2QLyp}D6Xafo!${TteyijlvdBsNrjV>+P1m_{c(eLnx=2Ze zK5J=z+=-Ay#uyXJrx6M3W-Sv~7*lEgq1aQf)Ur=g17H_?6GhqH*F8ciqffJv^cu-{ zQj_33o%s59Tgxv=Loi=liri|#7Qg(=3)_U^5C)s|!K}p&CT*j4(}6}Wq)_#na|;iS z7FxG^sT)&V0T|&3%I83zO^MI3nzJ}kmmBtAM>YXG{ma>&PLNX{>az{{d;XkcQPL)%~j$B{C>x@!9 zfN?%>E^Ih#CetJ3*WM1zje+ppw;EiiPN5~wc8ilo*`vw#7$5$#g)eKtM3E-u1Va1z zZQ{|`C*pA+#=^l!%C2Dx*;x<#l`&e}?jE&MLpU^*RZ%)jQZeQ$^g=o#RQJ~uAx9(A zYQoM_#GljUc};!2q-!qB+h18pdK)g2hF)fE!q!UdU{u)i%gRbe^b&a&Kyf{G9O=gr z&DCJ|>}G$VHkinSoY0_dWKM^?x%q3Y@%kVfTQsIf_KmaV7URU0Bc~={^(^@0c8dr$ z&PzXkJZG^V^3glMjav^3AkSu5vPa~Y)jE4*Q(FbZq-o@W=KPfhxPehSIwpEoE{7m& zbz488ne;;aW(7~fa0QC87LHzo_G1$j{<3pD*OoX@{{hl(0$&9=4mJcos`-*$sWTY?P;Rr{_-es+;R8!;kfhm@I>15 z8-yUqY3tWZ=9WyS0O*4t0X_gAR%h%nPwMrV>-1bUHCjb%kp$b9Z%lEwBwz3rGO9tSzOW_O?jCsL&G{ z1#F!T))T74wLMc#eQ+~M(Fl+)9FenuZxS%lceXms;$#$N*<$~x`7n|{ZFw~f@$@z{ z(lJ|SON)D&h%)2vU-Gf~Y~7xykpi#4-A^CG6N2eGcmf^tblZ`7Qz)KAJO!fynUvUL zV`MsAlW`ru*@9GlGhJysn*x5s<0D&7ovEcL2M1mQUlE0;-+bF9wcA)S-mk8X2+@G#KWy zVo3H#(V`TC0rQ3Ij8}Raxp4()s<(k>4PIZ*9*1hOQBi1P`g* zpyR4i4*p+qw~2`=Zor{cUsnguyhCZuFNle;ef;AQTpO^01Q#3z%%7jRMQbMJMb`58 z%c?NJR5bwd`pBrPOWq$99Q0uM@&T3-3C2m_T!5uCd!EjD296S|96cW`CaVCR766Gi zc>1d@iM#8w)^7@N6{CQc9L|^Qc#ildf?|7#`p)F6^k1X4o^!+>#wl2E*|9yNI6oy# ztD^vw8&Ncv(1Ei#KrFH|A_u`KN}7+rh;RBw)r*QDN2q@OsYJU z_c1#-IvJ?Y5$j7=K^4RYMeXL*9imZ3q~Fz))0nhHTMk3Yd|`tP zrvRSF04|P8rebghQy)$+*S-JMB>NMdOs7L0 zuBq%200_gCDazjGsTRUpBU(Z{4ONwatn_PYx8vkMWP(#%WZ!4f3N`gK*q~>geTzR{ z?6>=?zkz#w=u9M98?&zD%!WU}KH!T7H1&~c8cLNzrWjV-qZptcBspZW6$-HMM_{kFI zzV)l|MC3Gr}Tuq@ourQy?4fRas_o4yDAQ97X)TXmg+|Ar=i%ehYK``J&V ziJ~2W310yg$~vs>n|DNSumd)~d)n>;d3z;|wdsVfM*(iK>#nhy2yg*>epj%2&VuNo zYb?2(usQb$a8{AjZjVHFkl2@Bl6XDrUfgTI*pkI>=;k6S&X1z?dH(~qqAm}*DQHQC zVQ`MOYtHiw&GDOA;!(i!hs4m^AJfZEBJ#A~CW6ecw`)EQOua}gb*|~?Ms%;w%RsqQ z-3WLoqWrW*(+2)%*48Vby2Wsg-@LAZ)(v3!iE&ocm~guOhJQ2O>T1N-2J5llC?PV- z>=HgB55yPf=dUDeJ_QV|q)9liOH>&XR4K3OPcnc!pqxmSiToI1i|AB%g-rI?n>8Qn zKo017>@In=sQ;!x-^qX^;u$&of>O4!(>AyEmhoG~b;2%GjTsPwCXR&7@d)$Y!Shxi zaVLM8sR!qB(b_8J-#Z9A%p@;WcjtC{ddESLgiCz52lvXxz+m4Ir8C@X=G(k zel72<{klk{V&We#^eD& zQyLBQM0;kLF!S&sc60#TsWb2ty7a@s%8WJmjiAIp^|`u5!Obv&l%hR{_3r4b{wX7MqPx;aD56dm{WvP zY*^&@9H!|RC=5%gQ|@l5);}UREop-Sq?>CUNifGrkIPyKm6- zCR*m??qrNIoqidF4c?@`m~1MrKadO)W9l2g2IIO`gmM71{sE)21T+Y2R*7_2XMUC! zW8q}}Y0-g}7hGd1Lq@rJtrVb|@MYiLs4o`Chig9ef#~T0izeJSwJt-M4}2d{4dmFx zUJ?qy)A=|U)|dH_qs6W!`Ay}0<%2sBRyj)##HZ{0ZjMqc-D;#y!p|Cs3~>JI zW8B)m=9Z?JW8I@RYm(}wf`YV!f|YH>e+otgROtCsnAZ%0 zuqCG-m=RvHI6!of)Gz|1NzXpPLmf)KEs4l@e*sa4&g6%>i`v7L5(&zjB^Vb~Rq~-y z1Xu|L4o~doz%z;uZ#GY`vYe=hXp}<${u#*CpXoPJB;=T2gpijG6s5e7<-9+|(4R*3 z^o}Pq$msLcE_0*$2wVfmKCgu~*!@I=6BL_CF9B2VigC+pYb67S3@fuJ;NgCOWYNkb z>W(t$NQ(qi{F=fwn(4kpFaRdAvQM~aDc$L?sUBR}=Vpj)lsHaMELG~BSKH2gH_~{;wO~3xYkC31Mj1N9wV^t+DveN0l{t;9gv{_Wwq+s< zYR#xq^>s=-XC8F+i3XA=JjCCSdeg;lFcvPjjq6QFXf@xmLKrU_UFEV~~K}`CWz5ZQWCD#VoA7nW~sN&yr7-ovc1HPtKil#7>arpRfEh);AsgEv7_vR~p_ zfH^I|3szmwr4g85g778F=aFag(Q$k$Ja6MGPY?J}8sC5&qMkHo8OW_$Oraa=ZnOd< zR4;mg$Oh28`REvay>?LEfv}r(b00YEnIyLHo&bs#x?<}TB5zJCx$ei4P`QchIHzpy zxDtQjiY&TQ2-8P2r(B{rK{T|rgpRSV`_ZL^b1G;7VURTe(D}T6BuUoRuk=~6XA5`@ zxaaGCx4k?Udwsc%pK#ZqQxzql9)=Mj6lEVh^6p&4H3jLX!GPly+icdF8Rho{J4YbH zMR-(;vKeZ2^%NI$$Fy9tP1r2XfP!xMi+7wrJ@D^T0Y~PcBrlg-e0;CL+AklY;&-p~ zf6t`6tY!bhrj+xcFV2x$tQu`%mjdEAfO|Ak=lhhuiCjUv3PSuk)&(( z;>$fDw~ocq>yJ-tt0huD2t7IL4E|-rkr8d5_$Lgt0)ul+>5O9<)^w>L}E8c7}a_e+&zU~2*^-Vcx(^R_V zxCNVWpUxSmymOY%#?kLy_8F__YZ1W4j`=RDcQhU|30npF6N1oW>Ah=I%qKvHQ2^T! z7+<;eDh(##bWES**wsDX&d((W@^^^&bStT-s?#A=D0q7teinc8kFKdKag5nIDsDel z^)C&-3DD@_v~iPy12Z7gfQRNGRJ8!_?#zefm1q%u(0Z2! z{ciOabrurnobTa%DJB@D3$#QanNIo!FG`6fcOgumE}JcdUd?@8h;S%SY}rUoStb~n z25D}o{_sG}fOwB+6(J>#wU&6xIInMiG@g zYVr-orP4KZrgbc88YIxdhpC|-Spu-S!PG%8%^KJJHc44H@gNWQq-T5M(!h7SD)=D3 z7dO1V58&UlP~akbs@?If2hr&R$S*QXa zYRuE{{&3y;xtkp@Y_#xhHc*#rJ-p{DJ6S>sKrruNBWym|C2m8a_G^&aKtN06HZOxX zrQe*t5m*)Y(vjQ{{8R$IP&*98B}H(RZm2pfw#RfRX1rhw?1IK_Af zubDN`YzKlDBE3{fzZ1{GP`x3o{;wkcR1=IT-M6v!S`ZmD>1;B26|I`eq!zo=Y$8~A z=lwH>if*Oc4GTv$GGAof_jRS3zgY*g$qCCVugn&Z(}5)S)SSV`7DxFK9DVMd54Bmt zj#61lPswC9)*JHco7~}$615Rr5A2;)=Dd7?;kgZcHYl-0%W*Hk-SB zy~Q=(^r08%?W62QUwrPI=n4v{d?~WH=nb;c`3o#8Y-wO^io4q2Gj>!2wI!x#*7-+c zX(C*LlD}uId#?s>vP|g$50Km-&xe&|=VN*E)z>*P93HCy>h+r}eMC!$2J^cA;_Cfs zT1Q8?4!|D);-=B#J_|iy7;$8{XwuulJ_0;~T#hyG?}I=ybEa7q$iAXZv-BWS$~guH zoYf@K%grJbFO+vmnFC0#m>24Q@&$IE#r^NY+OuYFgiva}i z&tEQTUIPp)4Am8Kl$-l!nK{cu=UXin5Y&4ju%LUF3R?9)&};5*%oBk|mN6L3I#9MF z(O-u;vJk0HZFdj>0CN-}0sssv4}+$2knC@@4Duptz&X~i$%y0P z&4ngVtMa9XDj{Tr_L48d(pAsk%m z?%L7*AHMJA#|##aps#RKUM(o(WW=ft3MvxBPXh$_M2-S z<#-fJ{MXQ&;`L-hMu zn@ljkRZm`*+{K418+Mj3$AG$&x44>&>~%`E}@PTt>Od4g@bBZMK;YN zGSI6jb#OJ*y9x*o=SUX8XDDMw*+3uzFcLoS3&xSKGNc=E+e@{w_9$uD!>8zgPP%h; zR!RTj!qdB|X$d3o5e?EkW=g(FI+#rC1#*^BLf0JWh zWWLJU#1D}eOqE{+gy!4cq^MZRlwaHWr4WKU2ZTp%qEdrCIy1j9ZN*b95?i6A?ucNk zL|nogJBqbKD0ztC;fDvufDVPD+FLS8a(KefH8f1*d@(+-QaZoX>x$L z7H7?ik7aQFP21$i{S1Qi+jbzO`o8fVIR$>iBZe5oY0FSn$yd~Drn>Kh{w!@uWmn_%gKXYHNK#PAon}1}y%D ztA&}MHp|o7Mb|D-bv^E%FTkRsH3KaA9siaRA)BT*Yr%br1XnQhf^jgc>{pYPaN2>O z^5v=xR)sd z?*io7J`srtv*J7PHIOF)d{m;Q4v22} zq^Qv>JzVfCEi04UB!y^By(Bzn;l<0E;d^{0ey<`UaW?Mv=#WS_Cyy15-JIdaCR!dk zrDly14>J=*TjQY*7*jW|Et?KLln)-ElvTJ`H#IGzQ-Rrw^?||A@_%O^6UfsCJ-vAv zTQ1}$k4--|0nxWMMiDIa6|J?w*Pq)Y6aGB1PjnlsZ8up2MPa0N5$J{*+nN%hr{ok% zi`X1%w`%�+2!x9pSH@?4||;lt^{hny0UamSu^~l3Jk80tx{J#Ao!iJ*s@k6L#FI6bhiGh)c6}|I^NwYLxI0S6nv^(eHP3Wi831zYt5S|9x+`J4n#0i1`DUSe6o2w} z5EBjlq01Y^{NN_sp-&`H4ISK7zN?@prpxhd?Lat-H*()NYTdofleS;7q@_bviY+Gt z^+i8R>R%z};X_~K;b>fbz3-qugxp8JFq7+A+5USau&b+geD1uA`ot$T@NL4noc;)k zm?HcO2)g=)g1KPrES{<$~pgP_aww!bH6O+YLhRc#=#wghGV&iaELq(P7W9#R99R7T$Wu zkdXL`+?{{iz_3_jZxnj36}47FQZscNkvr^C>^)W)tQn1u2+SA;geVmX97Ie7WaQWp z#=0k>lizfJR6S@NUZx}^XA13>6y;&}(*_2+%HO7)T;mQaVP3DabYLNa2u$ zzElRlegTP^VG&NQYs_Xru;!kW0Uv&llJ{&Pbxi5+tWf&rv|k%jAyT}rnWJT9l7+0( zv{*M;W=vBE!QzxarUvMH0$CP?$oY^c*_f~_4*V*+(hbnLQ{L0yZcyQBRwQ|+C3KPC7H$PMVLOue zu4{tyR50)^mNF{T4oqPKcu9`bLJqIttlCAAN#;0rmJ3Phe=PB*WE&s}keK)iBXW&sD|W0=ZapD&U0*F|IcKrx*$C!#~}H1`Awi}nO^KSlmL2KY>X z?XxNRyNX#{W=LNGWYq<*E*V}{ZE@UE4|>Puu2#4~^6bCIRyc2YEf?rr)%^?@M@~9- z?CquZaCCk+yQBkM{n^d`Yd4&)(u`L9ugrYn|y}dz(pam z>v+Ap{9Q;bis!4;z z=`zcvc+ej^5Tq}Rx%YWLTDb6ena&nJOqe}UyK)f9_!mh+*9)yqx!-GZw|w+@%H*c% z+s&}Pv>>Ahgfm?ZeOsfm%-#lYY=@J`eQ{+9&|I8Ia)`L9*s+vjRUUqbutdtdR;r+5 zkZn|^A-6qEVW^3s(g7T0Yv4qW>kVk2SM&92?Usm<8cQ&fX?)X__Kz^GyQbnzG4lYL z%X_Q0fct6_XUgYXwV|#(;od8(qE|l85|PYOJ!2KYzf?9O)!Ylt$yHPz18uw|uO9_Y z1qGD}szm;EL}>OB$&5~Wi-QodoxKFCzU?g>E;!GC)?1O^=yOx=#+kuXZ%38B#SCpY zPfrBA@V|eyv37S}^EIl+2q^(lHj2T0Ip?I8?)=d?I|fz94|o2mrTk2@^Fk*14TNC;(yhsmA1T7 z^?og`?Y_e#^dB3_$`_dpW?YOM{SQ+uAjhsZrL{X9S2Lj`RnG zvNj}-F>)Se+*86h1S2f<0P2*&yTSDv9hlpr=L^c@UsV&aVy`a8nM1mGPj+}Z!aTv5 zaExBrI+^NJ#b1YSbc>$jTIDgn2I+pZsyf3(FzD#OdhKl*yQ0UA0xin7x*Ehqk%&f; zbE`;#gUpVGutKjJ&WskK$CRHeOlUPFHcBCj^0k>@<9?q4#3mrv03y!|%?BIf0>DbaLs|*GZ{rGg zH=tS>akFW{&5_a=Rui8GgFqQ=;hEHoM1v0RjGXW9^;*tL>EUp;7}qjQ~4St795QE%TP_%6Hy*=`teQE_Hie3F=s$xlpZXgh6<6-wy$T}BcOIfclNrxH07n4U}&4IIl+D3Z`N z`6XCnq#6R%sw3T%KTZ>K7J~J^pk`$pF9a$z6^^irzUG|@r)MSanJxtQHC5OcLsUyf z3PFagI4NhT#z9206u5f@PFUnNFGdOBmRPw7^4nUE32e_!LOgF0O3P9jx6}XR4ZMg4T zo9S2vQDk5;p6t58K0)S6h7ZBiTI23bcG`LvqEz4mXxLx^pk0H?2eE&|NZP({tcutb zKrim;id<}5cyct5-TV>}WYb=k`7-LZc|%M^k_~M7W_F06f*n2kJ1%NBoUBesrXqy~ zHbZTOgFBHuCyj(WVg8Fn1Pby5Ye<4GRQS4?ax>=nfH-ai;2+VX4v10HRrFv_UgturTJoskW1w zKzU7afZN>j??u*sPs?47IEPC%+fkV>z&-JOdRDTU=1XkeLrT!X%T`2FlWE= zcc{q+h5~~?{Q0za%iBZI`ueVyj1HtCTEMgf6eN0<29~WG-@jxkk{1Gbhh8`!E`n2=WRYlBZ|WUv?*{SpG@hpK0w zzk^HLF1jXCV8qd1_-#vTe50JSMf+a8|M7$BoRqD>stR0e?Mb6|DnJg=`KUgZ6VJ2M zo3;38lNJY!y_{N$&2yxOJy0$z5sw;_50umVbLsjx+WMLHNF4ngr)}w$7oZt~JEqur zaeGWn?x3o$vqXvB01S1?z+ z-KwOw7kCNwD#(eW&vw|BKK~9pm?}wy@cOMbSB05DC_g*bfs7^Hls}FevJruqzp)^4 z9GNLZ68v~-!_&Ok+(iz1qCwqC?x?;Q zoSXSs$~p6eqp6bwx)Hg^=|Pi^RKAO&&*hNO~CppvxbEaan z8=t$F>H`@4LE<*M7e0Lt3g$`zYLy+!!YaLj!3I2^(4p`*@mh6EBu4z4Z4T`w*bdxB ziTzeaL`t)>`qE>}SkySVs1pV3A;?$h_l>Bq-9C=6rII~m{BHuPnfUrkvISMkMxCtT z12`e5Yu$2XI}9NzPNlcM{kH{jx0uSPK-q(6iI5TjzUj4c6>t72=&p22K$#Sy2S_}v z0#{QoE#%PWwKR+|a`7mTZO~RWP0)FO$WO&W7`MP4juKE!$Df+1W|Olv@b4pB({n>g zw?TclI*+#z0cocch7-^&>DBv6__ybd8sxIPn#qT+Ttu}im3;#w1R7F)V3t900rnSC z7RF6SFg`fLj3mf^>eD7$`_Y741eP~s!lUEAED!VzO8!{o3GL|Yu#I6CiC_7zIN%$7 zDaQLUi+dg?iED7mep|HK!k>32z-#AGA!=D&jlco1ofL}r2h{b91rRzf=NW)DjS0j?DdEqxr{VCdkJVB|0XmOBt0(x@D$|{K(#Y?f3^i6IRFvfS|=oF@f z9AO?Ea6Xn74Qp9nv23F*m*VVMtuff)Xr^@)&YO4Rf7*GS2T(T8t{jp8zk`}%hLuVr z$a%Bd*Elntov3lZwHJpH&f~#ayVcxq0qNyn*p((kqRw7AjWG%4^*{R=lz-?$%VAht z`KjBJhOIXou^3;p%XpNN(h^n%gm9Wjy)Jh@R$=4^yWL>I{l{lI8g|VK5WgApkidSu z&m9Jb9K8U=4s!5=^?WhHdpf0TVR?57DSK>Fsi_dzELPS^xt2uzNpu^j3*N|$1_B+! zt|a20YrpTR@N(9oezfL={ww3;=vJ)ZjvE|Nf#Vs=91I?i6=i43L@-@9CGV+>&H3=r$d(yaBdy z@UOV!ReAkQtosM%vXeDZJfsF*HN?QO%Ok-W0!fA@wwCn{4qk>V^+qlt_Asp>Pw|;e zy7W_Sthf~|NFx`;H@Rtm!kK(}=VC1e%flNYtR8T!H;^~M)&uc{xlDj6m6;YpG>|e@ z9){Dip?4|g-pU7wecX7dGXIvr1^^aY+y;EO1YaZfb^86QcCef*bX=B08wflMefroM zvg2HBg&PxQ)`7BLrE&I6>G|Sx_kh0@L!Mtk$uqQdfHMJCL3!vRf&iY{;$Uflt<00` z5rVK3uz8J90*MkgCckZ|TgEu9wMfuxs9vZUutg>U9yT>w4=|@So3-k`X44m!EP4g9 zR(&iL&=ce>UwA}IS`b#F&3AN~mi|S^{w%#2JoxV!JzA3`UEi z7YZU?PacN?BLmGI5*h0)eK?Je>h8*^jAC)4|Ct8-ygq&!lMFIdfD`Q42Z|XCLjSDl zm%PSIQIq;b5QsuPg%V`Q4Gc6wWv5;kyX?+}?8;z0#t}uGBm*&C>Nf8?KHN{-1E&#Z zq%t|lnP7|Yh}$gMW&jJof)fc8lXqOcfq?I+PZ!7DB*{8$O}SR`tIV_gS~~N74;n2L zMtth2HP(`0$|}H_EUhD>rVJe5@GzoVzYOU)VOl;n>vUiOW>Y51og&BtG?AV!Xj_{8 zrj8g~^cX;Ejs%!Zc6D2x50lT=Q-d)8n1K@QiCRZE8nrP@Ii<2|uhqGz24EnPg(37Z zv|$!aZ!h`y?ci$w$AHNkE`d6_ODi!`@58uw>|%L~6>J=VC1{&;BHmsSbB#~}5pTl^ z*ljLx`x!mujo$pYJ4Y@Bz+nw5%Y;wjOb5*{fw8@pp3KW_|E4N z$Faf&bqio|ZkVZ@uK09V|E&2IDqlj+1$y0)eg@wIim6f~6lBe%=#Xr6yCmFMXWqfm zL%P-p!3-`aQ;1&-V|?+t+{5UD*kj{K&crRB7v?drAEX&!cmm?33W5FLO}A%NFM z-UFg-{#w=V^b``&TuK|Ijm@I#%moHrL0gFUD02Wd>}Cof&BO40yla~qPbZ&p5%o$F zpCN-y`*+yiMfYMtCR)f>>Mg*ZZV4E=D-ak7c4LBI5tjFy%p`O}^20zCp{-v*4&{e& z+d2!NAqn_jK7YotPgKplVSUQ^%cb3f-Jhr0N;XZNN(83F3Wvn-L-{g{fOD*tbTPs> zQC-^}Lis7ctGVq`P~xvtV0+`c++-8x3Wdb*L3uKas!iSxK%56Eb_FBcHChf z@@u!$dr(+&rv+8`d=|twfOEiF#-qeah9Ec44Qe2p>ShJ3oe_g%6LvkMgT|b=vrpp8 z#<1fut22Z_urAOU{3h-yQ7%SBuqfPXju)YqON96aki%T)c#>%y3ry^yfhe$U^i=xK z-rLfU$G~pG1CXq~Bv#O9`-Q!tF9zwsHw5IMNfhy{RCDrjupcI{ycivO_=Xo$X#__P zu6UZbG)L2v;8+-z>$Q-O%8`MqFFND$ds;86DpK;>@UvweBj5=CtVyU22|8i4_a3}T z;{l#gAm|I~o4x-|Y<~p^IlVudSyqn8L;2x4=W*>Bf01ENUi}E=5ODB02kJ0kHH_G$ zvh#1P;RCuyf&h6G^r|YV)69kp)XAKiT;l=$1mGT1uh8x<;5|P1pp)>;ao^8}Xh`a(hE*K?BTqj7pg0P91du2gdeUm;%0h}12Rl3Ipx zKLS|P=B?wGA-#oFbe^CSk4ULvruvg0wozNs-a_Zase0srSan!UPpv;Vr7cak>m|Zi zMkHvRv{p!EVTy9pHnf5HfKd;fq4JQHiZ6vK<;WORIEd*D5jfKl?u*<#E8mp{QR6^R zCkr^=V&c!B`^*_#fFo_PZbb@i9lG@b;+te17!{8KYkxSQ#9e$v{A~er*Rc|UWwsJ+ z2bcQUUFq;a(7Qn%AWETjJ~r;EOSabj4K?Th=X*>!^>G1XG+(@%v|}>i71S`p$jbD+ zDn!CoCd)nb#W3YGu;x@S3gmg+hkS%fz#dGql?{SE4q`SyzRJAMHji*2s+v*&Eek#)DZakru?I`>!#KS6~MOI!~r0cjnbbf647LFOG>^DN%8bh3U02Ks))f? z7m9_zL9+%vyr!-8Jve1H&36GupX|)#_qgljtb%_Z2r-D63Hd7Z{{A9wbw3$sF+*sB zaLSgniCOdf`MZar$n>6gI5M;Ni!c6;fSlb}Z!CAvPMn1ZES!2v%9f8XeqfKHytr{F z`@8(yX2+O<7YmLu>N>HaTqBR4F0WX!-R0TdQDkxB?$o`~F3)5| zB}GUOYLa2(1w?kpK6>F&p%%0ZrXuwM9t=3JGMBZ+xS z`T_7D83KDSb?>?7aUf^eVn^c;DZnsFL3eOT7st?5RpGc;$r=j_ol8@%RK1nJY)0b=Hk45-Tkz7pE0jB=<0Xgrp(pR_PUJB z-g5J^^ZG!|lZnj{^SqlMYfD7D*Jr;`=Dj1&PGx{gLjU&#v{?M@B;uH8Xt^Xn5`=%g zMpWRhYeWsT-HXJCgUq+DG1jEeF_>8KjD$5xO&vAGmzMUM6y9J`@YydGPdVLO#^u}* zp~ijc#MKv&doG!K?qdJ*95nKg+frW@KC9?GQ>UCXY7Kp3eR>y`# znWJ~IxyP6%B06A(z-L;#Lj<8%pc)>mUDxXm-)P95NG7*xW#Z9al!dzRSVysY(-Y$vWg4~MapkfrqiGBELKEGGAiPEx{e_-ec2Oht*R`mXg^Z*&QX`%A7q#%F%?>MK09b+Sw1H ze&r5aOu0I??>}X?;b=kO6($}=Dla{v$#Tv5S^BGIuOnWX9p}X|=Q6#T=+esD@gJ#v zcVji3^yY_i&&|7fUREh{F-*d5=tKJCgBNEl5B2Zpavt2y}|laJzr zq_Moz!kTMvTZ;1z$7N@XGG$!dj_Q@ZBYYP}Ot>pQK#`2hP)=RzNSwqEF?MQN-+8WG z%R6M!bri3W+$Li3`$>?Vb;Fjo_8zw&)%*A{6HHhl-0AVC;8L^0Nk~@|7wv265Z6A; zoGu5&$%jSr+783&Vj;0@(>5JonyIKo{k%B5AM?$Q$4zhA6fK-Zf|~ZLcVGy9p^qs} zO0I{_HeC#oupG=fb}}A`o#Oin3U+!;qN8)AxHgz|{puO9b_5rL#q&6L)a{|n^Rk%BXi zuR&sq>qa`s&7=?O4n0;?o%OA-F#o-tK}J=%7CRzPo>rPw)*(hj&Eu2)ue%?< z?_{YeV-W~nkv~(+miDU$e{q@z{aXDNN3Nmmfa}Kf{>9mN**iQP$nys>U&)iwR}_nz z&c{BoYfqwKfDSZB9B~;WPaUS)DjgkOKIQvWbX5GQ8qpzFzb-WuV?xGskH5Z6R!MqZLyDot*b5XU$1}NSiEcW1x_nU-b!^LL*VWATX;Qz?d!^j zOUe?fO-?FZZQZW+Q$c~`W?Hg4Y>$q0IEvq9$h%9Wj>}@)`}`{bm$hb_aqQujS(Y*s z>uVQPDC{0w>H2d?$!TuT^PfJ4jqHHB0iDS*VrPi$DP;mfd@4s=+TlG;6N%C&}N7oXS>>@s^_H~d&>S8g>9tZmVYCFRJRB)9P>WfZg(1g za5oJ4;;lKxdz0SdohxW--FOMQgHUMNySiENoiw*Z%X?ZEQw2>12l|7QUq{VNKOyN6 z3E?yOdclZiT8~w{8X~~qwN8G> zc?z43t$4Dp1YvTYlQ~DU6YrJo>gcK)GK-?1vHJqjXfN;Ru&S)}cN1ui-mPwcb39t< zT40;FOX?m$%5Kr1$9Ydx|Exkf;OdX#~m|iN94>zk1zo?))jy2fVpb zFRp)V|BP&v3jVcq-f3QqtmRU3!(r3a-JeP@zqz`i`fA>K{p0(g==S8p!;UWC0^z}o z)|*4|=at$w@yO%*a;x7pKrd=Y* zYF=C8NI11%k`!z&1 zZX(AFm@U%icU3=f_YLbGzp+5KO-49Rb9!am<+eRNOm(faclQkSr{stxSuQ@m|9DB& zR1Eb-?|Dui!^BcaywdAZGJeEDqoM1?|R%NGJ4R z=Cf?!OrFJ57SOsUyUas@`GipdsDkZM+nX5mV?BRC_I&H&NMCM>ywS4DCqMlY;wGNh zBR@7~f568|KKJJ|iBrf>eYXXbI`~>Pxf8Ud=Vz3G%`rDYZK-ZYtL;mzZB8gpZf5_= zY%a@i%*Sv{>w884RM8WK$LC5x;g335fqX_q%FW9~*wLkKT2qwNWHrZ@;|*siK2H(+ zkcF;g#VhzA!AEzl(es&;uOs3!q!`2!>+>m&Z=5fbYL!RgOZufzPh(c(q<|*U3Q6lF z_&tt@#2Lc;upxw25t2i;(j<*%o!@j6XJ#Wzv|cP`3d_qmt`(=4Y8s zLscF5I91#v<;egxe^Ta))Gm-YC^+q&&=_5zE4RT*Vrl4lwk$W}YfoYyi9UaUb{5Bo zC2H;5CyXJhy5%0%i0)8yfO*gx{@LZ zb?&!jG2k%M95enXHJ$~y=?7MrX_MO_99=#%rpe7ntvQ$7Ua$j}%tT|E`DH(N(JUgm6XBPvD%~N(bej$?2J%Ytb zbhfnQ-7{D?F2-s5QbjD_iz!BNcbA(VJp|nZak}6vsm_8@?_0JK>xJnQkkpli!>FGQ zUR9cW_vIp5u}IQ3A)MH`KsT`*g}@vudS}4<>nPBda1uCN-F%3ucJ*Sd1&HkQJRo_H zb6Go(Z{!Md3b(73;=ug;q-b<^T0GpW%=qBm^QFo$I>{fOS?&?ePq}IBh~m|H)f?Y+ zVzUh@GJ21brYiBip7tvL>H)X41&TA!rUmWPsj2SfAG5_=FC7zn0n#b;V56bk`=9OC z+vk~!t@o{sU#!32w!lXa$XFRn{A+&zw$6j=LZzXLfmLTID`8O)19~X$%g@T@Exx;~ zH1}k!uoJwe#;QHJ%0%>~*r1HuVI&p>wH0f;%Ws94q%e3*5FE%6N~1Wft*>1`G590I zC?KshI0NcOyc;x_seo4C5>Y=aj4$tkv`wDJU*f|OtrbZY7t6j^6=zvfeVs(kO4!Mn zl*+xx!eevJ`ye^H*OV+3Dl&N}OtnZa&J$~cY*^rM-GZV`iDZwG){aefy%+9%kaG;7 z>sKo(D__D|AvK+8w&C3#?te3S6pPtcp%6n#+B4$i{)IbPBWo< z?!9|2XFe=%L+gb*Yi@6)p?_DnSXGP^I^PCo-)5#Z7TsuNu$U0BnOw;+U(T|5vuFfE zp%{(S1JgE1Q)gW{`@9`bA=C$pT8zR7_qrh8#*pP&7~$l|M9f6oQ@u02=ZO>8~g}~cS79yY3Lz$!3 zrhKZKHDYYKq@JN1@Knf;6^2tZDdW}H8^oP_^&DKVl2*7z&Hk_9Zxi3{bcdfDavFL={I$g{b(~T~Ac_OF93-3h zY#1{+ga06IYx(tB;V5|I^Ja(e9th&w-NBR+evCj5pF~NITC85~oE@RZbn6~iv)6bi zMNEUJB8>EwNR6o>@5-hZ<1!^Hj$Y}#_6GN>bqhG;;$7q_Jyy|n&;F+IknyfwhCM0% zLB1Vc2Fk=|{@7aVb-TUKfcI+as=ZXs^#>fTM?K~SGc)`DSk2CY53FXu ze~N)AP6DKpv2nN7@^bg^=CyYBvb~++K;E?fpG5}f|5wSTYMp%4;RjeZ3jMXN*^~X0 zjf66@X<-Ev-A#$j3o#ndWQY1-_vx})x6q8$H$OeTDvZxPO>3v3Hr9I{qfB0eR`cGb zU`F>>@<=B?-p6(5QS~?saHlcX;$~(Pmesl*RmP=$~B%F|hk1`r_cZ%DzLhtPHu#>dQ znBgeS$zYTTcpy6VoPsB+_7g$fa=S~$#=m;rITo@zI-gx*wt^V)7IZu159&!@R_o!h z6L=V8xiGoa3XRT|t~mDk#^B5c^(GtF|46C8OZ02~)hkGKR~`6dNmbz}nh+h^E(jbVKT>ocyMT zCyP%Nr;9ML_HFP@=`QU*xqOKizJ_VQpyUT~91;KLptSVx`2S-P7>xh=dy^vPyvRo! zeh_|*Q}p5~a0zU6AD-=mNMt&Amt86%TG9;Omz>0Iw`9Itr9tQZoa2{>;KAXqXRM_= zy6e@1*46D)YhGz^g3q{bk9*}8>08VKNR60(ur;hy5lgXqmMypHHc>-kZTM~JR&|-2 z3Slg^0>UDRPkCNEMG(_Ia9h`oKvZM9hdy%~O)=R#PwOHp;H_$Q*p%gGa}&Q<9u>$8 z;ay_9NDryKSgaeq|KM8nsxzBf=RL=zm%vu4NleW4i9>GDTeD47uyL*EipOAkhwS8niKeS{Hjn|HBvc1f%T?7WVoePBpB{4uOS zl<6q+>yHF(%Vbe|cZG@21Eb8+gK3$!O((=>R&T$zAzt34G7%1xJ{+^Kj;Pe9T2c({By$Ce|O!#-~S&!|1HE{$*2A^2i2ci{sf)>)`D*Nk6QkMp#RkJCzSNJ7Ejy1wEPJy z{i)zjWB6|cKV1G&@V9CFr|6&d#NVP@?*AkDr*-kChX3BG|CUEX8}UFx`(GRPpW^?$ jsQ#z8jrV_u|7(fWQo{nq2pW(@6(6k!unl-&x1atG!QgkZ literal 0 HcmV?d00001 diff --git a/notebooks/wip/KNN.ipynb b/notebooks/wip/KNN.ipynb new file mode 100644 index 0000000..ab1a950 --- /dev/null +++ b/notebooks/wip/KNN.ipynb @@ -0,0 +1,1708 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 64, + "id": "01c46189-a598-4bfc-9565-a914346decf7", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "from sklearn.model_selection import train_test_split, GridSearchCV\n", + "from sklearn.preprocessing import StandardScaler\n", + "from sklearn.neighbors import KNeighborsClassifier\n", + "# from sklearn.metrics import confusion_matrix, roc_curve, roc_auc_score, RocCurveDisplay\n", + "from sklearn.metrics import confusion_matrix, recall_score, precision_score, roc_auc_score, roc_curve, accuracy_score, RocCurveDisplay\n", + "\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "id": "53f58e2c-169e-434c-9b8e-1bd0cb5f7715", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EnrollAgeIncomeHours
01261800014
1043130009
21554200016
315510000013
40551300012
\n", + "
" + ], + "text/plain": [ + " Enroll Age Income Hours\n", + "0 1 26 18000 14\n", + "1 0 43 13000 9\n", + "2 1 55 42000 16\n", + "3 1 55 100000 13\n", + "4 0 55 13000 12" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load the data\n", + "df = pd.read_excel(\"gym.xlsx\")\n", + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "id": "b5809395-d339-4a18-bef1-ea12b06cc9f7", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EnrollAgeIncomeHours
count1000.0000001000.0000001000.0000001000.000000
mean0.40300044.58200068340.00000010.182000
std0.49074613.87673744466.9282474.671263
min0.00000021.0000001000.0000002.000000
25%0.00000032.00000031000.0000006.000000
50%0.00000045.00000064000.00000010.000000
75%1.00000057.00000097000.00000014.000000
max1.00000068.000000198000.00000018.000000
\n", + "
" + ], + "text/plain": [ + " Enroll Age Income Hours\n", + "count 1000.000000 1000.000000 1000.000000 1000.000000\n", + "mean 0.403000 44.582000 68340.000000 10.182000\n", + "std 0.490746 13.876737 44466.928247 4.671263\n", + "min 0.000000 21.000000 1000.000000 2.000000\n", + "25% 0.000000 32.000000 31000.000000 6.000000\n", + "50% 0.000000 45.000000 64000.000000 10.000000\n", + "75% 1.000000 57.000000 97000.000000 14.000000\n", + "max 1.000000 68.000000 198000.000000 18.000000" + ] + }, + "execution_count": 66, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "id": "46f2b835-2f7d-4d65-a1e9-5dacaf6a370e", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(1000, 4)" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "id": "92834d50-c430-4431-b5d9-81b10415dca1", + "metadata": {}, + "outputs": [], + "source": [ + "indAtts = [\"Age\", \"Income\", \"Hours\"]\n", + "depAtt = \"Enroll\"" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "id": "3b789418-6284-41cb-9c41-5f2b5d2114ac", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AgeIncomeHours
0261800014
143130009
2554200016
35510000013
4551300012
\n", + "
" + ], + "text/plain": [ + " Age Income Hours\n", + "0 26 18000 14\n", + "1 43 13000 9\n", + "2 55 42000 16\n", + "3 55 100000 13\n", + "4 55 13000 12" + ] + }, + "execution_count": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Separate features and target variable\n", + "Xs = df[indAtts]\n", + "Xs.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "id": "c9c82753-ed45-4d63-9f5a-75fd54d196fb", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0 1\n", + "1 0\n", + "2 1\n", + "3 1\n", + "4 0\n", + " ..\n", + "995 0\n", + "996 0\n", + "997 1\n", + "998 1\n", + "999 0\n", + "Name: Enroll, Length: 1000, dtype: int64" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "y = df[depAtt]\n", + "y\n" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "id": "13b2648e-6a32-4775-9970-3e0c466271fe", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[-1.33974561, -1.13264376, 0.81774684],\n", + " [-0.11406079, -1.24514314, -0.25316311],\n", + " [ 0.7511285 , -0.59264674, 1.24611082],\n", + " ...,\n", + " [ 0.7511285 , 0.03734979, 1.46029281],\n", + " [ 1.68841689, -0.09764946, 1.03192883],\n", + " [ 0.24643475, -0.03014983, 1.6744748 ]])" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Scale the features\n", + "scaler = StandardScaler()\n", + "XsScaled = scaler.fit_transform(Xs)\n", + "XsScaled" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "id": "b3d1b271-1670-410e-a98b-c0af06571d70", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AgeIncomeHoursEnroll
0-1.339746-1.1326440.8177471
1-0.114061-1.245143-0.2531630
20.751128-0.5926471.2461111
30.7511280.7123460.6035651
40.751128-1.2451430.3893830
...............
995-0.402457-1.4251420.6035650
996-0.474556-1.425142-1.5382550
9970.7511280.0373501.4602931
9981.688417-0.0976491.0319291
9990.246435-0.0301501.6744750
\n", + "

1000 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Age Income Hours Enroll\n", + "0 -1.339746 -1.132644 0.817747 1\n", + "1 -0.114061 -1.245143 -0.253163 0\n", + "2 0.751128 -0.592647 1.246111 1\n", + "3 0.751128 0.712346 0.603565 1\n", + "4 0.751128 -1.245143 0.389383 0\n", + ".. ... ... ... ...\n", + "995 -0.402457 -1.425142 0.603565 0\n", + "996 -0.474556 -1.425142 -1.538255 0\n", + "997 0.751128 0.037350 1.460293 1\n", + "998 1.688417 -0.097649 1.031929 1\n", + "999 0.246435 -0.030150 1.674475 0\n", + "\n", + "[1000 rows x 4 columns]" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Combine scaled features and target into a new DataFrame\n", + "dfScaled = pd.DataFrame(XsScaled, columns=Xs.columns)\n", + "dfScaled[depAtt] = y.astype('category')\n", + "dfScaled" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "id": "4e6402c1-05f3-4cfe-b96d-9758d36aed57", + "metadata": {}, + "outputs": [], + "source": [ + "# Split the data into training and testing sets\n", + "X_train, X_test, y_train, y_test = train_test_split(\n", + " dfScaled[indAtts],\n", + " dfScaled[depAtt],\n", + " test_size=0.4,\n", + " random_state=1,\n", + " stratify=dfScaled[depAtt]\n", + ")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "id": "a9b32cbd-f135-4c17-9b52-7078722caae3", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
AgeIncomeHours
8080.0301370.8248451.674475
393-0.618755-0.9751450.175201
416-0.979250-1.4251420.817747
4860.679029-1.0651440.817747
422-0.114061-1.267643-1.324073
\n", + "
" + ], + "text/plain": [ + " Age Income Hours\n", + "808 0.030137 0.824845 1.674475\n", + "393 -0.618755 -0.975145 0.175201\n", + "416 -0.979250 -1.425142 0.817747\n", + "486 0.679029 -1.065144 0.817747\n", + "422 -0.114061 -1.267643 -1.324073" + ] + }, + "execution_count": 74, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "X_train.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 75, + "id": "2226b885-9cff-41aa-a0f4-35ef5682daaa", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
GridSearchCV(cv=5, estimator=KNeighborsClassifier(),\n",
+       "             param_grid={'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]})
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" + ], + "text/plain": [ + "GridSearchCV(cv=5, estimator=KNeighborsClassifier(),\n", + " param_grid={'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]})" + ] + }, + "execution_count": 75, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Perform k-NN classification with cross-validation to find the best k\n", + "knn = KNeighborsClassifier()\n", + "param_grid = {'n_neighbors': list(range(1, 11))}\n", + "grid_search = GridSearchCV(knn, param_grid, cv=5)\n", + "grid_search.fit(X_train, y_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 76, + "id": "779e861d-04cf-4d8f-94e0-e42c96525b61", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Best parameters: {'n_neighbors': 5}\n", + "Best cross-validation score: 0.915\n" + ] + } + ], + "source": [ + "print(\"Best parameters:\", grid_search.best_params_)\n", + "print(\"Best cross-validation score:\", grid_search.best_score_)" + ] + }, + { + "cell_type": "code", + "execution_count": 77, + "id": "046a78bc-4b77-44d9-a5d9-3d6084d1ad16", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
mean_fit_timestd_fit_timemean_score_timestd_score_timeparam_n_neighborsparamssplit0_test_scoresplit1_test_scoresplit2_test_scoresplit3_test_scoresplit4_test_scoremean_test_scorestd_test_scorerank_test_score
00.0011090.0004550.0036940.0005361{'n_neighbors': 1}0.8666670.9083330.8666670.9000000.9166670.8916670.0210829
10.0008860.0000900.0032210.0002292{'n_neighbors': 2}0.8333330.8583330.8833330.8666670.8666670.8616670.01633010
20.0006700.0000710.0027600.0003183{'n_neighbors': 3}0.9083330.9166670.8833330.9333330.9000000.9083330.0166672
30.0005450.0000200.0023110.0000664{'n_neighbors': 4}0.8500000.9250000.8583330.9333330.9000000.8933330.0339128
40.0004890.0000100.0021910.0000515{'n_neighbors': 5}0.8750000.9416670.8833330.9500000.9250000.9150000.0304591
50.0004570.0000060.0020550.0000386{'n_neighbors': 6}0.8666670.9416670.8583330.9333330.9166670.9033330.0344005
60.0004390.0000060.0019900.0000357{'n_neighbors': 7}0.8750000.9333330.8583330.9416670.9166670.9050000.0327454
70.0004360.0000050.0019740.0000088{'n_neighbors': 8}0.8666670.9333330.8583330.9333330.9083330.9000000.0320597
80.0004300.0000040.0019810.0000169{'n_neighbors': 9}0.8666670.9250000.8833330.9416670.9166670.9066670.0275883
90.0004720.0000470.0020840.00007910{'n_neighbors': 10}0.8416670.9416670.8666670.9416670.9166670.9016670.0406206
\n", + "
" + ], + "text/plain": [ + " mean_fit_time std_fit_time mean_score_time std_score_time \\\n", + "0 0.001109 0.000455 0.003694 0.000536 \n", + "1 0.000886 0.000090 0.003221 0.000229 \n", + "2 0.000670 0.000071 0.002760 0.000318 \n", + "3 0.000545 0.000020 0.002311 0.000066 \n", + "4 0.000489 0.000010 0.002191 0.000051 \n", + "5 0.000457 0.000006 0.002055 0.000038 \n", + "6 0.000439 0.000006 0.001990 0.000035 \n", + "7 0.000436 0.000005 0.001974 0.000008 \n", + "8 0.000430 0.000004 0.001981 0.000016 \n", + "9 0.000472 0.000047 0.002084 0.000079 \n", + "\n", + " param_n_neighbors params split0_test_score \\\n", + "0 1 {'n_neighbors': 1} 0.866667 \n", + "1 2 {'n_neighbors': 2} 0.833333 \n", + "2 3 {'n_neighbors': 3} 0.908333 \n", + "3 4 {'n_neighbors': 4} 0.850000 \n", + "4 5 {'n_neighbors': 5} 0.875000 \n", + "5 6 {'n_neighbors': 6} 0.866667 \n", + "6 7 {'n_neighbors': 7} 0.875000 \n", + "7 8 {'n_neighbors': 8} 0.866667 \n", + "8 9 {'n_neighbors': 9} 0.866667 \n", + "9 10 {'n_neighbors': 10} 0.841667 \n", + "\n", + " split1_test_score split2_test_score split3_test_score split4_test_score \\\n", + "0 0.908333 0.866667 0.900000 0.916667 \n", + "1 0.858333 0.883333 0.866667 0.866667 \n", + "2 0.916667 0.883333 0.933333 0.900000 \n", + "3 0.925000 0.858333 0.933333 0.900000 \n", + "4 0.941667 0.883333 0.950000 0.925000 \n", + "5 0.941667 0.858333 0.933333 0.916667 \n", + "6 0.933333 0.858333 0.941667 0.916667 \n", + "7 0.933333 0.858333 0.933333 0.908333 \n", + "8 0.925000 0.883333 0.941667 0.916667 \n", + "9 0.941667 0.866667 0.941667 0.916667 \n", + "\n", + " mean_test_score std_test_score rank_test_score \n", + "0 0.891667 0.021082 9 \n", + "1 0.861667 0.016330 10 \n", + "2 0.908333 0.016667 2 \n", + "3 0.893333 0.033912 8 \n", + "4 0.915000 0.030459 1 \n", + "5 0.903333 0.034400 5 \n", + "6 0.905000 0.032745 4 \n", + "7 0.900000 0.032059 7 \n", + "8 0.906667 0.027588 3 \n", + "9 0.901667 0.040620 6 " + ] + }, + "execution_count": 77, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Display detailed results\n", + "results = pd.DataFrame(grid_search.cv_results_)\n", + "results" + ] + }, + { + "cell_type": "code", + "execution_count": 78, + "id": "1f78ee56-b9c8-4d1a-aef9-ad37dfa41858", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
ActualPredicted
48911
24100
11900
57700
28700
.........
80411
97411
81011
39500
86100
\n", + "

400 rows × 2 columns

\n", + "
" + ], + "text/plain": [ + " Actual Predicted\n", + "489 1 1\n", + "241 0 0\n", + "119 0 0\n", + "577 0 0\n", + "287 0 0\n", + ".. ... ...\n", + "804 1 1\n", + "974 1 1\n", + "810 1 1\n", + "395 0 0\n", + "861 0 0\n", + "\n", + "[400 rows x 2 columns]" + ] + }, + "execution_count": 78, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Make predictions on the test set\n", + "best_knn = grid_search.best_estimator_\n", + "predictions = best_knn.predict(X_test)\n", + "# Combine y_test and predictions into a DataFrame\n", + "results_df = pd.DataFrame({'Actual': y_test, 'Predicted': predictions})\n", + "results_df" + ] + }, + { + "cell_type": "code", + "execution_count": 80, + "id": "777a6302-6139-4199-9ed0-68f5e8938612", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Confusion Matrix as DataFrame:\n", + " Actual_0 Actual_1\n", + "Predicted_0 217 22\n", + "Predicted_1 17 144\n" + ] + } + ], + "source": [ + "# Confusion matrix\n", + "conf_matrix = confusion_matrix(y_test, predictions)\n", + "\n", + "# Convert confusion matrix to DataFrame with predicted as rows and actual as columns\n", + "conf_matrix_df = pd.DataFrame(conf_matrix, index=['Predicted_0', 'Predicted_1'], columns=['Actual_0', 'Actual_1'])\n", + "print(\"Confusion Matrix as DataFrame:\")\n", + "print(conf_matrix_df)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "id": "aa493759-f506-4278-a212-4a3a0b5db15a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 0.9025\n", + "Precision: 0.8674698795180723\n", + "Recall (Sensitivity): 0.8944099378881988\n", + "Specificity: 0.9079497907949791\n", + "F1 Score: 0.8807339449541285\n" + ] + } + ], + "source": [ + "# Calculate metrics\n", + "precision = precision_score(y_test, predictions)\n", + "recall = recall_score(y_test, predictions)\n", + "accuracy = accuracy_score(y_test, predictions)\n", + "specificity = conf_matrix[0, 0] / (conf_matrix[0, 0] + conf_matrix[0, 1])\n", + "f1_score = 2 * (precision * recall) / (precision + recall)\n", + "\n", + "print(f\"Accuracy: {accuracy}\")\n", + "print(f\"Precision: {precision}\")\n", + "print(f\"Recall (Sensitivity): {recall}\")\n", + "print(f\"Specificity: {specificity}\")\n", + "print(f\"F1 Score: {f1_score}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "id": "c9a97f8e-0ebc-4b51-a4a1-ff059dd75535", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([1. , 0. , 0.2, 0.4, 0.2, 0.6, 1. , 0.2, 0.8, 0. , 0. , 0.2, 0. ,\n", + " 0. , 0.6, 0.6, 0. , 0. , 0. , 0.8, 1. , 0. , 1. , 0.8, 0. , 0.8,\n", + " 0. , 0.2, 1. , 0. , 0.8, 0. , 0.2, 0.2, 0. , 0. , 0.4, 0.4, 0. ,\n", + " 1. , 0. , 0.8, 0. , 0.8, 0. , 0.8, 0. , 0.6, 1. , 0.8, 0. , 1. ,\n", + " 1. , 0.8, 0.4, 0. , 0.8, 0. , 0.2, 0. , 0.6, 1. , 0.6, 0. , 1. ,\n", + " 0. , 0.8, 0. , 0. , 0.2, 0.2, 0.8, 1. , 0. , 0. , 0. , 0.8, 0.4,\n", + " 1. , 0. , 0. , 1. , 0. , 0.2, 0. , 0.8, 0. , 1. , 0. , 0. , 0. ,\n", + " 0. , 0. , 1. , 1. , 1. , 0. , 1. , 0. , 0. , 0.4, 0.2, 1. , 0. ,\n", + " 1. , 0.8, 1. , 1. , 0. , 1. , 0.8, 1. , 1. , 1. , 0. , 0. , 1. ,\n", + " 0.8, 0. , 0. , 0.2, 0.8, 0. , 1. , 1. , 1. , 0.8, 1. , 1. , 0.8,\n", + " 0.2, 0. , 0. , 0. , 0.6, 0. , 1. , 0.2, 0. , 1. , 0. , 0. , 0.8,\n", + " 0.6, 0. , 0. , 0. , 0.2, 0.4, 1. , 0.8, 0. , 1. , 0. , 0. , 1. ,\n", + " 1. , 0. , 0.6, 0. , 0. , 0. , 0.2, 0.2, 0.4, 0.2, 0.2, 0.4, 1. ,\n", + " 0.8, 0. , 0.8, 0. , 0. , 0.2, 1. , 0. , 0. , 0. , 0. , 1. , 0. ,\n", + " 0. , 1. , 0. , 0.2, 0. , 1. , 0. , 0.2, 1. , 0. , 0.4, 0.2, 0.2,\n", + " 0. , 0.6, 0.2, 0.6, 0.6, 0. , 0. , 0.8, 0.8, 0.8, 0. , 0. , 0. ,\n", + " 0. , 0. , 0. , 0.4, 0. , 0. , 0.6, 1. , 1. , 0.2, 0. , 0.8, 0. ,\n", + " 0. , 0. , 0. , 0.2, 1. , 1. , 0.2, 1. , 0.2, 0. , 0.8, 0. , 0. ,\n", + " 0. , 1. , 0.4, 1. , 0. , 0. , 1. , 1. , 0. , 0.2, 1. , 0.6, 0.4,\n", + " 0.8, 1. , 0. , 0. , 1. , 0.2, 0. , 1. , 0.8, 0.6, 0. , 0.8, 1. ,\n", + " 0.4, 0. , 0. , 0.6, 0.6, 0. , 1. , 0.2, 1. , 1. , 0.6, 0.2, 0.8,\n", + " 1. , 0.2, 0.2, 0. , 0. , 1. , 1. , 0.8, 0.8, 0. , 0.2, 1. , 0.8,\n", + " 0. , 0.8, 0. , 1. , 0. , 0. , 1. , 0.8, 0.2, 0.2, 0.2, 0. , 0.6,\n", + " 1. , 1. , 0.2, 0. , 0. , 0. , 0.2, 0.8, 1. , 1. , 1. , 0. , 0.8,\n", + " 0.8, 0.4, 0. , 0.4, 0. , 1. , 0.4, 0.8, 0.4, 0.2, 0. , 0. , 0. ,\n", + " 0. , 0. , 0. , 0.8, 0.8, 0. , 0.8, 0.8, 0. , 1. , 0.2, 0. , 0. ,\n", + " 0.6, 1. , 0.8, 0. , 0. , 0. , 0. , 0.8, 0. , 0.6, 0. , 0.8, 0.2,\n", + " 0. , 0. , 0. , 0.8, 0.6, 0. , 1. , 0. , 0.4, 0. , 0.4, 0. , 0.8,\n", + " 0. , 0. , 0.2, 1. , 0.4, 0. , 0.2, 0.2, 0.8, 0. , 0.8, 0. , 0.2,\n", + " 0.8, 0. , 0. , 0.8, 0.6, 0. , 0.8, 0. , 0.8, 0. , 1. , 0. , 0. ,\n", + " 0.2, 0.8, 1. , 0.8, 0. , 0.6, 1. , 0.8, 0.2, 0.2])" + ] + }, + "execution_count": 84, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Predict probabilities for ROC curve\n", + "probs= best_knn.predict_proba(X_test)[:, 1]\n", + "probs" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "id": "b23ed9f8-b1c0-491c-b048-112a0797299f", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "ROC AUC: 0.9423191870890616\n" + ] + } + ], + "source": [ + "roc_auc = roc_auc_score(y_test, probs)\n", + "print(\"ROC AUC:\", roc_auc)" + ] + }, + { + "cell_type": "code", + "execution_count": 90, + "id": "ffe52a48-533d-43db-b845-8aab740638ef", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkIAAAHHCAYAAABTMjf2AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAACEVUlEQVR4nO3dd1hTZxsG8DsJYU9lCIii1IED3H5q3Sit1aq1agUVR7V11FZqrXu1iq111dliFQfWXau1xT3qnri3WBeoqGwIkLzfH0o0AkoUOIHcv+vi0pycc/IkAfLwvM/7HpkQQoCIiIjICMmlDoCIiIhIKkyEiIiIyGgxESIiIiKjxUSIiIiIjBYTISIiIjJaTISIiIjIaDERIiIiIqPFRIiIiIiMFhMhIiIiMlpMhIjyiaenJ3r16iV1GEanWbNmaNasmdRhvNaECRMgk8kQGxsrdSgGRyaTYcKECflyrps3b0ImkyEsLCxfzkfFHxMhKhLCwsIgk8m0XyYmJnB3d0evXr1w9+5dqcMzaMnJyfjuu+/g4+MDS0tL2NnZoXHjxli2bBmKyhV2Lly4gAkTJuDmzZtSh5KNWq3GkiVL0KxZM5QoUQJmZmbw9PRE7969cfz4canDyxcrV67ErFmzpA5DhyHGREWTidQBEOlj0qRJKFeuHNLS0nD48GGEhYVh//79OHfuHMzNzSWN7fLly5DLDetvi/v376Nly5a4ePEiPvnkEwwePBhpaWlYv349goKC8PfffyM8PBwKhULqUF/pwoULmDhxIpo1awZPT0+d+7Zt2yZNUABSU1Px0UcfISIiAk2aNMGoUaNQokQJ3Lx5E2vWrMHSpUtx69YtlC5dWrIY88PKlStx7tw5fPXVVwVy/tTUVJiY6PdxlFtMZcuWRWpqKpRKZT5GSMUZEyEqUt5//33UqVMHAPDpp5/C0dERP/zwAzZt2oQuXbpIGpuZmVmhP2ZaWhpMTU1zTcCCgoJw8eJF/PHHH/jwww+124cMGYJvvvkGP/30E2rWrIlvv/22sEIG8LRKZWVllS/nMjU1zZfzvIlvvvkGERERmDlzZrYP5PHjx2PmzJmFGo8QAmlpabCwsCjUx30TGo0G6enpMDc3z9c/YmQymeR/FFERI4iKgCVLlggA4tixYzrb//rrLwFATJkyRWf7xYsXRadOnYSDg4MwMzMTtWvXFn/++We28z558kR89dVXomzZssLU1FS4u7uLHj16iIcPH2r3SUtLE+PGjRNeXl7C1NRUlC5dWnzzzTciLS1N51xly5YVQUFBQgghjh07JgCIsLCwbI8ZEREhAIjNmzdrt925c0f07t1bODs7C1NTU1GlShXx22+/6Ry3e/duAUD8/vvvYvTo0cLNzU3IZDLx5MmTHF+zQ4cOCQCiT58+Od6fkZEhKlSoIBwcHERKSooQQoioqCgBQEybNk3MmDFDlClTRpibm4smTZqIs2fPZjtHXl7nrPduz549YsCAAcLJyUnY29sLIYS4efOmGDBggKhYsaIwNzcXJUqUEB9//LGIiorKdvzLX7t37xZCCNG0aVPRtGnTbK/T6tWrxffffy/c3d2FmZmZaNGihbh69Wq25zB37lxRrlw5YW5uLurWrSv27duX7Zw5uX37tjAxMRGtWrV65X5Zxo8fLwCIq1eviqCgIGFnZydsbW1Fr169RHJyss6+ixcvFs2bNxdOTk7C1NRUeHt7i/nz52c7Z9myZcUHH3wgIiIiRO3atYWZmZmYOXOmXucQQoi///5bNGnSRFhbWwsbGxtRp04dER4eLoR4+vq+/NqXLVtWe2xefz4AiEGDBokVK1aIKlWqCBMTE/HHH39o7xs/frx234SEBPHll19qfy6dnJyEn5+fOHHixGtjyvoeXrJkic7jX7x4UXTu3Fk4OjoKc3NzUbFiRTFq1KhXvWVkJFgRoiItq2fEwcFBu+38+fNo1KgR3N3dMWLECFhZWWHNmjXo0KED1q9fj44dOwIAkpKS0LhxY1y8eBF9+vRBrVq1EBsbi02bNuHOnTtwdHSERqPBhx9+iP3796N///7w9vbG2bNnMXPmTFy5cgUbN27MMa46deqgfPnyWLNmDYKCgnTuW716NRwcHODv7w/g6fDV//73P8hkMgwePBhOTk74559/0LdvXyQkJGSrNHz33XcwNTXFsGHDoFKpcq2IbN68GQDQs2fPHO83MTFBQEAAJk6ciAMHDsDPz09737Jly5CYmIhBgwYhLS0Ns2fPRosWLXD27Fm4uLjo9TpnGThwIJycnDBu3DgkJycDAI4dO4aDBw/ik08+QenSpXHz5k0sWLAAzZo1w4ULF2BpaYkmTZpgyJAh+PnnnzFq1Ch4e3sDgPbf3EydOhVyuRzDhg1DfHw8fvzxRwQGBuLIkSPafRYsWIDBgwejcePGGDp0KG7evIkOHTrAwcHhtcNZ//zzDzIzM9GjR49X7veyLl26oFy5cggJCcHJkyexaNEiODs744cfftCJq2rVqvjwww9hYmKCzZs3Y+DAgdBoNBg0aJDO+S5fvoxu3brhs88+Q79+/VCpUiW9zhEWFoY+ffqgatWqGDlyJOzt7XHq1ClEREQgICAAo0ePRnx8PO7cuaOtcFlbWwOA3j8fu3btwpo1azB48GA4OjpmG+bM8vnnn2PdunUYPHgwqlSpgkePHmH//v24ePEiatWq9cqYcnLmzBk0btwYSqUS/fv3h6enJ65fv47Nmzdj8uTJeXvjqPiSOhMjyousqsCOHTvEw4cPxe3bt8W6deuEk5OTMDMzE7dv39bu27JlS1G9enWdv0g1Go1o2LChqFChgnbbuHHjBACxYcOGbI+n0WiEEEIsX75cyOVy8e+//+rcv3DhQgFAHDhwQLvtxYqQEEKMHDlSKJVK8fjxY+02lUol7O3tdao0ffv2Fa6uriI2NlbnMT755BNhZ2enrdZkVTrKly+v3fYqHTp0EAByrRgJIcSGDRsEAPHzzz8LIZ7/NW1hYSHu3Lmj3e/IkSMCgBg6dKh2W15f56z37t133xWZmZk6j5/T88iqZC1btky7be3atTpVoBflVhHy9vYWKpVKu3327NkCgLaypVKpRMmSJUXdunVFRkaGdr+wsDAB4LUVoaFDhwoA4tSpU6/cL0tWRejlCl3Hjh1FyZIldbbl9Lr4+/uL8uXL62wrW7asACAiIiKy7Z+Xc8TFxQkbGxtRv359kZqaqrNv1s+AEEJ88MEHOlWgLPr8fAAQcrlcnD9/Ptt58FJFyM7OTgwaNCjbfi/KLaacKkJNmjQRNjY24r///sv1OZLxMqzOTqLX8PPzg5OTEzw8PPDxxx/DysoKmzZt0v71/vjxY+zatQtdunRBYmIiYmNjERsbi0ePHsHf3x9Xr17VzjJbv349fH19s1UugKd9BgCwdu1aeHt7o3LlytpzxcbGokWLFgCA3bt35xpr165dkZGRgQ0bNmi3bdu2DXFxcejatSuApz0d69evR7t27SCE0HkMf39/xMfH4+TJkzrnDQoKylMPSGJiIgDAxsYm132y7ktISNDZ3qFDB7i7u2tv16tXD/Xr18fff/8NQL/XOUu/fv2yNWW/+DwyMjLw6NEjvPPOO7C3t8/2vPXVu3dvnWpZ48aNAQA3btwAABw/fhyPHj1Cv379dBp1AwMDdSqMucl6zV71+ubk888/17nduHFjPHr0SOc9ePF1iY+PR2xsLJo2bYobN24gPj5e5/hy5cppq4svyss5tm/fjsTERIwYMSJbX03Wz8Cr6Pvz0bRpU1SpUuW157W3t8eRI0dw79691+77Og8fPsS+ffvQp08flClTRue+vDxHKv44NEZFyrx581CxYkXEx8dj8eLF2Ldvn06T8rVr1yCEwNixYzF27Ngcz/HgwQO4u7vj+vXr6NSp0ysf7+rVq7h48SKcnJxyPVdufH19UblyZaxevRp9+/YF8HRYzNHRUftB8fDhQ8TFxeHXX3/Fr7/+mqfHKFeu3CtjzpL1AZ2YmAh7e/sc98ktWapQoUK2fStWrIg1a9YA0O91flXcqampCAkJwZIlS3D37l2d6fwvf+Dr6+UPvazk5smTJwCA//77DwDwzjvv6OxnYmKS65DNi2xtbQE8fw3zI66scx44cADjx4/HoUOHkJKSorN/fHw87OzstLdz+37IyzmuX78OAKhWrZpezyGLvj8fef3e/fHHHxEUFAQPDw/Url0bbdq0Qc+ePVG+fHm9Y8xKfN/0OVLxx0SIipR69eppZ4116NAB7777LgICAnD58mVYW1tDo9EAAIYNG5bjX8lA9g++V9FoNKhevTpmzJiR4/0eHh6vPL5r166YPHkyYmNjYWNjg02bNqFbt27aCkRWvN27d8/WS5TFx8dH53ZeZwR5e3tj48aNOHPmDJo0aZLjPmfOnAGAPP2V/qI3eZ1zivuLL77AkiVL8NVXX6FBgwaws7ODTCbDJ598on2MN5XbkgAin9ZOqly5MgDg7NmzqFGjRp6Pe11c169fR8uWLVG5cmXMmDEDHh4eMDU1xd9//42ZM2dme11yel31Pceb0vfnI6/fu126dEHjxo3xxx9/YNu2bZg2bRp++OEHbNiwAe+///5bx030IiZCVGQpFAqEhISgefPmmDt3LkaMGKH9i1GpVOo0/+bEy8sL586de+0+p0+fRsuWLd+ojN61a1dMnDgR69evh4uLCxISEvDJJ59o73dycoKNjQ3UavVr49VX27ZtERISgmXLluWYCKnVaqxcuRIODg5o1KiRzn1Xr17Ntv+VK1e0lRJ9XudXWbduHYKCgjB9+nTttrS0NMTFxensVxBDGGXLlgXwtLrVvHlz7fbMzEzcvHkzWwL6svfffx8KhQIrVqzQu2H6VTZv3gyVSoVNmzbpVI9eNQz7pufw8vICAJw7d+6VfyDk9vq/7c/Hq7i6umLgwIEYOHAgHjx4gFq1amHy5MnaRCivj5f1vfq6n3UyXuwRoiKtWbNmqFevHmbNmoW0tDQ4OzujWbNm+OWXXxAdHZ1t/4cPH2r/36lTJ5w+fRp//PFHtv2y/jrv0qUL7t69i9DQ0Gz7pKamamc/5cbb2xvVq1fH6tWrsXr1ari6uuokJQqFAp06dcL69etz/EX9Yrz6atiwIfz8/LBkyRL89ddf2e4fPXo0rly5guHDh2f7S33jxo06PT5Hjx7FkSNHtB9C+rzOr6JQKLJVaObMmQO1Wq2zLWvNoZcTpLdRp04dlCxZEqGhocjMzNRuDw8P1w6fvYqHhwf69euHbdu2Yc6cOdnu12g0mD59Ou7cuaNXXFkVo5eHCZcsWZLv52jdujVsbGwQEhKCtLQ0nftePNbKyirHocq3/fnIiVqtzvZYzs7OcHNzg0qlem1ML3NyckKTJk2wePFi3Lp1S+e+/KoOUtHGihAVed988w06d+6MsLAwfP7555g3bx7effddVK9eHf369UP58uVx//59HDp0CHfu3MHp06e1x61btw6dO3dGnz59ULt2bTx+/BibNm3CwoUL4evrix49emDNmjX4/PPPsXv3bjRq1AhqtRqXLl3CmjVrsHXrVu1QXW66du2KcePGwdzcHH379s22+OHUqVOxe/du1K9fH/369UOVKlXw+PFjnDx5Ejt27MDjx4/f+LVZtmwZWrZsifbt2yMgIACNGzeGSqXChg0bsGfPHnTt2hXffPNNtuPeeecdvPvuuxgwYABUKhVmzZqFkiVLYvjw4dp98vo6v0rbtm2xfPly2NnZoUqVKjh06BB27NiBkiVL6uxXo0YNKBQK/PDDD4iPj4eZmRlatGgBZ2fnN35tTE1NMWHCBHzxxRdo0aIFunTpgps3byIsLAxeXl55qjhMnz4d169fx5AhQ7Bhwwa0bdsWDg4OuHXrFtauXYtLly7pVADzonXr1jA1NUW7du3w2WefISkpCaGhoXB2ds4x6Xybc9ja2mLmzJn49NNPUbduXQQEBMDBwQGnT59GSkoKli5dCgCoXbs2Vq9ejeDgYNStWxfW1tZo165dvvx8vCwxMRGlS5fGxx9/DF9fX1hbW2PHjh04duyYTuUwt5hy8vPPP+Pdd99FrVq10L9/f5QrVw43b97Eli1bEBkZqVd8VAxJMleNSE+5LagohBBqtVp4eXkJLy8v7fTs69evi549e4pSpUoJpVIp3N3dRdu2bcW6det0jn306JEYPHiwcHd31y4GFxQUpDOVPT09Xfzwww+iatWqwszMTDg4OIjatWuLiRMnivj4eO1+L0+fz3L16lXtom/79+/P8fndv39fDBo0SHh4eAilUilKlSolWrZsKX799VftPlnTwteuXavXa5eYmCgmTJggqlatKiwsLISNjY1o1KiRCAsLyzZ9+MUFFadPny48PDyEmZmZaNy4sTh9+nS2c+fldX7Ve/fkyRPRu3dv4ejoKKytrYW/v7+4dOlSjq9laGioKF++vFAoFHlaUPHl1ym3hfZ+/vlnUbZsWWFmZibq1asnDhw4IGrXri3ee++9PLy6QmRmZopFixaJxo0bCzs7O6FUKkXZsmVF7969dabWZ02ff3GxzhdfnxcXkdy0aZPw8fER5ubmwtPTU/zwww9i8eLF2fbLWlAxJ3k9R9a+DRs2FBYWFsLW1lbUq1dP/P7779r7k5KSREBAgLC3t8+2oGJefz7wbEHFnOCF6fMqlUp88803wtfXV9jY2AgrKyvh6+ubbTHI3GLK7X0+d+6c6Nixo7C3txfm5uaiUqVKYuzYsTnGQ8ZFJgRrg0T01M2bN1GuXDlMmzYNw4YNkzocSWg0Gjg5OeGjjz7KcciHiIoX9ggRkdFKS0vL1ieybNkyPH78GM2aNZMmKCIqVOwRIiKjdfjwYQwdOhSdO3dGyZIlcfLkSfz222+oVq0aOnfuLHV4RFQImAgRkdHy9PSEh4cHfv75Zzx+/BglSpRAz549MXXqVEmvak9EhYc9QkRERGS02CNERERERouJEBERERkto+sR0mg0uHfvHmxsbHjlYSIioiJCCIHExES4ubllW5j2bRhdInTv3r3XXiiTiIiIDNPt27dRunTpfDuf0SVCNjY2AJ6+kLa2thJHQ0RERHmRkJAADw8P7ed4fjG6RChrOMzW1paJEBERURGT320tbJYmIiIio8VEiIiIiIwWEyEiIiIyWkyEiIiIyGgxESIiIiKjxUSIiIiIjBYTISIiIjJaTISIiIjIaDERIiIiIqPFRIiIiIiMlqSJ0L59+9CuXTu4ublBJpNh48aNrz1mz549qFWrFszMzPDOO+8gLCyswOMkIiKi4knSRCg5ORm+vr6YN29envaPiorCBx98gObNmyMyMhJfffUVPv30U2zdurWAIyUiIqLiSNKLrr7//vt4//3387z/woULUa5cOUyfPh0A4O3tjf3792PmzJnw9/cvqDCJiIiomCpSV58/dOgQ/Pz8dLb5+/vjq6++kiYgIiIiemMajUC6WgNVpgbpmRpkqJ/+m/7s36zt6WoNYh/GFkgMRSoRiomJgYuLi842FxcXJCQkIDU1FRYWFtmOUalUUKlU2tsJCQkFHicREZGhyVQ/TSgyMgVUavXTBOOFpCPbbXX2baoXk5WX9lGpX0pmXr4/674XtmVqRJ5iF0KD6KVfFcjrUqQSoTcREhKCiRMnSh0GEREZCSEEMtTildWNFxMGVbZkRI0MtW6l5Olxz5OXDLV44Th1tqRDe3+mWrs9jzmHpEwVcigVMpiayJ9/KeQwNVHAqU1PnFgyId8fs0glQqVKlcL9+/d1tt2/fx+2trY5VoMAYOTIkQgODtbeTkhIgIeHR4HGSUREhUMIkWPlIlv14qV9sg3FvJyw5FLdeDExebm6kVUVyVBrIIpC0mEih5lCnkPSIYfy2b9mL2x7+X6zl7a9vE9Ox73u/zKZTBvfyZMn8eDBA7z33nsAgIQEX9gZeyLUoEED/P333zrbtm/fjgYNGuR6jJmZGczMzAo6NCKiYu/lfg7dCkTO29PV6mdDMS8Pv7w4NCNeOC57dePp/eoch3Ay1Iafcchl0KlsvJhAKE1kLyQDCpi+kGBoKyMKhTZZMMshWck6l9lLyYhOMvNS0mEil+kkHYZEo9Hgp59+wpgxY2BtbY0zZ86gdOnSBfZ4kiZCSUlJuHbtmvZ2VFQUIiMjUaJECZQpUwYjR47E3bt3sWzZMgDA559/jrlz52L48OHo06cPdu3ahTVr1mDLli1SPQUiogKR+VK1Iaf+ihf7Ml7XaPpydePlxOTlc788XJOhzns/h5RM5DL9KxO53f8W1Q2zZ8mLUiGDiYJrF+fV7du3ERQUhN27dwMAmjVrluuIT36RNBE6fvw4mjdvrr2dNYQVFBSEsLAwREdH49atW9r7y5Urhy1btmDo0KGYPXs2SpcujUWLFnHqPBG9sax+jrxWN3QqGC/1YOhWN7I3o+Y6VPPCsEvW/UUg58iWBDyvbiiyD7so5FC+kCy8XKVQ6iQRrxmqyS1hUcghlxtmlYNeb+3atfjss8/w5MkTWFpa4ueff0afPn0KvHIlE6IojGTmn4SEBNjZ2SE+Ph62trZSh0NkVIR43uCZkUM/x8vJSE59Ga9vNH1e3cjpOJ1jn/1r6GQy5Et1w0zx0nDKS4mJModzmL0wNKPTxPpSPwfRm9JoNPj000+xZMkSAEDdunURHh6OChUq6OxXUJ/fRapHiIjyTq0RuglADj0aqmezS3Lq29C576XqRm5rfryu0bQo9HMo5LIXZq4ocqxAZN2n05ehc3/2fo5cG03zkNAYcj8H0duSy+WwsLCAXC7HyJEjMX78eCiVykJ7fFaEiAxAWoYaMfFpuBefiui4NETHp+JhogppGc+GaXJb5+PFYZyXkg51ERhbybGf44XGz5ebQV9uGM2pumH2UjKSl+qG2QvNqAoOrRAVuMzMTCQkJKBEiRIAgJSUFJw+ffqVk59YESIqolSZatyPVz1NcuJTER2fpk12ouPTEB2fhsfJ6QUex6uGVJS59GVkq17kR6Mp+zmIjFpUVBS6d+8OpVKJnTt3QqFQwNLS8pVJUEFiIkT0FjLUGsQ8S2aeJznPE5zo+FTEJuUtyTFXyuFmZwFXe3O42lnA2cYMlqaKHKsbzxMT3erGixUPnURHwaEVIpKWEAIrVqzAoEGDkJiYCFtbW1y8eBHVqlWTNC4mQkS5yFRrcD9RhZj4VNx7VsG5F5f2LPFJxb34NMQmqfK0cJqZiRyudk8TnKeJztP/u9mbo5Tt03/tLJRMVoioWIqLi8OAAQOwatUqAECjRo2wYsUKeHp6ShsYmAiRkVJrBB4kpuUwTPU82XmQmJanKcymCjlK2WUlN+ZwtbeAm505StlZwNXOHG72FnCwZJJDRMZp79696NGjB27fvg2FQoEJEyZgxIgRMDExjBTEMKIgykcajUBskgr3dIapnlZwYp5tu5+oylMzsVIhg4utuU41x83OAqXszLXDWCUsTdnrQkSUA41GgyFDhuD27dvw8vJCeHg46tevL3VYOpgIUZGi0Qg8Sk7P1o/zNMl5Ws25n5CWpxVwFXIZStmaa6s5bvYWKGVrDrdnPTquduZwtDZjkkNE9IbkcjmWLVuGefPmYcaMGbC2tpY6pGw4fZ4MhhACj5PTdRqNnw5TPa3mRMen4n68Cunq1y+AJ5cBzjbmOhWcrGQnq7rjZGPGqdJERPlICIFFixYhKSkJQ4cOzddzc/o8FWlCCMSlZLw0TPV0zZx7L0wjz8sqvzIZ4GRt9kIvjvkLs62ez7ji9X2IiApPbGws+vXrh40bN8LExAStW7dG1apVpQ7rtZgI0VsTQiAhLfPpcNWzxCYmPk070yprocC0jLxdysDR2uzZbKrnFZxSL1RzXGzNoWSSQ0RkMLZt24ZevXohOjoaSqUSISEh8Pb2ljqsPGEiRK+VmPa0knMvLiupedqbE5PwdFt0fBpS0tV5OldJK1O4vjBlPKsXJ2vYytnWDGYmigJ+RkRElB/S0tIwcuRIzJo1CwDg7e2NlStXokaNGpLGpQ8mQqQjSZWJX/Zex+k78U+Tnfg0JKoy83Ssg6USpeyeDle56iQ5T5MeF1tzmCuZ5BARFQdqtRpNmjTBsWPHAACDBg3Cjz/+CEtLS4kj0w8TIdLaffkBRm84i3vxadnuszU3eWGYKivZed6j42pnAQtTJjlERMZCoVAgMDAQN2/exOLFi9G2bVupQ3ojnDVGeJKcju/+uoANp+4CADxKWODzpl4oU8JSW9WxMmPOTERk7GJiYhAbG6u9LIZGo8Hjx4/h6OhY4I/NWWOU74QQ2HI2GuP/PI9HyemQy4A+jcohuHVFWJryW4OIiJ7bvHkz+vTpA3t7e5w6dQrW1taQy+WFkgQVJH7aGan7CWkYs/Ectl+4DwCo4GyNHz/2Qc0yDhJHRkREhiQlJQXDhg3DggULAABubm6IjY01yMUR3wQTISMjhMDqY7cx+e+LSEzLhFIhw8Bm72Bgcy/O1iIiIh0nT55EYGAgLl26BAD4+uuvMXnyZJiZmUkcWf5hImRE/nuUjBHrz+LQjUcAAN/SdvjhYx9ULsVeKSIiek6j0eCnn37CmDFjkJGRAVdXVyxbtgx+fn5Sh5bvmAgZAbVGYPH+KEzffhlpGRqYK+UY1roSejcqx0tMEBFRNjKZDLt370ZGRgY6duyI0NBQlCxZUuqwCgQToWLuUkwCvl13BqfvxAMAGnqVRMhH1VG2pJXEkRERkaHJzMyEiYkJZDIZlixZgoiICAQFBUEmK75/NHP6fDGlylRj3u7rmL/7GjI1AjZmJhj9gTe61vUo1t/QRESkv8TERAwZMgQymQyLFy+WOpwccfo85dmpW0/w7fozuHI/CQDg5+2C7ztUQyk7c4kjIyIiQ3P48GEEBgbixo0bkMvl+Prrr4vExVLzCxOhYiQlPRPTt13B4gNREOLpdb0mtq+KD6q7sgpEREQ6MjMzMWXKFEyaNAlqtRplypTBihUrjCoJApgIFRv7r8Zi5B9ncPtxKgDgo5ruGNu2ChysTCWOjIiIDE1UVBS6d++OgwcPAgC6deuG+fPnw97eXtrAJMBEqIiLT8nA5L8vYM3xOwAAd3sLTO5YDc0qOUscGRERGSK1Wg1/f39cvXoVtra2mD9/PgIDA6UOSzJMhIqwiHMxGPvnOTxMVAEAejYoi+HvVYY1rwtGRES5UCgUmDVrFkJCQrB8+XJ4enpKHZKkOGusCHqQmIYJm87j77MxAIDyjlaY2skH9cqVkDgyIiIyRPv27UN8fDzatWun3SaEKFL9o5w1RhBCYP3Ju/jurwuIT82AQi7DZ03KY0jLCjBX8vIYRESkKz09HRMmTMDUqVNhZ2eHM2fOwMPDAwCKVBJUkJgIFRG3H6dg1B9n8e/VWABAVTdb/NDJB9Xc7SSOjIiIDNHly5cRGBiIEydOAAA++ugjo2yGfh0mQkVAQloGOs4/iNgkFUxN5PjKrwL6NS4PpUIudWhERGRghBBYtGgRvvrqK6SkpMDBwQGhoaHo1KmT1KEZJCZCRcCuiw8Qm6SCu70FlvWtBy8na6lDIiIiA6RWq9G5c2f88ccfAIAWLVpg6dKlKF26tMSRGS6WFIqAreefNkV3qOnGJIiIiHKlUCjg4eEBpVKJadOmYfv27UyCXoMVIQOXlqHGnssPAQD+VUtJHA0RERmatLQ0JCQkwNn56fpxU6dORd++feHj4yNxZEUDK0IG7t+rsUjNUMPNzhzV2RhNREQvOH/+POrXr4/OnTtDrVYDACwsLJgE6YGJkIHLGhZrXbUUpzoSERGApw3Rc+bMQe3atXHmzBlcvHgR169flzqsIomJkAHLVGuw8+J9AEDrqi4SR0NERIYgJiYGbdq0wZAhQ6BSqfD+++/j7NmzqFixotShFUlMhAzY0ZuP8SQlAw6WStTz5KrRRETGbvPmzahevToiIiJgbm6OOXPmYMuWLXBx4R/Lb4rN0gZs2/mn1aCW3i4w4ZpBRERGLTMzE6NHj0ZsbCx8fHywcuVKVK1aVeqwijx+uhooIQS2PesP4mwxIiIyMTFBeHg4vvnmGxw9epRJUD5hRchAnb0bj3vxabA0VaBxBUepwyEiokKm0Wgwffp0aDQafPvttwCA6tWr48cff5Q4suKFiZCBypot1rSiEy+oSkRkZO7cuYOgoCDs2rULCoUC7du3R+XKlaUOq1ji0JiB2vqsP4jDYkRExmXt2rXw8fHBrl27YGlpiYULF6JSpUpSh1VssSJkgK4/TMK1B0kwkcvQvLKz1OEQEVEhSExMxJdffoklS5YAAOrUqYPw8HBOiy9gTIQMUNawWAOvkrCzUEocDRERFbTMzEw0bNgQ586dg0wmw6hRozB+/HgolfwMKGgcGjNAHBYjIjIuJiYm6N+/P8qUKYO9e/fi+++/ZxJUSJgIGZiY+DScvh0HmQxoXYULZBERFVdRUVGIjIzU3h48eDDOnj2Lxo0bSxeUEWIiZGC2XXg6LFbTwx7OtuYSR0NERPlNCIEVK1bA19cXnTp1QmJiIgBAJpPB1tZW4uiMDxMhA7OViygSERVbcXFxCAgIQI8ePZCYmAhXV1dtIkTSYCJkQOJS0nH4xmMATISIiIqbffv2wdfXF6tWrYJCocB3332HPXv2wM3NTerQjBpnjRmQnRcfQK0RqORiA09HK6nDISKifJCZmYlx48Zh6tSpEELAy8sL4eHhqF+/vtShEVgRMijPh8XYJE1EVFwoFAqcPn0aQgj06dMHp06dYhJkQFgRMhCp6Wrsu/oQANCaw2JEREWaEALp6ekwMzODTCbDkiVLsH//fnz00UdSh0YvYUXIQOy98hBpGRq421ugqhtnDRARFVWPHj1Cp06d0L9/f+02Z2dnJkEGiomQgdj2wmwxmUwmcTRERPQmtm/fjurVq+OPP/7A77//jitXrkgdEr0GEyEDkKHWYMfFrNWk2R9ERFTUpKWlITg4GK1bt0Z0dDS8vb1x5MgRXiesCGCPkAE4cuMxEtIyUdLKFHU8S0gdDhER6eH8+fMICAjAmTNnAAADBw7EtGnTYGlpKXFklBdMhAxA1mwxP28XKOQcFiMiKioyMzPRtm1b3Lx5E05OTli8eDHatm0rdVikBw6NSUyjEdrLavhX47AYEVFRYmJiggULFqBNmzY4e/Ysk6AiiBUhiZ2+E4f7CSpYmSrQ0MtR6nCIiOg1/vrrL6Snp2tngb333nvw9/fnRJciSvKK0Lx58+Dp6Qlzc3PUr18fR48efeX+s2bNQqVKlWBhYQEPDw8MHToUaWlphRRt/tt6/mmTdLPKzjBXKiSOhoiIcpOSkoKBAweiXbt26NOnD27duqW9j0lQ0SVpRWj16tUIDg7GwoULUb9+fcyaNQv+/v64fPkynJ2ds+2/cuVKjBgxAosXL0bDhg1x5coV9OrVCzKZDDNmzJDgGbwdIYTOtHkiIjJMJ0+eRGBgIC5dugQA6Nu3L1xc2M5QHEhaEZoxYwb69euH3r17o0qVKli4cCEsLS2xePHiHPc/ePAgGjVqhICAAHh6eqJ169bo1q3ba6tIhuragyTciE2GqUKO5pWcpA6HiIheotFoMG3aNPzvf//DpUuX4Orqim3btmH69OkwMzOTOjzKB5IlQunp6Thx4gT8/PyeByOXw8/PD4cOHcrxmIYNG+LEiRPaxOfGjRv4+++/0aZNm1wfR6VSISEhQefLUGTNFmv4TknYmCsljoaIiF6UkZGB1q1bY/jw4cjIyEDHjh1x5swZtGrVSurQKB9JlgjFxsZCrVZnKy26uLggJiYmx2MCAgIwadIkvPvuu1AqlfDy8kKzZs0watSoXB8nJCQEdnZ22i8PD498fR5vI6s/iMNiRESGR6lUonr16rC0tERoaCjWr18PR0dOailuJG+W1seePXswZcoUzJ8/HydPnsSGDRuwZcsWfPfdd7keM3LkSMTHx2u/bt++XYgR5+5uXCrO3o2HTPZ0/SAiIpJeYmIi7t27p70dEhKC06dP49NPP2VDdDElWbO0o6MjFAoF7t+/r7P9/v37KFUq5wrJ2LFj0aNHD3z66acAgOrVqyM5ORn9+/fH6NGjIZdnz+vMzMwMchw3q0m6TlkHONkYXnxERMbm8OHD6N69O0qVKoU9e/bAxMQE5ubmeOedd6QOjQqQZBUhU1NT1K5dGzt37tRu02g02LlzJxo0aJDjMSkpKdmSHYXi6ZRzIUTBBVsAtnK2GBGRQcjMzNS2XVy/fh23b982mNEDKniSTp8PDg5GUFAQ6tSpg3r16mHWrFlITk5G7969AQA9e/aEu7s7QkJCAADt2rXDjBkzULNmTdSvXx/Xrl3D2LFj0a5dO21CVBQ8Tk7H0ajHAJgIERFJKSoqCt27d8fBgwcBAN26dcP8+fNhb28vbWBUaCRNhLp27YqHDx9i3LhxiImJQY0aNRAREaFtoL5165ZOBWjMmDGQyWQYM2YM7t69CycnJ7Rr1w6TJ0+W6im8kR0X70MjAG9XW3iU4EX5iIgKmxAC4eHhGDhwIBITE2FjY4MFCxYgMDBQ6tCokMlEURtTeksJCQmws7NDfHw8bG1tJYlh6OpI/HHqLoa0eAfBrStJEgMRkTHLyMhA3bp1cfr0aTRq1AjLly9HuXLlpA6LXqGgPr95rTEJnL4TBwCoWdZB2kCIiIyUUqnEypUrsWHDBowYMQImJvw4NFZ85wtZfGoGbjxMBgD4lraXNhgiIiORkZGBCRMmwMLCAmPGjAEAVKlSBVWqVJE4MpIaE6FCdu5uPADAo4QFSliZShwNEVHxd+XKFQQGBuL48eNQKBTo1q0bvLy8pA6LDESRWlCxOIi8HQeA1SAiooImhEBoaChq1qyJ48ePw8HBAatXr2YSRDpYESpkZ571BzERIiIqOLGxsejXrx82btwIAGjRogWWLl2K0qVLSxsYGRwmQoXs9O2nQ2O+HvbSBkJEVExlZGTgf//7H65fvw6lUomQkBAMHTo0x6sPEPG7ohDdT0hDTEIa5DKgmrs0U/eJiIo7pVKJ4OBgeHt748iRI/j666+ZBFGu+J1RiE4/6w+q6GIDS1MW44iI8su5c+dw7Ngx7e0BAwbgxIkTqFmzpoRRUVHARKgQnbnzdFjMp7SdxJEQERUPQgjMmTMHderUQZcuXZCQkAAAkMlksLCwkDg6KgpYlihEWQsp+rBRmojorcXExKB3796IiIgAAHh7eyM9PV3iqKioYUWokAghtBWhGmyUJiJ6K3/99Rd8fHwQEREBc3NzzJkzB1u2bIGjo6PUoVERw4pQIfnvUQriUzNgaiJHpVI2UodDRFQkZWRk4Msvv8SCBQsAAD4+Pli5ciWqVq0qcWRUVLEiVEiyhsWqutlCqeDLTkT0JkxMTHD37l0AwNdff42jR48yCaK3wopQIdGuH8T+ICIivWg0GqSlpcHS0hIymQyLFi3CmTNn0LJlS6lDo2KApYlCklUR8vXgjDEiory6ffs2/Pz80L9/f+02JycnJkGUb1gRKgQZag3O38uaOm8vbTBEREXE2rVr0b9/f8TFxcHS0hJRUVEoV66c1GFRMcOKUCG4cj8RaRka2JiboFxJK6nDISIyaImJiejVqxe6dOmCuLg41K1bF5GRkUyCqEAwESoELy6kKJfLJI6GiMhwHT58GDVq1MDSpUshl8sxevRoHDhwABUqVJA6NCqmODRWCLIurcFGaSKi3KWnp6NLly64ffs2ypQpgxUrVqBx48ZSh0XFHCtCheD0HfYHERG9jqmpKX777TcEBATg9OnTTIKoULAiVMBS09W4cj8RAFeUJiJ6kRACK1asgFKpxCeffAIAaNWqFVq1aiVxZGRMmAgVsPP34qHWCDjbmKGUnbnU4RARGYS4uDgMGDAAq1atgo2NDRo2bIgyZcpIHRYZISZCBSwyqz+I1SAiIgDA3r170aNHD9y+fRsKhQLDhw+Hm5ub1GGRkWIiVMCyZoz5luZCikRk3NLT0zFhwgRMnToVQgh4eXkhPDwc9evXlzo0MmJMhApY1orSbJQmImOmUqnQuHFjHDt2DADQp08fzJ49G9bW1hJHRsaOs8YKUFxKOv57lALg6RpCRETGyszMDE2aNIGDgwPWrVuH3377jUkQGQQmQgUoa1jMs6Ql7C1NJY6GiKhwxcbG4vbt29rbkydPxtmzZ9GpUycJoyLSxUSoAJ1mozQRGalt27ahevXq6Nq1KzIzMwE8rQq5u7tLHBmRLiZCBYgLKRKRsUlLS8PQoUPh7++PmJgYxMXFISYmRuqwiHL1VolQWlpafsVR7AghtI3SNTzYH0RExd+5c+dQr149zJo1CwAwcOBAHD9+HKVLl5Y2MKJX0DsR0mg0+O677+Du7g5ra2vcuHEDADB27Fj89ttv+R5gURWTkIaHiSoo5DJUcWUiRETFlxACc+bMQZ06dXD27Fk4OTlh8+bNmDdvHiwtLaUOj+iV9E6Evv/+e4SFheHHH3+EqenzBuBq1aph0aJF+RpcUZbVH1TJxQYWpgppgyEiKkAZGRlYsmQJVCoV3n//fZw9exZt27aVOiyiPNE7EVq2bBl+/fVXBAYGQqF4/gHv6+uLS5cu5WtwRVlWf5Avh8WIqJgSQgB4erHUlStXYs6cOdiyZQtcXFwkjowo7/ReUPHu3bt45513sm3XaDTIyMjIl6CKA+2MMTZKE1Exk5KSgq+//hrOzs6YOHEiAKBy5cqoXLmyxJER6U/vRKhKlSr4999/UbZsWZ3t69atQ82aNfMtsKJMoxE4yxljRFQMnTx5EoGBgbh06RJMTEzQp0+fbJ8HREWJ3onQuHHjEBQUhLt370Kj0WDDhg24fPkyli1bhr/++qsgYixybsQmI1GVCXOlHBVduHIqERV9Go0GP/30E8aMGYOMjAy4urpi6dKlTIKoyNO7R6h9+/bYvHkzduzYASsrK4wbNw4XL17E5s2b0apVq4KIscg582zafDU3O5gouFQTERVtt2/fhp+fH7799ltkZGSgY8eOOHv2LH/nU7HwRhddbdy4MbZv357fsRQbXFGaiIoLlUqFhg0b4s6dO7C0tMTPP/+MPn36QCaTSR0aUb7Qu1xRvnx5PHr0KNv2uLg4lC9fPl+CKuqeryjNGWNEVLSZmZlh7NixqFOnDk6dOoW+ffsyCaJiRe9E6ObNm1Cr1dm2q1Qq3L17N1+CKsrSMzW4cC8BAGeMEVHRdPjwYRw6dEh7u1+/fjh48CAqVqwoYVREBSPPQ2ObNm3S/n/r1q2ws3te7VCr1di5cyc8PT3zNbii6HJMItLVGthZKFG2JFdUJaKiIzMzE1OmTMGkSZPg7u6O06dPw97eHjKZDEqlUurwiApEnhOhDh06AABkMhmCgoJ07lMqlfD09MT06dPzNbiiKPJZo7RPaTuWj4moyIiKikL37t1x8OBBAECjRo34O4yMQp4TIY1GAwAoV64cjh07BkdHxwILqig786xRugYbpYmoCBBCYMWKFRg0aBASExNha2uL+fPnIzAwUOrQiAqF3rPGoqKiCiKOYuMMF1IkoiJCpVKhV69eWLVqFYCnVaAVK1awzYGMyhtNn09OTsbevXtx69YtpKen69w3ZMiQfAmsKEpWZeLqg0QAgC9njBGRgTM1NUVaWhoUCgUmTJiAESNGwMTkjT4WiIosvb/jT506hTZt2iAlJQXJyckoUaIEYmNjYWlpCWdnZ6NOhM7djYdGAK525nC2NZc6HCKibNLT06FSqWBjYwOZTIbQ0FDcuHED9erVkzo0IknoPX1+6NChaNeuHZ48eQILCwscPnwY//33H2rXro2ffvqpIGIsMk4/a5TmtHkiMkRXrlxBo0aN0K9fP+2V4x0dHZkEkVHTOxGKjIzE119/DblcDoVCAZVKBQ8PD/z4448YNWpUQcRYZGgXUvTgsBgRGQ4hBEJDQ1GzZk0cP34c27Ztw507d6QOi8gg6J0IKZVKyOVPD3N2dsatW7cAAHZ2drh9+3b+RlfEZF1aowYrQkRkIGJjY/HRRx+hf//+SElJQYsWLXDmzBl4eHhIHRqRQdC7R6hmzZo4duwYKlSogKZNm2LcuHGIjY3F8uXLUa1atYKIsUh4lKTCnSepAIBqbJQmIgOwfft2BAUFITo6GkqlElOmTEFwcLD2j1kieoOK0JQpU+Dq6goAmDx5MhwcHDBgwAA8fPgQv/zyS74HWFRkTZv3crKCrTlXYCUiaaWlpaFPnz6Ijo6Gt7c3jhw5gmHDhjEJInqJ3hWhOnXqaP/v7OyMiIiIfA2oqGKjNBEZEnNzcyxduhTr16/HtGnTYGnJS/4Q5STf/jQ4efIk2rZtm1+nK3Ky+oN4xXkikoIQAnPmzMGKFSu021q0aIF58+YxCSJ6Bb0Soa1bt2LYsGEYNWoUbty4AQC4dOkSOnTogLp162ovw2FshBDaoTFfXlqDiApZTEwM2rRpgyFDhmDAgAGcEUakhzwPjf3222/o168fSpQogSdPnmDRokWYMWMGvvjiC3Tt2hXnzp2Dt7d3QcZqsO48ScWj5HSYyGXwdrWVOhwiMiKbN29Gnz59EBsbC3Nzc4SEhMDd3V3qsIiKjDxXhGbPno0ffvgBsbGxWLNmDWJjYzF//nycPXsWCxcuNNokCHjeKO3tagtzpULiaIjIGKSkpGDgwIH48MMPERsbCx8fHxw/fhyDBw/mVeOJ9JDnitD169fRuXNnAMBHH30EExMTTJs2DaVLly6w4IqKrEZp9gcRUWFITU1F3bp1ceHCBQDA119/jcmTJ8PMzEziyIiKnjwnQqmpqdqGO5lMBjMzM+00emOX1SjN/iAiKgwWFhZo27Ytnjx5gqVLl6JVq1ZSh0RUZOk1fX7RokWwtrYGAGRmZiIsLAyOjo46+xjbRVfVGoFzd581SnPqPBEVkDt37iAjIwPlypUDAHz33XcYPnw4SpYsKXFkREWbTGRdee81PD09XzvuLJPJtLPJ8mrevHmYNm0aYmJi4Ovrizlz5rzyAoBxcXEYPXo0NmzYgMePH6Ns2bKYNWsW2rRpk6fHS0hIgJ2dHeLj42Fr+/aNzVfuJ6L1zH2wNFXg7AR/KOQcmyei/LV27Vp89tlnqFixIv79918olVy0lYxPfn9+Z8lzRejmzZv59qBZVq9ejeDgYCxcuBD169fHrFmz4O/vj8uXL8PZ2Tnb/unp6WjVqhWcnZ2xbt06uLu747///oO9vX2+x5ZXWcNi1dztmAQRUb5KTEzEl19+iSVLlgAA1Go1Hj9+DBcXF4kjIyo+9F5ZOj/NmDED/fr1Q+/evQEACxcuxJYtW7B48WKMGDEi2/6LFy/G48ePcfDgQe1fRJ6enoUZcjZZjdI12B9ERPno8OHD6N69O65fvw6ZTIZRo0Zh/PjxrAYR5TPJLjqTnp6OEydOwM/P73kwcjn8/Pxw6NChHI/ZtGkTGjRogEGDBsHFxQXVqlXDlClToFarCyvsbLKmznPGGBHlh8zMTHz33Xd49913cf36dZQpUwZ79uzB999/zySIqABIVhGKjY2FWq3OVuJ1cXHBpUuXcjzmxo0b2LVrFwIDA/H333/j2rVrGDhwIDIyMjB+/Pgcj1GpVFCpVNrbCQkJ+fYcVJlqXIx+ej42ShNRftBoNPjzzz+hVqvRrVs3zJ8/X9Lhf6LiTtKhMX1pNBo4Ozvj119/hUKhQO3atXH37l1MmzYt10QoJCQEEydOLJB4LkYnIkMtUMLKFKUdLArkMYio+BNCQAgBuVwOU1NThIeH49ixY+jevbvUoREVe5INjTk6OkKhUOD+/fs62+/fv49SpUrleIyrqysqVqwIheL56s3e3t6IiYlBenp6jseMHDkS8fHx2q/bt2/n23PQrh9U2o4ruRLRG4mLi0NAQADGjRun3VapUiUmQUSF5I0SoevXr2PMmDHo1q0bHjx4AAD4559/cP78+Tyfw9TUFLVr18bOnTu12zQaDXbu3IkGDRrkeEyjRo1w7do1nYu7XrlyBa6urjA1Nc3xGDMzM9ja2up85ZfnK0rb59s5ich47Nu3D76+vli1ahWmTZuGu3fvSh0SkdHROxHau3cvqlevjiNHjmDDhg1ISkoCAJw+fTrX4ancBAcHIzQ0FEuXLsXFixcxYMAAJCcna2eR9ezZEyNHjtTuP2DAADx+/Bhffvklrly5gi1btmDKlCkYNGiQvk8jXzxfUZqN0kSUd+np6Rg1ahSaNWuGW7duwcvLC/v27ePFUokkoHeP0IgRI/D9998jODgYNjY22u0tWrTA3Llz9TpX165d8fDhQ4wbNw4xMTGoUaMGIiIitA3Ut27dglz+PFfz8PDA1q1bMXToUPj4+MDd3R1ffvklvv32W32fxltLSMvAjdhkAKwIEVHeXblyBYGBgTh+/DgAoE+fPpg1a5bO71MiKjx5Xlk6i7W1Nc6ePYty5crBxsYGp0+fRvny5XHz5k1UrlwZaWlpBRVrvsivlSkPXotFwKIjcLe3wIERLfIxQiIqrlJTU+Hp6YkHDx7AwcEBv/76Kz7++GOpwyIqEgpqZWm9h8bs7e0RHR2dbfupU6eMqqx7+tn6QVxIkYjyysLCAlOmTEGLFi1w5swZJkFEBkDvROiTTz7Bt99+i5iYGMhkMmg0Ghw4cADDhg1Dz549CyJGg5TVH8SFFInoVbZv3479+/drb/fp0wfbt29H6dKlJYyKiLLonQhNmTIFlStXhoeHB5KSklClShU0adIEDRs2xJgxYwoiRoN05tmMMV9WhIgoB2lpaQgODkbr1q0REBCAJ0+eAHh6ceoXex+JSFp6N0ubmpoiNDQUY8eOxblz55CUlISaNWuiQoUKBRGfQXqQmIZ78WmQyZ5ebJWI6EXnz59HQEAAzpw5AwBo164dzMzMJI6KiHKidyK0f/9+vPvuuyhTpgzKlClTEDEZvDO3n/YHVXC2hrVZkVqcm4gKkBACc+fOxTfffAOVSgUnJycsXrwYbdu2lTo0IsqF3vXZFi1aoFy5chg1ahQuXLhQEDEZvDNcSJGIXpKSkoI2bdpgyJAhUKlUeP/993H27FkmQUQGTu9E6N69e/j666+xd+9eVKtWDTVq1MC0adNw586dgojPIEU+mzHG/iAiymJhYQFra2uYmZlhzpw52LJlS7aLShOR4dF7HaEXRUVFYeXKlfj9999x6dIlNGnSBLt27crP+PLd265DIIRAze+2Iy4lA5sGN2JViMiIpaSkICMjA3Z2T3sFHz9+jOjoaFStWlXiyIiKH4NZR+hF5cqVw4gRIzB16lRUr14de/fuza+4DNatxymIS8mAqUKOyqXy740goqLl1KlTqF27Nvr164esvydLlCjBJIioiHnjROjAgQMYOHAgXF1dERAQgGrVqmHLli35GZtBylpI0dvNFqYmnAJLZGw0Gg2mTZuG+vXr49KlS9i/fz9iYmKkDouI3pDeU55GjhyJVatW4d69e2jVqhVmz56N9u3bw9LSsiDiMzhZCynW4EKKREbnzp07CAoK0rYAdOzYEb/++iscHR0ljoyI3pTeidC+ffvwzTffoEuXLkb5w88ZY0TGad26dejfvz+ePHkCS0tLzJ49G3379oVMJpM6NCJ6C3onQgcOHCiIOIqETLUGZ+9mzRhjRYjIWKSkpGDo0KF48uQJ6tSpg/DwcFSsWFHqsIgoH+QpEdq0aRPef/99KJVKbNq06ZX7fvjhh/kSmCG6+iAJaRkaWJuZoLyjtdThEFEhsbS0xLJly7Bjxw5MmDABSqVS6pCIKJ/kKRHq0KEDYmJi4OzsjA4dOuS6n0wmg1qtzq/YDE5Wf1B1dzvI5SyHExVXmZmZCAkJgYeHB3r16gUAaN68OZo3by5tYESU7/KUCGk0mhz/b2xOcyFFomIvKioKPXr0wIEDB2BlZQV/f3+4urpKHRYRFRC9538vW7YMKpUq2/b09HQsW7YsX4IyVFkVIV/OGCMqdoQQWLFiBXx9fXHgwAHY2tril19+YRJEVMzpnQj17t0b8fHx2bYnJiaid+/e+RKUIUrLUOPy/UQArAgRFTdxcXEIDAxEjx49kJiYiEaNGuH06dMIDAyUOjQiKmB6zxoTQuQ4XfTOnTvaZeaLo/P34qHWCDham8HVzlzqcIgon6SkpKBWrVqIioqCQqHAhAkTMGLECJiY6P3rkYiKoDz/pNesWRMymQwymQwtW7bU+SWhVqsRFRWF9957r0CCNASnbz+tgtXwsOO6IUTFiKWlJbp27Yq1a9ciPDwc9evXlzokIipEeU6EsmaLRUZGwt/fH9bWz6ePm5qawtPTE506dcr3AA0FF1IkKj6uXLkCuVyOd955BwAwceJEjBo1CjY2NhJHRkSFLc+J0Pjx4wEAnp6e6Nq1K8zNjWt4iDPGiIo+IQQWLVqEr776ClWqVMHBgwehVCphamoKU1NTqcMjIgnoPQgeFBRUEHEYtPiUDETFJgMAfNyLbx8UUXEWGxuLfv36YePGjQAAW1tbJCQkoGTJktIGRkSSylMiVKJECVy5cgWOjo5wcHB4ZY/M48eP8y04Q3HmbhwAoGxJSzhY8a9GoqJm27Zt6NWrF6Kjo6FUKhESEoKhQ4dCLtd74iwRFTN5SoRmzpypHTufOXOm0TULn3k2LMb+IKKiRaVSYeTIkZg5cyYAwNvbGytXrkSNGjWkDYyIDEaeEqEXh8Oylps3JpFcSJGoSJLL5di/fz8AYNCgQfjxxx9haWkpcVREZEj07hE6efIklEolqlevDgD4888/sWTJElSpUgUTJkwolg2HWTPG2ChNZPiEEFCr1TAxMYFSqUR4eDguX76Mtm3bSh0aERkgvQfIP/vsM1y5cgUAcOPGDXTt2hWWlpZYu3Ythg8fnu8BSi0mPg33E1SQy4CqbrZSh0NErxATE4M2bdpgzJgx2m0VKlRgEkREudI7Ebpy5Yp2fH3t2rVo2rQpVq5cibCwMKxfvz6/45Pc6WfVoIouNrA05UqzRIZq8+bNqF69OiIiIjBnzhzcv39f6pCIqAjQOxESQmivQL9jxw60adMGAODh4YHY2Nj8jc4APL/Qqr2kcRBRzlJSUjBgwAB8+OGHiI2NhY+PD44ePQoXFxepQyOiIkDvRKhOnTr4/vvvsXz5cuzduxcffPABACAqKqpY/uI5w4UUiQzWyZMnUatWLSxcuBAA8PXXX+Po0aOoWrWqxJERUVGh91jPrFmzEBgYiI0bN2L06NHaJerXrVuHhg0b5nuAUtJohHZozIczxogMSlJSElq1aoXHjx/Dzc0NS5cuhZ+fn9RhEVERo3ci5OPjg7Nnz2bbPm3aNCgUinwJylDcfJSMxLRMmJnIUakUr0FEZEisra0xffp0bNq0CaGhoVwhmojeyBt3/544cQIXL14EAFSpUgW1atXKt6AMRVY1qKqbLZQKrkBLJLW1a9fCyckJzZo1A/B0jbOgoCCjW+SViPKP3onQgwcP0LVrV+zduxf29vYAgLi4ODRv3hyrVq2Ck5NTfscomdO32R9EZAgSExMxZMgQhIWFwd3dHWfOnEGJEiWYABHRW9O7zPHFF18gKSkJ58+fx+PHj/H48WOcO3cOCQkJGDJkSEHEKJmsihBnjBFJ5/Dhw6hRowbCwsIgk8nQq1cv7SV/iIjelt4VoYiICOzYsQPe3t7abVWqVMG8efPQunXrfA1OShlqDS7cSwDAihCRFDIzMzFlyhRMmjQJarUaZcqUwYoVK9C4cWOpQyOiYkTvREij0UCpVGbbrlQqtesLFQeXYxKhytTA1twEniV5bSKiwpSUlAR/f38cPHgQABAQEIB58+Zph+OJiPKL3kNjLVq0wJdffol79+5pt929exdDhw5Fy5Yt8zU4KV2IfloNquZuxz4EokJmZWUFDw8P2NraYsWKFQgPD2cSREQFQu+K0Ny5c/Hhhx/C09MTHh4eAIDbt2+jWrVqWLFiRb4HKJW4lHQAgIutucSREBmHuLg4aDQabRP0ggULEBcXh3LlykkdGhEVY3onQh4eHjh58iR27typnT7v7e1d7BYyS0jNBADYmvP6YkQFbe/evejRowfq1KmD9evXQyaTwcHBAQ4ODlKHRkTFnF6f8qtXr8amTZuQnp6Oli1b4osvviiouCSXkJYBALC1yN4PRUT5Iz09HRMmTMDUqVMhhICpqSkePnwIZ2dnqUMjIiOR5x6hBQsWoFu3bjh+/DiuXr2KQYMG4ZtvvinI2CSVkPosETJnIkRUEC5fvoyGDRsiJCQEQgj06dMHp06dYhJERIUqz4nQ3LlzMX78eFy+fBmRkZFYunQp5s+fX5CxSSox7dnQmAWHxojykxACoaGhqFWrFk6cOAEHBwesW7cOv/32G9cHIqJCl+dE6MaNGwgKCtLeDggIQGZmJqKjowskMKlph8ZYESLKV8nJyfj++++RkpKCFi1a4MyZM+jUqZPUYRGRkcpzuUOlUsHKykp7Wy6Xw9TUFKmpqQUSmNS0zdLsESLKV9bW1lixYgWOHDmC4OBgyOW8jh8RSUevcZ+xY8fC0vL54oLp6emYPHky7OzstNtmzJiRf9FJiBUhovyRlpaGUaNGwdvbG/369QMANG7cmCtEE5FByHMi1KRJE1y+fFlnW8OGDXHjxg3t7eK08KC2WZo9QkRv7Ny5cwgICMDZs2dhZWWFDh06FKsLMxNR0ZfnT/k9e/YUYBiGJVOtQXK6GgArQkRvQgiBuXPn4ptvvoFKpYKTkxMWL17MJIiIDA7LHTnImjEGADZcUJFILzExMejduzciIiIAAO+//z6WLFkCFxcXiSMjIsqOn/I5yOoPsjJVwETBRk6ivEpMTETNmjURExMDc3NzTJs2DYMGDSpWw+ZEVLzwUz4HnDFG9GZsbGzw6aefwsfHB8ePH8fgwYOZBBGRQWMilAPOGCPKu1OnTulMpBg3bhyOHj2KqlWrShgVEVHeMBHKAWeMEb2eRqPBtGnTUL9+fQQEBCA9PR0AoFQqYWZmJnF0RER580aJ0L///ovu3bujQYMGuHv3LgBg+fLl2L9/f74GJxVWhIhe7c6dO2jVqhWGDx+OjIwMlC1bttgurkpExZveidD69evh7+8PCwsLnDp1CiqVCgAQHx+PKVOm5HuAUmCPEFHu1q5dCx8fH+zatQuWlpYIDQ3F+vXrdRZWJSIqKvROhL7//nssXLgQoaGhUCqfJwqNGjXCyZMn8zU4qTyvCHFojChLSkoK+vTpgy5duuDJkyeoU6cOTp06hU8//ZQN0URUZOmdCF2+fBlNmjTJtt3Ozg5xcXH5EZPknvcIsSJElMXU1BQXL16ETCbD6NGjcfDgQVSsWFHqsIiI3oreJY9SpUrh2rVr8PT01Nm+f/9+lC9fPr/iklTCswUV2SNExi4zMxMajQampqYwMTHBihUrcPfu3Rz/GCIiKor0rgj169cPX375JY4cOQKZTIZ79+4hPDwcw4YNw4ABAwoixkLHWWNEQFRUFJo2bYoxY8Zot3l5eTEJIqJiRe9EaMSIEQgICEDLli2RlJSEJk2a4NNPP8Vnn32GL7744o2CmDdvHjw9PWFubo769evj6NGjeTpu1apVkMlk6NChwxs9bm44a4yMmRACy5cvh6+vLw4ePIjQ0FDExsZKHRYRUYHQOxHK6g94/Pgxzp07h8OHD+Phw4f47rvv3iiA1atXIzg4GOPHj8fJkyfh6+sLf39/PHjw4JXH3bx5E8OGDUPjxo3f6HFfhbPGyFjFxcUhICAAPXv2RGJiIho1aoRTp07B0dFR6tCIiArEGy+oaGpqiipVqqBevXqwtrZ+4wBmzJiBfv36oXfv3qhSpQoWLlwIS0tLLF68ONdj1Go1AgMDMXHixALpS2JFiIzR3r174ePjg1WrVkGhUOC7777Dnj17svUDEhEVJ3o3wTRv3vyVU2V37dqV53Olp6fjxIkTGDlypHabXC6Hn58fDh06lOtxkyZNgrOzM/r27Yt///33lY+hUqm0ax0BQEJCwmvjYo8QGZv4+Hi0b98e8fHx8PLyQnh4OOrXry91WEREBU7vT/oaNWro3M7IyEBkZCTOnTuHoKAgvc4VGxsLtVoNFxcXne0uLi64dOlSjsfs378fv/32GyIjI/P0GCEhIZg4cWKeY8pUa5CcrgbAihAZDzs7O/z888/Yu3cvZs2aBRsbG6lDIiIqFHonQjNnzsxx+4QJE5CUlPTWAb1KYmIievTogdDQ0Dz3LIwcORLBwcHa2wkJCfDw8Mj9MZ5NnQcAGy6oSMWUEAKLFi1CuXLl4OfnBwDo2bMnevbsKXFkRESFK98+6bt374569erhp59+yvMxjo6OUCgUuH//vs72+/fvo1SpUtn2v379Om7evIl27dppt2k0GgCAiYkJLl++DC8vL51jzMzM9LoAZFZ/kJWpAiYKXpOWip/Y2Fj069cPGzduhKurK86fPw8HBwepwyIikkS+fdIfOnQI5ubmeh1jamqK2rVrY+fOndptGo0GO3fuRIMGDbLtX7lyZZw9exaRkZHarw8//BDNmzdHZGTkKys9ecUZY1Scbdu2DT4+Pti4cSOUSiWCg4N5jTAiMmp6V4Q++ugjndtCCERHR+P48eMYO3as3gEEBwcjKCgIderUQb169TBr1iwkJyejd+/eAJ6W693d3RESEgJzc3NUq1ZN53h7e3sAyLb9TXHGGBVHaWlpGDlyJGbNmgUA8Pb2Rnh4OGrWrCltYEREEtM7EXr5r0e5XI5KlSph0qRJaN26td4BdO3aFQ8fPsS4ceMQExODGjVqICIiQttAfevWLcjlhTdExRljVNzEx8ejcePGOHv2LABg4MCBmDZtGiwtLSWOjIhIenp92qvVavTu3RvVq1fP156CwYMHY/DgwTnet2fPnlceGxYWlm9xAKwIUfFja2uLatWqISYmBosXL0bbtm2lDomIyGDolQgpFAq0bt0aFy9eLLbNlewRouIgJiYGSqUSJUuWhEwmw/z586FSqbItVUFEZOz0HnOqVq0abty4URCxGITnFSEOjVHRtHnzZlSvXh19+/aFEALA0146JkFERNnpnQh9//33GDZsGP766y9ER0cjISFB56uoe94jxIoQFS0pKSkYOHAgPvzwQ8TGxiIqKgpPnjyROiwiIoOW50Ro0qRJSE5ORps2bXD69Gl8+OGHKF26NBwcHODg4AB7e/tiMVyW8GxBRfYIUVFy8uRJ1K5dGwsWLADwdDbm0aNHUaJECYkjIyIybHke/5k4cSI+//xz7N69uyDjkRxnjVFRotFo8NNPP2HMmDHIyMiAq6srli5dilatWkkdGhFRkZDnT/usXoOmTZsWWDCGgLPGqChJSkrC/PnzkZGRgY4dOyI0NBQlS5aUOiwioiJDr7LHq646X1xw1hgVBUIIyGQy2NraIjw8HBcvXkTfvn2N4meUiCg/6ZUIVaxY8bW/aB8/fvxWAUmNFSEyZImJiRgyZAj+97//4bPPPgMANGrUCI0aNZI4MiKiokmvRGjixInF/rpE7BEiQ3X48GEEBgbixo0bWLduHTp37sxmaCKit6TXp/0nn3wCZ2fngopFcplqDZLT1QBYESLDkZmZiSlTpmDSpElQq9UoU6YMli9fziSIiCgf5DkRMobeg8RnU+cBwIYLKpIBiIqKQvfu3XHw4EEAQLdu3TB//nztxYaJiOjt6D1rrDjL6g+yMlXARFF4F3olyklcXBxq166NJ0+ewMbGBgsWLEBgYKDUYRERFSt5ToQ0Gk1BxmEQOGOMDIm9vT2GDBmCHTt2YPny5ShXrpzUIRERFTsse7yAM8ZIavv27cPFixe1t8eMGYM9e/YwCSIiKiBMhF7AGWMklYyMDIwePRrNmjVDQEAAVCoVAMDExAQmJvx+JCIqKPwN+4KsipANK0JUiK5cuYLAwEAcP34cAFCzZk1kZmbCzMxM4siIiIo/VoReoO0R4owxKgRCCISGhqJmzZo4fvw4HBwcsHbtWixevBhWVlZSh0dEZBT4if8CbY8Qm6WpgCUmJqJnz57YuHEjAKBFixZYunQpSpcuLW1gRERGhhWhF2h7hDg0RgXMwsICDx48gFKpxLRp07B9+3YmQUREEmBF6AUJaVnT5/myUP7LaoA2MzODiYkJVqxYgbi4ONSsWVPiyIiIjBcrQi9gRYgKyvnz51GvXj2MGjVKu61cuXJMgoiIJMZE6AXsEaL8JoTAnDlzUKdOHZw5cwYrVqzAkydPpA6LiIieYSL0guezxpgI0duLiYnBBx98gCFDhiAtLQ3vvfceTp8+DQcHB6lDIyKiZ5gIveB5RYg9QvR2/vrrL/j4+OCff/6BmZkZ5syZg7///hulSpWSOjQiInoBP/FfwB4hyg9PnjxB9+7dER8fDx8fH6xcuRJVq1aVOiwiIsoBE6FnMtUaJKerAbBHiN6Og4MD5s+fjxMnTmDKlClcIZqIyIBxaOyZxGdT5wHAhitLkx40Gg2mTZuGrVu3arcFBARg+vTpTIKIiAwcP/GfyeoPsjRVQKlgfkh5c+fOHQQFBWHXrl0oVaoULl68CHt7e6nDIiKiPOIn/jOcMUb6Wrt2LXx8fLBr1y5YWVlh8uTJsLOzkzosIiLSAytCz3DGGOVVYmIihgwZgrCwMABA3bp1ER4ejgoVKkgbGBER6Y2f+s9wxhjlxePHj1G3bl3cuHEDMpkMo0aNwvjx46FU8vuGiKgoYiL0DFeVprwoUaIEGjZsiMzMTCxfvhxNmjSROiQiInoLTISeed4jxJeEdEVFRcHKygrOzs4AgHnz5kGj0bApmoioGGCz9DOsCNHLhBBYvnw5fH190bdvXwghAAC2trZMgoiIigkmQs+wR4heFBcXh4CAAPTs2ROJiYmIi4tDQkKC1GEREVE+YyL0TMKzBRU5a4z27dsHX19frFq1CgqFAt9//z327NnDqfFERMUQP/WfYUWIMjIyMGHCBISEhEAIAS8vL4SHh6N+/fpSh0ZERAWEFaFnErUVISZCxio1NRW///47hBDo27cvIiMjmQQRERVzrAg9o22WZkXIqGQ1QMtkMtja2mLlypW4e/cuOnXqJHFkRERUGFgRekY7NMYeIaMRGxuLjh07YsGCBdpt//vf/5gEEREZESZCz2ibpVkRMgrbtm1D9erV8eeff2LUqFGIj4+XOiQiIpIAEyEAmWoNklTsETIGaWlpGDp0KPz9/RETEwNvb2/OCCMiMmIcBwK0SRAA2HBl6WLr3LlzCAgIwNmzZwEAAwcOxLRp02BpaSlxZEREJBV+6uP55TUsTRVQKlgkK44ePXqEBg0aICkpCU5OTli8eDHatm0rdVhERCQxJkLgjDFjULJkSQwfPhyHDh3CkiVL4OLiInVIRERkAJgIgTPGiqvNmzejXLlyqFatGgBg1KhRkMvlkMlkEkdGRESGguNAYEWouElJScGAAQPw4YcfIjAwEGlpaQAAhULBJIiIiHSwBILnPUKcMVb0nTx5EgEBAbh8+TIAwM/Pj8kPERHlihUhvFgRYl5YVGk0Gvz444/43//+h8uXL8PV1RXbt2/H9OnTYWZmJnV4RERkoPjJjxd7hFgRKoqePHmCTp06Yffu3QCAjh07IjQ0FCVLlpQ4MiIiMnSsCIGrShd1tra2yMjIgKWlJRYtWoT169czCSIiojxhRQicNVYUJSYmQqlUwtzcHAqFAuHh4VCpVKhQoYLUoRERURHCihA4a6yoOXz4MGrUqIERI0Zot5UpU4ZJEBER6Y2JEDhrrKjIzMzEpEmT8O677+LGjRvYuHEjEhISpA6LiIiKMCZCYEWoKIiKikLTpk0xfvx4qNVqBAQEIDIyEra2tlKHRkRERRgTIbBHyJAJIbB8+XL4+vri4MGDsLW1xYoVKxAeHg57e3upwyMioiKOn/zgrDFD9ujRI3zxxRdITExEo0aNsGLFCnh6ekodFhERFRNGnwhlqjVIUrFHyFA5Ojril19+wdWrVzFixAiYmBj9tywREeUjo/9UyUqCAMCGK0tLLj09HRMmTMC7776LNm3aAAC6du0qcVRERFRcGUSP0Lx58+Dp6Qlzc3PUr18fR48ezXXf0NBQNG7cGA4ODnBwcICfn98r93+drBljlqYKKBUG8XIYrcuXL6Nhw4YICQlB7969kZiYKHVIRERUzEn+yb969WoEBwdj/PjxOHnyJHx9feHv748HDx7kuP+ePXvQrVs37N69G4cOHYKHhwdat26Nu3fvvtHjc8aY9IQQCA0NRa1atXDixAk4ODhg/vz5sLGxkTo0IiIq5mRCCCFlAPXr10fdunUxd+5cAE8vnunh4YEvvvhCZ8G83KjVajg4OGDu3Lno2bPna/dPSEiAnZ0d4uPjYWtri4PXYhGw6Agqulhj29Cmb/18SD+xsbHo168fNm7cCABo0aIFli5ditKlS0sbGBERGZSXP7/zi6RNMenp6Thx4gRGjhyp3SaXy+Hn54dDhw7l6RwpKSnIyMhAiRIlcrxfpVJBpVJpb7+8AB8rQtJ5+PAhfH19ER0dDaVSiZCQEAwdOhRyueSFSiIiMhKSfuLExsZCrVbDxcVFZ7uLiwtiYmLydI5vv/0Wbm5u8PPzy/H+kJAQ2NnZab88PDx07ueq0tJxcnJC69at4e3tjSNHjuDrr79mEkRERIWqSE+Tmjp1KlatWoU9e/bA3Nw8x31GjhyJ4OBg7e2EhASdZOh5RahIvxRFxvnz5+Ho6KhNfufOnQu5XA5LS0uJIyMiImMk6Z/fjo6OUCgUuH//vs72+/fvo1SpUq889qeffsLUqVOxbds2+Pj45LqfmZkZbG1tdb5e9HxVaVaECpIQAnPmzEHt2rXRp08fZLWmWVtbMwkiIiLJSJoImZqaonbt2ti5c6d2m0ajwc6dO9GgQYNcj/vxxx/x3XffISIiAnXq1HmrGLiqdMGLiYlBmzZtMGTIEG2/VnJyssRRERERGcD0+eDgYISGhmLp0qW4ePEiBgwYgOTkZPTu3RsA0LNnT51m6h9++AFjx47F4sWL4enpiZiYGMTExCApKemNHp/XGStYmzdvRvXq1REREQFzc3PMnTsXf/31F6ytraUOjYiISPoeoa5du+Lhw4cYN24cYmJiUKNGDURERGh7SG7duqXTQLtgwQKkp6fj448/1jnP+PHjMWHCBL0fn7PGCkZKSgq+/vprLFy4EADg4+ODlStXomrVqhJHRkRE9JzkiRAADB48GIMHD87xvj179ujcvnnzZr4+NmeNFQy1Wo3t27cDAL7++mtMnjwZZmZmEkdFRESkyyASISmxIpR/NBoNgKdrQdnY2OD3339HfHx8rksbEBERSU3yHiGpsUcof9y5cwetWrXSrhAOAHXr1mUSREREBo2JEGeNvbW1a9fCx8cHu3btwqRJk964cZ2IiKiwGXUilKnWIEnFHqE3lZiYiN69e6NLly548uQJ6tati0OHDnFGGBERFRlGnQhlJUEAYMOVpfVy+PBh1KhRA2FhYZDJZBg9ejQOHDiAChUqSB0aERFRnhn1p3/WjDELpQJKhVHnhHq5f/8+mjdvjrS0NJQpUwYrVqxA48aNpQ6LiIhIb8adCKWxUfpNuLi4YOzYsTh37hzmz58Pe3t7qUMiIiJ6I0adAWhnjLFR+pWEEFixYgV8fX2113UbOXIkZDKZxJERERG9HaMeD3peEWIilJu4uDgEBASgZ8+eCAgIQGpqKgAwCSIiomLByCtCWVPnjfplyNXevXvRo0cP3L59GwqFAp988gmUSiaNRERUfBh1BsCKUM7S09MxYcIETJ06FUIIeHl5ITw8HPXr15c6NCIionxl3IkQe4SyefjwIdq0aYPjx48DAPr06YNZs2bBxsZG4siIiIjyn3EnQlmrSnPWmFaJEiVgZWUFBwcH/Prrr/j444+lDomIiKjAGHUGwIrQU7GxsbCysoKFhQUUCgVWrFgBAChdurTEkRERERUszhqDcfcIbdu2DT4+Phg+fLh2W+nSpZkEERGRUTDuRCjVeC+4mpaWhuDgYPj7+yM6Oho7d+5EcnKy1GEREREVKuNOhIx0Zenz58+jfv36mDlzJgBg4MCBOH78OKysrCSOjIiIqHAZdyJkZD1CQgjMmTMHtWvXxpkzZ+Dk5ITNmzdj3rx5sLS0lDo8IiKiQmdcpZCXPJ81ZhyJ0IMHDzB+/HioVCq8//77WLJkCVxcXKQOi4iISDJGmwhlqjVIUhnXytIuLi4IDQ1FdHQ0Bg0axMtkEBGR0TOODCAHWUkQANgU06GxlJQUDBs2DG3atEHbtm0BAJ06dZI4KiIiIsNhtIlQ4rNhMQulAqYmxa9V6uTJkwgMDMSlS5ewfv163Lhxg83QRERELyl+GUAeJRbTGWMajQbTpk3D//73P1y6dAmurq5YsWIFkyAiIqIcFK8sQA+JxXANoTt37iAoKAi7du0CAHTs2BGhoaEoWbKkxJEREREZJqNNhBJUxWtV6ejoaPj4+ODJkyewtLTE7Nmz0bdvXzZEExERvYLRJkLPK0LF4yVwdXVFx44dcebMGYSHh6NixYpSh0RERGTwikcW8AYSi0FF6MiRIyhTpgxcXV0BAHPmzIFSqYRSWXSfExERUWEy3mbpItwjlJmZiUmTJqFRo0bo3bs3NBoNAMDS0pJJEBERkR6MuCKUtap00XoJoqKi0L17dxw8eBAAUKJECahUKlhYWEgcGRERUdFjtBWhonadMSEEVqxYAV9fXxw8eBC2trZYsWIFVq5cySSIiIjoDRWtckg+Kko9QgkJCfj888/x+++/AwAaNWqE5cuXo1y5chJHRkREVLQZbyKUqgZQNCpCCoUCx48fh0KhwPjx4zFy5EiYmBjtW0dU6IQQyMzMhFqtljoUomJNqVRCoVAU6mMa7afp84qQYb4EGRkZUCgUkMvlsLKywqpVq5CRkYH69etLHRqRUUlPT0d0dDRSUlKkDoWo2JPJZChdujSsra0L7TENMwsoBE+vNSY3yIrQlStXEBgYiMDAQHz11VcAgFq1akkbFJER0mg0iIqKgkKhgJubG0xNTblIKVEBEULg4cOHuHPnDipUqFBolSEjToQyAJgZVI+QEAKLFi3CV199hZSUFNy9exf9+/eHpaWl1KERGaX09HRoNBp4eHjw55CoEDg5OeHmzZvaUZHCYLSzxpJUWT1ChpELxsbG4qOPPkL//v2RkpKCFi1a4OjRo/zlS2QA5HKj/VVJVKikqLga/U+3jQEMjW3btg0+Pj7YuHEjlEolpk2bhu3bt6N06dJSh0ZERFSsGUY5RCIWSgVMTaTNBe/du4d27dohPT0d3t7eCA8PR82aNSWNiYiIyFgYdUXIEGaMubm5YdKkSRg4cCCOHz/OJIiISGKXL19GqVKlkJiYKHUoxUp6ejo8PT1x/PhxqUPRYdyJkATDYkIIzJ07F5GRkdptw4cPx7x589gPRET5plevXpDJZJDJZFAqlShXrhyGDx+OtLS0bPv+9ddfaNq0KWxsbGBpaYm6desiLCwsx/OuX78ezZo1g52dHaytreHj44NJkybh8ePHBfyMCs/IkSPxxRdfwMbGRupQCsy8efPg6ekJc3Nz1K9fH0ePHn3l/hkZGZg0aRK8vLxgbm4OX19fRERE5Lr/1KlTIZPJtDOfAcDU1BTDhg3Dt99+m19PI18YdyJUyDPGYmJi8MEHH+CLL75AQECA9hcSp+MSUUF47733EB0djRs3bmDmzJn45ZdfMH78eJ195syZg/bt26NRo0Y4cuQIzpw5g08++QSff/45hg0bprPv6NGj0bVrV9StWxf//PMPzp07h+nTp+P06dNYvnx5oT2v9PT0Ajv3rVu38Ndff6FXr15vdZ6CjPFtrV69GsHBwRg/fjxOnjwJX19f+Pv748GDB7keM2bMGPzyyy+YM2cOLly4gM8//xwdO3bEqVOnsu177Ngx/PLLL/Dx8cl2X2BgIPbv34/z58/n63N6K8LIxMfHCwDC46s1otfiI4X2uJs3bxZOTk4CgDAzMxNz5swRGo2m0B6fiPSXmpoqLly4IFJTU7XbNBqNSFZlSPKlz++MoKAg0b59e51tH330kahZs6b29q1bt4RSqRTBwcHZjv/5558FAHH48GEhhBBHjhwRAMSsWbNyfLwnT57kGsvt27fFJ598IhwcHISlpaWoXbu29rw5xfnll1+Kpk2bam83bdpUDBo0SHz55ZeiZMmSolmzZqJbt26iS5cuOselp6eLkiVLiqVLlwohhFCr1WLKlCnC09NTmJubCx8fH7F27dpc4xRCiGnTpok6derobIuNjRWffPKJcHNzExYWFqJatWpi5cqVOvvkFKMQQpw9e1a89957wsrKSjg7O4vu3buLhw8fao/7559/RKNGjYSdnZ0oUaKE+OCDD8S1a9deGePbqlevnhg0aJD2tlqtFm5ubiIkJCTXY1xdXcXcuXN1tn300UciMDBQZ1tiYqKoUKGC2L59u2jatKn48ssvs52refPmYsyYMTk+Tk4/c1myPr/j4+Nf9fT0Jn2TjIQKoyKUkpKCYcOGYcGCBQAAHx8frFy5ElWrVi3wxyai/JeaoUaVcVsleewLk/xhafpmv7bPnTuHgwcPomzZstpt69atQ0ZGRrbKDwB89tlnGDVqFH7//XfUr18f4eHhsLa2xsCBA3M8v729fY7bk5KS0LRpU7i7u2PTpk0oVaoUTp48CY1Go1f8S5cuxYABA3DgwAEAwLVr19C5c2ckJSVpVyHeunUrUlJS0LFjRwBASEgIVqxYgYULF6JChQrYt28funfvDicnJzRt2jTHx/n3339Rp04dnW1paWmoXbs2vv32W9ja2mLLli3o0aMHvLy8UK9evVxjjIuLQ4sWLfDpp59i5syZSE1NxbfffosuXbpg165dAIDk5GQEBwfDx8cHSUlJGDduHDp27IjIyMhcl22YMmUKpkyZ8srX68KFCyhTpky27enp6Thx4gRGjhyp3SaXy+Hn54dDhw7lej6VSgVzc3OdbRYWFti/f7/OtkGDBuGDDz6An58fvv/++xzPVa9ePfz777+vjL8wGXciVMA9QtHR0WjRogUuXboEAAgODsaUKVNgZmZWoI9LRAQ87f2xtrZGZmYmVCoV5HI55s6dq73/ypUrsLOzg6ura7ZjTU1NUb58eVy5cgUAcPXqVZQvXx5KpX6/N1euXImHDx/i2LFjKFGiBADgnXfe0fu5VKhQAT/++KP2tpeXF6ysrPDHH3+gR48e2sf68MMPYWNjA5VKhSlTpmDHjh1o0KABAKB8+fLYv38/fvnll1wTof/++y9bIuTu7q6TLH7xxRfYunUr1qxZo5MIvRzj999/j5o1a+okLYsXL4aHhweuXLmCihUrolOnTjqPtXjxYjg5OeHChQuoVq1ajjF+/vnn6NKlyytfLzc3txy3x8bGQq1Ww8XFRWe7i4uL9rMqJ/7+/pgxYwaaNGkCLy8v7Ny5Exs2bNC5/t6qVatw8uRJHDt27LWx/ffff6/cpzAZdyJUwLPGXFxc4Orqivj4eCxduhStWrUq0McjooJnoVTgwiR/yR5bH82bN8eCBQuQnJyMmTNnwsTEJNsHb14JId7ouMjISNSsWVObBL2p2rVr69w2MTFBly5dEB4ejh49eiA5ORl//vknVq1aBeBpxSglJSXb79309PRXzs5NTU3NVvlQq9WYMmUK1qxZg7t37yI9PR0qlSrbBJeXYzx9+jR2796d43Wzrl+/jooVK+Lq1asYN24cjhw5gtjYWG2l7NatW7kmQiVKlHjr11Nfs2fPRr9+/VC5cmXIZDJ4eXmhd+/eWLx4MQDg9u3b+PLLL7F9+/Zsr9/LLCwsDOrafcadCBVARejOnTsoUaIELC0tIZfLER4eDqVSCUdHx3x/LCIqfDKZ7I2HpwqblZWVtvqyePFi+Pr64rfffkPfvn0BABUrVkR8fDzu3buXrYKQnp6O69evo3nz5tp99+/fj4yMDL2qQhYWFq+8Xy6XZ0uyMjIycnwuLwsMDETTpk3x4MEDbN++HRYWFnjvvfcAPB2SA4AtW7bA3d1d57hXVeUdHR3x5MkTnW3Tpk3D7NmzMWvWLFSvXh1WVlb46quvsjVEvxxjUlIS2rVrhx9++CHb42RV4dq1a4eyZcsiNDQUbm5u0Gg0qFat2iubrd9maMzR0REKhQL379/X2X7//n2UKlUq1/M5OTlh48aNSEtLw6NHj+Dm5oYRI0agfPnyAIATJ07gwYMHOtfFVKvV2LdvH+bOnQuVSqW9ZMbjx4/h5OT0yvgLE2eN5aO1a9fCx8dHp4Tq6urKJIiIJCeXyzFq1CiMGTMGqampAIBOnTpBqVRi+vTp2fZfuHAhkpOT0a1bNwBAQEAAkpKSMH/+/BzPHxcXl+N2Hx8fREZG5jq93snJCdHR0TrbXlxe5FUaNmwIDw8PrF69GuHh4ejcubM2SatSpQrMzMxw69YtvPPOOzpfHh4euZ6zZs2auHDhgs62AwcOoH379ujevTt8fX11hgxfpVatWjh//jw8PT2zxWBlZYVHjx7h8uXLGDNmDFq2bAlvb+9sSVhOPv/8c0RGRr7yK7ehMVNTU9SuXRs7d+7UbtNoNNi5c6d2CPFVzM3N4e7ujszMTKxfvx7t27cHALRs2RJnz57ViaFOnToIDAxEZGSkznXDzp07Z1hr5uVr63UR8OKssb9O38uXcyYkJIjevXsLAAKAqFevnkhJScmXcxORdF41g8XQ5TQbKyMjQ7i7u4tp06Zpt82cOVPI5XIxatQocfHiRXHt2jUxffp0YWZmJr7++mud44cPHy4UCoX45ptvxMGDB8XNmzfFjh07xMcff5zrbDKVSiUqVqwoGjduLPbv3y+uX78u1q1bJw4ePCiEECIiIkLIZDKxdOlSceXKFTFu3Dhha2ubbdZYTrOPhBBi9OjRokqVKsLExET8+++/2e4rWbKkCAsLE9euXRMnTpwQP//8swgLC8v1ddu0aZNwdnYWmZmZ2m1Dhw4VHh4e4sCBA+LChQvi008/Fba2tjqvb04x3r17Vzg5OYmPP/5YHD16VFy7dk1ERESIXr16iczMTKFWq0XJkiVF9+7dxdWrV8XOnTtF3bp1BQDxxx9/5Brj21q1apUwMzMTYWFh4sKFC6J///7C3t5exMTEaPfp0aOHGDFihPb24cOHxfr168X169fFvn37RIsWLUS5cuVeOVswt/etbNmyYtmyZTkeI8WsMaNOhPZdefDW5zt06JDw8vISAIRMJhOjR48W6enp+RApEUmtuCVCQggREhIinJycRFJSknbbn3/+KRo3biysrKyEubm5qF27tli8eHGO5129erVo0qSJsLGxEVZWVsLHx0dMmjTplR+IN2/eFJ06dRK2trbC0tJS1KlTRxw58nz5knHjxgkXFxdhZ2cnhg4dKgYPHpznROjChQsCgChbtmy25QU0Go2YNWuWqFSpklAqlcLJyUn4+/uLvXv35hprRkaGcHNzExEREdptjx49Eu3btxfW1tbC2dlZjBkzRvTs2fO1iZAQQly5ckV07NhR2NvbCwsLC1G5cmXx1VdfaWPdvn278Pb2FmZmZsLHx0fs2bOnwBMhIYSYM2eOKFOmjDA1NRX16tXTLmfw4vMJCgrS3t6zZ482zpIlS4oePXqIu3fvvvIxcnpNDh48KOzt7XMtFkiRCMmEeMMOuCIqISEBdnZ28PhqDTYHt4Kvh/0bnSczMxNTpkzBpEmToFarUaZMGSxfvhxNmjTJ34CJSDJpaWmIiopCuXLlXtsASsXHvHnzsGnTJmzdKs0yCcVZ165d4evri1GjRuV4/6t+5rI+v+Pj42Fra5tvMRWNjr8C8jY9Qg8fPsTs2bOhVqvRrVs3zJ8/P9d1NIiIqOj47LPPEBcXh8TExGJ9mY3Clp6ejurVq2Po0KFSh6LDuBMh8zd/+q6urli8eDESExPRvXv3fIyKiIikZGJigtGjR0sdRrFjamqKMWPGSB1GNkY9a8xGj+nzcXFx6NatG/7880/ttqxZBERERFQ0GW0iZK6Uw9Qkb09/79698PHxwapVq/D555/nePVmIiIiKnqMNhHKy7BYeno6Ro4ciebNm+P27dvw8vLCxo0b2TRJZGSMbE4JkWSk+Fkz2h6h1w2LXb58GYGBgThx4gQAoE+fPpg9e3aOS6UTUfGUtThfSkrKa1dIJqK3l7Wi9osLMBY0JkI5uH37NmrVqoWUlBQ4ODggNDT0ja/PQ0RFl0KhgL29PR48eAAAsLS0hEwmkzgqouJJo9Hg4cOHsLS0hIlJ4aUnRpwI5Z5tenh4oHv37rh27RqWLl2K0qVLF2JkRGRIsq6/lJUMEVHBkcvlKFOmTKH+wWHEiZBuRWj79u2oWrWq9vosP//8M5RKJeRyo22jIiI8vciqq6srnJ2dc7wYKBHlH1NT00L/3DWIRGjevHmYNm0aYmJi4Ovrizlz5qBevXq57r927VqMHTsWN2/eRIUKFfDDDz+gTZs2ej1m1pXn09LSMHLkSMyaNQt+fn7YunUr5HL5K69OTETGR6FQFGrfAhEVDsnLHatXr0ZwcDDGjx+PkydPwtfXF/7+/rmWoQ8ePIhu3bqhb9++OHXqFDp06IAOHTrg3Llzej2ujbkJzp07h3r16mHWrFkAgIoVK/IvPiIiIiMi+bXG6tevj7p162Lu3LkAnjZLeXh44IsvvsCIESOy7d+1a1ckJyfjr7/+0m773//+hxo1amDhwoWvfbysa5V89Nm32BI2CyqVCk5OTli8eDHatm2bf0+MiIiI8k1BXWtM0opQeno6Tpw4AT8/P+02uVwOPz8/HDp0KMdjDh06pLM/APj7++e6f242/PIDVCoV3n//fZw9e5ZJEBERkRGStEcoNjYWarUaLi4uOttdXFxw6dKlHI+JiYnJcf+YmJgc91epVFCpVNrb8fHxAACFiRIhUyajf//+kMlkSEhIeJunQkRERAUo63M6vweyDKJZuiCFhIRg4sSJ2barMzMwfPhwDB8+XIKoiIiI6E08evQIdnZ2+XY+SRMhR0dHKBQK3L9/X2f7/fv3tWt3vKxUqVJ67T9y5EgEBwdrb8fFxaFs2bK4detWvr6QpL+EhAR4eHjg9u3b+TreS2+G74fh4HthOPheGI74+HiUKVMGJUqUyNfzSpoImZqaonbt2ti5cyc6dOgA4Gmz9M6dOzF48OAcj2nQoAF27tyJr776Srtt+/btaNCgQY77m5mZ5TgV3s7Ojt/UBsLW1pbvhQHh+2E4+F4YDr4XhiO/1xmSfGgsODgYQUFBqFOnjnYqe3JyMnr37g0A6NmzJ9zd3RESEgIA+PLLL9G0aVNMnz4dH3zwAVatWoXjx4/j119/lfJpEBERUREkeSLUtWtXPHz4EOPGjUNMTAxq1KiBiIgIbUP0rVu3dLK/hg0bYuXKlRgzZgxGjRqFChUqYOPGjahWrZpUT4GIiIiKKMkTIQAYPHhwrkNhe/bsybatc+fO6Ny58xs9lpmZGcaPH8+Vow0A3wvDwvfDcPC9MBx8LwxHQb0Xki+oSERERCQVyS+xQURERCQVJkJERERktJgIERERkdFiIkRERERGq1gmQvPmzYOnpyfMzc1Rv359HD169JX7r127FpUrV4a5uTmqV6+Ov//+u5AiLf70eS9CQ0PRuHFjODg4wMHBAX5+fq9970g/+v5sZFm1ahVkMpl24VN6e/q+F3FxcRg0aBBcXV1hZmaGihUr8ndVPtH3vZg1axYqVaoECwsLeHh4YOjQoUhLSyukaIuvffv2oV27dnBzc4NMJsPGjRtfe8yePXtQq1YtmJmZ4Z133kFYWJj+DyyKmVWrVglTU1OxePFicf78edGvXz9hb28v7t+/n+P+Bw4cEAqFQvz444/iwoULYsyYMUKpVIqzZ88WcuTFj77vRUBAgJg3b544deqUuHjxoujVq5ews7MTd+7cKeTIiyd9348sUVFRwt3dXTRu3Fi0b9++cIIt5vR9L1QqlahTp45o06aN2L9/v4iKihJ79uwRkZGRhRx58aPvexEeHi7MzMxEeHi4iIqKElu3bhWurq5i6NChhRx58fP333+L0aNHiw0bNggA4o8//njl/jdu3BCWlpYiODhYXLhwQcyZM0coFAoRERGh1+MWu0SoXr16YtCgQdrbarVauLm5iZCQkBz379Kli/jggw90ttWvX1989tlnBRqnMdD3vXhZZmamsLGxEUuXLi2oEI3Km7wfmZmZomHDhmLRokUiKCiIiVA+0fe9WLBggShfvrxIT08vrBCNhr7vxaBBg0SLFi10tgUHB4tGjRoVaJzGJi+J0PDhw0XVqlV1tnXt2lX4+/vr9VjFamgsPT0dJ06cgJ+fn3abXC6Hn58fDh06lOMxhw4d0tkfAPz9/XPdn/LmTd6Ll6WkpCAjIyPfL7BnjN70/Zg0aRKcnZ3Rt2/fwgjTKLzJe7Fp0yY0aNAAgwYNgouLC6pVq4YpU6ZArVYXVtjF0pu8Fw0bNsSJEye0w2c3btzA33//jTZt2hRKzPRcfn1+G8TK0vklNjYWarVae3mOLC4uLrh06VKOx8TExOS4f0xMTIHFaQze5L142bfffgs3N7ds3+ikvzd5P/bv34/ffvsNkZGRhRCh8XiT9+LGjRvYtWsXAgMD8ffff+PatWsYOHAgMjIyMH78+MIIu1h6k/ciICAAsbGxePfddyGEQGZmJj7//HOMGjWqMEKmF+T2+Z2QkIDU1FRYWFjk6TzFqiJExcfUqVOxatUq/PHHHzA3N5c6HKOTmJiIHj16IDQ0FI6OjlKHY/Q0Gg2cnZ3x66+/onbt2ujatStGjx6NhQsXSh2a0dmzZw+mTJmC+fPn4+TJk9iwYQO2bNmC7777TurQ6A0Vq4qQo6MjFAoF7t+/r7P9/v37KFWqVI7HlCpVSq/9KW/e5L3I8tNPP2Hq1KnYsWMHfHx8CjJMo6Hv+3H9+nXcvHkT7dq1027TaDQAABMTE1y+fBleXl4FG3Qx9SY/G66urlAqlVAoFNpt3t7eiImJQXp6OkxNTQs05uLqTd6LsWPHokePHvj0008BANWrV0dycjL69++P0aNH61wknApWbp/ftra2ea4GAcWsImRqaoratWtj586d2m0ajQY7d+5EgwYNcjymQYMGOvsDwPbt23Pdn/LmTd4LAPjxxx/x3XffISIiAnXq1CmMUI2Cvu9H5cqVcfbsWURGRmq/PvzwQzRv3hyRkZHw8PAozPCLlTf52WjUqBGuXbumTUYB4MqVK3B1dWUS9Bbe5L1ISUnJluxkJaiCl+4sVPn2+a1fH7fhW7VqlTAzMxNhYWHiwoULon///sLe3l7ExMQIIYTo0aOHGDFihHb/AwcOCBMTE/HTTz+JixcvivHjx3P6fD7R972YOnWqMDU1FevWrRPR0dHar8TERKmeQrGi7/vxMs4ayz/6vhe3bt0SNjY2YvDgweLy5cvir7/+Es7OzuL777+X6ikUG/q+F+PHjxc2Njbi999/Fzdu3BDbtm0TXl5eokuXLlI9hWIjMTFRnDp1Spw6dUoAEDNmzBCnTp0S//33nxBCiBEjRogePXpo98+aPv/NN9+Iixcvinnz5nH6fJY5c+aIMmXKCFNTU1GvXj1x+PBh7X1NmzYVQUFBOvuvWbNGVKxYUZiamoqqVauKLVu2FHLExZc+70XZsmUFgGxf48ePL/zAiyl9fzZexEQof+n7Xhw8eFDUr19fmJmZifLly4vJkyeLzMzMQo66eNLnvcjIyBATJkwQXl5ewtzcXHh4eIiBAweKJ0+eFH7gxczu3btz/AzIev2DgoJE06ZNsx1To0YNYWpqKsqXLy+WLFmi9+PKhGAtj4iIiIxTseoRIiIiItIHEyEiIiIyWkyEiIiIyGgxESIiIiKjxUSIiIiIjBYTISIiIjJaTISIiIjIaDERIiIdYWFhsLe3lzqMNyaTybBx48ZX7tOrVy906NChUOIhIsPGRIioGOrVqxdkMlm2r2vXrkkdGsLCwrTxyOVylC5dGr1798aDBw/y5fzR0dF4//33AQA3b96ETCZDZGSkzj6zZ89GWFhYvjxebiZMmKB9ngqFAh4eHujfvz8eP36s13mYtBEVrGJ19Xkieu69997DkiVLdLY5OTlJFI0uW1tbXL58GRqNBqdPn0bv3r1x7949bN269a3PndtVw19kZ2f31o+TF1WrVsWOHTugVqtx8eJF9OnTB/Hx8Vi9enWhPD4RvR4rQkTFlJmZGUqVKqXzpVAoMGPGDFSvXh1WVlbw8PDAwIEDkZSUlOt5Tp8+jebNm8PGxga2traoXbs2jh8/rr1///79aNy4MSwsLODh4YEhQ4YgOTn5lbHJZDKUKlUKbm5ueP/99zFkyBDs2LEDqamp0Gg0mDRpEkqXLg0zMzPUqFEDERER2mPT09MxePBguLq6wtzcHGXLlkVISIjOubOGxsqVKwcAqFmzJmQyGZo1awZAt8ry66+/ws3NTefK7gDQvn179OnTR3v7zz//RK1atWBubo7y5ctj4sSJyMzMfOXzNDExQalSpeDu7g4/Pz907twZ27dv196vVqvRt29flCtXDhYWFqhUqRJmz56tvX/ChAlYunQp/vzzT211ac+ePQCA27dvo0uXLrC3t0eJEiXQvn173Lx585XxEFF2TISIjIxcLsfPP/+M8+fPY+nSpdi1axeGDx+e6/6BgYEoXbo0jh07hhMnTmDEiBFQKpUAgOvXr+O9995Dp06dcObMGaxevRr79+/H4MGD9YrJwsICGo0GmZmZmD17NqZPn46ffvoJZ86cgb+/Pz788ENcvXoVAPDzzz9j06ZNWLNmDS5fvozw8HB4enrmeN6jR48CAHbs2IHo6Ghs2LAh2z6dO3fGo0ePsHv3bu22x48fIyIiAoGBgQCAf//9Fz179sSXX36JCxcu4JdffkFYWBgmT56c5+d48+ZNbN26FaamptptGo0GpUuXxtq1a3HhwgWMGzcOo0aNwpo1awAAw4YNQ5cuXfDee+8hOjoa0dHRaNiwITIyMuDv7w8bGxv8+++/OHDgAKytrfHee+8hPT09zzEREVAsrz5PZOyCgoKEQqEQVlZW2q+PP/44x33Xrl0rSpYsqb29ZMkSYWdnp71tY2MjwsLCcjy2b9++on///jrb/v33XyGXy0VqamqOx7x8/itXroiKFSuKOnXqCCGEcHNzE5MnT9Y5pm7dumLgwIFCCCG++OIL0aJFC6HRaHI8PwDxxx9/CCGEiIqKEgDEqVOndPYJCgoS7du3195u37696NOnj/b2L7/8Itzc3IRarRZCCNGyZUsxZcoUnXMsX75cuLq65hiDEEKMHz9eyOVyYWVlJczNzbVX0p4xY0auxwghxKBBg0SnTp1yjTXrsStVqqTzGqhUKmFhYSG2bt36yvMTkS72CBEVU82bN8eCBQu0t62srAA8rY6EhITg0qVLSEhIQGZmJtLS0pCSkgJLS8ts5wkODsann36K5cuXa4d3vLy8ADwdNjtz5gzCw8O1+wshoNFoEBUVBW9v7xxji4+Ph7W1NTQaDdLS0vDuu+9i0aJFSEhIwL1799CoUSOd/Rs1aoTTp08DeDqs1apVK1SqVAnvvfce2rZti9atW7/VaxUYGIh+/fph/vz5MDMzQ3h4OD755BPI5XLt8zxw4IBOBUitVr/ydQOASpUqYdOmTUhLS8OKFSsQGRmJL774QmefefPmYfHixbh16xZSU1ORnp6OGjVqvDLe06dP49q1a7CxsdHZnpaWhuvXr7/BK0BkvJgIERVTVlZWeOedd3S23bx5E23btsWAAQMwefJklChRAvv370ffvn2Rnp6e4wf6hAkTEBAQgC1btuCff/7B+PHjsWrVKnTs2BFJSUn47LPPMGTIkGzHlSlTJtfYbGxscPLkScjlcri6usLCwgIAkJCQ8NrnVatWLURFReGff/7Bjh070KVLF/j5+WHdunWvPTY37dq1gxACW7ZsQd26dfHvv/9i5syZ2vuTkpIwceJEfPTRR9mONTc3z/W8pqam2vdg6tSp+OCDDzBx4kR89913AIBVq1Zh2LBhmD59Oho0aAAbGxtMmzYNR44ceWW8SUlJqF27tk4CmsVQGuKJigomQkRG5MSJE9BoNJg+fbq22pHVj/IqFStWRMWKFTF06FB069YNS5YsQceOHVGrVi1cuHAhW8L1OnK5PMdjbG1t4ebmhgMHDqBp06ba7QcOHEC9evV09uvatSu6du2Kjz/+GO+99x4eP36MEiVK6Jwvqx9HrVa/Mh5zc3N89NFHCA8Px7Vr11CpUiXUqlVLe3+tWrVw+fJlvZ/ny8aMGYMWLVpgwIAB2ufZsGFDDBw4ULvPyxUdU1PTbPHXqlULq1evhrOzM2xtbd8qJiJjx2ZpIiPyzjvvICMjA3PmzMGNGzewfPlyLFy4MNf9U1NTMXjwYOzZswf//fcfDhw4gGPHjmmHvL799lscPHgQgwcPRmRkJK5evYo///xT72bpF33zzTf44YcfsHr1aly+fBkjRoxAZGQkvvzySwDAjBkz8Pvvv+PSpUu4cuUK1q5di1KlSuW4CKSzszMsLCwQERGB+/fvIz4+PtfHDQwMxJYtW7B48WJtk3SWcePGYdmyZZg4cSLOnz+PixcvYtWqVRgzZoxez61Bgwbw8fHBlClTAAAVKlTA8ePHsXXrVly5cgVjx47FsWPHdI7x9PTEmTNncPnyZcTGxiIjIwOBgYFwdHRE+/bt8e+//yIqKgp79uzBkCFDcOfOHb1iIjJ6UjcpEVH+y6nBNsuMGTOEq6ursLCwEP7+/mLZsmUCgHjy5IkQQreZWaVSiU8++UR4eHgIU1NT4ebmJgYPHqzTCH306FHRqlUrYW1tLaysrISPj0+2ZucXvdws/TK1Wi0mTJgg3N3dhVKpFL6+vuKff/7R3v/rr7+KGjVqCCsrK2FraytatmwpTp48qb0fLzRLCyFEaGio8PDwEHK5XDRt2jTX10etVgtXV1cBQFy/fj1bXBEREaJhw4bCwsJC2Nrainr16olff/011+cxfvx44evrm23777//LszMzMStW7dEWlqa6NWrl7CzsxP29vZiwIABYsSIETrHPXjwQPv6AhC7d+8WQggRHR0tevbsKRwdHYWZmZkoX7686Nevn4iPj881JiLKTiaEENKmYkRERETS4NAYERERGS0mQkRERGS0mAgRERGR0WIiREREREaLiRAREREZLSZCREREZLSYCBEREZHRYiJERERERouJEBERERktJkJERERktJgIERERkdFiIkRERERG6//8xRx4Gn1VJwAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plot ROC curve\n", + "fpr, tpr, _ = roc_curve(y_test, probs )\n", + "plt.figure()\n", + "plt.plot(fpr, tpr, label=f'ROC curve (area = {roc_auc:.2f})')\n", + "plt.plot([0, 1], [0, 1], 'k--')\n", + "plt.xlim([0.0, 1.0])\n", + "plt.ylim([0.0, 1.05])\n", + "plt.xlabel('False Positive Rate')\n", + "plt.ylabel('True Positive Rate')\n", + "plt.title('Receiver Operating Characteristic')\n", + "plt.legend(loc=\"lower right\")\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "68206bb3-19e3-435a-a311-e82035c1d57a", + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/wip/KNN_adjusted.ipynb b/notebooks/wip/KNN_adjusted.ipynb new file mode 100644 index 0000000..d8bc894 --- /dev/null +++ b/notebooks/wip/KNN_adjusted.ipynb @@ -0,0 +1,2308 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "id": "e46934d2-da89-44cb-a2e2-0491b10c1350", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "from sklearn.model_selection import train_test_split, GridSearchCV\n", + "from sklearn.preprocessing import StandardScaler\n", + "from sklearn.neighbors import KNeighborsClassifier\n", + "# from sklearn.metrics import confusion_matrix, roc_curve, roc_auc_score, RocCurveDisplay\n", + "from sklearn.metrics import confusion_matrix, recall_score, precision_score, roc_auc_score, roc_curve, accuracy_score, RocCurveDisplay\n", + "\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "a320a6f1-c80e-4e53-959d-ddf3488f9302", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EnrollAgeIncomeHours
01261800014
1043130009
21554200016
315510000013
40551300012
\n", + "
" + ], + "text/plain": [ + " Enroll Age Income Hours\n", + "0 1 26 18000 14\n", + "1 0 43 13000 9\n", + "2 1 55 42000 16\n", + "3 1 55 100000 13\n", + "4 0 55 13000 12" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load the data\n", + "gymEnrollAgeIncomeHoursDf = pd.read_excel(\"gym.xlsx\")\n", + "gymEnrollAgeIncomeHoursDf.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "5c204cb7-ccaa-4f83-8d44-92adc224e876", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EnrollAgeIncomeHours
count1000.0000001000.0000001000.0000001000.000000
mean0.40300044.58200068340.00000010.182000
std0.49074613.87673744466.9282474.671263
min0.00000021.0000001000.0000002.000000
25%0.00000032.00000031000.0000006.000000
50%0.00000045.00000064000.00000010.000000
75%1.00000057.00000097000.00000014.000000
max1.00000068.000000198000.00000018.000000
\n", + "
" + ], + "text/plain": [ + " Enroll Age Income Hours\n", + "count 1000.000000 1000.000000 1000.000000 1000.000000\n", + "mean 0.403000 44.582000 68340.000000 10.182000\n", + "std 0.490746 13.876737 44466.928247 4.671263\n", + "min 0.000000 21.000000 1000.000000 2.000000\n", + "25% 0.000000 32.000000 31000.000000 6.000000\n", + "50% 0.000000 45.000000 64000.000000 10.000000\n", + "75% 1.000000 57.000000 97000.000000 14.000000\n", + "max 1.000000 68.000000 198000.000000 18.000000" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gymEnrollAgeIncomeHoursDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "92b6d925-f586-45a6-b89a-3b74204f0b94", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "70586f38-33be-49c7-93c0-867a24de8aa9", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EnrollAgeIncomeHoursscalerAgescalerIncomescalerHoursEnrollCategories
01261800014-1.339746-1.1326440.8177471
1043130009-0.114061-1.245143-0.2531630
215542000160.751128-0.5926471.2461111
3155100000130.7511280.7123460.6035651
405513000120.751128-1.2451430.3893830
...........................
995039500013-0.402457-1.4251420.6035650
99603850003-0.474556-1.425142-1.5382550
99715570000170.7511280.0373501.4602931
99816864000151.688417-0.0976491.0319291
99904867000180.246435-0.0301501.6744750
\n", + "

1000 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " Enroll Age Income Hours scalerAge scalerIncome scalerHours \\\n", + "0 1 26 18000 14 -1.339746 -1.132644 0.817747 \n", + "1 0 43 13000 9 -0.114061 -1.245143 -0.253163 \n", + "2 1 55 42000 16 0.751128 -0.592647 1.246111 \n", + "3 1 55 100000 13 0.751128 0.712346 0.603565 \n", + "4 0 55 13000 12 0.751128 -1.245143 0.389383 \n", + ".. ... ... ... ... ... ... ... \n", + "995 0 39 5000 13 -0.402457 -1.425142 0.603565 \n", + "996 0 38 5000 3 -0.474556 -1.425142 -1.538255 \n", + "997 1 55 70000 17 0.751128 0.037350 1.460293 \n", + "998 1 68 64000 15 1.688417 -0.097649 1.031929 \n", + "999 0 48 67000 18 0.246435 -0.030150 1.674475 \n", + "\n", + " EnrollCategories \n", + "0 1 \n", + "1 0 \n", + "2 1 \n", + "3 1 \n", + "4 0 \n", + ".. ... \n", + "995 0 \n", + "996 0 \n", + "997 1 \n", + "998 1 \n", + "999 0 \n", + "\n", + "[1000 rows x 8 columns]" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Scale the features\n", + "scalerAge = StandardScaler()\n", + "gymEnrollAgeIncomeHoursDf['scalerAge'] = scalerAge.fit_transform(gymEnrollAgeIncomeHoursDf[[\"Age\"]])\n", + "scalerIncome = StandardScaler()\n", + "gymEnrollAgeIncomeHoursDf['scalerIncome'] = scalerAge.fit_transform(gymEnrollAgeIncomeHoursDf[[\"Income\"]])\n", + "scalerHours = StandardScaler()\n", + "gymEnrollAgeIncomeHoursDf['scalerHours'] = scalerAge.fit_transform(gymEnrollAgeIncomeHoursDf[[\"Hours\"]])\n", + "gymEnrollAgeIncomeHoursDf['EnrollCategories'] = gymEnrollAgeIncomeHoursDf['Enroll'].astype('category')\n", + "gymEnrollAgeIncomeHoursDf" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "dcbdbd6a-0569-454d-8f26-4cf7e5c7032d", + "metadata": {}, + "outputs": [], + "source": [ + "# testTransformer = pd.DataFrame([[26], [43], [55]], columns=['Age'])\n", + "# scalerAge.transform(tt)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "c3add96b-f801-4b29-87d8-77dc8057c721", + "metadata": {}, + "outputs": [], + "source": [ + "indAtts = [\"scalerAge\", \"scalerIncome\", \"scalerHours\"]\n", + "depAtt = \"EnrollCategories\"" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "2285e5a5-0a99-4589-b965-3267a543de5e", + "metadata": {}, + "outputs": [], + "source": [ + "# Split the data into training and testing sets\n", + "(gymEnrollAgeIncomeHoursDfX_train,\n", + "gymEnrollAgeIncomeHoursDfX_test,\n", + "gymEnrollAgeIncomeHoursDfy_train,\n", + "gymEnrollAgeIncomeHoursDfy_test) = train_test_split(\n", + " gymEnrollAgeIncomeHoursDf[indAtts],\n", + " gymEnrollAgeIncomeHoursDf[depAtt],\n", + " test_size=0.4,\n", + " random_state=1,\n", + " stratify=gymEnrollAgeIncomeHoursDf[depAtt]\n", + ")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "550ac433-5d99-46de-9620-7ef93e79fcbe", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
scalerAgescalerIncomescalerHours
8080.0301370.8248451.674475
393-0.618755-0.9751450.175201
416-0.979250-1.4251420.817747
4860.679029-1.0651440.817747
422-0.114061-1.267643-1.324073
\n", + "
" + ], + "text/plain": [ + " scalerAge scalerIncome scalerHours\n", + "808 0.030137 0.824845 1.674475\n", + "393 -0.618755 -0.975145 0.175201\n", + "416 -0.979250 -1.425142 0.817747\n", + "486 0.679029 -1.065144 0.817747\n", + "422 -0.114061 -1.267643 -1.324073" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gymEnrollAgeIncomeHoursDfX_train.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "5799c2d6-26f6-483a-9632-42ae9ca6cf05", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
GridSearchCV(cv=5, estimator=CustomKNNClassifier(),\n",
+       "             param_grid={'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]})
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" + ], + "text/plain": [ + "GridSearchCV(cv=5, estimator=CustomKNNClassifier(),\n", + " param_grid={'n_neighbors': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]})" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Perform k-NN classification with cross-validation to find the best k\n", + "class CustomKNNClassifier(KNeighborsClassifier):\n", + " def prob(self, X):\n", + " return self.predict_proba(X)[:, 1]\n", + "# gymEnrollAgeIncomeHoursDfKnn = KNeighborsClassifier()\n", + "gymEnrollAgeIncomeHoursDfKnn = CustomKNNClassifier()\n", + "param_grid = {'n_neighbors': list(range(1, 11))}\n", + "grid_search = GridSearchCV(gymEnrollAgeIncomeHoursDfKnn, param_grid, cv=5)\n", + "grid_search.fit(gymEnrollAgeIncomeHoursDfX_train, gymEnrollAgeIncomeHoursDfy_train)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "d89ab3d4-4fe5-482c-b447-3334a69b28e2", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "bestParameters: {'n_neighbors': 5}\n", + "bestCrossValidationScore: 0.915\n" + ] + } + ], + "source": [ + "bestParameters = grid_search.best_params_\n", + "bestCrossValidationScore = grid_search.best_score_\n", + "print(\"bestParameters:\", bestParameters)\n", + "print(\"bestCrossValidationScore:\", bestCrossValidationScore)" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "18fee4f2-df43-4d0f-a1be-1b0b2458f30a", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
mean_fit_timestd_fit_timemean_score_timestd_score_timeparam_n_neighborsparamssplit0_test_scoresplit1_test_scoresplit2_test_scoresplit3_test_scoresplit4_test_scoremean_test_scorestd_test_scorerank_test_score
00.0015100.0009310.0040200.0006581{'n_neighbors': 1}0.8666670.9083330.8666670.9000000.9166670.8916670.0210829
10.0007380.0001210.0026980.0002602{'n_neighbors': 2}0.8333330.8583330.8833330.8666670.8666670.8616670.01633010
20.0007060.0000820.0026010.0001063{'n_neighbors': 3}0.9083330.9166670.8833330.9333330.9000000.9083330.0166672
30.0006200.0000740.0023590.0001024{'n_neighbors': 4}0.8500000.9250000.8583330.9333330.9000000.8933330.0339128
40.0005380.0000120.0021570.0000355{'n_neighbors': 5}0.8750000.9416670.8833330.9500000.9250000.9150000.0304591
50.0005110.0000160.0020730.0000356{'n_neighbors': 6}0.8666670.9416670.8583330.9333330.9166670.9033330.0344005
60.0004780.0000060.0020260.0000367{'n_neighbors': 7}0.8750000.9333330.8583330.9416670.9166670.9050000.0327454
70.0004760.0000170.0019790.0000158{'n_neighbors': 8}0.8666670.9333330.8583330.9333330.9083330.9000000.0320597
80.0004720.0000110.0019900.0000179{'n_neighbors': 9}0.8666670.9250000.8833330.9416670.9166670.9066670.0275883
90.0004690.0000080.0020080.00003110{'n_neighbors': 10}0.8416670.9416670.8666670.9416670.9166670.9016670.0406206
\n", + "
" + ], + "text/plain": [ + " mean_fit_time std_fit_time mean_score_time std_score_time \\\n", + "0 0.001510 0.000931 0.004020 0.000658 \n", + "1 0.000738 0.000121 0.002698 0.000260 \n", + "2 0.000706 0.000082 0.002601 0.000106 \n", + "3 0.000620 0.000074 0.002359 0.000102 \n", + "4 0.000538 0.000012 0.002157 0.000035 \n", + "5 0.000511 0.000016 0.002073 0.000035 \n", + "6 0.000478 0.000006 0.002026 0.000036 \n", + "7 0.000476 0.000017 0.001979 0.000015 \n", + "8 0.000472 0.000011 0.001990 0.000017 \n", + "9 0.000469 0.000008 0.002008 0.000031 \n", + "\n", + " param_n_neighbors params split0_test_score \\\n", + "0 1 {'n_neighbors': 1} 0.866667 \n", + "1 2 {'n_neighbors': 2} 0.833333 \n", + "2 3 {'n_neighbors': 3} 0.908333 \n", + "3 4 {'n_neighbors': 4} 0.850000 \n", + "4 5 {'n_neighbors': 5} 0.875000 \n", + "5 6 {'n_neighbors': 6} 0.866667 \n", + "6 7 {'n_neighbors': 7} 0.875000 \n", + "7 8 {'n_neighbors': 8} 0.866667 \n", + "8 9 {'n_neighbors': 9} 0.866667 \n", + "9 10 {'n_neighbors': 10} 0.841667 \n", + "\n", + " split1_test_score split2_test_score split3_test_score split4_test_score \\\n", + "0 0.908333 0.866667 0.900000 0.916667 \n", + "1 0.858333 0.883333 0.866667 0.866667 \n", + "2 0.916667 0.883333 0.933333 0.900000 \n", + "3 0.925000 0.858333 0.933333 0.900000 \n", + "4 0.941667 0.883333 0.950000 0.925000 \n", + "5 0.941667 0.858333 0.933333 0.916667 \n", + "6 0.933333 0.858333 0.941667 0.916667 \n", + "7 0.933333 0.858333 0.933333 0.908333 \n", + "8 0.925000 0.883333 0.941667 0.916667 \n", + "9 0.941667 0.866667 0.941667 0.916667 \n", + "\n", + " mean_test_score std_test_score rank_test_score \n", + "0 0.891667 0.021082 9 \n", + "1 0.861667 0.016330 10 \n", + "2 0.908333 0.016667 2 \n", + "3 0.893333 0.033912 8 \n", + "4 0.915000 0.030459 1 \n", + "5 0.903333 0.034400 5 \n", + "6 0.905000 0.032745 4 \n", + "7 0.900000 0.032059 7 \n", + "8 0.906667 0.027588 3 \n", + "9 0.901667 0.040620 6 " + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Display detailed results\n", + "cv_results = pd.DataFrame(grid_search.cv_results_)\n", + "cv_results" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "90b63369-b0c5-43ff-a93f-6742af667a8f", + "metadata": {}, + "outputs": [], + "source": [ + "gymEnrollAgeIncomeHoursDfKnnFit = grid_search.best_estimator_" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "id": "c230dab1-b0ef-4dde-b3f8-00db325ef856", + "metadata": {}, + "outputs": [], + "source": [ + "# from copy import deepcopy" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "933f59a6-19ca-4d42-81ef-0b7f31c59c59", + "metadata": {}, + "outputs": [], + "source": [ + "# gymEnrollAgeIncomeHoursDfKnnFit.predictHalfCutOff = deepcopy( gymEnrollAgeIncomeHoursDfKnnFit.predict)\n", + "gymEnrollAgeIncomeHoursDfKnnFit.predictHalfCutOff = gymEnrollAgeIncomeHoursDfKnnFit.predict" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "55875572-b648-486a-9941-5ea39fa37274", + "metadata": {}, + "outputs": [], + "source": [ + " gymEnrollAgeIncomeHoursDfKnnFit.predict = gymEnrollAgeIncomeHoursDfKnnFit.prob" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "392ddc06-c0fb-4ac7-b327-89fb9a44cda0", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
scalerAgescalerIncomescalerHours
4891.1116241.0498440.389383
241-0.041962-0.7051460.175201
119-0.186160-0.705146-0.681527
577-1.267647-0.052650-1.109891
2870.246435-0.8851451.674475
............
8040.1743361.387342-0.895709
9741.4000201.139844-1.752437
8100.8953270.5773471.246111
3950.1743360.1723491.246111
8610.246435-0.0751500.603565
\n", + "

400 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " scalerAge scalerIncome scalerHours\n", + "489 1.111624 1.049844 0.389383\n", + "241 -0.041962 -0.705146 0.175201\n", + "119 -0.186160 -0.705146 -0.681527\n", + "577 -1.267647 -0.052650 -1.109891\n", + "287 0.246435 -0.885145 1.674475\n", + ".. ... ... ...\n", + "804 0.174336 1.387342 -0.895709\n", + "974 1.400020 1.139844 -1.752437\n", + "810 0.895327 0.577347 1.246111\n", + "395 0.174336 0.172349 1.246111\n", + "861 0.246435 -0.075150 0.603565\n", + "\n", + "[400 rows x 3 columns]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gymEnrollAgeIncomeHoursDfX_test" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "fd901e0c-b0cb-479d-a579-6e2fcd4bd9af", + "metadata": {}, + "outputs": [], + "source": [ + "predictionProb = gymEnrollAgeIncomeHoursDfKnnFit.predict(gymEnrollAgeIncomeHoursDfX_test)\n", + "predictHalfCutOff = gymEnrollAgeIncomeHoursDfKnnFit.predictHalfCutOff(gymEnrollAgeIncomeHoursDfX_test)\n", + "gymEnrollAgeIncomeHoursDfX_test['predictionProb'] = predictionProb\n", + "gymEnrollAgeIncomeHoursDfX_test['predictHalfCutOff'] = predictHalfCutOff" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "0983f992-c261-402f-8bb2-e120146e0ad8", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
scalerAgescalerIncomescalerHourspredictionProbpredictHalfCutOff
4891.1116241.0498440.3893831.01
241-0.041962-0.7051460.1752010.00
119-0.186160-0.705146-0.6815270.20
577-1.267647-0.052650-1.1098910.40
2870.246435-0.8851451.6744750.20
..................
8040.1743361.387342-0.8957090.61
9741.4000201.139844-1.7524371.01
8100.8953270.5773471.2461110.81
3950.1743360.1723491.2461110.20
8610.246435-0.0751500.6035650.20
\n", + "

400 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " scalerAge scalerIncome scalerHours predictionProb predictHalfCutOff\n", + "489 1.111624 1.049844 0.389383 1.0 1\n", + "241 -0.041962 -0.705146 0.175201 0.0 0\n", + "119 -0.186160 -0.705146 -0.681527 0.2 0\n", + "577 -1.267647 -0.052650 -1.109891 0.4 0\n", + "287 0.246435 -0.885145 1.674475 0.2 0\n", + ".. ... ... ... ... ...\n", + "804 0.174336 1.387342 -0.895709 0.6 1\n", + "974 1.400020 1.139844 -1.752437 1.0 1\n", + "810 0.895327 0.577347 1.246111 0.8 1\n", + "395 0.174336 0.172349 1.246111 0.2 0\n", + "861 0.246435 -0.075150 0.603565 0.2 0\n", + "\n", + "[400 rows x 5 columns]" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gymEnrollAgeIncomeHoursDfX_test" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "6adf11fd-106f-42dc-9ac0-fe7b4378fc3e", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Confusion Matrix as DataFrame:\n", + " Actual_0 Actual_1\n", + "Predicted_0 217 22\n", + "Predicted_1 17 144\n" + ] + } + ], + "source": [ + "# Confusion matrix\n", + "conf_matrix = confusion_matrix(gymEnrollAgeIncomeHoursDfy_test, gymEnrollAgeIncomeHoursDfX_test['predictHalfCutOff'])\n", + "\n", + "# Convert confusion matrix to DataFrame with predicted as rows and actual as columns\n", + "conf_matrix_df = pd.DataFrame(conf_matrix, index=['Predicted_0', 'Predicted_1'], columns=['Actual_0', 'Actual_1'])\n", + "print(\"Confusion Matrix as DataFrame:\")\n", + "print(conf_matrix_df)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "id": "0d372830-8fc0-48ae-b4d2-82208c3479e4", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 0.9025\n", + "Precision: 0.8674698795180723\n", + "Recall (Sensitivity): 0.8944099378881988\n", + "Specificity: 0.9079497907949791\n", + "F1 f1Score: 0.8807339449541285\n" + ] + } + ], + "source": [ + "# Calculate metrics\n", + "precision = precision_score(gymEnrollAgeIncomeHoursDfy_test, gymEnrollAgeIncomeHoursDfX_test['predictHalfCutOff'])\n", + "recall = recall_score(gymEnrollAgeIncomeHoursDfy_test, gymEnrollAgeIncomeHoursDfX_test['predictHalfCutOff'])\n", + "accuracy = accuracy_score(gymEnrollAgeIncomeHoursDfy_test, gymEnrollAgeIncomeHoursDfX_test['predictHalfCutOff'])\n", + "specificity = conf_matrix[0, 0] / (conf_matrix[0, 0] + conf_matrix[0, 1])\n", + "f1Score = 2 * (precision * recall) / (precision + recall)\n", + "\n", + "print(f\"Accuracy: {accuracy}\")\n", + "print(f\"Precision: {precision}\")\n", + "print(f\"Recall (Sensitivity): {recall}\")\n", + "print(f\"Specificity: {specificity}\")\n", + "print(f\"F1 f1Score: {f1Score}\")" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "id": "a2929726-c175-4fdf-bedd-6aae4b4b29e1", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "ROC AUC: 0.9423191870890616\n" + ] + } + ], + "source": [ + "roc_auc = roc_auc_score(gymEnrollAgeIncomeHoursDfy_test, gymEnrollAgeIncomeHoursDfX_test['predictionProb'])\n", + "print(\"ROC AUC:\", roc_auc)" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "3e864f0c-15ea-44d8-a047-47559c5f2ec3", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plot ROC curve\n", + "fpr, tpr, _ = roc_curve(gymEnrollAgeIncomeHoursDfy_test, gymEnrollAgeIncomeHoursDfX_test['predictionProb'] )\n", + "plt.figure()\n", + "plt.plot(fpr, tpr, label=f'ROC curve (area = {roc_auc:.2f})')\n", + "plt.plot([0, 1], [0, 1], 'k--')\n", + "plt.xlim([0.0, 1.0])\n", + "plt.ylim([0.0, 1.05])\n", + "plt.xlabel('False Positive Rate')\n", + "plt.ylabel('True Positive Rate')\n", + "plt.title('Receiver Operating Characteristic')\n", + "plt.legend(loc=\"lower right\")\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "id": "dd3d8160-083d-4748-bb46-576cf43486ae", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'accuracy': 0.9025,\n", + " 'recall': 0.8944099378881988,\n", + " 'precision': 0.8674698795180723,\n", + " 'sensitivity': 0.8944099378881988,\n", + " 'specificity': 0.9079497907949791,\n", + " 'f1Score': 0.8807339449541285,\n", + " 'roc_auc': 0.9423191870890616,\n", + " 'cvK': 5,\n", + " 'bestParameters': {'n_neighbors': 5},\n", + " 'bestCrossValidationScore': 0.915}" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics = {}\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['accuracy'] = accuracy\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['recall'] = recall\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['precision'] = precision\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['sensitivity'] = recall\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['specificity'] = specificity\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['f1Score'] = f1Score\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['roc_auc'] = roc_auc\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['cvK'] = 5\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['bestParameters'] = bestParameters\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics['bestCrossValidationScore'] = bestCrossValidationScore\n", + "gymEnrollAgeIncomeHoursDfKnnFit.customMetrics" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "id": "ad7005e8-82d3-4ac4-beab-964f0c3992c7", + "metadata": {}, + "outputs": [], + "source": [ + "gymEnrollAgeIncomeHoursDfKnnFit.internaltransformers = [\n", + " {\n", + " \"origin\": \"Age\",\n", + " \"to\": \"scalerAge\",\n", + " \"transformerModel\": scalerAge,\n", + " \"methodToCall\": \"fit_transform\"\n", + " },\n", + " {\n", + " \"origin\": \"Income\",\n", + " \"to\": \"scalerIncome\",\n", + " \"transformerModel\": scalerIncome,\n", + " \"methodToCall\": \"fit_transform\"\n", + " },\n", + " {\n", + " \"origin\": \"Hours\",\n", + " \"to\": \"scalerHours\",\n", + " \"transformerModel\": scalerHours,\n", + " \"methodToCall\": \"fit_transform\"\n", + " },\n", + "]" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "id": "8e29e775-b422-4d03-a037-82d8b3795214", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
CustomKNNClassifier()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" + ], + "text/plain": [ + "CustomKNNClassifier()" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"gymEnrollAgeIncomeHoursDfKnnFit\",\n", + " \"model\": gymEnrollAgeIncomeHoursDfKnnFit,\n", + " \"description\": \"gymEnrollAgeIncomeHoursDf\",\n", + " \"modelType\": \"knn\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"Age\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Income\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Hours\",\n", + " \"type\": \"int\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Enroll_probibility\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/wip/Linear_Probability_and_logistic_Regression.ipynb b/notebooks/wip/Linear_Probability_and_logistic_Regression.ipynb new file mode 100644 index 0000000..61d67c3 --- /dev/null +++ b/notebooks/wip/Linear_Probability_and_logistic_Regression.ipynb @@ -0,0 +1,1785 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "id": "xwFyEsosINqT" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "pKewSQysItJ-" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "id": "Lz-DyAtNWsJR" + }, + "outputs": [], + "source": [ + "# Download Dataset from https://www.dropbox.com/scl/fi/32vgpt3jvtztu86avdnwg/Mortgage.xlsx?rlkey=qx1d46hzgn4h67zrcyajdyl3e&dl=1\n", + "# and add it to colab" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "id": "0zM8FGMJXJ70" + }, + "outputs": [], + "source": [ + "# mortgageDf = pd.read_excel(\"./Mortgage.xlsx\")\n", + "mortgageDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/32vgpt3jvtztu86avdnwg/Mortgage.xlsx?rlkey=qx1d46hzgn4h67zrcyajdyl3e&dl=1\")" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "t0LUca0Myqw5", + "outputId": "4d635fe3-6bb5-4417-f511-3bd87a662ae3" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2
0116.3549.94
1134.4356.16
2139.1936.89
3123.5856.88
4029.9227.05
5125.2644.38
6136.5148.98
7111.7055.55
8032.2131.28
9128.7435.63
10118.2839.50
11010.1231.39
12010.3929.47
13021.4629.34
14133.5640.37
15137.9122.92
16131.8147.56
17025.8844.58
18138.4047.85
19026.6225.50
20014.3621.87
21122.2220.79
22132.1051.56
23011.7532.96
24110.3248.59
25011.4334.78
26012.5833.27
27027.5325.63
28136.7137.05
29017.8526.86
\n", + "
" + ], + "text/plain": [ + " y x1 x2\n", + "0 1 16.35 49.94\n", + "1 1 34.43 56.16\n", + "2 1 39.19 36.89\n", + "3 1 23.58 56.88\n", + "4 0 29.92 27.05\n", + "5 1 25.26 44.38\n", + "6 1 36.51 48.98\n", + "7 1 11.70 55.55\n", + "8 0 32.21 31.28\n", + "9 1 28.74 35.63\n", + "10 1 18.28 39.50\n", + "11 0 10.12 31.39\n", + "12 0 10.39 29.47\n", + "13 0 21.46 29.34\n", + "14 1 33.56 40.37\n", + "15 1 37.91 22.92\n", + "16 1 31.81 47.56\n", + "17 0 25.88 44.58\n", + "18 1 38.40 47.85\n", + "19 0 26.62 25.50\n", + "20 0 14.36 21.87\n", + "21 1 22.22 20.79\n", + "22 1 32.10 51.56\n", + "23 0 11.75 32.96\n", + "24 1 10.32 48.59\n", + "25 0 11.43 34.78\n", + "26 0 12.58 33.27\n", + "27 0 27.53 25.63\n", + "28 1 36.71 37.05\n", + "29 0 17.85 26.86" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "id": "GQRNPIeyy6ub" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "90" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf.size" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": { + "id": "yumMybniy85d" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2
count30.00000030.00000030.000000
mean0.56666724.30566737.819333
std0.5040079.84284710.942216
min0.00000010.12000020.790000
25%0.00000014.85750029.372500
50%1.00000025.57000036.260000
75%1.00000032.18250047.777500
max1.00000039.19000056.880000
\n", + "
" + ], + "text/plain": [ + " y x1 x2\n", + "count 30.000000 30.000000 30.000000\n", + "mean 0.566667 24.305667 37.819333\n", + "std 0.504007 9.842847 10.942216\n", + "min 0.000000 10.120000 20.790000\n", + "25% 0.000000 14.857500 29.372500\n", + "50% 1.000000 25.570000 36.260000\n", + "75% 1.000000 32.182500 47.777500\n", + "max 1.000000 39.190000 56.880000" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "aspq6hoPy_xZ", + "outputId": "87b2268e-26fd-4432-e306-66e2d1a8492f" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(30, 3)" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": { + "id": "z_hVTvPrzYJr" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "id": "pIniVuaIzaaZ", + "outputId": "06201dcc-cc86-4530-e507-1b19f4ff689f" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "fig1 = plt.figure(\n", + " figsize=(8, 8)\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "VHdpDE7o42Pf", + "outputId": "5e6f4cb2-ac18-4aec-b0d2-7074dfb4db85" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plt.scatter(\n", + " mortgageDf[\"x1\"],\n", + " mortgageDf[\"y\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('x1')\n", + "plt.ylabel('y')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "ean6vMxkWfHF" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "knAa4W9R47rZ", + "outputId": "ca740df8-0e62-4012-8479-87ca155eb604" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plt.scatter(\n", + " mortgageDf[\"x2\"],\n", + " mortgageDf[\"y\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('x2')\n", + "plt.ylabel('y')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "alIhUPPUzvli", + "outputId": "b111f786-d897-4e69-f5c7-0f90f579f9f5" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y R-squared: 0.506\n", + "Model: OLS Adj. R-squared: 0.469\n", + "Method: Least Squares F-statistic: 13.82\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 7.37e-05\n", + "Time: 02:33:18 Log-Likelihood: -10.931\n", + "No. Observations: 30 AIC: 27.86\n", + "Df Residuals: 27 BIC: 32.07\n", + "Df Model: 2 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -0.8682 0.281 -3.089 0.005 -1.445 -0.291\n", + "x1 0.0188 0.007 2.694 0.012 0.004 0.033\n", + "x2 0.0258 0.006 4.107 0.000 0.013 0.039\n", + "==============================================================================\n", + "Omnibus: 1.526 Durbin-Watson: 2.217\n", + "Prob(Omnibus): 0.466 Jarque-Bera (JB): 0.712\n", + "Skew: 0.357 Prob(JB): 0.700\n", + "Kurtosis: 3.247 Cond. No. 194.\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "model1 = sm.OLS(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\", \"x2\"]])\n", + ")\n", + "model1Fit = model1.fit()\n", + "print(model1Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "S-AyfiLN0Due", + "outputId": "4759147c-0b56-48b4-9058-76ad422e55de" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1
0116.3549.940.729871
1134.4356.161.231162
2139.1936.890.823078
3123.5856.881.045349
4029.9227.050.394258
5125.2644.380.754114
6136.5148.981.084883
7111.7055.550.787177
8032.2131.280.546666
9128.7435.630.593656
10118.2839.500.496558
11010.1231.390.133337
12010.3929.470.088829
13021.4629.340.294027
14133.5640.370.806902
15137.9122.920.438106
16131.8147.560.959656
17025.8844.580.770960
18138.4047.851.091301
19026.6225.500.292049
20014.3621.87-0.032692
21122.2220.790.087491
22132.1051.561.068443
23011.7532.960.204600
24110.3248.590.581396
25011.4334.780.245584
26012.5833.270.228245
27027.5325.630.312551
28136.7137.050.780489
29017.8526.860.161955
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1\n", + "0 1 16.35 49.94 0.729871\n", + "1 1 34.43 56.16 1.231162\n", + "2 1 39.19 36.89 0.823078\n", + "3 1 23.58 56.88 1.045349\n", + "4 0 29.92 27.05 0.394258\n", + "5 1 25.26 44.38 0.754114\n", + "6 1 36.51 48.98 1.084883\n", + "7 1 11.70 55.55 0.787177\n", + "8 0 32.21 31.28 0.546666\n", + "9 1 28.74 35.63 0.593656\n", + "10 1 18.28 39.50 0.496558\n", + "11 0 10.12 31.39 0.133337\n", + "12 0 10.39 29.47 0.088829\n", + "13 0 21.46 29.34 0.294027\n", + "14 1 33.56 40.37 0.806902\n", + "15 1 37.91 22.92 0.438106\n", + "16 1 31.81 47.56 0.959656\n", + "17 0 25.88 44.58 0.770960\n", + "18 1 38.40 47.85 1.091301\n", + "19 0 26.62 25.50 0.292049\n", + "20 0 14.36 21.87 -0.032692\n", + "21 1 22.22 20.79 0.087491\n", + "22 1 32.10 51.56 1.068443\n", + "23 0 11.75 32.96 0.204600\n", + "24 1 10.32 48.59 0.581396\n", + "25 0 11.43 34.78 0.245584\n", + "26 0 12.58 33.27 0.228245\n", + "27 0 27.53 25.63 0.312551\n", + "28 1 36.71 37.05 0.780489\n", + "29 0 17.85 26.86 0.161955" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predict1 = model1Fit.predict(sm.add_constant(mortgageDf[[\"x1\", \"x2\"]]))\n", + "mortgageDf['predict1'] = predict1\n", + "mortgageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "9ouX-mzz4sl-", + "outputId": "4f669fe5-a841-4e26-e487-90d2480e94b8" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([0.28356899])" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model1Fit.predict([[1, 20, 30]])" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ujSQIAwa8DRG", + "outputId": "97600e44-d792-4b0d-d47b-05c561a3d9a9" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([-0.10389379])" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model1Fit.predict([[1, 20, 15]])" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "yQ8XuYfr8Fs6", + "outputId": "5d629786-b70c-4aa8-e5d3-b4dda6255567" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([1.17698081])" + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model1Fit.predict([[1, 40, 50]])" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "l_wGiUmL9Xta", + "outputId": "13825eaa-f1b2-4256-c42b-25cf40345311" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.363910\n", + " Iterations 7\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 30\n", + "Model: Logit Df Residuals: 27\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.4681\n", + "Time: 02:33:18 Log-Likelihood: -10.917\n", + "converged: True LL-Null: -20.527\n", + "Covariance Type: nonrobust LLR p-value: 6.708e-05\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -9.3671 3.196 -2.931 0.003 -15.631 -3.103\n", + "x1 0.1349 0.064 2.107 0.035 0.009 0.260\n", + "x2 0.1782 0.065 2.758 0.006 0.052 0.305\n", + "==============================================================================\n" + ] + } + ], + "source": [ + "logisticRegYFromX1AndX2Model = sm.Logit(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\", \"x2\"]])\n", + ")\n", + "logisticRegYFromX1AndX2ModelFit = logisticRegYFromX1AndX2Model.fit()\n", + "print(logisticRegYFromX1AndX2ModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"logisticRegYFromX1AndX2ModelFit\",\n", + " \"model\": logisticRegYFromX1AndX2ModelFit,\n", + " \"description\": \"Predict Logistic Regression Y based on x1,x2 for mortgageDf\",\n", + " \"modelType\": \"sm.Logit\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"x1\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"x2\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"y\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "hICJCcTx9gKy", + "outputId": "cfea633a-e79c-45ac-845f-636b78a3f38d" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1predict2
0116.3549.940.7298710.850564
1134.4356.161.2311620.994966
2139.1936.890.8230780.923739
3123.5856.881.0453490.981132
4029.9227.050.3942580.375201
5125.2644.380.7541140.875451
6136.5148.981.0848830.986447
7111.7055.550.7871770.892025
8032.2131.280.5466660.634794
9128.7435.630.5936560.702665
10118.2839.500.4965580.534624
11010.1231.390.1333370.082606
12010.3929.470.0888290.062198
13021.4629.340.2940270.223902
14133.5640.370.8069020.913332
15137.9122.920.4381060.458048
16131.8147.560.9596560.967716
17025.8844.580.7709600.887885
18138.4047.851.0913010.987144
19026.6225.500.2920490.225940
20014.3621.87-0.0326920.028410
21122.2220.790.0874910.065109
22132.1051.561.0684430.984517
23011.7532.960.2046000.129233
24110.3248.590.5813960.664852
25011.4334.780.2455840.164303
26012.5833.270.2282450.149244
27027.5325.630.3125510.252476
28136.7137.050.7804890.899188
29017.8526.860.1619550.102289
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1 predict2\n", + "0 1 16.35 49.94 0.729871 0.850564\n", + "1 1 34.43 56.16 1.231162 0.994966\n", + "2 1 39.19 36.89 0.823078 0.923739\n", + "3 1 23.58 56.88 1.045349 0.981132\n", + "4 0 29.92 27.05 0.394258 0.375201\n", + "5 1 25.26 44.38 0.754114 0.875451\n", + "6 1 36.51 48.98 1.084883 0.986447\n", + "7 1 11.70 55.55 0.787177 0.892025\n", + "8 0 32.21 31.28 0.546666 0.634794\n", + "9 1 28.74 35.63 0.593656 0.702665\n", + "10 1 18.28 39.50 0.496558 0.534624\n", + "11 0 10.12 31.39 0.133337 0.082606\n", + "12 0 10.39 29.47 0.088829 0.062198\n", + "13 0 21.46 29.34 0.294027 0.223902\n", + "14 1 33.56 40.37 0.806902 0.913332\n", + "15 1 37.91 22.92 0.438106 0.458048\n", + "16 1 31.81 47.56 0.959656 0.967716\n", + "17 0 25.88 44.58 0.770960 0.887885\n", + "18 1 38.40 47.85 1.091301 0.987144\n", + "19 0 26.62 25.50 0.292049 0.225940\n", + "20 0 14.36 21.87 -0.032692 0.028410\n", + "21 1 22.22 20.79 0.087491 0.065109\n", + "22 1 32.10 51.56 1.068443 0.984517\n", + "23 0 11.75 32.96 0.204600 0.129233\n", + "24 1 10.32 48.59 0.581396 0.664852\n", + "25 0 11.43 34.78 0.245584 0.164303\n", + "26 0 12.58 33.27 0.228245 0.149244\n", + "27 0 27.53 25.63 0.312551 0.252476\n", + "28 1 36.71 37.05 0.780489 0.899188\n", + "29 0 17.85 26.86 0.161955 0.102289" + ] + }, + "execution_count": 50, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predict2 = logisticRegYFromX1AndX2ModelFit.predict(sm.add_constant(mortgageDf[[\"x1\", \"x2\"]]))\n", + "mortgageDf['predict2'] = predict2\n", + "mortgageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "tBfMgF0Y9usy", + "outputId": "5d06c271-8f99-48b1-bdeb-a1a4539bf6c9" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(array([0.21042055]), array([0.01806123]), array([0.99289663]))" + ] + }, + "execution_count": 51, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "logisticRegYFromX1AndX2ModelFit.predict([[1, 20, 30]]), logisticRegYFromX1AndX2ModelFit.predict([[1, 20, 15]]), logisticRegYFromX1AndX2ModelFit.predict([[1, 40, 50]])" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "iLB_t1-lWjAn", + "outputId": "c70ee1d3-96ac-4f8e-c888-53b93d95097e" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y R-squared: 0.197\n", + "Model: OLS Adj. R-squared: 0.168\n", + "Method: Least Squares F-statistic: 6.875\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 0.0140\n", + "Time: 02:33:19 Log-Likelihood: -18.211\n", + "No. Observations: 30 AIC: 40.42\n", + "Df Residuals: 28 BIC: 43.23\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 0.0141 0.227 0.062 0.951 -0.451 0.479\n", + "x1 0.0227 0.009 2.622 0.014 0.005 0.040\n", + "==============================================================================\n", + "Omnibus: 5.223 Durbin-Watson: 2.358\n", + "Prob(Omnibus): 0.073 Jarque-Bera (JB): 1.806\n", + "Skew: -0.084 Prob(JB): 0.405\n", + "Kurtosis: 1.810 Cond. No. 70.8\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "model3 = sm.OLS(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\"]])\n", + ")\n", + "model3Fit = model3.fit()\n", + "print(model3Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "PuixWL0hWw1e", + "outputId": "59957621-cba1-4317-83a5-9fcc264f00b8" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.579907\n", + " Iterations 5\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 30\n", + "Model: Logit Df Residuals: 28\n", + "Method: MLE Df Model: 1\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.1525\n", + "Time: 02:33:19 Log-Likelihood: -17.397\n", + "converged: True LL-Null: -20.527\n", + "Covariance Type: nonrobust LLR p-value: 0.01235\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -2.2077 1.140 -1.936 0.053 -4.442 0.027\n", + "x1 0.1043 0.046 2.282 0.022 0.015 0.194\n", + "==============================================================================\n" + ] + } + ], + "source": [ + "model4 = sm.Logit(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\"]])\n", + ")\n", + "model4Fit = model4.fit()\n", + "print(model4Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "YLIrig6rXKhw", + "outputId": "7f663d14-7f38-4131-928e-1bf212b2dc32" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "min = 0\n", + "min" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "w5OmNUfaXNsk", + "outputId": "ba3a9d1f-76a0-40b7-fc25-322c48facf01" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(49.19, 30)" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "max = mortgageDf[\"x1\"].max() + 10\n", + "max, len(mortgageDf[\"x1\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": { + "id": "sBBshZgnXQzO" + }, + "outputs": [], + "source": [ + "x = np.linspace(min - 5, max + 5, 500)\n", + "# x" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": { + "id": "2zxAZeT5XwgE" + }, + "outputs": [], + "source": [ + "import math" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": { + "id": "X2BmYiiDXgbw" + }, + "outputs": [], + "source": [ + "lREq = 0.0141 + x * 0.0227\n", + "logREq = pow(math.e, (-2.2077 + 0.1043 * x))/ (1+ pow(math.e, (-2.2077 + 0.1043 * x)))" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "C_8MU1W7YgR8", + "outputId": "322b707d-cf36-4a26-fd69-60ca2664f9c3" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "500" + ] + }, + "execution_count": 59, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(lREq)" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "VZ6BxMqpXCOH", + "outputId": "196f43f9-0a5d-4747-d188-29cb66c80c9e" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "plt.scatter(\n", + " mortgageDf[\"x1\"],\n", + " mortgageDf[\"y\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.plot(\n", + " x,\n", + " lREq,\n", + " color='red',\n", + " alpha=0.9,\n", + " label='lREq',\n", + ")\n", + "\n", + "plt.plot(\n", + " x,\n", + " logREq,\n", + " color='green',\n", + " alpha=0.9,\n", + " label='logREq',\n", + ")\n", + "\n", + "plt.xlabel('x1')\n", + "plt.ylabel('y')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/wip/Linear_Probability_and_logistic_Regression_holdout.ipynb b/notebooks/wip/Linear_Probability_and_logistic_Regression_holdout.ipynb new file mode 100644 index 0000000..44be657 --- /dev/null +++ b/notebooks/wip/Linear_Probability_and_logistic_Regression_holdout.ipynb @@ -0,0 +1,3289 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 56, + "metadata": { + "id": "xwFyEsosINqT" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": { + "id": "pKewSQysItJ-" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": { + "id": "Lz-DyAtNWsJR" + }, + "outputs": [], + "source": [ + "# Download Dataset from https://www.dropbox.com/scl/fi/32vgpt3jvtztu86avdnwg/Mortgage.xlsx?rlkey=qx1d46hzgn4h67zrcyajdyl3e&dl=1\n", + "# and add it to colab" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": { + "id": "0zM8FGMJXJ70" + }, + "outputs": [], + "source": [ + "# mortgageDf = pd.read_excel(\"./Mortgage.xlsx\")\n", + "mortgageDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/32vgpt3jvtztu86avdnwg/Mortgage.xlsx?rlkey=qx1d46hzgn4h67zrcyajdyl3e&dl=1\")" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "t0LUca0Myqw5", + "outputId": "527eb991-fb2c-420a-e8fe-9b983e793560" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2
0116.3549.94
1134.4356.16
2139.1936.89
3123.5856.88
4029.9227.05
5125.2644.38
6136.5148.98
7111.7055.55
8032.2131.28
9128.7435.63
10118.2839.50
11010.1231.39
12010.3929.47
13021.4629.34
14133.5640.37
15137.9122.92
16131.8147.56
17025.8844.58
18138.4047.85
19026.6225.50
20014.3621.87
21122.2220.79
22132.1051.56
23011.7532.96
24110.3248.59
25011.4334.78
26012.5833.27
27027.5325.63
28136.7137.05
29017.8526.86
\n", + "
" + ], + "text/plain": [ + " y x1 x2\n", + "0 1 16.35 49.94\n", + "1 1 34.43 56.16\n", + "2 1 39.19 36.89\n", + "3 1 23.58 56.88\n", + "4 0 29.92 27.05\n", + "5 1 25.26 44.38\n", + "6 1 36.51 48.98\n", + "7 1 11.70 55.55\n", + "8 0 32.21 31.28\n", + "9 1 28.74 35.63\n", + "10 1 18.28 39.50\n", + "11 0 10.12 31.39\n", + "12 0 10.39 29.47\n", + "13 0 21.46 29.34\n", + "14 1 33.56 40.37\n", + "15 1 37.91 22.92\n", + "16 1 31.81 47.56\n", + "17 0 25.88 44.58\n", + "18 1 38.40 47.85\n", + "19 0 26.62 25.50\n", + "20 0 14.36 21.87\n", + "21 1 22.22 20.79\n", + "22 1 32.10 51.56\n", + "23 0 11.75 32.96\n", + "24 1 10.32 48.59\n", + "25 0 11.43 34.78\n", + "26 0 12.58 33.27\n", + "27 0 27.53 25.63\n", + "28 1 36.71 37.05\n", + "29 0 17.85 26.86" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "GQRNPIeyy6ub", + "outputId": "af3a1828-5bfb-4458-ee99-ecebf88ab76e" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "90" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf.size" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "yumMybniy85d", + "outputId": "e85c111d-108b-4a30-e3f1-cbcb8b515223" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2
count30.00000030.00000030.000000
mean0.56666724.30566737.819333
std0.5040079.84284710.942216
min0.00000010.12000020.790000
25%0.00000014.85750029.372500
50%1.00000025.57000036.260000
75%1.00000032.18250047.777500
max1.00000039.19000056.880000
\n", + "
" + ], + "text/plain": [ + " y x1 x2\n", + "count 30.000000 30.000000 30.000000\n", + "mean 0.566667 24.305667 37.819333\n", + "std 0.504007 9.842847 10.942216\n", + "min 0.000000 10.120000 20.790000\n", + "25% 0.000000 14.857500 29.372500\n", + "50% 1.000000 25.570000 36.260000\n", + "75% 1.000000 32.182500 47.777500\n", + "max 1.000000 39.190000 56.880000" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "aspq6hoPy_xZ", + "outputId": "6fa553af-188e-40f6-bf37-3a61224c5b0c" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(30, 3)" + ] + }, + "execution_count": 63, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": { + "id": "z_hVTvPrzYJr" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 34 + }, + "id": "pIniVuaIzaaZ", + "outputId": "34e78f06-e2c7-4701-c78f-5aae99a9deb0" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "fig1 = plt.figure(\n", + " figsize=(8, 8)\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "VHdpDE7o42Pf", + "outputId": "e2532b62-f91f-4497-e2da-540c54f34f2f" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plt.scatter(\n", + " mortgageDf[\"x1\"],\n", + " mortgageDf[\"y\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('x1')\n", + "plt.ylabel('y')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "ean6vMxkWfHF" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "knAa4W9R47rZ", + "outputId": "cb8121da-a185-417f-fa26-a0e9ad2b8faa" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plt.scatter(\n", + " mortgageDf[\"x2\"],\n", + " mortgageDf[\"y\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('x2')\n", + "plt.ylabel('y')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "alIhUPPUzvli", + "outputId": "8f9061b4-09dd-4525-f39e-797b603cfd53" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y R-squared: 0.506\n", + "Model: OLS Adj. R-squared: 0.469\n", + "Method: Least Squares F-statistic: 13.82\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 7.37e-05\n", + "Time: 15:09:54 Log-Likelihood: -10.931\n", + "No. Observations: 30 AIC: 27.86\n", + "Df Residuals: 27 BIC: 32.07\n", + "Df Model: 2 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -0.8682 0.281 -3.089 0.005 -1.445 -0.291\n", + "x1 0.0188 0.007 2.694 0.012 0.004 0.033\n", + "x2 0.0258 0.006 4.107 0.000 0.013 0.039\n", + "==============================================================================\n", + "Omnibus: 1.526 Durbin-Watson: 2.217\n", + "Prob(Omnibus): 0.466 Jarque-Bera (JB): 0.712\n", + "Skew: 0.357 Prob(JB): 0.700\n", + "Kurtosis: 3.247 Cond. No. 194.\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "model1 = sm.OLS(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\", \"x2\"]])\n", + ")\n", + "model1Fit = model1.fit()\n", + "print(model1Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "S-AyfiLN0Due", + "outputId": "827d6090-8431-46a4-fb36-c6e884539662" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1
0116.3549.940.729871
1134.4356.161.231162
2139.1936.890.823078
3123.5856.881.045349
4029.9227.050.394258
5125.2644.380.754114
6136.5148.981.084883
7111.7055.550.787177
8032.2131.280.546666
9128.7435.630.593656
10118.2839.500.496558
11010.1231.390.133337
12010.3929.470.088829
13021.4629.340.294027
14133.5640.370.806902
15137.9122.920.438106
16131.8147.560.959656
17025.8844.580.770960
18138.4047.851.091301
19026.6225.500.292049
20014.3621.87-0.032692
21122.2220.790.087491
22132.1051.561.068443
23011.7532.960.204600
24110.3248.590.581396
25011.4334.780.245584
26012.5833.270.228245
27027.5325.630.312551
28136.7137.050.780489
29017.8526.860.161955
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1\n", + "0 1 16.35 49.94 0.729871\n", + "1 1 34.43 56.16 1.231162\n", + "2 1 39.19 36.89 0.823078\n", + "3 1 23.58 56.88 1.045349\n", + "4 0 29.92 27.05 0.394258\n", + "5 1 25.26 44.38 0.754114\n", + "6 1 36.51 48.98 1.084883\n", + "7 1 11.70 55.55 0.787177\n", + "8 0 32.21 31.28 0.546666\n", + "9 1 28.74 35.63 0.593656\n", + "10 1 18.28 39.50 0.496558\n", + "11 0 10.12 31.39 0.133337\n", + "12 0 10.39 29.47 0.088829\n", + "13 0 21.46 29.34 0.294027\n", + "14 1 33.56 40.37 0.806902\n", + "15 1 37.91 22.92 0.438106\n", + "16 1 31.81 47.56 0.959656\n", + "17 0 25.88 44.58 0.770960\n", + "18 1 38.40 47.85 1.091301\n", + "19 0 26.62 25.50 0.292049\n", + "20 0 14.36 21.87 -0.032692\n", + "21 1 22.22 20.79 0.087491\n", + "22 1 32.10 51.56 1.068443\n", + "23 0 11.75 32.96 0.204600\n", + "24 1 10.32 48.59 0.581396\n", + "25 0 11.43 34.78 0.245584\n", + "26 0 12.58 33.27 0.228245\n", + "27 0 27.53 25.63 0.312551\n", + "28 1 36.71 37.05 0.780489\n", + "29 0 17.85 26.86 0.161955" + ] + }, + "execution_count": 69, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predict1 = model1Fit.predict(sm.add_constant(mortgageDf[[\"x1\", \"x2\"]]))\n", + "mortgageDf['predict1'] = predict1\n", + "mortgageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "9ouX-mzz4sl-", + "outputId": "6f95fccb-ab1c-4fef-a53f-d744ad00a45b" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([0.28356899])" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model1Fit.predict([[1, 20, 30]])" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ujSQIAwa8DRG", + "outputId": "ff3d1a58-32f5-4bef-cb57-97ab79bbdd53" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([-0.10389379])" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model1Fit.predict([[1, 20, 15]])" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "yQ8XuYfr8Fs6", + "outputId": "06169e06-16e7-44be-c599-ba17fceb48ca" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([1.17698081])" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model1Fit.predict([[1, 40, 50]])" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "l_wGiUmL9Xta", + "outputId": "9beb1054-bd82-4438-b3f7-d115d51a8b88" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.363910\n", + " Iterations 7\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 30\n", + "Model: Logit Df Residuals: 27\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.4681\n", + "Time: 15:09:54 Log-Likelihood: -10.917\n", + "converged: True LL-Null: -20.527\n", + "Covariance Type: nonrobust LLR p-value: 6.708e-05\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -9.3671 3.196 -2.931 0.003 -15.631 -3.103\n", + "x1 0.1349 0.064 2.107 0.035 0.009 0.260\n", + "x2 0.1782 0.065 2.758 0.006 0.052 0.305\n", + "==============================================================================\n" + ] + } + ], + "source": [ + "model2 = sm.Logit(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\", \"x2\"]])\n", + ")\n", + "model2Fit = model2.fit()\n", + "print(model2Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "hICJCcTx9gKy", + "outputId": "6d072132-6408-4df8-ac73-75bb7a7bd6b2" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1predict2
0116.3549.940.7298710.850564
1134.4356.161.2311620.994966
2139.1936.890.8230780.923739
3123.5856.881.0453490.981132
4029.9227.050.3942580.375201
5125.2644.380.7541140.875451
6136.5148.981.0848830.986447
7111.7055.550.7871770.892025
8032.2131.280.5466660.634794
9128.7435.630.5936560.702665
10118.2839.500.4965580.534624
11010.1231.390.1333370.082606
12010.3929.470.0888290.062198
13021.4629.340.2940270.223902
14133.5640.370.8069020.913332
15137.9122.920.4381060.458048
16131.8147.560.9596560.967716
17025.8844.580.7709600.887885
18138.4047.851.0913010.987144
19026.6225.500.2920490.225940
20014.3621.87-0.0326920.028410
21122.2220.790.0874910.065109
22132.1051.561.0684430.984517
23011.7532.960.2046000.129233
24110.3248.590.5813960.664852
25011.4334.780.2455840.164303
26012.5833.270.2282450.149244
27027.5325.630.3125510.252476
28136.7137.050.7804890.899188
29017.8526.860.1619550.102289
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1 predict2\n", + "0 1 16.35 49.94 0.729871 0.850564\n", + "1 1 34.43 56.16 1.231162 0.994966\n", + "2 1 39.19 36.89 0.823078 0.923739\n", + "3 1 23.58 56.88 1.045349 0.981132\n", + "4 0 29.92 27.05 0.394258 0.375201\n", + "5 1 25.26 44.38 0.754114 0.875451\n", + "6 1 36.51 48.98 1.084883 0.986447\n", + "7 1 11.70 55.55 0.787177 0.892025\n", + "8 0 32.21 31.28 0.546666 0.634794\n", + "9 1 28.74 35.63 0.593656 0.702665\n", + "10 1 18.28 39.50 0.496558 0.534624\n", + "11 0 10.12 31.39 0.133337 0.082606\n", + "12 0 10.39 29.47 0.088829 0.062198\n", + "13 0 21.46 29.34 0.294027 0.223902\n", + "14 1 33.56 40.37 0.806902 0.913332\n", + "15 1 37.91 22.92 0.438106 0.458048\n", + "16 1 31.81 47.56 0.959656 0.967716\n", + "17 0 25.88 44.58 0.770960 0.887885\n", + "18 1 38.40 47.85 1.091301 0.987144\n", + "19 0 26.62 25.50 0.292049 0.225940\n", + "20 0 14.36 21.87 -0.032692 0.028410\n", + "21 1 22.22 20.79 0.087491 0.065109\n", + "22 1 32.10 51.56 1.068443 0.984517\n", + "23 0 11.75 32.96 0.204600 0.129233\n", + "24 1 10.32 48.59 0.581396 0.664852\n", + "25 0 11.43 34.78 0.245584 0.164303\n", + "26 0 12.58 33.27 0.228245 0.149244\n", + "27 0 27.53 25.63 0.312551 0.252476\n", + "28 1 36.71 37.05 0.780489 0.899188\n", + "29 0 17.85 26.86 0.161955 0.102289" + ] + }, + "execution_count": 74, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predict2 = model2Fit.predict(sm.add_constant(mortgageDf[[\"x1\", \"x2\"]]))\n", + "mortgageDf['predict2'] = predict2\n", + "mortgageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 75, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "tBfMgF0Y9usy", + "outputId": "29db0b46-acbc-42c5-ab11-4490a2eecc47" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(array([0.21042055]), array([0.01806123]), array([0.99289663]))" + ] + }, + "execution_count": 75, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "model2Fit.predict([[1, 20, 30]]), model2Fit.predict([[1, 20, 15]]), model2Fit.predict([[1, 40, 50]])" + ] + }, + { + "cell_type": "code", + "execution_count": 76, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "iLB_t1-lWjAn", + "outputId": "77dc990d-db61-4e4a-e26e-0593cadeb631" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y R-squared: 0.197\n", + "Model: OLS Adj. R-squared: 0.168\n", + "Method: Least Squares F-statistic: 6.875\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 0.0140\n", + "Time: 15:09:54 Log-Likelihood: -18.211\n", + "No. Observations: 30 AIC: 40.42\n", + "Df Residuals: 28 BIC: 43.23\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 0.0141 0.227 0.062 0.951 -0.451 0.479\n", + "x1 0.0227 0.009 2.622 0.014 0.005 0.040\n", + "==============================================================================\n", + "Omnibus: 5.223 Durbin-Watson: 2.358\n", + "Prob(Omnibus): 0.073 Jarque-Bera (JB): 1.806\n", + "Skew: -0.084 Prob(JB): 0.405\n", + "Kurtosis: 1.810 Cond. No. 70.8\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + } + ], + "source": [ + "model3 = sm.OLS(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\"]])\n", + ")\n", + "model3Fit = model3.fit()\n", + "print(model3Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 77, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "PuixWL0hWw1e", + "outputId": "237434c6-c5eb-4ccd-a39e-d73fb6f1d215" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.579907\n", + " Iterations 5\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 30\n", + "Model: Logit Df Residuals: 28\n", + "Method: MLE Df Model: 1\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.1525\n", + "Time: 15:09:54 Log-Likelihood: -17.397\n", + "converged: True LL-Null: -20.527\n", + "Covariance Type: nonrobust LLR p-value: 0.01235\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -2.2077 1.140 -1.936 0.053 -4.442 0.027\n", + "x1 0.1043 0.046 2.282 0.022 0.015 0.194\n", + "==============================================================================\n" + ] + } + ], + "source": [ + "model4 = sm.Logit(\n", + " mortgageDf[\"y\"],\n", + " sm.add_constant(mortgageDf[[\"x1\"]])\n", + ")\n", + "model4Fit = model4.fit()\n", + "print(model4Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 78, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "YLIrig6rXKhw", + "outputId": "211239e6-b133-460b-fa77-c68169153bfa" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0" + ] + }, + "execution_count": 78, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "min = 0\n", + "min" + ] + }, + { + "cell_type": "code", + "execution_count": 79, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "w5OmNUfaXNsk", + "outputId": "14e9ae85-7cd1-47fd-a370-6904d3b170d5" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(49.19, 30)" + ] + }, + "execution_count": 79, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "max = mortgageDf[\"x1\"].max() + 10\n", + "max, len(mortgageDf[\"x1\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 80, + "metadata": { + "id": "sBBshZgnXQzO" + }, + "outputs": [], + "source": [ + "x = np.linspace(min - 5, max + 5, 500)\n", + "# x" + ] + }, + { + "cell_type": "code", + "execution_count": 81, + "metadata": { + "id": "2zxAZeT5XwgE" + }, + "outputs": [], + "source": [ + "import math" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "metadata": { + "id": "X2BmYiiDXgbw" + }, + "outputs": [], + "source": [ + "lREq = 0.0141 + x * 0.0227\n", + "logREq = pow(math.e, (-2.2077 + 0.1043 * x))/ (1+ pow(math.e, (-2.2077 + 0.1043 * x)))" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "C_8MU1W7YgR8", + "outputId": "33939ed7-8fc1-4813-bb7c-06c6f792c694" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "500" + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(lREq)" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "id": "VZ6BxMqpXCOH", + "outputId": "b11dad1f-c306-46d0-fe8b-afc16e3f91f2" + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAGwCAYAAABVdURTAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAABwIUlEQVR4nO3dd3gUVdvH8e+mE0JIaEmAQKSD0hEMNpSmKGJH4aEpIE0p+iAIUlQEAZEONsSGIq+KKB0ElC5NEekSQEhCE5IQkmx25/1jnkQiAbKkTLL5fa4rF5mZMzP3nF1278w5c47NMAwDERERETfhYXUAIiIiIjlJyY2IiIi4FSU3IiIi4laU3IiIiIhbUXIjIiIibkXJjYiIiLgVJTciIiLiVrysDiCvOZ1OTp48SbFixbDZbFaHIyIiIllgGAbx8fGULVsWD49r35spdMnNyZMnCQ8PtzoMERERuQHHjx+nfPny1yxT6JKbYsWKAWblBAYGWhxN3rDb7axYsYJWrVrh7e1tdTj5nurLNaov16i+XKc6c4271ldcXBzh4eHp3+PXUuiSm7SmqMDAwEKV3Pj7+xMYGOhWb/TcovpyjerLNaov16nOXOPu9ZWVLiXqUCwiIiJuRcmNiIiIuBUlNyIiIuJWCl2fm6xyOBzY7Xarw8gRdrsdLy8vkpKScDgcVoeT7xXG+vL29sbT09PqMEREcoSSm38xDIOYmBjOnz9vdSg5xjAMQkNDOX78uMb2yYLCWl9BQUGEhoYWqmsWEfek5OZf0hKbMmXK4O/v7xYf9E6nk4SEBAICAq478JEUvvoyDIPExEROnToFQFhYmMURiYhkj5KbyzgcjvTEpmTJklaHk2OcTicpKSn4+fkVii/r7CqM9VWkSBEATp06RZkyZdREJSIFWuH45M6itD42/v7+FkcikvfS3vfu0tdMRAovJTeZcIemKBFX6X0vIu5CyY2IiIi4FSU3IiIi4laU3Ei+NmrUKOrVq2d1GCIiUoAoucklDgds3AgLF5r/5vZYcF27dsVms2Gz2fD29iYkJISWLVsyZ84cnE6nS8eaO3cuQUFBORJXs2bN0uPy8/OjVq1azJw5M8v7v/TSS6xevdqlc0ZERDB58mQXI81f1q5di81mu2K8pWbNmjFgwABLYhIRyZLt2+HsWUtDUHKTC5YsgUaN4L77oGNH899Gjcz1uem+++4jOjqaqKgoli5dyj333EP//v1p27YtqampuXvya+jRowfR0dH88ccfPPnkk/Tt25cvvvgiS/sGBAS41WP5+UVKSorVIYiIu3E6YeZMePhh6N/fXLaIkpsctmQJ/Oc/cOAA+PpCsWLmvwcOmOtzM8Hx9fUlNDSUcuXK0aBBA1555RW+++47li1bxrx589LLTZo0idq1a1O0aFHCw8Pp06cPCQkJgHnHoFu3bly4cCH9jsuoUaMA+PTTT2nUqBHFihUjNDSUDh06pA/8di3+/v6EhoZSqVIlRo0aRdWqVVm0aBEAx44do127dgQEBBAYGMiTTz5JbGxs+r7/bpbq2rUrDz/8MBMnTiQsLIySJUvSt2/f9MeXmzVrxtGjRxk4cGB6/ABHjx6lbdu2BAcHU7RoUW6++WaWZPPFWLt2LY0bN6Zo0aIEBQVx++23c/To0fTt33//Pbfeeit+fn6UKlWKRx55JH3bteoyKiqKe+65B4Dg4GBsNhtdu3ala9eurFu3jilTpqRfW1RUFAC///47999/PwEBAYSEhNCpUyfOnDmTfr5mzZrRr18/BgwYQKlSpWjdunW2rl1EJIOzZ6FzZ3jjDbOpolgxsPCPKCU3OcjhgGHDIDkZAgPB2xs8PMx/AwPN9cOH534T1eXuvfde6taty/fff5++zsPDg6lTp7Jnzx4+/vhjfvzxRwYPHgxA06ZNmTx5MoGBgURHRxMdHc1LL70EmOOfvP766/z6668sXLiQqKgounbt6nJMRYoUISUlBafTSbt27Th37hzr1q1j5cqV/Pnnn7Rv3/6a+69Zs4bDhw+zZs0aPv74Y+bOncvcuXMB+OabbyhfvjyvvfZaevwAffv2JTk5mZ9++ondu3fz1ltvERAQ4HLsaVJTU3n44Ye5++67+e2339i0aRM9e/ZMT6YWL17MI488Qps2bdi5cyerV6+mcePG6ftfqy7Dw8P5+uuvAdi/fz/R0dFMmTKFKVOmEBkZmX4nLDo6mvDwcM6fP8+9995L/fr12bZtG8uWLSM2NpYnn3wyQ8wff/wxPj4+bNiwgdmzZ9/wtYuIZLB5M7RoAT/+aP41P2GCeQfHz8+ykDRCcQ7asgUOHwZ/f/j3kCE2m7n+0CGzXNOmeRdX9erV+fXXX9OXL++zERERwRtvvEGvXr2YOXMmPj4+FC9eHJvNRmhoaIbjPPPMM+m/V6pUialTp3LrrbemT1VwPQ6Hgy+++ILffvuNnj17snr1anbv3s2RI0cIDw8H4JNPPuHmm2/ml19+4dZbb830OMHBwUyfPh1PT09q1KjBAw88wOrVq+nRowclSpTA09Mz/Y5ImmPHjvHYY49Ru3bt9PizIy4ujgsXLvDggw9SuXJlAGrWrJm+fcyYMTz11FOMHj06fV3dunXTf79eXZYoUQKAMmXKZOj/5OPjk34nLM306dOpX78+b775Zvq6OXPmEB4ezoEDB6hWrRoAVatWZfz48dm6bhGRdA4HTJsGEyeaTVCVK8N778Fln4VW0Z2bHHTqlPlaX23kek9Pc3sWWnJylGEYGQZoW7VqFc2bN6dcuXIUK1aMTp06cfbsWRITE695nO3bt9O2bVsqVKhAsWLFuPvuuwEzcbiWmTNnEhAQQJEiRejRowcDBw6kd+/e7N27l/Dw8PTEBqBWrVoEBQWxd+/eqx7v5ptvzjA9QFhY2HWbx1544QXeeOMNbr/9dkaOHMlvv/121bJjx46lfPnyBAYGEhAQkOn1lShRgq5du9K6dWvatm3LlClT0u8SAezatYvmzZtf9Rw3WpeZ+fXXX1mzZg0BAQHpPzVq1ADg8OHD6eUaNmzo8rFFRDJ1+jR06ADjx5uJzeOPw7Jl+SKxASU3OapMmX8SmMykJT5lyuRtXPv27aNChQqA2Z/jwQcfpE6dOnz99dds376dGTNmANfuZHrx4kVat25NYGAgn3/+Ob/88gvffvvtdfcD6NixI7t27eLIkSNcvHiRSZMmZWvOJm9v7wzLNpvtuk+Ede/enT///JNOnTqxe/duGjVqxLRp0zIt+9xzz/HTTz+xY8cOdu3aRdmyZTMt99FHH7Fp0yaaNm3K/PnzqVatGps3bwb+maspM9mpy8wkJCTQtm1bdu3aleHn4MGD3HXXXenlihYt6vKxRUSusH49tGwJP/9sNj298w5MnQr56DNGyU0OatLEvCuXmAiGkXGbYZjrq1Qxy+WVH3/8kd27d/PQQw8B5h0Dp9PJ22+/zW233Ua1atU4efJkhn18fHxw/CtD27dvH2fPnmXcuHHceeed1KhRI0udiQGKFy9OlSpVKFeuXIakpmbNmhw/fpzjx4+nr/vjjz84f/48tWrVutFLzjR+MPuy9OrVi2+++YYXX3yR999/P9P9S5QoQaVKlahSpQpVqlTBy+vqrbf169dn6NChbNy4kVtuuSW943adOnWu+gh7VurSx8cH4IrryOzaGjRowJ49e4iIiEiPOe1HCY2I5BiHw2yCat/ebIKoXt28W3OdfpJWUHKTgzw9YcwYsz9VXBzY7ebdOrvdXPb1NTuS59aEy8nJycTExHDixAl27NjBm2++Sbt27XjggQd46qmnAKhSpQp2u51p06bx559/8umnn17RuTQiIoKEhARWr17NmTNnSExMpEKFCvj4+KTvt2jRIl5//fVsxduiRQtq165Nx44d2bFjB1u3bqVz587cfffdNGrU6IaPGxERwU8//cSJEyfSnxgaMGAAy5cv58iRI+zYsYM1a9Zk6CPjqiNHjjB06FA2bdrE0aNHWbFiBQcPHkw/5siRI/niiy8YOXIke/fuTe/EDGSpLitWrIjNZuOHH37g9OnT6U+zRUREsGXLFqKiojhz5gxOp5O+ffty7tw5nn76aX755RcOHz7M8uXL6datW6ZJnoiIy2JjzSRm0iTzr/WnnjIf//1fn778xtLk5qeffqJt27aULVsWm83GwoULr1n+m2++oWXLlpQuXZrAwEAiIyNZvnx53gSbRW3awGefma93cjLEx5v/Vq9urm/TJvfOvWzZMsLCwoiIiOC+++5jzZo1TJ06lYULF6b3Ualbty6TJk3irbfe4pZbbuHzzz9n7NixGY7TtGlTevXqRfv27SldujTjx4+ndOnSzJ07lwULFlCrVi3GjRvHxIkTsxWvzWbju+++Izg4mLvuuosWLVpQqVIl5s+fn63jvvbaa0RFRVG5cmVKly4NmHdA+vbtS82aNbnvvvuoVq2aS4MJ/pu/vz/79u3jscceo1q1avTs2ZO+ffvy3HPPAeaj1wsWLGDRokXUq1ePe++9l61btwJkqS7LlSvH6NGjGTJkCCEhIfTr1w8wBzX09PSkVq1alC5dmmPHjlG2bFk2bNiAw+GgVatW1K5dmwEDBhAUFJSt5j8REQDWrTOfhtq40XwyZto0M8m5RvO71WyG8e8GlLyzdOlSNmzYQMOGDXn00Uf59ttvefjhh69afsCAAZQtW5Z77rmHoKAgPvroIyZOnMiWLVuoX79+ls4ZFxdH8eLFuXDhAoGBgRm2JSUlceTIEW666Sb8svkIm8NhPhV16pTZx6ZJk9y7Y3M9TqeTuLg4AgMD9WWXBYW1vm70/W+321myZAlt2rS5oj+UXEn15TrVmWtyrL5SU81mqGnTzLs1NWuaT0P97wnRvHat7+9/s/RR8Pvvv5/7778/y+X/PaT+m2++yXfffcf333+f5eQmr3h65u3j3iIiIjkmOhp694b/3XGmc2cYNcrSsWtcUaDHuXE6ncTHx6ePCZKZ5ORkkpOT05fj4uIAM7NNG9U2jd1uxzAMnE6ny/Mx5WdpN+fSrk2urbDWl9PpxDAM7HZ7hkftryft/9G//z9J5lRfrlOduSa79WX78Uc8Bw6E8+ehaFEcb72F0bZt2sFzKErXuXI9BTq5mThxIgkJCVeMxHq5sWPHZhhILc2KFSvw9/fPsM7Ly4vQ0FASEhLccu6d+Ph4q0MoUApbfaWkpHDp0iV++umnG5qLbOXKlbkQlftSfblOdeYaV+vLlppK1W++4aalS0kF4ipWZFfv3lzy9Mz9yRGz4HpjsV3O0j43l7PZbNftc3O5efPm0aNHD7777jtatGhx1XKZ3bkJDw/nzJkzmfa5OX78OBEREdnuc5OfGIZBfHw8xYoVyzCYn2SusNZXUlISUVFRhIeHu9znZuXKlbRs2VL9IbJA9eU61Zlrbqi+/voLz379sO3cCYCzSxecw4fD/4alyA/i4uIoVapU/u9zc6O+/PJLunfvzoIFC66Z2IA5maSvr+8V6729va940R0OBzabDQ8PD7fqSJrWtJJ2bXJthbW+PDw8sNlsmf7fyIob3a+wUn25TnXmmizX1/LlMGAAXLhgToQ4aRKebdpg0TMwV+XKa1/gkpsvvviCZ555hi+//JIHHnjA6nBEREQKJrsdXn8dPvjAXK5XD2bPhv+NaF+QWZrcJCQkcOjQofTlI0eOsGvXLkqUKEGFChUYOnQoJ06c4JNPPgHMpqguXbowZcoUmjRpQkxMDGAOdV+8eHFLrkFERKTAOXoUevWCtEmVe/aEYcPATe6MWXrPfdu2bdSvXz/9Me5BgwZRv359RowYAUB0dHSGiQTfe+89UlNT6du3L2FhYek//fv3tyR+ERGRAmfxYmjVykxsiheHuXPNx7zdJLEBi+/cNGvWjGv1Z547d26G5bVr1+ZuQAVYs2bNqFev3hVjAYmIiADmcPmvvQYffWQuN2xoNkOVK2dtXLmg8PSWLESaNWuGzWbDZrPh5+dHjRo1mDRpUoZEMioqKr3Mv3/SZrYWERE3ceQItG37T2LTpw98841bJjZQADsUS9b06NGD1157jeTkZFatWkWvXr0ICQmhb9++GcqtWrWKm2++OcO6kiVL5mWoIiKSm777Dv77X0hIgBIlYOpUuPdeq6PKVbpz46b8/f0JDQ2lYsWKdOvWjZtvvplVq1ZdUa5kyZKEhoZm+Ln8cbtx48YREhJCsWLFePbZZxkyZAj16tXLwysREZEbkpQEgweb0ygkJJiTHK5a5faJDejOzfUZBly6ZM25ixSBbA4iZxgGP//8MwcPHqR69eou7fvVV18xatQoZsyYwR133MGnn37K1KlTqVSpUrZiEhGR3FU0OhrPdu1g3z7ze6R/fxg0CLwKx9d+4bjK7Lh0CapUsebchw6Z08vfgJkzZ/LBBx+QkpKC3W7Hz8+P559//opyTZs2vWKguoSEBMCcqPTZZ5/l2WefBeCNN95g1apVJCUl3VBMIiKS+2xff81to0ebI6yXKgXTp8Ndd1kdVp5ScuOmOnbsyLBhw/j7778ZMWIEDRs2pGkm05TPnz+fmjVrZnqMvXv30qtXrwzrIiMjWbNmTa7ELCIi2ZCYCMOG4Tl/Pl7JyRj33INt5kwICbE6sjyn5OZ6ihQx76BYde4bVLx4car8747T/PnzqVq1KnfddRetWrXKUC48PDy9nIiIFFD798Nzz8GBA2CzcahdO6rPmoWHG82T6AolN9djs91w01B+ERAQwHPPPcfgwYNp2bJllieDrFmzJlu2bKFz587p6/SYuIhIPmIYMH8+vPKK2YG4TBkcU6Zw+Px5qnvmt9mh8o6eliokunXrxoEDB/j6668zrD979iwxMTEZftL61PTv3585c+bw0UcfceDAAUaOHMmePXusCF9ERP7t4kV44QWzo3BSktmvZtUqjEy6IBQ2Sm4KieDgYDp16sSoUaPSZ70GaNGiRYapLMLCwli4cCEA7du359VXX2Xw4ME0bNiQo0eP0rt3b4uuQERE0u3dC61bw9dfg4cHDBkC8+aZHYhFzVLu4vKpKa42TcWsWbPSn4yKiIi45tQXaV555RVeeeWV9OVRo0ZlJ0wREckOw4DPPoNXX4WUFAgNhVmzzDFsJJ2SGxERkYIgPt4caXjRInO5eXOYMsUcdVgyUHIjIiKS3+3ebT4NFRVlDsQ3ZAj06mU2SckVVCviklGjRrFr1y6rwxARKRwMw5zs8sEHzcSmXDn49ltz4kslNlelOzciIiL5UVwcvPgiLF5sLrdqBZMnQ1CQlVEVCEpuRERE8pudO81mp+PHwdsbhg+H7t2zPd9gYaHkRkREJL8wDHj/fRgzBux2qFABZs+GevWsjqxAUXIjIiKSH5w/DwMGwIoV5vIDD8Dbb0NgoJVRFUhKbkRERKy2fbv5NNTJk2Yz1KhR0LWrmqFukJIbERERqzidZrPT2LHgcEBEBLz3Htxyi9WRFWh6jsxNNGvWjAEDBlgdhoiIZNW5c9C5M7zxhpnYtGsHy5crsckBSm4kU3PnzsVms2Gz2fDw8CAsLIz27dtz7NixDOWaNWuWXu7yn169elkUuYhIAbBlC7RoAT/+CL6+MH48zJwJxYpZHZlbULOUXFVgYCD79+/HMAyOHDlCnz59eOKJJ9iyZUuGcj169OC1117LsM7f3z8vQxURKRicTpg2DSZMMH+vXNlshqpZ0+rI3Iru3Lihv//+m86dOxMcHIy/vz9t2rTh8OHDGcq8//77hIeH4+/vzyOPPMKkSZMI+tfAUDabjdDQUMLCwmjatCnPPvssW7duJS4uLkM5f39/QkNDM/wEXta7f+vWrdSvXx8/Pz8aNWrEt99+i81m00jHIlK4nD4NHTrAW2+Zic3jj8OyZUpscoHu3FyHYRhcSr1kybmLeBXBdgM95bt27crBgwdZtGgRgYGBDB48mCeffJI//vgDX19fNmzYQK9evXjrrbd46KGHWLVqFa+++uo1j3nq1Cm+/fZbPD098fT0zHIsCQkJPPjgg7Rs2ZLPPvuMI0eO0L9/f5evSUSkQNuwAfr2hVOnwM/P7ED85JN6GiqXKLm5jkupl6gytYol5z70wiH8vV1r3klLajZs2EDTpk0B+Oyzz6hYsSILFy6kffv2TJs2jfvvv5+XXnoJgGrVqrFx40Z++OGHDMe6cOECAQEBGIZBYmIiAC+88AJFixbNUG7mzJl88MEHGda9++67dOzYkXnz5uF0Ovnwww/x8/Pj5ptv5q+//qJ3794uXZeISIHkcJhTJrzzjnm3plo1ePddqF7d6sjcmpIbN7N37168vLxo0qRJ+rqSJUtSpUoV9u3bB8D+/ft55JFHMuzXuHHjK5KbYsWKsWPHDux2O0uXLuXzzz9nzJgxV5yzY8eODBs2LMO6kJCQ9Hjq1KmDn59f+rbIyMjsXaSISEEQGwv9+pl3bQCeesocebhIEWvjKgSU3FxHEa8iHHrhkGXntpKHhwdVqph3rWrWrMnhw4fp3bs3n376aYZyxYsXTy8nIiLATz+Zic2ZM+DvD+PGmX1sJE8oubkOm83mctOQlWrWrElqaipbtmxJb5Y6e/Yshw4doub/Oq1Vr16dX375JcN+/17OzJAhQ6hcuTIDBw6kQYMGWY7n008/JSkpKf3uzebNm125JBGRgiM11ZwyYepUc56omjXNZij9AZin9LSUm6latSrt2rWjR48erF+/nl9//ZVOnToRFhZGu3btAHj++edZsmQJkyZN4uDBg7z77rssXbr0up2Xw8PDeeSRRxgxYkSG9YmJicTExGT4+fvvvwHo0KEDNpuNHj168Mcff7BkyRImTpyYOxcvImKl6Gh44gmYMsVMbDp1gsWLldhYQMmNG/roo49o2LAhDz74IJGRkRiGwVdffYW3tzcAt99+O7Nnz2bSpEnUrVuXZcuWMXDgwAz9Yq5m4MCBLF68mK1bt6ave//99wkLC8vw8/TTTwMQEBDA999/z+7du6lfvz7Dhg3jrbfeyp0LFxGxyurV5qB8W7ZAQADMmmU+8p2Fz1XJeWqWchNr165N/z04OJhPPvkkfdnpdF4xNk2PHj3o0aNHhuXL+8107dqVrl27XnGe2267DcMwMj3v1dx2220ZxrSJioq67j4iIgWC3W4mMTNnmsu33GIOyhcRYWlYhZ2Sm0Jq4sSJtGzZkqJFi7J06VI+/vhjZqb95xQRkes7cQJ69TJn9Abo1g1GjDCnUxBLKbkppLZu3cr48eOJj4+nUqVKTJ06le7du1sdlohIwbBiBfTvDxcuQGCg2Yn4gQesjkr+R8lNIfXVV19Zdu6IiIgMTVsiIgWG3W6OVfPee+ZyvXpm/5qKFS0NSzJSciMiIpIVx46ZzVBpfQh79IDhw+F/D2tI/qHkJhO6qyCFkd73ItewZAkMGgRxcVC8uPm4d6tWVkclV6Hk5jJpj0onJiZSRMNjSyGTNn+Yt/4KFflHcjK89hp89JG53LCh2QxVvry1cck1Kbm5jKenJ0FBQZw6dQoAf3//G5qVO79xOp2kpKSQlJSEh4eGNrqey+vr0iUPUlPBy8scQT2zt4NhQGIi1y2XF24klrSJUU+dOkVcXBDff+9JmTLQpAm4MAH8DXM4zKFBTp3iuud1peyNlM+r67jRY0dHm6P5ly4NoaE3fv3ZjdWVeC4/V8mS5rqzZ3M2nlwTFQU9e8Lvv5vLffrAyy+rGaoAsDS5+emnn5gwYQLbt28nOjqab7/9locffvia+6xdu5ZBgwaxZ88ewsPDGT58eKbjsdyo0NBQgPQExx0YhsGlS5coUqSIWyRruS2tvi5cKILd/k99eXtDUFDGOe8uXYLz580+htcqlxeyE8vFi7BwYRDTpoWSmmp+sVSubPabbNMm92JesgSGDYPDh80vuGud15WyN1I+r67jRo+9fz8kJZkJrM1mjg1Xvbrr1//ww7Bw4Y3H6ko8l8eQkvLPe9PbG3x8ciaeXLNoEbz0EiQkQHCwOZ1C8+YWBiSusDS5uXjxInXr1uWZZ57h0UcfvW75I0eO8MADD9CrVy8+//xzVq9eTffu3QkLC6N169Y5EpPNZiMsLIwyZcpgv/xbogCz2+389NNP3HXXXWpyyIK1a+04HD8xfPhdgHf6X5ZJSeYH8vjxcPfdsG4dDB5sfmj7+XHVcnkhO7GsWwfPPOPN+fOe+PubiZDDAQcOwH/+A599ljtfMkuWmMdPTjbvMKXFnNl5XSl7I+Xz6jpu9NiJieZrm5ZIGIaZzO7d69r1790Lv/5qvieKFXM9VlfigX9i8PL6pzyY63x9sx9PrkhKgpEjIW2C4MaNzWaosLA8DkSyw2bkk16ENpvtunduXn75ZRYvXszvabcIgaeeeorz58+zbNmyLJ0nLi6O4sWLc+HCBQIDA7MbdoFgt9tZsmQJbdq0UXJzHQ4H3H67naFDlzBgQBuSk/+pL8Mw+xJWrw6bN5u3zg8cMIe4uPyG2OXlfvkl92+vOxzQqNGNxZKdfdPcyPvLlfOCazHmxDVl1Y2cK6v1lXbs/fvNOx6pqebx085hGODhYSYJWb3+U6fM7V5eUKpUxmNdr15ciadaNXP54EEzaTl7NmN5wzDPYRhZi8fpzKPPsMOHzWaovXvNYF54AV580QywAHHXz3xXvr8L1Cu2adMmWrRokWFd69atGTBgwFX3SU5OJjk5OX05bRoCu93uNndmriftOgvL9WbHli1w8qRZT35+9iv6q3h5wV9/wdy55uCkJUpk3vyeVm7TJjMJyu2YbzSW7Oyb5kbeX66cF1yLMSeuKTeuI+1cWa2vtGMHBkJ8vHl349/vR8Mwk4esXH9KSsaBcz09zWNeK9Ybjef4cXO5RAlznY/PleX//Wf1teJp0CD3P8Ns33yD57Bh5m2pEiVwTJ2KceedZqAF7LPTXT/zXbmeAnXnplq1anTr1o2hQ4emr1uyZAkPPPDAVZ9wGjVqFKNHj75i/bx58/D398+R2EVEpGDySE6m5uefU/7nnwE4W7Mmu3v2JDkoyNrA5AqJiYl06NDB/e7c3IihQ4cyaNCg9OW4uDjCw8Np1apVoWqWWrlyJS1btnSrW5S5YcsW6NDBzrRpKxkypGWGZikw/4BLToY33jDH7vL1zfwv9rRy33yTN3duHn30xmLJzr7/lHH9/eXKecG1GHPimrLqRs6V1fpKO7aHh3mnBK5+p8TpvP71p6TA33//sxwcnPFOyfXqxZV4UlPN5SJFzHVp573WnZtrxdOgQS59hh04gGefPtgOHoQiRXD270+ZF16geb54VOvGuetn/r8ngL6WApXchIaGEhsbm2FdbGwsgYGBVx2XxtfXF99MJjHz9vZ2qxc9KwrjNbsqMhLKljV/T0ryvmqfm65dzT6G1+trERmZ+31uIiOhXLkbiyU7+/6bK+8vV84LrsWYk9eUk9fx73Ndr77Sjn29Pi6Q9etPTv6nj0tah/Os1osr8fy7z01KyvX73FwrHqcza3WWZYYBX30FQ4eaJy1TBqZPx/OOOyjYaU1G7vaZ78q1FKhBTyIjI1m9enWGdStXriQy7RNQJJs8PeHVV83f4+PND3Gn0/w3Ls78a/iNN8y/MMeMMZfj4q5eLi/+APT0vPFYsrNvXsXsaox5eU25ea60Y6c9/ZaWFBiGeQ7DMJMCV67fy8s8jqenmWy4Eqsr8YwZA2++af4eH//PeEuXl/X3z148N+ziRXPCy4EDzcTmrrtg5Uq4444cPpFYyrBQfHy8sXPnTmPnzp0GYEyaNMnYuXOncfToUcMwDGPIkCFGp06d0sv/+eefhr+/v/Hf//7X2Lt3rzFjxgzD09PTWLZsWZbPeeHCBQMwLly4kOPXk1+lpKQYCxcuNFJSUqwOpUBIq68mTVKMYsUMw9/fMIoVM4z69Q1j8eKMZRcvNox69YzrlssL2YklO/tm5/3lynldjTEvXxtXzuVqfaUdu0gRw7DZzHTCw8NcvpHrHzUqe/XiSjyXx+Dra5bz8DB/dyWeHPsM++MPw7jzTsMICzOMcuUMY8oUw3A4snfMfMhdP/Nd+f62tEPx2rVrueeee65Y36VLF+bOnUvXrl2Jiopi7dq1GfYZOHAgf/zxB+XLl+fVV191aRA/PQruPrcoc0tafbVu3YYdO7yvO2pqfhpdNTux3Oi+2X1/FbYRim/00fnCPEJxtj/DDAM+/9y8LZucbAY7a1bud4iziLt+5heYR8GbNWt2zcn65s6dm+k+O3fuzMWoREyentC0ac6VywvZicWq63DlvK7GmJfXlJvnutFjX22/7Maa069Zrr5O8fHmCJfffWcu33uvOdpwiRK5dMLCyTAMzl46S0xCDNHx0RTxLsIdFaxr6itQHYpFRESy7PffzUH5oqLMDGroUOjV65+ez5JlcclxnIw/mf5zIu6E+XvCP7+nOFLSy99W/jYlNyIiIjnGMMyRNkeNMnsoly0L775rzugtmYpLjuPYhWMcPX+UoxeOcvzCcY7FHUtPZBJSEq57DJvNRin/UoQGhFK1RNU8iPrqlNyIiIj7iIszJ7z84QdzuVUrmDzZnEG2EHM4HZyIP5EhgTl24RhHLxzl6PmjnE86f91jBPkFUbZYWcoFlqNswP/+LVY2/ScsIAxvz/zRx0fJjYiIuIddu8xmp2PHzBEMhw2DHj2uHG3QjcUlx7Hv1D42nN/A7xt/J+pCFIf/Psyff/+ZodkoM6X8S1ExqCIVAitQMagi4YHhGRIYf++CM6q/khsRESnYDAM++MAcGMduh/BwmD0b6te3OrJcYRgGpy6eYt+Zfew/u59D5w5x6NwhDv99mNMXTwOQlJSE3xm/DPt5e3pTsXjFDAlMxeIVqVC8AhWKV6CoT1ErLidXKLkREZGC6/x5c0C+5cvN5TZtYNIkc3hmNxCXHMeBswfYe3ov+87sY9/Zfew7s4+/L/191X3KFC2Dv6c/TWs2pXqp6lQuUZnKwZUpH1geTw93GoP56pTciIhIwbR9u9kMdeKE2Qw1apQ5N0oBbIYyDIPohGh2x+7mt9jf+P307/xx+g9OxJ3ItLyHzYOIoAhqlKpBtZLVqBxcOT2J8fPwM8e5ude9xrlxhZIbEREpWJxOs9lp3Dhz3oaICPNpqNq1rY4sSwzD4NiFY+w+tdtMZk79xu7Y3Zy7dC7T8qEBodQoVYOapWpSvVR1apaqSdWSVfHz8su0vN1uz83wCwQlNyIiUnCcOwcDBsCqVebyQw/BhAnmDJ351NnEs+yI3sGO6B1sj97Ob7G/EZd85QzXnh6eVCtZjTpl6lA7pDa1SteiRqkaBPkF5X3QBZySGxERKRBsW7fC889DTIw5e+0bb0DHjvmqGcrusLP3zF62n9yensxEnY+6opy3pzc1S9Wkdpna1Akxk5mapWri6+Wb90G7ISU3IiKSvzmdVPrhBzyXLTMnoqpUCd5/H2rWtDoyEu2JbDu5jc1/bWbzX5vZFbOLpNSkK8pVLVmVBqENaFi2IfVC61G9ZPV8MyaMO1JyIyIi+deZM3j27UvVlSvBzw8ee8zsa1PUmseW45Lj+OXEL2z6axOb/9rMb7G/kepMzVAm0DeQBmENaBjWkIZlG1I/tD7F/YpbEm9hpeRGRETyp40boW9fbLGxOHx8cIwfj1ceN0Ml2hPZ/Ndmfjr6E5v+2sSeU3twGs4MZcoWK0tk+UgiwyO5teytVC5RGQ+b5q+ykpIbERHJXxwOc8qEd94BpxOjalU2t2/PXe3b53pi4zSc7I7dzU9Hf2Ld0XX8cvIX7I6MTx9FBEUQWT6S28rfRmR4JOUDy+dqTOI6JTciIpJ/nDoF/frB+vXmcvv2OEaNImHt2lw75Ym4E+nJzM/Hfr5igLzygeW5u+Ld3FHhDm4rfxshASG5FovkDCU3IiKSP/z8M/TtC2fOgL+/2bfm8cfNKRVykMPpYGfMTlYeXsmqI6vYe3pvhu3FfIvRNLwpd1e8m7sr3k1EUAS2fPREllyfkhsREbFWaiq8/TZMnWrOE1WzpjkoX5UqOXaKuOQ41kWtY9Wfq1h9ZHWGAfM8bB7UD6tPs4rNuKviXdQLracnmQo4JTciImKdmBjo0wc2bzaX//MfeO0188mobIpNiGXJwSUsPbSUzX9tzvBUU6BvIPdE3EPLyi2596Z7NVCem1FyIyIi1vjxR3jhBXPU4aJFYeJEaNcuW4c8EXeCxQcXs/jgYrad3IZhGOnbKpeoTMtKLWlRqQW3lr1Vd2fcmJIbERHJW3Y7vPUWzJxpLt9yi9kMddNNN3S4qPNRLDm4hB8O/MCumF0ZtjUs25A2VdpwX5X7uCn4xo4vBY+SGxERyTsnTkDv3rBtm7ncrRuMGAG+rk07cOriKb7b9x3f7PuGX2N+TV9vs9loUq4JD1R9gDZV2xBWLCwno5cCQsmNiIjkjZUrzWaoCxfMiS7ffhsefDDLu8cnx7PqwCq+2fsN64+tTx9Mz9PDk8jykTxY7UHuq3IfZYqWya0rkAJCyY2IiOQuux3efNNsegKoWxdmz4aKFa+/q8POij9XMPP4TAZ8MIBkR3L6toZlG/JojUdpW70tpfxL5Vb0UgApuRERkdxz7JjZDLVzp7ncowcMHw7e1+7Me+DsAb7Y/QX/t/f/OJt4lqSkJPz8/KhcojKP1niUR2o+QkRQRO7HLwWSkhsREckdS5bAoEEQFweBgTBlCrRufdXiCSkJLNq/iC9+/4LtJ7enry/tX5qaRWsyuO1g6petrwH15LqU3IiISM5KSYHRo+Gjj8zlhg1h1iwof+UcTIZhsO3kNubtnsf3B74n0Z4ImP1oWlRqQYdbOnBH+TtYsWwFtcvUVmIjWaLkRkREck5UFDz3HOzebS736QMvv3xFM1RCSgL/98f/8fGvH7P/zP709ZVLVObpW57m8VqPp3cMtufw9Avi/pTciIhIzli0CF56CRISIDjYbIZq0SJDkYNnDzJ311wW/LGAhJQEAIp4F+Ghag/RoXYHGpVtpLszkm1KbkREJHuSkmDUKPjkE3O5cWOzGSrMHGMm1ZnKisMrmLtrLuuPrU/frXKJynSr143Haz1OoG+gBYGLu1JyIyIiN+7wYejZE/buBZsNnn/evHvj5cX5pPN88usnfPzrx0THRwPmJJWtKrfimfrPcHv47bpLI7lCyY2IiNyYb76BwYMhMRFKloTp0+Huu4k6H8X729/nyz1fcsl+CYCS/iXpcEsHOtftTLnAchYHLu5OyY2IiLjm0iVzrJovvjCXmzaFGTPY5jjO7EXdWXpoafqElTeXuZnnGj7HQ9UfwsfTx8KgpTBRciMiIll34ID5NNT+/WCz4Rw4gGVtazDrx+4Zxqa596Z76dWol5qexBJKbkREJGvmz4dXXoFLl0gNKc3C4Y8zLf4HDv7wDgDent48VvMxnmv4HNVLVbc4WCnMlNyIiMi1XbxoJjULFpDiYfDVgxWZ0SCVo1GzAAj0DaRrva48U/8ZTVop+YKSGxERubq9e+G557h05CCf10xi5j0BxBQ5BhehRJESPNfwObrU66JHuSVfUXIjIiJXMgyYN4+kka8wt+J5Zj6RwpkyAeDtICQghD6N+tCxTkf8vf2tjlTkCkpuREQko4QEUga/yOd75zP1/ovEBnlDYHEqBEfQr3E/nrz5ST35JPmakhsREUln/20nX41+knfCjnLyVgcUK0b50GoMihzEYzUfw9vT+/oHEbGYh9UBzJgxg4iICPz8/GjSpAlbt269ZvnJkydTvXp1ihQpQnh4OAMHDiQpKSmPohURcU8ORyoLZvTlrndv47+V/+RkMQgJq8LYtlPY8MwGnrrlKSU2UmBYeudm/vz5DBo0iNmzZ9OkSRMmT55M69at2b9/P2XKXNnjft68eQwZMoQ5c+bQtGlTDhw4QNeuXbHZbEyaNMmCKxARKdgMw2D174sY80Vv9qfGQlEo5RXI8/ePpFNkL/y8/KwOUcRlliY3kyZNokePHnTr1g2A2bNns3jxYubMmcOQIUOuKL9x40Zuv/12OnToAEBERARPP/00W7ZsydO4RUTcwa8xv/L69y+x8c914HBQ3O5BvwqP063vB/j7FLU6PJEbZllyk5KSwvbt2xk6dGj6Og8PD1q0aMGmTZsy3adp06Z89tlnbN26lcaNG/Pnn3+yZMkSOnXqdNXzJCcnk5ycnL4cFxcHgN1ux26359DV5G9p11lYrje7VF+uUX25Jj/U19ELR5mwcTzf//oVJCTg44BnT4bRu+8nFG98p+Xx/Vt+qLOCxF3ry5XrsRlpE4DksZMnT1KuXDk2btxIZGRk+vrBgwezbt26q96NmTp1Ki+99BKGYZCamkqvXr2YNWvWVc8zatQoRo8efcX6efPm4e+vRxhFpPBISE3g+9Pf8+PZVdguxuNpt/PoQR862W/lzH/6kKrPRMnHEhMT6dChAxcuXCAw8NrjKhWop6XWrl3Lm2++ycyZM2nSpAmHDh2if//+vP7667z66quZ7jN06FAGDRqUvhwXF0d4eDitWrW6buW4C7vdzsqVK2nZsiXe3uoQeD2qL9eovlxjRX3ZHXY+2/0Zb29+m/iL5/BKiKPZcU+G7Q6l+vOvYXTuDPl4/ie9x1zjrvWV1vKSFZYlN6VKlcLT05PY2NgM62NjYwkNDc10n1dffZVOnTrRvXt3AGrXrs3Fixfp2bMnw4YNw8Pjyoe/fH198fX1vWK9t7e3W73oWVEYrzk7VF+uUX25Jq/qa13UOkasHcHBswchMZFax5MYsb0Yd/lWh09nQ506uR5DTtF7zDXuVl+uXItlj4L7+PjQsGFDVq9enb7O6XSyevXqDM1Ul0tMTLwigfH09ATMHv8iImI68vcRuizswtNfP83BMwcocS6RCSttLF8czF23PgHLlxeoxEbEFZY2Sw0aNIguXbrQqFEjGjduzOTJk7l48WL601OdO3emXLlyjB07FoC2bdsyadIk6tevn94s9eqrr9K2bdv0JEdEpDCLT45nypYpvL/jfewOO16pTp751cagDX4E2vxg3Ovwn//k62YokeyyNLlp3749p0+fZsSIEcTExFCvXj2WLVtGSEgIAMeOHctwp2b48OHYbDaGDx/OiRMnKF26NG3btmXMmDFWXYKISL5gGAYL9y1k9LrRnLp4CoB7Usoy+rMTVPnbBpUqw3vvQa1aFkcqkvss71Dcr18/+vXrl+m2tWvXZlj28vJi5MiRjBw5Mg8iExEpGA6dO8Qrq19h/bH1ANwUUJ7RvwTQfMlebNjg0Udh3DgICLA4UpG8YXlyIyIiN+aS/RJTtkxh1rZZ2B12fL18GRDSjt7j1+AT8xf4FYE334T27dUMJYWKkhsRkQJo1Z+rGPbjMI5fOA5A84h7eeNIBBVfmgtOJ1StCu++CzVqWBuoiAWU3IiIFCDR8dEM+3EYyw4tAyCsWBhv1H+J+yZ8g239HLNQ+/YwZgxoUD4ppJTciIgUAE7DyWe/fcYbP71BQkoCXh5e9GzYk4HOxhTt/l84fRqKFIG33oLHH7c6XBFLKbkREcnn/vz7T15a8RKb/9oMQMOyDZlwz1hqfLIEpnQDw4CaNc1mqCpVLI5WxHpKbkRE8im7w867299l4saJpDhS8Pf2Z+gdQ+kaeh+efZ6HzWayQ8eO8Prr4OdnbcAi+YSSGxGRfGh37G4GrRjEnlN7ALg74m7GtxhP+I5D0Lk1nDsHRYvChAnw8MPWBiuSzyi5ERHJR5JSk3h749vM3j4bh9NBkF8Qo5uN5vGq7bBNnAjTp5sFb77ZHJTvppusDVgkH1JyIyKST+yK2UX/Zf3NSS6Bh6o/xOv3vE7pC3azk/C2bWbBrl1h5EjIZFJgEVFyIyJiObvDzuTNk5m6dSoOp4MyRcvwVou3aF2lNaxcCf37w/nzUKwYvP02PPig1SGL5GtKbkRELLT39F5eWPZCet+ah2s8zJh7xxDsFQCjR5tPQAHUrQuzZ0PFihZGK1IwKLkREbGAw+ng3a3vMmHjBOwOO8FFghnXfBxtq7eF48eh139g506zcI8eMGwY+PhYG7RIAaHkRkQkj8Ukx/DY/z3GzhgzeWlVuRUTWk6gdNHSsHQpDBwIcXEQGAhTpkDr1hZHLFKwKLkREckjhmHwyW+fMPLwSDx8PCjmW4zX73mdJ2o9gc1uh+HDYc7/plBo2BBmzYLy5a0NWqQAUnIjIpIHziSeYdDyQaz6cxUpzhSahzdnyv1TKFusLERFQa9e8NtvZuHevWHIEPD2tjRmkYJKyY2ISC5bc2QNA5YP4PTF0/h4+vBo2KNMengSPj4+8P338NJLEB8PwcFmM1SLFlaHLFKgKbkREcklyanJjPl5DB/s+ACA6qWqM6XVFI5sPYItJcUcq+bjj83Ct95qPg0VFmZhxCLuQcmNiEgu2HdmH32X9GXv6b0APFP/GYbfNRxPw5PYmE14tmsHe81tPP88/Pe/4KWPZJGcoP9JIiI5yDAM5u6ay+h1o0lxpFDKvxTvtH6H5pWaA5C6YAGRo0djAyhZEqZNg2bNrAxZxO0ouRERySF/X/qbAcsHsPLwSgDuvele3mn9jvmI96VL8OqreM6bh1dSEkazZthmzYKQEIujFnE/Sm5ERHLAtpPbeO6H54iOj8bH04cRd4+gW71u2Gw2OHgQnnsO9u0Dm41D7dpRfdYsPPz8rA5bxC0puRERyQan4WTWL7MYt2EcDqeDm4Jv4r0H3+PmMjebBb76CoYONe/clC6NY8oUDl+4QHVPT2sDF3FjSm5ERG7Q2cSz9F/Wnx+P/AiY80KNbzmeAJ8ASEw0k5oFC8zCd94J06djBAXBkiXWBS1SCCi5ERG5AVv+2kLvxb2JSYjB18uXN+55gw61O5jNUHv3ms1Qhw6Bh4c5js3zz4OnJ9jtVocu4vaU3IiIuMBpOJm+dToTNk7A4XRQuURl3nvwPWqWrgmGAfPmmZNcJiebnYVnzoTISKvDFilUlNyIiGTRmcQzPL/0edZFrQPg8VqPM7b5WIr6FIWEBHj5Zfj2W7PwPffA1Knm494ikqeU3IiIZMH2k9vp8X0PYhJi8PPyY2zzsTx585NmM9SePdCzJxw5YjY9DRlizg/l4WF12CKFkpIbEZFrSBuUb9S6UdgddqqUqML7bd+neqnqZjPUxx+b0yikpJhTJ8yebU6lICKWUXIjInIVifZEBq8czDd7vwGgbbW2vN36bfNpqLg4c8qE7783C7dsCZMnm5NfioillNyIiGTiyN9HeHbRs+w7sw9PD0+G3zmcng17ms1Qv/4KvXrB0aPmfFDDhpnNUjab1WGLCEpuRESusPzQcl5Y9gLxyfGUKVqG2Q/O5rbyt5nNUB9+CK+9Zj7SXb682QzVoIHVIYvIZZTciIj8j8PpYPyG8UzbOg2AxuUa8+6D7xISEAIXLsCgQbB0qVn4/vth0iQoXtzCiEUkM0puREQwRxvuvbg364+tB6BHgx4Mv2s43p7esGOH2Qz111/g7W12IO7WTc1QIvmUkhsRKfR2Ru+k+/fdiY6Pxt/bn0mtJ/FQ9YfMZqjZs+HNNyE1FSpWhHffhTp1rA5ZRK5ByY2IFGrzf5/P4FWDsTvsVC5RmQ/afmA+5v333zBgAKxcaRZ86CEYPx4CAy2NV0SuT8mNiBRKdoed19a9xoc7PwSgdZXWTL1vKsV8i8Evv5jNUNHR4ONjdiDu1EnNUCIFhJIbESl0zl06x3M/PMeGYxsAeDHyRQZGDsTDAKZPh7feAocDbroJ3nsPbr7Z2oBFxCVKbkSkUPnj9B90+64bxy8cp6hPUabdP437qtwHZ8/CCy/AmjVmwUceMZOcgABrAxYRlym5EZFC4/v93zNg+QAu2S8RERTBR+0+MvvXbNoEffpAbCz4+cGYMfDUU2qGEimgLJ/VbcaMGURERODn50eTJk3YunXrNcufP3+evn37EhYWhq+vL9WqVWPJkiV5FK2IFEQOp4Nx68fx3A/Pccl+ibsj7mZJxyVUD64C77wDTzxhJjZVq8KSJfD000psRAowS+/czJ8/n0GDBjF79myaNGnC5MmTad26Nfv376dMmTJXlE9JSaFly5aUKVOG//u//6NcuXIcPXqUoKCgvA9eRAqEuOQ4+i3px6o/VwHQu1Fvht45FK8z56Df07DeHNeG9u3NOzb+/hZGKyI5wdLkZtKkSfTo0YNu3boBMHv2bBYvXsycOXMYMmTIFeXnzJnDuXPn2LhxI97e3gBERETkZcgiUoAcPneYrt915fC5w/h6+fJ2q7d5tOajZkLTty+cPg1FisC4cebdGxFxC5YlNykpKWzfvp2hQ4emr/Pw8KBFixZs2rQp030WLVpEZGQkffv25bvvvqN06dJ06NCBl19+GU9Pz0z3SU5OJjk5OX05Li4OALvdjt1uz8Eryr/SrrOwXG92qb5ck1/ra03UGvot60dCSgKhAaG8/+D71Cl5M4633sJj6lQwDIzq1XHMmGE2R+VR/Pm1vvIz1Zlr3LW+XLkey5KbM2fO4HA4CAkJybA+JCSEffv2ZbrPn3/+yY8//kjHjh1ZsmQJhw4dok+fPtjtdkaOHJnpPmPHjmX06NFXrF+xYgX+hez288q0wcgkS1RfrslP9bXq7Cq+iPkCp+Gkqn9V+pbqy+lVv3N6dj9K7N8PwPG772Zfhw44Dx6EgwfzPMb8VF8FherMNe5WX4mJiVkuW6CelnI6nZQpU4b33nsPT09PGjZsyIkTJ5gwYcJVk5uhQ4cyaNCg9OW4uDjCw8Np1aoVgYVkpFG73c7KlStp2bJlenOeXJ3qyzX5qb5SnamM/mk0Xx/6Gh9fH56s9SRv3vMmPus34jmivznqcMmSON58k4iHHybCghjzU30VFKoz17hrfaW1vGSFZclNqVKl8PT0JDY2NsP62NhYQkNDM90nLCwMb2/vDE1QNWvWJCYmhpSUFHx8fK7Yx9fXF19f3yvWe3t7u9WLnhWF8ZqzQ/XlGqvrKy45jt6Le7PmyBpsNhvD7hxG73o9sE2YYA7MB1CrFrz3Hl6VKlkWZxqr66sgUp25xt3qy5VrsexRcB8fHxo2bMjq1avT1zmdTlavXk1kZGSm+9x+++0cOnQIp9OZvu7AgQOEhYVlmtiISOFw/MJx2n3ZjjVH1uDn5ccHbT+gT7mHsT3++D+JTdeusHgx5IPERkRyl6Xj3AwaNIj333+fjz/+mL1799K7d28uXryY/vRU586dM3Q47t27N+fOnaN///4cOHCAxYsX8+abb9K3b1+rLkFELLb95HYemPcA+8/sJyQghIVPLeT+o97QooU5R1SxYuZM3m++CZncxRUR9+Nys1SXLl149tlnueuuu7J98vbt23P69GlGjBhBTEwM9erVY9myZemdjI8dO4aHxz/5V3h4OMuXL2fgwIHUqVOHcuXK0b9/f15++eVsxyIiBc93+76j/7L+pDhSuLnMzXzy4IeETZsLs2ebBerUMX/XkBEihYrLyc2FCxdo0aIFFStWpFu3bnTp0oVy5crdcAD9+vWjX79+mW5bu3btFesiIyPZvHnzDZ9PRAo+wzB4Z/M7TNw4EYBWlVsxo85QinbqAzt2mIW6d4fhw81ZvUWkUHG5WWrhwoWcOHGC3r17M3/+fCIiIrj//vv5v//7P7d7pl5E8p/k1GSeX/p8emLTq1EvPvR9gqJt2pmJTWAgzJkDr72mxEakkLqhPjelS5dm0KBB/Prrr2zZsoUqVarQqVMnypYty8CBAzlowZgRIuL+ziSe4YkFT/DN3m/w8vBiwj1jGbE6Fc9ne0BcHDRoACtXwn33WR2qiFgoWx2Ko6OjWblyJStXrsTT05M2bdqwe/duatWqxTvvvJNTMYqIcODsAR6Y9wDbTm4j0DeQebdPouMrX8AHH5gFevWCb7+F8HBrAxURy7nc58Zut7No0SI++ugjVqxYQZ06dRgwYAAdOnRIHxTv22+/5ZlnnmHgwIE5HrCIFD7rotbR84eexCfHExEUwSfFu1Kl0zCIj4egIJgyBVq2tDpMEcknXE5uwsLCcDqdPP3002zdupV69epdUeaee+7RTN0ikiM+3vUxw9cMx+F00CTsVj7cfRMlPh5lbrz1Vpg1C8qWtTRGEclfXE5u3nnnHZ544gn8/PyuWiYoKIgjR45kKzARKdwcTgej143mgx1ms9MT5Vsz4cNj+Pz+lVng+efhpZfAjUZgFZGc4XJy06lTp9yIQ0QkXUJKAn0W92HVn6sAGBLYhueHr8V2MRFKloRp06BZM2uDFJF8q0BNnCki7u9E3Ak6L+zM3tN78fX0YWp0fdq+vcTcGBkJM2fC/wb6FBHJjJIbEck3dkbvpOt3XTl98TSlvQKZu7oY9bdtAZsNBg6EAQPASx9bInJt+pQQkXzhhwM/8PzS50lOTaamsySfvB9HuXNxULo0zJgBd9xhdYgiUkAouRERSxmGwbSt0xi3fhwYBi3+Dmbmp6cJSPUwE5rp06FMGavDFJECRMmNiFgmxZHCf1f8lwV/LIDUVLrvLcLIlX/jafOC/74IL7wAnp5WhykiBYySGxGxxLlL53h20bNs+WsLnknJvLHWgy577BASanYajoy0OkQRKaCU3IhInjt07hCdv+1M1N9HKHYhiXeXeNAs2tt8vHvaNPNxbxGRG6TkRkTy1Ppj6+m+qDtxF88RHnuJT5YWoXqCL7zyMvTpAx7ZmvJORETJjYjknc9/+5yhq4eSejGeRkeS+ejHQEqWKAefzDanUhARyQFKbkQk1zmcDsb8PIbZv8yCuDge2QeTNhbHt3krmDwZgoOtDlFE3IiSGxHJVRdTLtJ3SV9W7F8C58/z0g4/Bu4tju3V4dCzpzlAn4hIDlJyIyK5Jjo+ms7fdmbP0V/wuZDAlA2BtHNUgYWzoUEDq8MTETel5EZEcsVvsb/R5ev/EBt9iJIX7MxdG0zDRm3hnXegeHGrwxMRN6bkRkRy3NKDS+m3sCeXzsVS/ayNT9aXIfzF1+CZZ9QMJSK5TsmNiOQYwzCY9ctMxiwfhhEfT7OTPsyOuoXALz6AunWtDk9ECgklNyKSI+wOOy8vHcCXv3wEycl021+E0aFP47XkbQgMtDo8ESlElNyISLYlpCbQae6DbDq6Ho9UB6/tCuaZ/7wNnTurGUpE8pySGxHJliPnDjNxx4vE2k9TNNXG7IM1aD75K7j5ZqtDE5FCSsmNiNywjb8v5dl5T3HeHk/5RC8+8XyMml+8DwEBVocmIoWYJnERkRsy/9s3ePrTdlxITaDeGW++u/Udak6Zp8RGRCynOzci4hJnqp1xEx9m+rllALT9uwwPN3yZ0h012rCI5A+6cyMiWZZ48ig9XqqentgMsEUydcIfpITfZHFkIiL/0J0bEcmSmNXf0fnr//B7QCLehgdvV3+ex7tPwm63Wx2aiEgGSm5E5NocDn6d+F+6/jWN2AAnJY0izHl0LrdGPm51ZCIimVJyIyJXFxvLD0Me5YUSW0gqYlDdtxyf9FtNeEhVqyMTEbkq9bkRkUwZa9cypVc9epbeTJIX3FvuDhYN36PERkTyPd25EZGMUlNJHj+WF3eO45uqSeDlRfdGPRnx8Dt4eegjQ0TyP31Sicg/oqM50+8Znglcw7ab7Hj6F+XNtpPp1PAZqyMTEckyJTciYlq1in3De9GlwTGOF3MSGBzG+09/wZ0V77Q6MhERlyi5ESns7HYYN47ViybT+44LJPh7EVGuNp8+9RWVS1S2OjoREZcpuREpzP76C6N3Lz68uJ5RzeJxFvWnaY2WvN/uQ4KLBFsdnYjIDdHTUiKF1fLl2Fs2Z4jXWkbcmoAzOIgOTZ/jiyfmK7ERkQItXyQ3M2bMICIiAj8/P5o0acLWrVuztN+XX36JzWbj4Ycfzt0ARdyJ3Q4jRvD3c13oeOsxPq2Viq1UKUa2epMJLSfg7eltdYQiItlieXIzf/58Bg0axMiRI9mxYwd169aldevWnDp16pr7RUVF8dJLL3HnnersKJJlR4/CQw+x7/9mc3+bc6yv7E3RkHDmPvopzzV6DpsmvhQRN2B5cjNp0iR69OhBt27dqFWrFrNnz8bf3585c+ZcdR+Hw0HHjh0ZPXo0lSpVysNoRQqwH36AVq1YfnYrbduc51j5YlQsfzPfd/ielpVbWh2diEiOsbRDcUpKCtu3b2fo0KHp6zw8PGjRogWbNm266n6vvfYaZcqU4dlnn+Xnn3++5jmSk5NJTk5OX46LiwPAbrcXmgn/0q6zsFxvdrldfSUn4/H669g+/YQptROZ0CgZigfTtOKdzLx/JsFFgrN1rW5XX7lM9eU61Zlr3LW+XLkeS5ObM2fO4HA4CAkJybA+JCSEffv2ZbrP+vXr+fDDD9m1a1eWzjF27FhGjx59xfoVK1bg7+/vcswF2cqVK60OoUBxh/ryj42l7syZeJ08yuC7EllU05NUP39aBN7NU75PsWnN1f+IcJU71FdeUn25TnXmGnerr8TExCyXLVCPgsfHx9OpUyfef/99SpUqlaV9hg4dyqBBg9KX4+LiCA8Pp1WrVgQGBuZWqPmK3W5n5cqVtGzZEm9vdRa9HnepL9uiRXhOmMBfxNHxMTt7wgMoUiSAN+55g6dufirHzuMu9ZVXVF+uU525xl3rK63lJSssTW5KlSqFp6cnsbGxGdbHxsYSGhp6RfnDhw8TFRVF27Zt09c5nU4AvLy82L9/P5UrZxx0zNfXF19f3yuO5e3t7VYvelYUxmvOjgJbX0lJMGIEfPYZW8qk0P0+O2dLBlAqoAwfPvQht5a7NVdOW2DryyKqL9epzlzjbvXlyrVY2qHYx8eHhg0bsnr16vR1TqeT1atXExkZeUX5GjVqsHv3bnbt2pX+89BDD3HPPfewa9cuwsPD8zJ8kfzn0CF44AH47DM+q3qJJx51cLZ0UW4JrcPSjktzLbEREclPLG+WGjRoEF26dKFRo0Y0btyYyZMnc/HiRbp16wZA586dKVeuHGPHjsXPz49bbrklw/5BQUEAV6wXKXQWLIAhQ7AnJzLqbicf1fEEHx8eqv4Q77R+hyLeRayOUEQkT1ie3LRv357Tp08zYsQIYmJiqFevHsuWLUvvZHzs2DE8PCx/Yl0k/0pMhGHDYP58Tvs5eK69N5tDDWyevrx8+8s83/h5jV8jIoWK5ckNQL9+/ejXr1+m29auXXvNfefOnZvzAYkUFPv3w3PPwYEDbC+TSvfHfIj1dxLgE8j0NtNpVbmV1RGKiOS5fJHciIiLDAPmz4dXXsFIusRnjXwYfrsTu5eTqiWrMuehOZrRW0QKLSU3IgXNxYvw8svwzTckexgMfaI4X5Y/Dx4ePFD1Ad657x0CfAKsjlJExDJKbkQKkj/+gJ494c8/OVEMuncJ5lff83jYvHjlzlfo3ai3+teISKGn5EakIDAM+OwzePVVSElh/c3F6HVfKuc4T3CRYGY/MJs7K2oSWRERUHIjkv/Fx8N//wuLFmFgMOvRCrwZcRwnUDukNh8+9CHlA8tbHaWISL6h5EYkP9u923waKiqKi34eDOp1E997Hgag/c3tGdtiLH5efhYHKSKSvyi5EcmPDAPmzoVRo8BuZ1/1kvR41IvDKYfx9vTmtWav0bluZ/WvERHJhJIbkfwmLg4GDYIlSwD46tHqDKl8hKSUFEIDQnmv7Xs0KtvI4iBFRPIvJTci+cnOndCrFxw/ziU/T4b1rcmX/A5OuDvibqbfP52S/iWtjlJEJF9TciOSHxgGvP8+jBkDdjt/1gihx2M+7E36HQ+bBy81fYkXmryAh01TkYiIXI+SGxGrnT8P/fvDypUALHq8Ni9WPsTFpEuULlqaGW1mcEeFO6yNUUSkAFFyI2KlbdvMZqiTJ0nx82b0C3X4yLEdUiEyPJKZbWYSEhBidZQiIgWKkhsRKzidMHs2jB0LDgdHa4bR6wl/fr24HYAXmrzAS01fwstD/0VFRFylT06RvHb2rNkM9eOPACxsX5fBNx0k4WI0QX5BTLt/Gs0rNbc4SBGRgkvJjUhe2rLFbIaKjeViUW+G96vF/NRfwQ63lruVmW1mUi6wnNVRiogUaEpuRPKC0wnTpsGECeB08nvdMHo9CH8m/YqHzYMBtw1gwG0D1AwlIpID9EkqkttOn4bnn4effsLA4IP/1OKN0IPYk1IJDQhlRpsZRIZHWh2liIjbUHIjkpvWr4d+/eDUKc4G+TCgRzirnXvBgNZVWjOp1SSCiwRbHaWIiFtRciOSGxwOmDwZJk0Cw+CnxiG8cE8Sp1IP4+Ppw6hmo+hSt4vmhhIRyQVKbkRyWmws9O0LGzdyydNgTKeKzClxFFJtVCtZjVkPzKJm6ZpWRyki4raU3IjkpHXrzGaos2f5rawn/doX45DHMcBG13pdefWuVyniXcTqKEVE3JqSG5GckJoKEyfCtGmk4mR6i2JMqp1Aqsd5yhQtwzut3+Gem+6xOkoRkUJByY1IdkVHQ58+sGULUQGpPP9UINuLJwDwQNUHGN9yvDoNi4jkISU3ItmxejW88ALG3+f4rLbBqGaeXPJJpJhvMcbcO4bHaj6mTsMiInlMyY3IjbDb4a23YOZMov0d/PdRT36s4ARPD5qGN2XKfVM00rCIiEWU3Ii46sQJ6NULY/s2vqiSxOh7PYgv5om3px+v3PEKPRr2wMPmYXWUIiKFlpIbEVesWAH9+/NX6jleuu8SP1XxBl9fGoQ1YFLrSVQrWc3qCEVECj0lNyJZYbfDG2/gfP89Pqt6ideb2rkYHICvrz8v3/4yPRr0wNPD0+ooRUQEJTci13fsGPTqxdFD23ipRTwbKntBQHEal2vMpNaTqBRcyeoIRUTkMkpuRK5l8WIcLw1ibmgsb7ZL5FJwMfyKFmfYncPoVr+b+taIiORDSm5EMuFht+Px6qvs+f5D/ts0nl2hQFAJIiveztut3iYiKMLqEEVE5CqU3Ij8W1QUtce+xhthR/igTSKOgKIElgjjlbuG8Z86/9HdGhGRfE7JjcjlvvuOtRP7MKRJLNGBNigezEO1H2d0s9GEBIRYHZ2IiGSBkhsRgKQkYke8yKvHPuKHyGScnp6El6/FuPvfpnml5lZHJyIiLlByI4We/eA+Phr1MBPLHCKhgoFn0WLcG9KGGZ1nUdy/uNXhiYiIi5TcSKG24ZMxDN/0BvvLpYCHB/XKN+LNR2dz9Jej+Hv7Wx2eiIjcACU3UihFn/6T0e88zKLUPVAMgj0DeKXNWJ6+oxeOVAdHOWp1iCIicoOU3EihkuJI4b0lr/POholccqbgYUDnEvcw+IX5BBUtCYADh8VRiohIdii5kULBMAxWHV7J6G9e4M+zh8AwaBQXwJuPzuCWVv+xOjwREclB+WLAjhkzZhAREYGfnx9NmjRh69atVy37/vvvc+eddxIcHExwcDAtWrS4ZnmRPaf20P7Lx+jyySP8eeYgpS/ZmHo+ku9eP6TERkTEDVme3MyfP59BgwYxcuRIduzYQd26dWndujWnTp3KtPzatWt5+umnWbNmDZs2bSI8PJxWrVpx4sSJPI5c8rvYhFgGLR9Eq7n3sn73YrwTk+m7N4Cfq4zh8dk/YStd2uoQRUQkF1ie3EyaNIkePXrQrVs3atWqxezZs/H392fOnDmZlv/888/p06cP9erVo0aNGnzwwQc4nU5Wr16dx5FLfnXJfol3Nr3D7XNu58tfPsI4e5aHDnvx86YaDHt1JYEvDAYPy9/6IiKSSyztc5OSksL27dsZOnRo+joPDw9atGjBpk2bsnSMxMRE7HY7JUqUyHR7cnIyycnJ6ctxcXEA2O127HZ7NqIvONKu092vN9WZyjf7vmHiponEJkRDXDwN/3IwclswDeq0xvHN29hLlIDr1ENhqa+covpyjerLdaoz17hrfblyPTbDMIxcjOWaTp48Sbly5di4cSORkZHp6wcPHsy6devYsmXLdY/Rp08fli9fzp49e/Dz87ti+6hRoxg9evQV6+fNm4e/v8YxcQeGYbA9fjvfxn7LyeSTeDgcVDiTwisbPLn/mB+HHnucqNatdbdGRKQAS0xMpEOHDly4cIHAwMBrli3QT0uNGzeOL7/8krVr12aa2AAMHTqUQYMGpS/HxcWl99O5XuW4C7vdzsqVK2nZsiXe3t5Wh5OjNhzfwPiN49l1ahfYIBQ/+m1I4pk9QfiElsPxwwxqNWhALReO6c71lRtUX65RfblOdeYad62vtJaXrLA0uSlVqhSenp7ExsZmWB8bG0toaOg19504cSLjxo1j1apV1KlT56rlfH198fX1vWK9t7e3W73oWeFO17wrZhdv/vwm64+tB8Df04+eR0vR65tjBNr9oHVreOcdPIKCbvgc7lRfeUH15RrVl+tUZ65xt/py5VosvU/v4+NDw4YNM3QGTuscfHkz1b+NHz+e119/nWXLltGoUaO8CFXyiT2n9vDsd8/S5vM2rD+2Hm9Pb54p+wCbvglm8Py/CMQXXnsN5syBbCQ2IiJScFneLDVo0CC6dOlCo0aNaNy4MZMnT+bixYt069YNgM6dO1OuXDnGjh0LwFtvvcWIESOYN28eERERxMTEABAQEEBAQIBl1yG56/dTvzNp0ySWHVoGgM1m4/Gaj/HS0XKED5lpdhKuUAFmz4Z69awNVkRELGV5ctO+fXtOnz7NiBEjiImJoV69eixbtoyQkBAAjh07hsdlHUFnzZpFSkoKjz/+eIbjjBw5klGjRuVl6JIHdsfu5u1Nb7Pi8ArATGraVW/HgFrPUG30dFjxf2bBBx+EiROhkPSjEhGRq7M8uQHo168f/fr1y3Tb2rVrMyxHRUXlfkBiuV9jfmXS5kmsPLwSAA+bh5nU3DaAqlFx8GQvOHECvL1h9Gjo0gVsNoujFhGR/CBfJDciYD7Svf7Yeqb/Mp2fj/4MmEnNIzUeYcBtA6gcdJPZ7DRuHKSmQkQEvPce3HKLtYGLiEi+ouRGLOdwOlh8cDEzf5nJb7G/AeDp4Zme1FQKrgTnzpl3Z9I6nz/8MIwfD+pnJSIi/6LkRiyTnJrMV3u+Yta2WUSdjwLAz8uPjrU78lyj5ygfWN4suGUL9O4NMTHg6wtvvAEdOqgZSkREMqXkRvLc6Yun+eTXT/jkt084ffE0AEF+QTxb/1m61e9GiSL/m0rD6YTp02HCBHA4oHJlsxmqZk0LoxcRkfxOyY3kmd9P/c4HOz7g233fYneYc4SULVaW3o1683Ttp/H3vmw6jDNnoF8/+Oknc/nxx2HsWCha1ILIRUSkIFFyI7nK4XSw/PByPtjxAZv/2py+vmHZhnSv3502Vdvg7fmvUSc3bIC+feHUKfDzM5Oa9u3zOHIRESmolNxIrjh98TTz98zn098+5fiF4wB4eXjxYLUH6d6gOw3CGly5k8MBkyfDO++YTVLVq8O770K1ankbvIiIFGhKbiTHGIbBhuMb+PTXT1l2eFl601NwkWA61elE13pdCQ24ypxhsbHw/POw3pwriqefNjsOFymSR9GLiIi7UHIj2Xbu0jm+2vMVn/72KUf+PpK+vkFYAzrV6US7Gu3w88p81nbA7FfTr5/Zz8bf33zE+9FH8yByERFxR0pu5IY4DScbj2/ki91f8MPBH9Lv0gT4BPBYzcfoVLcTtUrXuvZBUlPh7bdh6lQwDPMpqPfeM5+KEhERuUFKbsQlR/4+woI/FrDgjwWciDuRvr5OSB061enEwzUepqhPFp5oio6GPn3MMWwAOneGUaPMDsQiIiLZoORGrisuOY5F+xfx1Z6v2HZyW/r6QN9AHqr+EB1rd6RuaN2sH/DHH83+NX//bY4wPHEiPPRQLkQuIiKFkZIbyZTdYWdt1Fq+3vs1yw4tI8WRAphzPTWLaMaTNz9Jq8qtrt2X5oqD2uGtt2DmTHO5dm3zaaiIiJy/ABERKbSU3Ei6VGcqG49vZOG+hSw9tJQLSRfSt1UvVZ0naj3BYzUfIyQgxPWDnzgBvXrB9u3m8jPPwIgR4OOTQ9GLiIiYlNwUck7DyZa/trBo/yJ+OPgDZxPPpm8rU7QMD1Z7kCdvfpLaZWpju9G5nFasgP794cIFCAyESZOgTZscugIREZGMlNwUQqnOVLb8tYWlh5ay+OBiYhNi07cFFwnmwaoP8lD1h7it/G14enje+InsdhgzxnwCCqBePZg9GypUyN4FiIiIXIOSm0Ii2ZnMssPLWHVkFSv+XJGhySnQN5D7q9xPuxrtuD389iunQ7gRx46ZM3nv3GkuP/ccvPIKeOfAsUVERK5ByY0bO5t4llV/rmLxgcUs378czz//uQtTokgJWlZqSZuqbbg74m58PHOw78uSJTBoEMTFQfHi5jg2LVvm3PFFRESuQcmNG3E4Hfwa+ytrjqzhx6gf2RWzC8MwALA77UQERtCmahvuq3Ifjco2yl6TU2ZSUmD0aPjoI3O5YUOzGapcuZw9j4iIyDUouSngzl06x9qotfx45EfWRK3h70t/Z9h+S5lbaHlTS4qcKELPR3rik1tPJ0VFmU1Pu3eby336wMsvqxlKRETynJKbAuaS/RLbTm5j/bH1rD++PsPdGTD7z9xV8S7uvele7om4h5CAEOx2O0uWLLnxp52uZ9EieOklSEiAEiXMZqh7782dc4mIiFyHkpt8zu6wsytmF+uPrWfD8Q38cvKX9Hmc0tQqXYt7b7qXe2+6l4ZhDXOmQ3BWJCXByJHw6afmcpMmMGsWhF5l5m8REZE8oOQmn7E77PwW+xtbT2xlw/ENbP5rM4n2xAxlQgNCubPCndxR4Q7urHgnoQEWJBOHD0PPnrB3L9hs5jg2gwaBl95SIiJiLX0TWSwuOY7tJ7ez9cRWtp7cyo7oHSSnJmcoE1wkmDvC7+D2CrdzZ4U7iQiKyL0mpqz4+muzP01iIpQqBdOnw113WRePiIjIZZTc5CHDMDh64Si7Ynbxy4lf2HJiC3vP7M3QZwbMZKZxucbcVu427qx4JzVK1cDD5mFR1Je5dAmGDYMvvzSXb7/dTGxCbmA6BhERkVyi5CYXnbp4il9jfmVnzE52xexiV8wuziedv6JcRFAETco14dZyt9K4XGMqB1e29s5MZg4cMJ+G2r/fbIYaNAgGDADPHH6cXEREJJuU3OSQRHsiO6PNJCYtmTkZf/KKcj6ePtxS5hYahjWkcbnG3FruVsoULWNBxC6YPx+GDjU7EJcpAzNmmHdtRERE8iElNzlkw7ENdFnYJcM6m81GtZLVqBdSj3qh9agfVp+apWrm3dNM2XXxojllwoIF5vLdd8O0aWY/GxERkXxKyU0OqRdaj/KB5akfWp+6oXWpH1qf2iG1CfAJsDq0G7N3r9kMdegQeHjA4MHQr5/5u4iISD6m5CaHlC5amq09tlodRvYZBsybB8OHQ3KyOWbNrFnmGDYiIiIFgJIb+Ud8vHmH5rvvzOXmzWHKFHPUYRERkQJCyY2Yfv/dHJQvKsociG/IEOjVS81QIiJS4Ci5KewMAz7+2JxGwW43Z/CePduc0VtERKQAUnJTmMXFmRNe/vCDudyqFUyeDEFBVkYlIiKSLUpuCqtdu8xmp2PHwNvb7EDcvbs5QJ+IiEgBpuSmsDEM+PBDeP11sxmqQgWzGapePasjExERyRFKbgqT8+fNp6GWLzeXH3gA3n4bAgMtDUtERCQnKbkpJIofOoTn66/DyZNmM9SoUdC1q5qhRETE7Si5cXdOJx7vvkvjceOweXtDRAS89x7ccovVkeVbDof576JFcOYMlC5tjmXYpEnGeUIdDtiyBWJi4PRpc1aKsLCM5dLKnDplTsv172Nc7fyu7pOda3XHc91IHNeKL6diTzsOmP9GRrp+nPxSjyL5mpEPTJ8+3ahYsaLh6+trNG7c2NiyZcs1y3/11VdG9erVDV9fX+OWW24xFi9enOVzXbhwwQCMCxcuZDfs/O/sWcPo1MlwhoUZl4KDjdSePQ0jLs7qqPK1xYsNo0mTFGPhwoWGv3+KAYZhsxlGkSKGUa+euT2tXL165nqbzci0XFqZYsUMw9/f/PfyY1zt/K7uk51rzYlzpaSY9ZWSkpLr58quq8UxatTV48up2NOOU7q0WV+lS6e4fJz8Uo95LSvvMfmHu9aXK9/flic3X375peHj42PMmTPH2LNnj9GjRw8jKCjIiI2NzbT8hg0bDE9PT2P8+PHGH3/8YQwfPtzw9vY2du/enaXzFZrkZssWw2jQwDDCwgxnRISxbcAAIyU52eqo8rXFiw0jONgwgoLMD4YiRVLSExcwDF9fc/uoUea/vr7/bLs8wfH1NYyAAPPH398wSpUyjJAQ819/f3PfzL6M0s7vyj7ZvdacONf1Pkjz8rqu5Wpx+Pr+87r9O74beR2vd+7y5c36Kl8+xaXj5Jd6tIK7flnnFnetL1e+vy0ffnbSpEn06NGDbt26UatWLWbPno2/vz9z5szJtPyUKVO47777+O9//0vNmjV5/fXXadCgAdOnT8/jyPMpp9OcufuxxyA6GipXJvW77/irWTP1r7kGhwOGDYOkpH+apWw288fDw/w3NdXc/tZb5rRbqakZt9tsZqqTmmpOqH7xotlX29vbLOPtbS4nJ5tP3qed5/LzJydnfZ/sXqu7netG4vDyMrelvW6Xx1esmOuvY1bPDa4dJ7/Uo0hBYWmfm5SUFLZv387QoUPT13l4eNCiRQs2bdqU6T6bNm1i0KBBGda1bt2ahQsXZlo+OTmZ5OTk9OW4uDgA7HY7drs9m1eQz5w5g+eAAdh+/hkA56OP4nzjDew+PnDkiPtdbw7asgVOnDC/KFJTzXry97dnyAcNA/z9zS+7okXNdf/OF9Pu5aTx9AQfn4xlvLzgr79g06Z/5iNNO3+JEv98+V1vn+xea06dK+19ldn7Ky+v61quFkdKivn6pL1GHh7//J6SAkWKmK9nVl/HrJzb19esp7R/s3Kc/FKPVrnWe0yu5K715cr12Azj8o/ivHXy5EnKlSvHxo0biYyMTF8/ePBg1q1bx5a0nneX8fHx4eOPP+bpp59OXzdz5kxGjx5NbGzsFeVHjRrF6NGjr1g/b948/P39c+hKrBe8bx913n0Xv/Pncfj48EenTpy8/XbdrREREbeQmJhIhw4duHDhAoHXGcLE7Z+WGjp0aIY7PXFxcYSHh9OqVavrVk6B4HDgMW0aHtOmgdOJUbs2jhkzqFe9OvX+V8Rut7Ny5UpatmyJd2Z/9glbtsCjj5p/uaem2vnww5V0796SS5f+qa/L79wEBJj/Xu/OTYkSV/7Fb7ebzQjffJPxzs2jj4Kvb+Z/mWe2T3avNafOda33V15e17VcLY6UFPj773+Wg4Mz3rn5+2/z9czq65iVc/v62hk3biVDhrQkOdk7S8fJL/VoFX2GucZd6yut5SUrLE1uSpUqhaen5xV3XGJjYwkNDc10n9DQUJfK+/r64uvre8V6b2/vgv+inzoF/frB+vXm8lNPYRszBo8iRTIt7hbXnEsiI805Q/fvN2/xAyQmepOUZNaXYZiJT1ricvGi+WXidP6T4KQlNp6e5now+0AkJf1zHsMwp/SqXj3jY8Bp5z9wwGwa+3dzWGb7ZPdac/pcmb2/8vK6ruVqcRiGmcSkpv7zuqW9Xk4nXLpk/p7V1zEr506TnOzNpUveWTpOfqlHq+kzzDXuVl+uXIulHYp9fHxo2LAhq1evTl/ndDpZvXp1hmaqy0VGRmYoD7By5cqrlndbP/8MLVqYiY2/v9mJeNIks5OAuMzTE8aMAT+/f74c0pIVp9P818vL3P7yy+Zf0F5eGbcbhvml4+Vl9skpWtT80rHbzTJ2u7ns6wtvvJHxSyjt/L6+Wd8nu9fqbue6kTjSkpq01+3y+OLjXX8ds3pucO04+aUeRQqMXH926zq+/PJLw9fX15g7d67xxx9/GD179jSCgoKMmJgYwzAMo1OnTsaQIUPSy2/YsMHw8vIyJk6caOzdu9cYOXJk4XoU3G43jLfeMoyyZQ0jLMww7r3XMA4evOYu7vpYYG7IbJwbDw9z/Jr69bM2zk1auczGJLn8GFc7v6v7ZOdac+JcNzrOTW5d17VcLY7MxrnJzut4rXNfPs6Nq8fJL/WY1/QZ5hp3rS9Xvr8t7VCcZvr06UyYMIGYmBjq1avH1KlTafK/huNmzZoRERHB3Llz08svWLCA4cOHExUVRdWqVRk/fjxt2rTJ0rni4uIoXrx4ljok5TsxMdCnD2zebC536gSjR5u3E67BbrezZMkS2rRp41a3KHNLUpKd5cuXkJrahjNnvDVC8XVk9f2VX0bWtXqE4k2b7Jw9u4SSJdsQGemtEYqzQJ9hrnHX+nLl+ztfdCju168f/fr1y3Tb2rVrr1j3xBNP8MQTT+RyVPnMmjXw/PNw7pzZm3XCBGjXzuqo3FLaF8VDD2XeefPyck2bXv9Y1yuTE/vcKHc9143Eca34cip2T08zGVmy5MaTkvxSjyL5Wb5IbuQa7HYYPx5mzDCXb7nFnBsqIsLSsERERPIrJTf52YkT0Ls3bNtmLnfrBiNGmL0HRUREJFNKbvKrlSuhf384f9589vPtt+GBB6yOSkREJN9TcpPf2O3w5pvw7rvmcr16MGsWVKxoaVgiIiIFhZKb/OTYMbMZaudOc7lnT3O2PDfq7S4iIpLblNzkF0uXwsCB5ohcxYvDlCnQqpXVUYmIiBQ4Sm6slpICr70Gc+aYyw0bms1Q5ctbG5eIiEgBpeTGSlFR0KsX/Pabudynjzm2v5qhREREbpiSG6ssWgQvvQQJCeZUxFOnQvPmVkclIiJS4Cm5yWvJyTByJHzyibncuLHZDBUWZm1cIiIibkLJTV7680/zCag//jCnIX7hBXjxRXM6YhEREckR+lbNK998A4MHQ2IilCxpTqdw111WRyUiIuJ2lNzktkuXYPhw+OILc/n222H6dAgJsTYuERERN6XkJjcdOADPPQf795vNUIMGwYABNzYVsIiIiGSJkpvcMn8+vPKKeeemTBmzGer2262OSkRExO0puclpFy+aSc2CBebyXXfBtGlQurS1cYmIiBQSSm5y0t69ZjPUoUPg4WF2IO7Xz/xdRERE8oSSm5yyYoWZ2CQnQ2ioOXZNkyZWRyUiIlLoKLnJKbVqgZ+f2a9m6lQoUcLqiERERAolJTc5pXx5WLwYIiLUDCUiImIhJTc5qVIlqyMQEREp9HSLQURERNyKkhsRERFxK0puRERExK0ouRERERG3ouRGRERE3IqSGxEREXErSm5ERETErSi5EREREbei5EZERETcipIbERERcStKbkRERMStKLkRERERt6LkRkRERNxKoZsV3DAMAOLi4iyOJO/Y7XYSExOJi4vD29vb6nDyPdWXa1RfrlF9uU515hp3ra+07+207/FrKXTJTXx8PADh4eEWRyIiIiKuio+Pp3jx4tcsYzOykgK5EafTycmTJylWrBg2m83qcPJEXFwc4eHhHD9+nMDAQKvDyfdUX65RfblG9eU61Zlr3LW+DMMgPj6esmXL4uFx7V41he7OjYeHB+XLl7c6DEsEBga61Rs9t6m+XKP6co3qy3WqM9e4Y31d745NGnUoFhEREbei5EZERETcipKbQsDX15eRI0fi6+trdSgFgurLNaov16i+XKc6c43qqxB2KBYRERH3pjs3IiIi4laU3IiIiIhbUXIjIiIibkXJjYiIiLgVJTdubsaMGURERODn50eTJk3YunWr1SHlGz/99BNt27albNmy2Gw2Fi5cmGG7YRiMGDGCsLAwihQpQosWLTh48KA1weYDY8eO5dZbb6VYsWKUKVOGhx9+mP3792cok5SURN++fSlZsiQBAQE89thjxMbGWhSxtWbNmkWdOnXSB1KLjIxk6dKl6dtVV9c2btw4bDYbAwYMSF+nOvvHqFGjsNlsGX5q1KiRvr2w15WSGzc2f/58Bg0axMiRI9mxYwd169aldevWnDp1yurQ8oWLFy9St25dZsyYken28ePHM3XqVGbPns2WLVsoWrQorVu3JikpKY8jzR/WrVtH37592bx5MytXrsRut9OqVSsuXryYXmbgwIF8//33LFiwgHXr1nHy5EkeffRRC6O2Tvny5Rk3bhzbt29n27Zt3HvvvbRr1449e/YAqqtr+eWXX3j33XepU6dOhvWqs4xuvvlmoqOj03/Wr1+fvq3Q15Uhbqtx48ZG375905cdDodRtmxZY+zYsRZGlT8Bxrfffpu+7HQ6jdDQUGPChAnp686fP2/4+voaX3zxhQUR5j+nTp0yAGPdunWGYZj14+3tbSxYsCC9zN69ew3A2LRpk1Vh5ivBwcHGBx98oLq6hvj4eKNq1arGypUrjbvvvtvo37+/YRh6f/3byJEjjbp162a6TXVlGLpz46ZSUlLYvn07LVq0SF/n4eFBixYt2LRpk4WRFQxHjhwhJiYmQ/0VL16cJk2aqP7+58KFCwCUKFECgO3bt2O32zPUWY0aNahQoUKhrzOHw8GXX37JxYsXiYyMVF1dQ9++fXnggQcy1A3o/ZWZgwcPUrZsWSpVqkTHjh05duwYoLqCQjhxZmFx5swZHA4HISEhGdaHhISwb98+i6IqOGJiYgAyrb+0bYWZ0+lkwIAB3H777dxyyy2AWWc+Pj4EBQVlKFuY62z37t1ERkaSlJREQEAA3377LbVq1WLXrl2qq0x8+eWX7Nixg19++eWKbXp/ZdSkSRPmzp1L9erViY6OZvTo0dx55538/vvvqiuU3IjIDejbty+///57hjZ+uVL16tXZtWsXFy5c4P/+7//o0qUL69atszqsfOn48eP079+flStX4ufnZ3U4+d7999+f/nudOnVo0qQJFStW5KuvvqJIkSIWRpY/qFnKTZUqVQpPT88resfHxsYSGhpqUVQFR1odqf6u1K9fP3744QfWrFlD+fLl09eHhoaSkpLC+fPnM5QvzHXm4+NDlSpVaNiwIWPHjqVu3bpMmTJFdZWJ7du3c+rUKRo0aICXlxdeXl6sW7eOqVOn4uXlRUhIiOrsGoKCgqhWrRqHDh3S+wslN27Lx8eHhg0bsnr16vR1TqeT1atXExkZaWFkBcNNN91EaGhohvqLi4tjy5Ythbb+DMOgX79+fPvtt/z444/cdNNNGbY3bNgQb2/vDHW2f/9+jh07Vmjr7N+cTifJycmqq0w0b96c3bt3s2vXrvSfRo0a0bFjx/TfVWdXl5CQwOHDhwkLC9P7C/S0lDv78ssvDV9fX2Pu3LnGH3/8YfTs2dMICgoyYmJirA4tX4iPjzd27txp7Ny50wCMSZMmGTt37jSOHj1qGIZhjBs3zggKCjK+++4747fffjPatWtn3HTTTcalS5csjtwavXv3NooXL26sXbvWiI6OTv9JTExML9OrVy+jQoUKxo8//mhs27bNiIyMNCIjIy2M2jpDhgwx1q1bZxw5csT47bffjCFDhhg2m81YsWKFYRiqq6y4/Gkpw1CdXe7FF1801q5daxw5csTYsGGD0aJFC6NUqVLGqVOnDMNQXSm5cXPTpk0zKlSoYPj4+BiNGzc2Nm/ebHVI+caaNWsM4IqfLl26GIZhPg7+6quvGiEhIYavr6/RvHlzY//+/dYGbaHM6gowPvroo/Qyly5dMvr06WMEBwcb/v7+xiOPPGJER0dbF7SFnnnmGaNixYqGj4+PUbp0aaN58+bpiY1hqK6y4t/JjersH+3btzfCwsIMHx8fo1y5ckb79u2NQ4cOpW8v7HVlMwzDsOaekYiIiEjOU58bERERcStKbkRERMStKLkRERERt6LkRkRERNyKkhsRERFxK0puRERExK0ouRERERG3ouRGRERE3IqSGxEREXErSm5ExK1ER0fToUMHqlWrhoeHBwMGDLA6JBHJY0puRMStJCcnU7p0aYYPH07dunWtDkdELKDkRkQKlNOnTxMaGsqbb76Zvm7jxo34+PiwevVqIiIimDJlCp07d6Z48eIWRioiVvGyOgAREVeULl2aOXPm8PDDD9OqVSuqV69Op06d6NevH82bN7c6PBHJB5TciEiB06ZNG3r06EHHjh1p1KgRRYsWZezYsVaHJSL5hJqlRKRAmjhxIqmpqSxYsIDPP/8cX19fq0MSkXxCyY2IFEiHDx/m5MmTOJ1OoqKirA5HRPIRNUuJSIGTkpLCf/7zH9q3b0/16tXp3r07u3fvpkyZMlaHJiL5gJIbESlwhg0bxoULF5g6dSoBAQEsWbKEZ555hh9++AGAXbt2AZCQkMDp06fZtWsXPj4+1KpVy8KoRSSv2AzDMKwOQkQkq9auXUvLli1Zs2YNd9xxBwBRUVHUrVuXcePG0bt3b2w22xX7VaxYUc1XIoWEkhsRERFxK+pQLCIiIm5FyY2IiIi4FSU3IiIi4laU3IiIiIhbUXIjIiIibkXJjYiIiLgVJTciIiLiVpTciIiIiFtRciMiIiJuRcmNiIiIuBUlNyIiIuJW/h/HhgzER89whQAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "\n", + "plt.scatter(\n", + " mortgageDf[\"x1\"],\n", + " mortgageDf[\"y\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.plot(\n", + " x,\n", + " lREq,\n", + " color='red',\n", + " alpha=0.9,\n", + " label='lREq',\n", + ")\n", + "\n", + "plt.plot(\n", + " x,\n", + " logREq,\n", + " color='green',\n", + " alpha=0.9,\n", + " label='logREq',\n", + ")\n", + "\n", + "plt.xlabel('x1')\n", + "plt.ylabel('y')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "NqT4-52vZyo-", + "outputId": "96763409-58d1-4435-bc54-afcf8fc9d05f" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1predict2
0116.3549.940.7298710.850564
1134.4356.161.2311620.994966
2139.1936.890.8230780.923739
3123.5856.881.0453490.981132
4029.9227.050.3942580.375201
5125.2644.380.7541140.875451
6136.5148.981.0848830.986447
7111.7055.550.7871770.892025
8032.2131.280.5466660.634794
9128.7435.630.5936560.702665
10118.2839.500.4965580.534624
11010.1231.390.1333370.082606
12010.3929.470.0888290.062198
13021.4629.340.2940270.223902
14133.5640.370.8069020.913332
15137.9122.920.4381060.458048
16131.8147.560.9596560.967716
17025.8844.580.7709600.887885
18138.4047.851.0913010.987144
19026.6225.500.2920490.225940
20014.3621.87-0.0326920.028410
21122.2220.790.0874910.065109
22132.1051.561.0684430.984517
23011.7532.960.2046000.129233
24110.3248.590.5813960.664852
25011.4334.780.2455840.164303
26012.5833.270.2282450.149244
27027.5325.630.3125510.252476
28136.7137.050.7804890.899188
29017.8526.860.1619550.102289
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1 predict2\n", + "0 1 16.35 49.94 0.729871 0.850564\n", + "1 1 34.43 56.16 1.231162 0.994966\n", + "2 1 39.19 36.89 0.823078 0.923739\n", + "3 1 23.58 56.88 1.045349 0.981132\n", + "4 0 29.92 27.05 0.394258 0.375201\n", + "5 1 25.26 44.38 0.754114 0.875451\n", + "6 1 36.51 48.98 1.084883 0.986447\n", + "7 1 11.70 55.55 0.787177 0.892025\n", + "8 0 32.21 31.28 0.546666 0.634794\n", + "9 1 28.74 35.63 0.593656 0.702665\n", + "10 1 18.28 39.50 0.496558 0.534624\n", + "11 0 10.12 31.39 0.133337 0.082606\n", + "12 0 10.39 29.47 0.088829 0.062198\n", + "13 0 21.46 29.34 0.294027 0.223902\n", + "14 1 33.56 40.37 0.806902 0.913332\n", + "15 1 37.91 22.92 0.438106 0.458048\n", + "16 1 31.81 47.56 0.959656 0.967716\n", + "17 0 25.88 44.58 0.770960 0.887885\n", + "18 1 38.40 47.85 1.091301 0.987144\n", + "19 0 26.62 25.50 0.292049 0.225940\n", + "20 0 14.36 21.87 -0.032692 0.028410\n", + "21 1 22.22 20.79 0.087491 0.065109\n", + "22 1 32.10 51.56 1.068443 0.984517\n", + "23 0 11.75 32.96 0.204600 0.129233\n", + "24 1 10.32 48.59 0.581396 0.664852\n", + "25 0 11.43 34.78 0.245584 0.164303\n", + "26 0 12.58 33.27 0.228245 0.149244\n", + "27 0 27.53 25.63 0.312551 0.252476\n", + "28 1 36.71 37.05 0.780489 0.899188\n", + "29 0 17.85 26.86 0.161955 0.102289" + ] + }, + "execution_count": 85, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 86, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 990 + }, + "id": "jLJD6VGqY1Xc", + "outputId": "dacd3002-ceb1-4b40-e315-9adba673b28b" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1predict2yHat2
0116.3549.940.7298710.8505641
1134.4356.161.2311620.9949661
2139.1936.890.8230780.9237391
3123.5856.881.0453490.9811321
4029.9227.050.3942580.3752010
5125.2644.380.7541140.8754511
6136.5148.981.0848830.9864471
7111.7055.550.7871770.8920251
8032.2131.280.5466660.6347941
9128.7435.630.5936560.7026651
10118.2839.500.4965580.5346241
11010.1231.390.1333370.0826060
12010.3929.470.0888290.0621980
13021.4629.340.2940270.2239020
14133.5640.370.8069020.9133321
15137.9122.920.4381060.4580480
16131.8147.560.9596560.9677161
17025.8844.580.7709600.8878851
18138.4047.851.0913010.9871441
19026.6225.500.2920490.2259400
20014.3621.87-0.0326920.0284100
21122.2220.790.0874910.0651090
22132.1051.561.0684430.9845171
23011.7532.960.2046000.1292330
24110.3248.590.5813960.6648521
25011.4334.780.2455840.1643030
26012.5833.270.2282450.1492440
27027.5325.630.3125510.2524760
28136.7137.050.7804890.8991881
29017.8526.860.1619550.1022890
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1 predict2 yHat2\n", + "0 1 16.35 49.94 0.729871 0.850564 1\n", + "1 1 34.43 56.16 1.231162 0.994966 1\n", + "2 1 39.19 36.89 0.823078 0.923739 1\n", + "3 1 23.58 56.88 1.045349 0.981132 1\n", + "4 0 29.92 27.05 0.394258 0.375201 0\n", + "5 1 25.26 44.38 0.754114 0.875451 1\n", + "6 1 36.51 48.98 1.084883 0.986447 1\n", + "7 1 11.70 55.55 0.787177 0.892025 1\n", + "8 0 32.21 31.28 0.546666 0.634794 1\n", + "9 1 28.74 35.63 0.593656 0.702665 1\n", + "10 1 18.28 39.50 0.496558 0.534624 1\n", + "11 0 10.12 31.39 0.133337 0.082606 0\n", + "12 0 10.39 29.47 0.088829 0.062198 0\n", + "13 0 21.46 29.34 0.294027 0.223902 0\n", + "14 1 33.56 40.37 0.806902 0.913332 1\n", + "15 1 37.91 22.92 0.438106 0.458048 0\n", + "16 1 31.81 47.56 0.959656 0.967716 1\n", + "17 0 25.88 44.58 0.770960 0.887885 1\n", + "18 1 38.40 47.85 1.091301 0.987144 1\n", + "19 0 26.62 25.50 0.292049 0.225940 0\n", + "20 0 14.36 21.87 -0.032692 0.028410 0\n", + "21 1 22.22 20.79 0.087491 0.065109 0\n", + "22 1 32.10 51.56 1.068443 0.984517 1\n", + "23 0 11.75 32.96 0.204600 0.129233 0\n", + "24 1 10.32 48.59 0.581396 0.664852 1\n", + "25 0 11.43 34.78 0.245584 0.164303 0\n", + "26 0 12.58 33.27 0.228245 0.149244 0\n", + "27 0 27.53 25.63 0.312551 0.252476 0\n", + "28 1 36.71 37.05 0.780489 0.899188 1\n", + "29 0 17.85 26.86 0.161955 0.102289 0" + ] + }, + "execution_count": 86, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf['yHat2'] = mortgageDf['predict2'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "mortgageDf" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "HR8tECzUY1NR" + }, + "source": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "FRq8XsHGYvyA" + }, + "source": [ + "Hold-out" + ] + }, + { + "cell_type": "code", + "execution_count": 87, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "ugSmcm30aIO2", + "outputId": "d71903ab-b450-476a-b05f-9f5230920e9e" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1predict2yHat2
0116.3549.940.7298710.8505641
11010.1231.390.1333370.0826060
6136.5148.981.0848830.9864471
24110.3248.590.5813960.6648521
17025.8844.580.7709600.8878851
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1 predict2 yHat2\n", + "0 1 16.35 49.94 0.729871 0.850564 1\n", + "11 0 10.12 31.39 0.133337 0.082606 0\n", + "6 1 36.51 48.98 1.084883 0.986447 1\n", + "24 1 10.32 48.59 0.581396 0.664852 1\n", + "17 0 25.88 44.58 0.770960 0.887885 1" + ] + }, + "execution_count": 87, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.model_selection import train_test_split\n", + "# Split the data into train and test sets\n", + "# trainSet, testSet = train_test_split(wagesDf, test_size=0.15, random_state=55)\n", + "trainSet, testSet = train_test_split(mortgageDf, test_size=0.15)\n", + "\n", + "trainSet.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "8gQc9YQqaQ0G", + "outputId": "6a67b0ce-9f65-4711-8b45-d27929aad16b" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "((30, 6), (25, 6), (5, 6))" + ] + }, + "execution_count": 88, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "mortgageDf.shape, trainSet.shape, testSet.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 89, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "4Lz67KCiaQtC", + "outputId": "4dbed20d-28d4-470a-d898-df6f4cd557d7" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.379717\n", + " Iterations 7\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 25\n", + "Model: Logit Df Residuals: 22\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.4464\n", + "Time: 15:09:54 Log-Likelihood: -9.4929\n", + "converged: True LL-Null: -17.148\n", + "Covariance Type: nonrobust LLR p-value: 0.0004735\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -8.5488 3.211 -2.662 0.008 -14.843 -2.254\n", + "x1 0.1183 0.066 1.783 0.075 -0.012 0.248\n", + "x2 0.1613 0.061 2.642 0.008 0.042 0.281\n", + "==============================================================================\n" + ] + } + ], + "source": [ + "modelHoldOut = sm.Logit(\n", + " trainSet[\"y\"],\n", + " sm.add_constant(trainSet[[\"x1\", \"x2\"]])\n", + ")\n", + "modelHoldOutFit = modelHoldOut.fit()\n", + "print(modelHoldOutFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 90, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 30\n", + "Model: Logit Df Residuals: 28\n", + "Method: MLE Df Model: 1\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.1525\n", + "Time: 15:09:54 Log-Likelihood: -17.397\n", + "converged: True LL-Null: -20.527\n", + "Covariance Type: nonrobust LLR p-value: 0.01235\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -2.2077 1.140 -1.936 0.053 -4.442 0.027\n", + "x1 0.1043 0.046 2.282 0.022 0.015 0.194\n", + "==============================================================================\n" + ] + } + ], + "source": [ + "print(model4Fit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 91, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "nRTs2yv9alHP", + "outputId": "f0305ea5-32c2-45b5-e09e-73dc9b467c1c" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1predict2yHat2predictHoldOut
23011.7532.960.2046000.12923300.136728
10118.2839.500.4965580.53462410.496200
25011.4334.780.2455840.16430300.169793
16131.8147.560.9596560.96771610.947146
9128.7435.630.5936560.70266510.645341
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1 predict2 yHat2 predictHoldOut\n", + "23 0 11.75 32.96 0.204600 0.129233 0 0.136728\n", + "10 1 18.28 39.50 0.496558 0.534624 1 0.496200\n", + "25 0 11.43 34.78 0.245584 0.164303 0 0.169793\n", + "16 1 31.81 47.56 0.959656 0.967716 1 0.947146\n", + "9 1 28.74 35.63 0.593656 0.702665 1 0.645341" + ] + }, + "execution_count": 91, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictHoldOut = modelHoldOutFit.predict(sm.add_constant(testSet[[\"x1\", \"x2\"]]))\n", + "testSet['predictHoldOut'] = predictHoldOut\n", + "testSet" + ] + }, + { + "cell_type": "code", + "execution_count": 92, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "1SXIG-xRbFc-", + "outputId": "011931e1-25e3-4261-9103-5aad2b1371ab" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
yx1x2predict1predict2yHat2predictHoldOutyHatHoldOutisHoldOutCorrect
23011.7532.960.2046000.12923300.13672801
10118.2839.500.4965580.53462410.49620000
25011.4334.780.2455840.16430300.16979301
16131.8147.560.9596560.96771610.94714611
9128.7435.630.5936560.70266510.64534111
\n", + "
" + ], + "text/plain": [ + " y x1 x2 predict1 predict2 yHat2 predictHoldOut yHatHoldOut \\\n", + "23 0 11.75 32.96 0.204600 0.129233 0 0.136728 0 \n", + "10 1 18.28 39.50 0.496558 0.534624 1 0.496200 0 \n", + "25 0 11.43 34.78 0.245584 0.164303 0 0.169793 0 \n", + "16 1 31.81 47.56 0.959656 0.967716 1 0.947146 1 \n", + "9 1 28.74 35.63 0.593656 0.702665 1 0.645341 1 \n", + "\n", + " isHoldOutCorrect \n", + "23 1 \n", + "10 0 \n", + "25 1 \n", + "16 1 \n", + "9 1 " + ] + }, + "execution_count": 92, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "testSet['yHatHoldOut'] = testSet['predictHoldOut'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "testSet['isHoldOutCorrect'] = testSet.apply(lambda row: 1 if row['y'] == row['yHatHoldOut'] else 0, axis=1)\n", + "testSet" + ] + }, + { + "cell_type": "code", + "execution_count": 93, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "bntHtTtwbMYi", + "outputId": "1bfe2cc6-2034-4f1f-864b-630b19fcc96d" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "80.0" + ] + }, + "execution_count": 93, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "accuracy = (np.sum(testSet['isHoldOutCorrect']) / len(testSet['yHatHoldOut'])) * 100\n", + "accuracy" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "z7KjTxz4caDz" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "OVzr96gecftN" + }, + "source": [ + "K-Fold Cross validation" + ] + }, + { + "cell_type": "code", + "execution_count": 94, + "metadata": { + "id": "x56ASbXkciNv" + }, + "outputs": [], + "source": [ + "from sklearn.model_selection import KFold" + ] + }, + { + "cell_type": "code", + "execution_count": 95, + "metadata": { + "id": "tjliLeknckTS" + }, + "outputs": [], + "source": [ + "# Initialize KFold\n", + "kf = KFold(n_splits=5, shuffle=True, random_state=55)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 96, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "2Inr3vF2cn14", + "outputId": "a2ac2909-88e6-49a9-8d44-c1c50a44bf0e" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimization terminated successfully.\n", + " Current function value: 0.385918\n", + " Iterations 7\n", + "expr=1\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 24\n", + "Model: Logit Df Residuals: 21\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.4318\n", + "Time: 15:09:54 Log-Likelihood: -9.2620\n", + "converged: True LL-Null: -16.301\n", + "Covariance Type: nonrobust LLR p-value: 0.0008773\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -8.3046 3.201 -2.595 0.009 -14.578 -2.031\n", + "x1 0.1361 0.068 2.014 0.044 0.004 0.269\n", + "x2 0.1491 0.062 2.397 0.017 0.027 0.271\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.330523\n", + " Iterations 8\n", + "expr=2\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 24\n", + "Model: Logit Df Residuals: 21\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.5208\n", + "Time: 15:09:54 Log-Likelihood: -7.9326\n", + "converged: True LL-Null: -16.552\n", + "Covariance Type: nonrobust LLR p-value: 0.0001805\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -10.9794 4.293 -2.557 0.011 -19.394 -2.565\n", + "x1 0.1529 0.080 1.912 0.056 -0.004 0.310\n", + "x2 0.2185 0.092 2.384 0.017 0.039 0.398\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.222706\n", + " Iterations 8\n", + "expr=3\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 24\n", + "Model: Logit Df Residuals: 21\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.6771\n", + "Time: 15:09:54 Log-Likelihood: -5.3449\n", + "converged: True LL-Null: -16.552\n", + "Covariance Type: nonrobust LLR p-value: 1.358e-05\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -15.7518 6.276 -2.510 0.012 -28.052 -3.451\n", + "x1 0.1539 0.101 1.524 0.127 -0.044 0.352\n", + "x2 0.3209 0.139 2.316 0.021 0.049 0.592\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.433994\n", + " Iterations 7\n", + "expr=4\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 24\n", + "Model: Logit Df Residuals: 21\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.3707\n", + "Time: 15:09:54 Log-Likelihood: -10.416\n", + "converged: True LL-Null: -16.552\n", + "Covariance Type: nonrobust LLR p-value: 0.002163\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -8.1881 3.232 -2.533 0.011 -14.523 -1.853\n", + "x1 0.1129 0.064 1.752 0.080 -0.013 0.239\n", + "x2 0.1604 0.065 2.453 0.014 0.032 0.289\n", + "==============================================================================\n", + "Optimization terminated successfully.\n", + " Current function value: 0.368962\n", + " Iterations 7\n", + "expr=5\n", + " Logit Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y No. Observations: 24\n", + "Model: Logit Df Residuals: 21\n", + "Method: MLE Df Model: 2\n", + "Date: Sun, 09 Jun 2024 Pseudo R-squ.: 0.4423\n", + "Time: 15:09:54 Log-Likelihood: -8.8551\n", + "converged: True LL-Null: -15.878\n", + "Covariance Type: nonrobust LLR p-value: 0.0008917\n", + "==============================================================================\n", + " coef std err z P>|z| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const -8.1001 3.273 -2.475 0.013 -14.516 -1.685\n", + "x1 0.1358 0.070 1.952 0.051 -0.001 0.272\n", + "x2 0.1503 0.067 2.229 0.026 0.018 0.282\n", + "==============================================================================\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['y'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['y'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['y'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['y'] == row['yHatCross'] else 0, axis=1)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:22: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['val_predictions'] = val_predictions\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:23: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + "/var/folders/v4/9b_k_xyj56ggnxlhf09pt8y40000gn/T/ipykernel_36878/46880013.py:24: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['y'] == row['yHatCross'] else 0, axis=1)\n" + ] + } + ], + "source": [ + "check = kf.split(mortgageDf)\n", + "check\n", + "experiment = 1\n", + "# Loop through each fold\n", + "# Initialize variables to store results\n", + "accuracies = []\n", + "\n", + "for train_index, val_index in check:\n", + " # Split the data\n", + " trainSet, valSet = mortgageDf.iloc[train_index], mortgageDf.iloc[val_index]\n", + "\n", + " # Fit the model\n", + "\n", + " trainModel = sm.Logit(\n", + " trainSet[\"y\"],\n", + " sm.add_constant(trainSet[[\"x1\", \"x2\"]])\n", + " )\n", + " trainModelFit = trainModel.fit()\n", + "\n", + " # Predict on the validation set\n", + " val_predictions = trainModelFit.predict(sm.add_constant(valSet[[\"x1\", \"x2\"]]))\n", + " valSet['val_predictions'] = val_predictions\n", + " valSet['yHatCross'] = valSet['val_predictions'].apply(lambda x: 1 if x > 0.5 else 0)\n", + " valSet['isCrossCorrect'] = valSet.apply(lambda row: 1 if row['y'] == row['yHatCross'] else 0, axis=1)\n", + " accuracy = (np.sum(valSet['isCrossCorrect']) / len(valSet['yHatCross'])) * 100\n", + " accuracies.append(accuracy)\n", + "\n", + "\n", + " # Print summary for each fold (optional)\n", + " print(f'expr={experiment}')\n", + " experiment = experiment +1\n", + " print(trainModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 97, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ZrdsnnRhfE9w", + "outputId": "78aaab6b-1f66-43cf-c2a7-c18f84430a8e" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "[100.0, 83.33333333333334, 66.66666666666666, 100.0, 83.33333333333334]" + ] + }, + "execution_count": 97, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "accuracies" + ] + }, + { + "cell_type": "code", + "execution_count": 98, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ZPFkA9gAfLyJ", + "outputId": "f90e1a89-2679-4daf-98db-349e5f8ed1db" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Average accuracies across all folds: 86.66666666666667\n" + ] + } + ], + "source": [ + "print(f\"Average accuracies across all folds: {sum(accuracies) /len(accuracies)}\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/notebooks/wip/Linear_regression_example.ipynb b/notebooks/wip/Linear_regression_example.ipynb new file mode 100644 index 0000000..d461066 --- /dev/null +++ b/notebooks/wip/Linear_regression_example.ipynb @@ -0,0 +1,3837 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "xwFyEsosINqT" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "import pandas as pd" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "pKewSQysItJ-" + }, + "outputs": [], + "source": [ + "# https://www.statsmodels.org/stable/index.html\n", + "import statsmodels.api as sm" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "id": "Lz-DyAtNWsJR" + }, + "outputs": [], + "source": [ + "# Download Dataset from https://www.dropbox.com/scl/fo/v71bqw2zowgla028cwdh0/AEfemP4C8qQ2X5tTNXMCqUQ/Session%203?dl=0&preview=educationWage.xlsx&rlkey=rlkgo6o58ex2kjbiv4b7cr9nj&subfolder_nav_tracking=1\n", + "# and add it to colab" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "id": "0zM8FGMJXJ70" + }, + "outputs": [], + "source": [ + "educationWageDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/u494o4buy26erbqi1p3xj/educationWage.xlsx?rlkey=7j2bgns66szpuc6xebfhgfha5&dl=1\")\n", + "# educationWageDf = pd.read_excel(\"./educationWage.xlsx\")" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "wsIgDGYcXT_z", + "outputId": "df04b4a7-5823-4168-e65b-1a539afc94e4" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EducationWage
020160
118120
21270
316100
41065
523160
6240
7555
\n", + "
" + ], + "text/plain": [ + " Education Wage\n", + "0 20 160\n", + "1 18 120\n", + "2 12 70\n", + "3 16 100\n", + "4 10 65\n", + "5 23 160\n", + "6 2 40\n", + "7 5 55" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 204 + }, + "id": "mE_jpf50ZSQ3", + "outputId": "e928191e-8299-4b0d-de74-88905fc4f4b5" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "pandas.core.frame.DataFrame" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "type(educationWageDf)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "sPAT8difZamr", + "outputId": "200cdc13-fdfe-44f0-90cb-9bf0e72fb03c" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(0 20\n", + " 1 18\n", + " 2 12\n", + " 3 16\n", + " 4 10\n", + " 5 23\n", + " 6 2\n", + " 7 5\n", + " Name: Education, dtype: int64,\n", + " pandas.core.series.Series)" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageDf[\"Education\"], type(educationWageDf[\"Education\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 472 + }, + "id": "L0294jIPa23E", + "outputId": "ac786e84-a4c5-4fdf-d1f8-a9c781f2f6dd" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkQAAAG2CAYAAACeUpnVAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAAA5W0lEQVR4nO3de1xVdb7/8fdGNhshBTcoG0ZA8pJ343iLNBXF8ZbjbWbS4ykzT06Nl5RzrKjUdDTSbk5mmR1H83HSmWlmtNsjGgZBJ0O8xczJlMQwm1FQMOAHjLiT/fuj3I92XvKyYS1Yr+fj4SPWd6393Z+1Pyx7u/baa9s8Ho9HAAAAFhZgdAEAAABGIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLMzQQ7dy5U2PHjlVMTIxsNpu2bdvms76qqkqzZ89W27Zt1bx5c3Xt2lVr16712ebs2bOaNWuWIiIidNNNN2nSpEkqKSlpwL0AAACNnaGBqLq6Wr169dKaNWsuuT41NVUZGRn63//9Xx06dEjz5s3T7Nmz9fbbb3u3mT9/vt555x29+eab2rFjh06cOKGJEyc21C4AAIAmwGaWL3e12WzaunWrxo8f7x3r3r277rrrLi1cuNA71rt3b40aNUrLli1TRUWFWrdurc2bN+unP/2pJOnw4cPq0qWLcnNzddtttzX0bgAAgEYo0OgCruT222/X22+/rfvuu08xMTHKycnRZ599phdeeEGStH//frndbqWkpHgf07lzZ8XFxV0xENXW1qq2tta7XFdXpzNnzigiIkI2m61+dwoAAPiFx+PR//t//08xMTEKCLixN71MHYhWr16tmTNnqm3btgoMDFRAQIBee+01DRo0SJJUXFysoKAghYeH+zwuKipKxcXFl503PT1dS5Ysqc/SAQBAA/nyyy/Vtm3bG5rD9IFo9+7devvttxUfH6+dO3dq1qxZiomJ8TkrdK3S0tKUmprqXa6oqFBcXJw+++wzOZ1Of5SO6+R2u5Wdna3k5GTZ7Xajy7E0emEe9MJc6Id5nDlzRp06dVKLFi1ueC7TBqJ//etfeuyxx7R161aNGTNGktSzZ0/l5+fr2WefVUpKilwul86dO6fy8nKfs0QlJSVyuVyXndvhcMjhcFw07nQ6FRER4fd9wdVzu90KCQlRREQEf9EYjF6YB70wF/phPv643MW09yFyu91yu90XvSfYrFkz1dXVSfrmAmu73a6srCzv+oKCAh0/flxJSUkNWi8AAGi8DD1DVFVVpcLCQu9yUVGR8vPz5XQ6FRcXp8GDB2vBggVq3ry54uPjtWPHDm3atEnPP/+8JCksLEwzZsxQamqqnE6nWrZsqTlz5igpKYlPmAEAgKtmaCDat2+fkpOTvcsXruuZNm2aNm7cqN/+9rdKS0vT1KlTdebMGcXHx2v58uV64IEHvI954YUXFBAQoEmTJqm2tlYjRozQyy+/3OD7AgAAGi9DA9GQIUN0pdsguVwubdiw4YpzBAcHa82aNZe9uSMAAMAPMe01RAAAAA2FQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACyPQAQAACzP0EC0c+dOjR07VjExMbLZbNq2bdtF2xw6dEg/+clPFBYWptDQUPXt21fHjx/3rj979qxmzZqliIgI3XTTTZo0aZJKSkoacC8AAFZyrLRakvRFWY3BldS/z09XKbvglIq+3eemzNBAVF1drV69emnNmjWXXH/06FENHDhQnTt3Vk5Ojv7+979r4cKFCg4O9m4zf/58vfPOO3rzzTe1Y8cOnThxQhMnTmyoXQAAWER5zTnds36P7nzpQ0nSmNV/1T3r96iixm1wZf53YV+HPrdD0zfsVfKzOU12Xy8INPLJR40apVGjRl12/eOPP67Ro0dr5cqV3rH27dt7f66oqND69eu1efNmDR06VJK0YcMGdenSRbt379Ztt91Wf8UDACxl7pZ87SosVeB3TiXsKizVnC0fa9OMfsYVVg8u7Ot3NdV9vcDQQHQldXV1eu+99/Twww9rxIgR+vjjj5WQkKC0tDSNHz9ekrR//3653W6lpKR4H9e5c2fFxcUpNzf3soGotrZWtbW13uXKykpJktvtltvddNNvY3Dh9acPxqMX5kEvjHestFp5n59SYIDkCPBIuvDfOuV9fkqFxRWKjwgxtkg/+e6++oYEj+n21Z/HhGkD0alTp1RVVaWnn35ay5Yt04oVK5SRkaGJEycqOztbgwcPVnFxsYKCghQeHu7z2KioKBUXF1927vT0dC1ZsuSi8ezsbIWEmKPJVpeZmWl0CfgWvTAPemGsld87MfKrPnXenw/m5ehgA9dTn76/r99lpn2tqfHfdVymDUR1dd/8oo0bN07z58+XJN1666366KOPtHbtWg0ePPi6505LS1Nqaqp3ubKyUrGxsUpOTlZERMSNFY4b4na7lZmZqeHDh8tutxtdjqXRC/OgF8Y7VlrtvXbIEeDRr/rUaeG+ANXW2SRJ7825wzRnTW7Ud/f1Usy0r2VlZX6by7SBKDIyUoGBgeratavPeJcuXfThh980yuVy6dy5cyovL/c5S1RSUiKXy3XZuR0OhxwOx0Xjdrudv2xMgl6YB70wD3phnI7R4ep/c5tvr6v55h/stXU2fV0XoAEdItXBFWZsgX703X097/F4x5vZbKbbV38eD6a9D1FQUJD69u2rgoICn/HPPvtM8fHxkqTevXvLbrcrKyvLu76goEDHjx9XUlJSg9YLAGjaVk9J1IAOkT5jAzpEavWURIMqqj9W2tcLDD1DVFVVpcLCQu9yUVGR8vPz5XQ6FRcXpwULFuiuu+7SoEGDlJycrIyMDL3zzjvKycmRJIWFhWnGjBlKTU2V0+lUy5YtNWfOHCUlJfEJMwCAX4WF2LVpRj8VFlfoYF6O3ptzh6nOlvjThX0tKq3WsbJqtYsIVUJkqNFl1StDA9G+ffuUnJzsXb5wXc+0adO0ceNGTZgwQWvXrlV6errmzp2rW265RX/84x81cOBA72NeeOEFBQQEaNKkSaqtrdWIESP08ssvN/i+AACsIT4iRAe//W9TlxDZ9IPQBYYGoiFDhsjznfcnL+W+++7Tfffdd9n1wcHBWrNmzWVv7ggAAPBDTHsNEQAAQEMhEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMsjEAEAAMszNBDt3LlTY8eOVUxMjGw2m7Zt23bZbR944AHZbDatWrXKZ/zMmTOaOnWqWrZsqfDwcM2YMUNVVVX1WzgAAGhSDA1E1dXV6tWrl9asWXPF7bZu3ardu3crJibmonVTp07VwYMHlZmZqXfffVc7d+7UzJkz66tkAADQBAUa+eSjRo3SqFGjrrjNP//5T82ZM0cffPCBxowZ47Pu0KFDysjI0N69e9WnTx9J0urVqzV69Gg9++yzlwxQAAAA32doIPohdXV1uvvuu7VgwQJ169btovW5ubkKDw/3hiFJSklJUUBAgPLy8jRhwoRLzltbW6va2lrvcmVlpSTJ7XbL7Xb7eS9wLS68/vTBePTCPOiFudAP8/BnD0wdiFasWKHAwEDNnTv3kuuLi4vVpk0bn7HAwEA5nU4VFxdfdt709HQtWbLkovHs7GyFhITcWNHwi8zMTKNLwLfohXnQC3OhH8arqanx21ymDUT79+/Xr3/9ax04cEA2m82vc6elpSk1NdW7XFlZqdjYWCUnJysiIsKvz4Vr43a7lZmZqeHDh8tutxtdjqXRC/OgF+ZCP8yjrKzMb3OZNhD99a9/1alTpxQXF+cdO3/+vP7rv/5Lq1at0rFjx+RyuXTq1Cmfx3399dc6c+aMXC7XZed2OBxyOBwXjdvtdn65TYJemAe9MA96YS70w3j+fP1NG4juvvtupaSk+IyNGDFCd999t6ZPny5JSkpKUnl5ufbv36/evXtLkrZv3666ujr179+/wWsGAACNk6GBqKqqSoWFhd7loqIi5efny+l0Ki4u7qK3r+x2u1wul2655RZJUpcuXTRy5Ejdf//9Wrt2rdxut2bPnq3JkyfzCTMAAHDVDL0P0b59+5SYmKjExERJUmpqqhITE7Vo0aKrnuONN95Q586dNWzYMI0ePVoDBw7UunXr6qtkAADQBBl6hmjIkCHyeDxXvf2xY8cuGnM6ndq8ebMfqwIAAFbDd5kBAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLIxABAADLMzQQ7dy5U2PHjlVMTIxsNpu2bdvmXed2u/XII4+oR48eCg0NVUxMjO655x6dOHHCZ44zZ85o6tSpatmypcLDwzVjxgxVVVU18J4AAPzl89NVyi44paLSaqNLgYUEGvnk1dXV6tWrl+677z5NnDjRZ11NTY0OHDighQsXqlevXvrqq6/00EMP6Sc/+Yn27dvn3W7q1Kk6efKkMjMz5Xa7NX36dM2cOVObN29u6N0BANyA8ppzmrslXzuPnPaODerYWqunJCosxG5gZbACQwPRqFGjNGrUqEuuCwsLU2Zmps/YSy+9pH79+un48eOKi4vToUOHlJGRob1796pPnz6SpNWrV2v06NF69tlnFRMTU+/7AADwj7lb8rWrsNRnbFdhqeZs+VibZvQzqCpYhaGB6FpVVFTIZrMpPDxckpSbm6vw8HBvGJKklJQUBQQEKC8vTxMmTLjkPLW1taqtrfUuV1ZWSvrmbTq3211/O4AfdOH1pw/GoxfmYYVeHCutVt7npxQY8P3/MXmU9/kpFRZXKD4ixKDqfFmhH42FP3vQaALR2bNn9cgjj2jKlClq2bKlJKm4uFht2rTx2S4wMFBOp1PFxcWXnSs9PV1Lliy5aDw7O1shIeY44Kzu+2cHYRx6YR5NvRcrr3AS6GBejg42XClXpan3ozGoqanx21yNIhC53W79/Oc/l8fj0SuvvHLD86WlpSk1NdW7XFlZqdjYWCUnJysiIuKG58f1c7vdyszM1PDhw2W3c82AkeiFeVihF8dKq3XnSx9edv17c+4w1Rmipt6PxqKsrMxvc5k+EF0IQ1988YW2b9/uPTskSS6XS6dOnfLZ/uuvv9aZM2fkcrkuO6fD4ZDD4bho3G6388ttEvTCPOiFeTTlXnSMDlf/m9toV2Gpzns83vFmNpsGdIhUB1eYgdVdWlPuR2Phz9ff1PchuhCGjhw5or/85S8Xnb1JSkpSeXm59u/f7x3bvn276urq1L9//4YuFwBwA1ZPSdSADpE+YwM6RGr1lESDKoKVGHqGqKqqSoWFhd7loqIi5efny+l0Kjo6Wj/96U914MABvfvuuzp//rz3uiCn06mgoCB16dJFI0eO1P3336+1a9fK7XZr9uzZmjx5Mp8wA4BGJizErk0z+qmotFrHyqrVLiJUCZGhRpcFizA0EO3bt0/Jycne5QvX9UybNk1PPvmk3n77bUnSrbfe6vO47OxsDRkyRJL0xhtvaPbs2Ro2bJgCAgI0adIkvfjiiw1SPwDA/xIiCUJoeIYGoiFDhsjznfeKv+9K6y5wOp3chBEAANwQU19DBAAA0BAIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIIRAAAwPIMDUQ7d+7U2LFjFRMTI5vNpm3btvms93g8WrRokaKjo9W8eXOlpKToyJEjPtucOXNGU6dOVcuWLRUeHq4ZM2aoqqqqAfcCABqXz09XKbvglIpKq40uBTANQwNRdXW1evXqpTVr1lxy/cqVK/Xiiy9q7dq1ysvLU2hoqEaMGKGzZ896t5k6daoOHjyozMxMvfvuu9q5c6dmzpzZULsAAI1Gec053bN+j4Y+t0PTN+xV8rM5umf9HlXUuI0uDTBcoJFPPmrUKI0aNeqS6zwej1atWqUnnnhC48aNkyRt2rRJUVFR2rZtmyZPnqxDhw4pIyNDe/fuVZ8+fSRJq1ev1ujRo/Xss88qJiamwfYFAMxu7pZ87Sos9RnbVViqOVs+1qYZ/QyqCjAHQwPRlRQVFam4uFgpKSnesbCwMPXv31+5ubmaPHmycnNzFR4e7g1DkpSSkqKAgADl5eVpwoQJl5y7trZWtbW13uXKykpJktvtltvNv5SMdOH1pw/Goxfm4Y9eHCutVt7npxQY8P2/+D3K+/yUCosrFB8RckN1WgXHhnn4swemDUTFxcWSpKioKJ/xqKgo77ri4mK1adPGZ31gYKCcTqd3m0tJT0/XkiVLLhrPzs5WSAh/IZhBZmam0SXgW/TCPG60FyuvcBLoYF6ODt7Q7NbDsWG8mpoav81l2kBUn9LS0pSamupdrqysVGxsrJKTkxUREWFgZXC73crMzNTw4cNlt9uNLsfS6IV5+KMXx0qrdedLH152/Xtz7uAM0VXi2DCPsrIyv81l2kDkcrkkSSUlJYqOjvaOl5SU6NZbb/Vuc+rUKZ/Hff311zpz5oz38ZficDjkcDguGrfb7fxymwS9MA96YR430ouO0eHqf3Mb7Sos1XmPxzvezGbTgA6R6uAK81eZlsGxYTx/vv6mvQ9RQkKCXC6XsrKyvGOVlZXKy8tTUlKSJCkpKUnl5eXav3+/d5vt27errq5O/fv3b/CaAcDMVk9J1IAOkT5jAzpEavWURIMqAszjus8QnTt3TkVFRWrfvr0CA69vmqqqKhUWFnqXi4qKlJ+fL6fTqbi4OM2bN0/Lli1Tx44dlZCQoIULFyomJkbjx4+XJHXp0kUjR47U/fffr7Vr18rtdmv27NmaPHkynzADgO8JC7Fr04x+Kiqt1rGyarWLCFVCZKjRZQGmcM1niGpqajRjxgyFhISoW7duOn78uCRpzpw5evrpp69prn379ikxMVGJid/86yQ1NVWJiYlatGiRJOnhhx/WnDlzNHPmTPXt21dVVVXKyMhQcHCwd4433nhDnTt31rBhwzR69GgNHDhQ69atu9bdAgDLSIgMVfItbQhDwHdc86mdtLQ0/e1vf1NOTo5GjhzpHU9JSdGTTz6pRx999KrnGjJkiDzfeS/7+2w2m5YuXaqlS5dedhun06nNmzdf9XMCAAB83zUHom3btul3v/udbrvtNtlsNu94t27ddPToUb8WBwAA0BCu+S2z06dPX3TvH+mbr+H4bkACAABoLK45EPXp00fvvfeed/lCCPqf//kf76e/AAAAGpNrfsvsqaee0qhRo/Tpp5/q66+/1q9//Wt9+umn+uijj7Rjx476qBEAAKBeXfMZooEDByo/P19ff/21evTooT//+c9q06aNcnNz1bt37/qoEQAAoF5d1w2E2rdvr9dee83ftQAAABjimgPRhW+G/z6bzSaHw6GgoKAbLgoAAKAhXXMgCg8Pv+Knydq2bat7771XixcvVkCAab8ZBAAAwOuaA9HGjRv1+OOP695771W/fv0kSXv27NHrr7+uJ554QqdPn9azzz4rh8Ohxx57zO8FAwAA+Ns1B6LXX39dzz33nH7+8597x8aOHasePXro1VdfVVZWluLi4rR8+XICEQAAaBSu+T2tjz76yPvdY9+VmJio3NxcSd98Eu3Cd5wBAACY3TUHotjYWK1fv/6i8fXr1ys2NlaSVFZWplatWt14dQAAAA3gmt8ye/bZZ/Wzn/1M77//vvr27Svpm2+tP3z4sP7whz9Ikvbu3au77rrLv5UCAADUk2sORD/5yU9UUFCgV199VQUFBZKkUaNGadu2bWrXrp0k6cEHH/RrkQAAAPXpum7M2K5dO6Wnp/u7FgAAAENcVyCSpJqaGh0/flznzp3zGe/Zs+cNFwUAANCQrjkQnT59WtOnT9f7779/yfXnz5+/4aIAAAAa0jV/ymzevHkqLy9XXl6emjdvroyMDL3++uvq2LGj3n777fqoEQAAoF5d8xmi7du366233lKfPn0UEBCg+Ph4DR8+XC1btlR6errGjBlTH3UCAADUm2s+Q1RdXa02bdpIklq1aqXTp09Lknr06KEDBw74tzoAAIAGcM2B6JZbbvF+3L5Xr1569dVX9c9//lNr165VdHS03wsEAACob1f9lllRUZESEhL00EMP6eTJk5KkxYsXa+TIkXrjjTcUFBSkjRs31ledAAAA9eaqA1H79u0VHx+v5ORkJScn6x//+Id69+6tL774QocPH1ZcXJwiIyPrs1YAAIB6cdWBaPv27crJyVFOTo62bNmic+fO6eabb9bQoUOVnJysH/3oR/VZJwAAQL256kA0ZMgQDRkyRJJ09uxZffTRR96A9Prrr8vtdqtz5846ePBgfdUKAABQL67rTtXBwcEaOnSoBg4cqOTkZL3//vt69dVXdfjwYX/XBwAAUO+uKRCdO3dOu3fvVnZ2tnJycpSXl6fY2FgNGjRIL730kgYPHlxfdQIAANSbqw5EQ4cOVV5enhISEjR48GD94he/0ObNm/moPQAAaPSuOhD99a9/VXR0tIYOHaohQ4Zo8ODBioiIqM/aAAAAGsRV35ixvLxc69atU0hIiFasWKGYmBj16NFDs2fP1h/+8AfvHasBAAAam6sORKGhoRo5cqSefvpp5eXlqbS0VCtXrlRISIhWrlyptm3bqnv37n4t7vz581q4cKESEhLUvHlztW/fXr/61a/k8Xi823g8Hi1atEjR0dFq3ry5UlJSdOTIEb/WAQAAmrZr/uqOC0JDQ+V0OuV0OtWqVSsFBgbq0KFD/qxNK1as0CuvvKKXXnpJhw4d0ooVK7Ry5UqtXr3au83KlSv14osvau3atcrLy1NoaKhGjBihs2fP+rUWAADQdF31NUR1dXXat2+fcnJylJ2drV27dqm6ulo/+tGPlJycrDVr1ig5OdmvxX300UcaN26cxowZI0lq166dtmzZoj179kj65uzQqlWr9MQTT2jcuHGSpE2bNikqKkrbtm3T5MmT/VoPAABomq46EIWHh6u6uloul0vJycl64YUXNGTIELVv377eirv99tu1bt06ffbZZ+rUqZP+9re/6cMPP9Tzzz8v6ZvvVysuLlZKSor3MWFhYerfv79yc3MvG4hqa2tVW1vrXa6srJQkud1uud3uetsf/LALrz99MB69MA96YS70wzz82YOrDkTPPPOMkpOT1alTJ789+Q959NFHVVlZqc6dO6tZs2Y6f/68li9frqlTp0qSiouLJUlRUVE+j4uKivKuu5T09HQtWbLkovHs7GyFhIT4cQ9wvTIzM40uAd+iF+ZBL8yFfhivpqbGb3NddSD6xS9+4bcnvVq///3v9cYbb2jz5s3q1q2b8vPzNW/ePMXExGjatGnXPW9aWppSU1O9y5WVlYqNjVVycjK3EjCY2+1WZmamhg8fLrvdbnQ5lkYvzINemAv9MI+ysjK/zXVdX93RUBYsWKBHH33U+9ZXjx499MUXXyg9PV3Tpk2Ty+WSJJWUlPjcILKkpES33nrrZed1OBxyOBwXjdvtdn65TYJemAe9MA96YS70w3j+fP2v+1NmDaGmpkYBAb4lNmvWTHV1dZKkhIQEuVwuZWVleddXVlYqLy9PSUlJDVorAABovEx9hmjs2LFavny54uLi1K1bN3388cd6/vnndd9990mSbDab5s2bp2XLlqljx45KSEjQwoULFRMTo/HjxxtbPAAAaDRMHYhWr16thQsX6pe//KVOnTqlmJgY/eIXv9CiRYu82zz88MOqrq7WzJkzVV5eroEDByojI0PBwcEGVg4AABoTUweiFi1aaNWqVVq1atVlt7HZbFq6dKmWLl3acIUBAIAmxdTXEAEAADQEAhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8U391BwBczuenq/TFmRq1iwhVQmSo0eUAaOQIRAAalfKac5q7JV87j5z2jg3q2FqrpyQqLMRuYGUAGjPeMgPQqMzdkq9dhaU+Y7sKSzVny8cGVQSgKSAQAWg0Pj9dpZ1HTuu8x+Mzft7j0c4jp1VUWm1QZQAaOwIRgEbjizM1V1x/rIxABOD6EIgANBrxzpArrm8XwcXVAK4PgQhAo3Fz65s0qGNrNbPZfMab2Wwa1LE1nzYDcN0IRAAaldVTEjWgQ6TP2IAOkVo9JdGgigA0BXzsHkCjEhZi16YZ/VRUWq1jZdXchwiAXxCIADRKCZEEIQD+w1tmAC7p2LcfYf+i7Mqf7AKApoBABMBHec053bN+j+586UNJ0pjVf9U96/eoosZtcGUAUH8IRAB8cCdoAFZEIALgxZ2gAVgVgQiAF3eCBmBVBCIAXtwJGoBVEYgAeHEnaABWRSAC4IM7QQOwIm7MCMDHhTtBFxZX6GBejt6bc4c6uMKMLgsA6hVniABcUnxEiM9/AaApM30g+uc//6n/+I//UEREhJo3b64ePXpo37593vUej0eLFi1SdHS0mjdvrpSUFB05csTAigEAQGNj6kD01VdfacCAAbLb7Xr//ff16aef6rnnnlOrVq2826xcuVIvvvii1q5dq7y8PIWGhmrEiBE6e/asgZUDAIDGxNTXEK1YsUKxsbHasGGDdywhIcH7s8fj0apVq/TEE09o3LhxkqRNmzYpKipK27Zt0+TJkxu8ZgAA0PiY+gzR22+/rT59+uhnP/uZ2rRpo8TERL322mve9UVFRSouLlZKSop3LCwsTP3791dubq4RJQMAgEbI1GeIPv/8c73yyitKTU3VY489pr1792ru3LkKCgrStGnTVFxcLEmKioryeVxUVJR33aXU1taqtrbWu1xZWSlJcrvdcrv5AksjXXj96YPx6IV50AtzoR/m4c8emDoQ1dXVqU+fPnrqqackSYmJifrkk0+0du1aTZs27brnTU9P15IlSy4az87OVkgIn6gxg8zMTKNLwLfohXnQC3OhH8arqbny1w1dC1MHoujoaHXt2tVnrEuXLvrjH/8oSXK5XJKkkpISRUdHe7cpKSnRrbfeetl509LSlJqa6l2urKxUbGyskpOTFRER4cc9wLVyu93KzMzU8OHDZbfbjS7H0uiFedALc6Ef5lFWVua3uUwdiAYMGKCCggKfsc8++0zx8fGSvrnA2uVyKSsryxuAKisrlZeXpwcffPCy8zocDjkcjovG7XY7v9wmQS/Mg16YB70wF/phPH++/qYORPPnz9ftt9+up556Sj//+c+1Z88erVu3TuvWrZMk2Ww2zZs3T8uWLVPHjh2VkJCghQsXKiYmRuPHjze2eAAA0GiYOhD17dtXW7duVVpampYuXaqEhAStWrVKU6dO9W7z8MMPq7q6WjNnzlR5ebkGDhyojIwMBQcHG1g5AABoTEwdiCTpzjvv1J133nnZ9TabTUuXLtXSpUsbsCoAANCUmPo+RLCeY6XVkqQvyvz3yQEAAH4IgQimUF5zTves36M7X/pQkjRm9V91z/o9qqjhPh8AgPpHIIIpzN2Sr12FpT5juwpLNWfLxwZVBACwEgIRDPf56SrtPHJa5z0en/HzHo92Hjmtom/fRgMAoL4QiGC4L85c+XqhY2UEIgBA/SIQwXDxzit/XUq7iNAGqgQAYFUEIhju5tY3aVDH1mpms/mMN7PZNKhjayVEEogAAPWLQARTWD0lUQM6RPqMDegQqdVTEg2qCABgJaa/MSOsISzErk0z+qmwuEIH83L03pw71MEVZnRZAACL4AwRTCU+IsTnvwAANAQCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsDwCEQAAsLxGFYiefvpp2Ww2zZs3zzt29uxZzZo1SxEREbrppps0adIklZSUGFckAABodBpNINq7d69effVV9ezZ02d8/vz5euedd/Tmm29qx44dOnHihCZOnGhQlf73+ekqZRecUlFptdGlAADQZAUaXcDVqKqq0tSpU/Xaa69p2bJl3vGKigqtX79emzdv1tChQyVJGzZsUJcuXbR7927ddtttRpV8w8przmnulnztPHLaOzaoY2utnpKosBC7gZUBAND0NIozRLNmzdKYMWOUkpLiM75//3653W6f8c6dOysuLk65ubkNXaZfzd2Sr12FpT5juwpLNWfLxwZVBABA02X6M0S//e1vdeDAAe3du/eidcXFxQoKClJ4eLjPeFRUlIqLiy87Z21trWpra73LlZWVkiS32y232+2fwm/AsdJq5X1+SoEB32+QR3mfn1JhcYXiI0IMqq5+XXj9zdAHq6MX5kEvzIV+mIc/e2DqQPTll1/qoYceUmZmpoKDg/02b3p6upYsWXLReHZ2tkJCzBE0Vva7/LqDeTk62HClGCIzM9PoEvAtemEe9MJc6Ifxampq/DaXzePxePw2m59t27ZNEyZMULNmzbxj58+fl81mU0BAgD744AOlpKToq6++8jlLFB8fr3nz5mn+/PmXnPdSZ4hiY2N18uRJRURE1Nv+XK1jpdW686UPL7v+vTl3NOkzRJmZmRo+fLjsdq6VMhK9MA96YS70wzzKysoUHR2tiooKtWzZ8obmMvUZomHDhun//u//fMamT5+uzp0765FHHlFsbKzsdruysrI0adIkSVJBQYGOHz+upKSky87rcDjkcDguGrfb7ab45e4YHa7+N7fRrsJSnf9OXm1ms2lAh0h1cIUZWF3DMEsvQC/MhF6YC/0wnj9ff1MHohYtWqh79+4+Y6GhoYqIiPCOz5gxQ6mpqXI6nWrZsqXmzJmjpKSkRv0JM0laPSVRc7Z87PMpswEdIrV6SqKBVQEA0DSZOhBdjRdeeEEBAQGaNGmSamtrNWLECL388stGl3XDwkLs2jSjn4pKq3WsrFrtIkKVEBlqdFkAADRJjS4Q5eTk+CwHBwdrzZo1WrNmjTEF1bOESIIQAAD1rVHchwgAAKA+EYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlEYgAAIDlmT4Qpaenq2/fvmrRooXatGmj8ePHq6CgwGebs2fPatasWYqIiNBNN92kSZMmqaSkxKCKAQBAY2P6QLRjxw7NmjVLu3fvVmZmptxut3784x+rurrau838+fP1zjvv6M0339SOHTt04sQJTZw40cCqAQBAYxJodAE/JCMjw2d548aNatOmjfbv369BgwapoqJC69ev1+bNmzV06FBJ0oYNG9SlSxft3r1bt912mxFlAwCARsT0gej7KioqJElOp1OStH//frndbqWkpHi36dy5s+Li4pSbm3vJQFRbW6va2lrvcmVlpSTJ7XbL7XbXZ/n4ARdef/pgPHphHvTCXOiHefizB40qENXV1WnevHkaMGCAunfvLkkqLi5WUFCQwsPDfbaNiopScXHxJedJT0/XkiVLLhrPzs5WSEiI3+vGtcvMzDS6BHyLXpgHvTAX+mG8mpoav83VqALRrFmz9Mknn+jDDz+8oXnS0tKUmprqXa6srFRsbKySk5MVERFxo2XiBrjdbmVmZmr48OGy2+1Gl2Np9MI86IW50A/zKCsr89tcjSYQzZ49W++++6527typtm3besddLpfOnTun8vJyn7NEJSUlcrlcl5zL4XDI4XBcNG632/nlNgl6YR70wjzohbnQD+P58/U3/afMPB6PZs+era1bt2r79u1KSEjwWd+7d2/Z7XZlZWV5xwoKCnT8+HElJSU1dLkAAKARMv0ZolmzZmnz5s1666231KJFC+91QWFhYWrevLnCwsI0Y8YMpaamyul0qmXLlpozZ46SkpL4hBkAALgqpg9Er7zyiiRpyJAhPuMbNmzQvffeK0l64YUXFBAQoEmTJqm2tlYjRozQyy+/3MCVAgCAxsr0gcjj8fzgNsHBwVqzZo3WrFnTABUBAICmxvTXEAEAANQ3AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALA8AhEAALC8JhOI1qxZo3bt2ik4OFj9+/fXnj17jC4JAAA0Ek0iEP3ud79TamqqFi9erAMHDqhXr14aMWKETp06ZXRpAACgEWgSgej555/X/fffr+nTp6tr165au3atQkJC9Jvf/Mbo0gAAQCMQaHQBN+rcuXPav3+/0tLSvGMBAQFKSUlRbm7uJR9TW1ur2tpa73JFRYUk6cyZM/VbLH6Q2+1WTU2NysrKZLfbjS7H0uiFedALc6Ef5nHh/9sej+eG52r0gai0tFTnz59XVFSUz3hUVJQOHz58ycekp6dryZIlF4136tSpXmoEAAD1p6ysTGFhYTc0R6MPRNcjLS1Nqamp3uXy8nLFx8fr+PHjN/yC4sZUVlYqNjZWX375pVq2bGl0OZZGL8yDXpgL/TCPiooKxcXFyel03vBcjT4QRUZGqlmzZiopKfEZLykpkcvluuRjHA6HHA7HReNhYWH8cptEy5Yt6YVJ0AvzoBfmQj/MIyDgxi+JbvQXVQcFBal3797KysryjtXV1SkrK0tJSUkGVgYAABqLRn+GSJJSU1M1bdo09enTR/369dOqVatUXV2t6dOnG10aAABoBJpEILrrrrt0+vRpLVq0SMXFxbr11luVkZFx0YXWl+NwOLR48eJLvo2GhkUvzINemAe9MBf6YR7+7IXN44/PqgEAADRijf4aIgAAgBtFIAIAAJZHIAIAAJZHIAIAAJZn+UC0Zs0atWvXTsHBwerfv7/27NljdEmW9OSTT8pms/n86dy5s9FlWcLOnTs1duxYxcTEyGazadu2bT7rPR6PFi1apOjoaDVv3lwpKSk6cuSIMcU2cT/Ui3vvvfei42TkyJHGFNvEpaenq2/fvmrRooXatGmj8ePHq6CgwGebs2fPatasWYqIiNBNN92kSZMmXXSTYNy4q+nFkCFDLjo2HnjggWt6HksHot/97ndKTU3V4sWLdeDAAfXq1UsjRozQqVOnjC7Nkrp166aTJ096/3z44YdGl2QJ1dXV6tWrl9asWXPJ9StXrtSLL76otWvXKi8vT6GhoRoxYoTOnj3bwJU2fT/UC0kaOXKkz3GyZcuWBqzQOnbs2KFZs2Zp9+7dyszMlNvt1o9//GNVV1d7t5k/f77eeecdvfnmm9qxY4dOnDihiRMnGlh103Q1vZCk+++/3+fYWLly5bU9kcfC+vXr55k1a5Z3+fz5856YmBhPenq6gVVZ0+LFiz29evUyugzLk+TZunWrd7murs7jcrk8zzzzjHesvLzc43A4PFu2bDGgQuv4fi88Ho9n2rRpnnHjxhlSj9WdOnXKI8mzY8cOj8fzzXFgt9s9b775pnebQ4cOeSR5cnNzjSrTEr7fC4/H4xk8eLDnoYceuqF5LXuG6Ny5c9q/f79SUlK8YwEBAUpJSVFubq6BlVnXkSNHFBMTo5tvvllTp07V8ePHjS7J8oqKilRcXOxznISFhal///4cJwbJyclRmzZtdMstt+jBBx9UWVmZ0SVZQkVFhSR5v0R0//79crvdPsdG586dFRcXx7FRz77fiwveeOMNRUZGqnv37kpLS1NNTc01zdsk7lR9PUpLS3X+/PmL7mYdFRWlw4cPG1SVdfXv318bN27ULbfcopMnT2rJkiW644479Mknn6hFixZGl2dZxcXFknTJ4+TCOjSckSNHauLEiUpISNDRo0f12GOPadSoUcrNzVWzZs2MLq/Jqqur07x58zRgwAB1795d0jfHRlBQkMLDw3225dioX5fqhST9+7//u+Lj4xUTE6O///3veuSRR1RQUKA//elPVz23ZQMRzGXUqFHen3v27Kn+/fsrPj5ev//97zVjxgwDKwPMY/Lkyd6fe/TooZ49e6p9+/bKycnRsGHDDKysaZs1a5Y++eQTrms0gcv1YubMmd6fe/TooejoaA0bNkxHjx5V+/btr2puy75lFhkZqWbNml30iYCSkhK5XC6DqsIF4eHh6tSpkwoLC40uxdIuHAscJ+Z08803KzIykuOkHs2ePVvvvvuusrOz1bZtW++4y+XSuXPnVF5e7rM9x0b9uVwvLqV///6SdE3HhmUDUVBQkHr37q2srCzvWF1dnbKyspSUlGRgZZCkqqoqHT16VNHR0UaXYmkJCQlyuVw+x0llZaXy8vI4TkzgH//4h8rKyjhO6oHH49Hs2bO1detWbd++XQkJCT7re/fuLbvd7nNsFBQU6Pjx4xwbfvZDvbiU/Px8SbqmY8PSb5mlpqZq2rRp6tOnj/r166dVq1apurpa06dPN7o0y/nv//5vjR07VvHx8Tpx4oQWL16sZs2aacqUKUaX1uRVVVX5/CuqqKhI+fn5cjqdiouL07x587Rs2TJ17NhRCQkJWrhwoWJiYjR+/Hjjim6irtQLp9OpJUuWaNKkSXK5XDp69KgefvhhdejQQSNGjDCw6qZp1qxZ2rx5s9566y21aNHCe11QWFiYmjdvrrCwMM2YMUOpqalyOp1q2bKl5syZo6SkJN12220GV9+0/FAvjh49qs2bN2v06NGKiIjQ3//+d82fP1+DBg1Sz549r/6Jbugzak3A6tWrPXFxcZ6goCBPv379PLt37za6JEu66667PNHR0Z6goCDPj370I89dd93lKSwsNLosS8jOzvZIuujPtGnTPB7PNx+9X7hwoScqKsrjcDg8w4YN8xQUFBhbdBN1pV7U1NR4fvzjH3tat27tsdvtnvj4eM/999/vKS4uNrrsJulSfZDk2bBhg3ebf/3rX55f/vKXnlatWnlCQkI8EyZM8Jw8edK4opuoH+rF8ePHPYMGDfI4nU6Pw+HwdOjQwbNgwQJPRUXFNT2P7dsnAwAAsCzLXkMEAABwAYEIAABYHoEIAABYHoEIAABYHoEIAABYHoEIAABYHoEIAABYHoEIgOnYbDZt27bN6DJ07733ckduwCIIRADq1b333iubzXbRn5EjRxpdmtexY8dks9m83390wa9//Wtt3LjRkJoANCxLf5cZgIYxcuRIbdiwwWfM4XAYVM3VCwsLM7oEAA2EM0QA6p3D4ZDL5fL506pVK0nSkSNHNGjQIAUHB6tr167KzMz0eWxOTo5sNpvKy8u9Y/n5+bLZbDp27Jh3bNeuXRoyZIhCQkLUqlUrjRgxQl999ZUkKSMjQwMHDlR4eLgiIiJ055136ujRo97HXvj27MTERNlsNg0ZMkTSxW+Z1dbWau7cuWrTpo2Cg4M1cOBA7d2796Jas7Ky1KdPH4WEhOj2229XQUGBP15GAPWIQATAMHV1dZo4caKCgoKUl5entWvX6pFHHrnmefLz8zVs2DB17dpVubm5+vDDDzV27FidP39eklRdXa3U1FTt27dPWVlZCggI0IQJE1RXVydJ2rNnjyTpL3/5i06ePKk//elPl3yehx9+WH/84x/1+uuv68CBA95vmj9z5ozPdo8//riee+457du3T4GBgbrvvvuueZ8ANCzeMgNQ7959913ddNNNPmOPPfaY+vTpo8OHD+uDDz5QTEyMJOmpp57SqFGjrmn+lStXqk+fPnr55Ze9Y926dfP+PGnSJJ/tf/Ob36h169b69NNP1b17d7Vu3VqSFBERIZfLdcnnqK6u1iuvvKKNGzd663vttdeUmZmp9evXa8GCBd5tly9frsGDB0uSHn30UY0ZM0Znz55VcHDwNe0XgIbDGSIA9S45OVn5+fk+fx544AEdOnRIsbGx3jAkSUlJSdc8/4UzRJdz5MgRTZkyRTfffLNatmypdu3aSZKOHz9+1c9x9OhRud1uDRgwwDtmt9vVr18/HTp0yGfbnj17en+Ojo6WJJ06deqqnwtAw+MMEYB6Fxoaqg4dOlzXYwMCvvl3m8fj8Y653W6fbZo3b37FOcaOHav4+Hi99tpriomJUV1dnbp3765z585dV00/xG63e3+22WyS5H17DoA5cYYIgGG6dOmiL7/8UidPnvSO7d6922ebC29nfXeb7388vmfPnsrKyrrkc5SVlamgoEBPPPGEhg0bpi5dungvtr4gKChIkrzXHF1K+/btFRQUpF27dnnH3G639u7dq65du15hLwE0BpwhAlDvamtrVVxc7DMWGBiolJQUderUSdOmTdMzzzyjyspKPf744z7bdejQQbGxsXryySe1fPlyffbZZ3ruued8tklLS1OPHj30y1/+Ug888ICCgoKUnZ2tn/3sZ3I6nYqIiNC6desUHR2t48eP69FHH/V5fJs2bdS8eXNlZGSobdu2Cg4Ovugj96GhoXrwwQe1YMECOZ1OxcXFaeXKlaqpqdGMGTP8+GoBMAJniADUu4yMDEVHR/v8GThwoAICArR161b961//Ur9+/fSf//mfWr58uc9j7Xa7tmzZosOHD6tnz55asWKFli1b5rNNp06d9Oc//1l/+9vf1K9fPyUlJemtt95SYGCgAgIC9Nvf/lb79+9X9+7dNX/+fD3zzDM+jw8MDNSLL76oV199VTExMRo3btwl9+Ppp5/WpEmTdPfdd+vf/u3fVFhYqA8++MB7CwEAjZfN89035gEAACyIM0QAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDyCEQAAMDy/j+igrENAK09oQAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "educationWageDf.plot.scatter(\n", + " x = 'Education',\n", + " y = 'Wage',\n", + " xlim = (0, 25),\n", + " ylim = (0, 180),\n", + " grid = True\n", + ")\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "70sdSooaXIP6" + }, + "source": [ + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "5kGS_KvQxDnB" + }, + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "CAzIv4nUbLNs" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "izbdCJO6bGgr", + "outputId": "3afc22ab-f6cd-42a3-f1bc-2ed7d9888438" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(0 20\n", + " 1 18\n", + " 2 12\n", + " 3 16\n", + " 4 10\n", + " 5 23\n", + " 6 2\n", + " 7 5\n", + " Name: Education, dtype: int64,\n", + " pandas.core.series.Series)" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageDf[\"Education\"], type(educationWageDf[\"Education\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "qZTj0erZbNa4", + "outputId": "dc8383c8-059b-47e1-f8d6-2af3ff19f1b6" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "( const Education\n", + " 0 1.0 20\n", + " 1 1.0 18\n", + " 2 1.0 12\n", + " 3 1.0 16\n", + " 4 1.0 10\n", + " 5 1.0 23\n", + " 6 1.0 2\n", + " 7 1.0 5,\n", + " pandas.core.frame.DataFrame)" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sm.add_constant(educationWageDf[\"Education\"]), type(sm.add_constant(educationWageDf[\"Education\"]))" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "id": "3CZ6j-I1XH59" + }, + "outputs": [], + "source": [ + "educationWageLiniarRgressionModel = sm.OLS(\n", + " educationWageDf[\"Wage\"],\n", + " sm.add_constant(educationWageDf[\"Education\"])\n", + ")\n" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "id": "OfbVQb61inFN" + }, + "outputs": [], + "source": [ + "educationWageLiniarRgressionModelFit = educationWageLiniarRgressionModel.fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "QjoNi0wP_MiT", + "outputId": "0562af9c-3690-46fd-cdd8-24082338010b" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Wage R-squared: 0.906\n", + "Model: OLS Adj. R-squared: 0.890\n", + "Method: Least Squares F-statistic: 57.64\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 0.000272\n", + "Time: 01:23:10 Log-Likelihood: -32.114\n", + "No. Observations: 8 AIC: 68.23\n", + "Df Residuals: 6 BIC: 68.39\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 16.1358 11.887 1.357 0.223 -12.950 45.221\n", + "Education 6.0464 0.796 7.592 0.000 4.098 7.995\n", + "==============================================================================\n", + "Omnibus: 0.619 Durbin-Watson: 0.926\n", + "Prob(Omnibus): 0.734 Jarque-Bera (JB): 0.522\n", + "Skew: 0.213 Prob(JB): 0.770\n", + "Kurtosis: 1.823 Cond. No. 32.5\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/jasonjafari/gitHub/ml_models_deployments/venv/lib/python3.12/site-packages/scipy/stats/_axis_nan_policy.py:531: UserWarning: kurtosistest only valid for n>=20 ... continuing anyway, n=8\n", + " res = hypotest_fun_out(*samples, **kwds)\n" + ] + } + ], + "source": [ + "print(educationWageLiniarRgressionModelFit.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"educationWageLiniarRgressionModelFit\",\n", + " \"model\": educationWageLiniarRgressionModelFit,\n", + " \"description\": \"predict Wage based on Education with linear regression\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Education\",\n", + " \"type\": \"int\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Wage\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "TYSiZnRL_tIx", + "outputId": "bf581098-bd2b-4ee8-eb05-22300b7840dd" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "const 16.135762\n", + "Education 6.046358\n", + "dtype: float64" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageLiniarRgressionModelFit.params" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "id": "gCeVAjLWd1zt" + }, + "outputs": [], + "source": [ + "# wage = b0 + b1 * Education" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "rgycwEPzibXT", + "outputId": "7b8a339e-4337-4cdf-a8c5-152d8041f8f9" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "0 137.062914\n", + "1 124.970199\n", + "2 88.692053\n", + "3 112.877483\n", + "4 76.599338\n", + "5 155.201987\n", + "6 28.228477\n", + "7 46.367550\n", + "dtype: float64" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedWage = educationWageLiniarRgressionModelFit.predict(sm.add_constant(educationWageDf[\"Education\"]))\n", + "predictedWage" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "BNQ2w_HAeGGq", + "outputId": "0c22f719-fd71-44d1-e9ea-3607b59b3f3a" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EducationWagepredictedWage
020160137.062914
118120124.970199
2127088.692053
316100112.877483
4106576.599338
523160155.201987
624028.228477
755546.367550
\n", + "
" + ], + "text/plain": [ + " Education Wage predictedWage\n", + "0 20 160 137.062914\n", + "1 18 120 124.970199\n", + "2 12 70 88.692053\n", + "3 16 100 112.877483\n", + "4 10 65 76.599338\n", + "5 23 160 155.201987\n", + "6 2 40 28.228477\n", + "7 5 55 46.367550" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageDf['predictedWage'] = predictedWage\n", + "educationWageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ooBEi1bmBE1F", + "outputId": "53ed63f4-88ec-4b48-e494-782811aa2b71" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([106.83112583])" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "testPredict = educationWageLiniarRgressionModelFit.predict([[1,15]])\n", + "testPredict" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "hfmtTSDajJa1" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt\n" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 718 + }, + "id": "FYmVGYFxjRJg", + "outputId": "5a08c13d-43b1-4ec7-92b3-cff806da38a0" + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAsAAAAK9CAYAAAAqk9rwAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAACbhElEQVR4nOzdeVxU1fsH8M8w7CAgyCKKiLig5o4bLixiKO5aaqm55VIuqd+sLHNLc0nNXctKzbTUXFJzQwU1RNw1930XUAwQUBjg/P64PwaHGRQUuMPM5/168cJz7p07z8wBfDg851yFEEKAiIiIiMhImMgdABERERFRcWICTERERERGhQkwERERERkVJsBEREREZFSYABMRERGRUWECTERERERGhQkwERERERkVJsBEREREZFSYABMRERGRUWECTJSHW7duQaFQYOXKlXKHkqeIiAgoFApERETIHYpeWblyJRQKBW7duiV3KKRDQb63ss+dPXt20QdGxY7fqyQXJsBksLJ/sOb1ceTIEblDzLclS5boXSIeEBCAt956S+4wSpT169dDoVBg8+bNWsfq1KkDhUKB8PBwrWMVKlSAn59fcYQomx07dmDSpElFdv07d+5g6NChqFixIiwsLODi4oLOnTsjMjJS69zsXyz//PPPl14zOTkZEydOxFtvvQUbGxs4OTmhbt26+OSTT/DgwYOXPjb7ObI/lEolXFxc8M477+DixYtv9FqJ6NVM5Q6AqKhNmTIFXl5eWv2VK1eWIZrXs2TJEpQpUwb9+vXT6G/ZsiWePXsGc3NzeQKjAmnevDkA4J9//kGXLl3U/UlJSTh37hxMTU0RGRmJwMBA9bG7d+/i7t276NmzZ7HHW1Q8PT3x7NkzmJmZqft27NiBxYsXF0kSHBkZidDQUADAhx9+iBo1aiAmJgYrV65EixYtMH/+fIwYMaJA11SpVGjZsiUuXbqEvn37YsSIEUhOTsb58+exdu1adOnSBe7u7q+8zsiRI9GwYUOoVCqcPXsWy5YtQ0REBM6dOwc3N7fXer0lSZ8+fdCzZ09YWFjIHQoZGSbAZPDatm0LX19fucMoEiYmJrC0tJQ7DMond3d3eHl54Z9//tHoj4qKghAC7777rtax7HZ28mwIFApFsX3d/vfff3jnnXdgZWWFyMhIeHt7q4+NGTMGISEhGDVqFBo0aFCgWfYtW7bg1KlTWLNmDd5//32NY8+fP0d6enq+rtOiRQu888476na1atXw0Ucf4ddff8Vnn32W73gKQ2pqKqytrYv1OZVKJZRKZbE+JxHAEggiAEBCQgL69esHe3t7ODg4oG/fvkhISNA6LyAgAAEBAVr9/fr1Q8WKFTX6srKyMH/+fNSqVQuWlpZwdnZGmzZtcPz4cfU5K1asQFBQEFxcXGBhYYEaNWpg6dKlGtepWLEizp8/jwMHDqj/XJodQ141wBs2bECDBg1gZWWFMmXKoHfv3rh//75WzLa2trh//z46d+4MW1tbODs749NPP0VmZma+37tX2blzJ1q0aAEbGxuUKlUK7dq1w/nz59XHZ8+eDYVCgdu3b2s9dty4cTA3N8d///2n7ouOjkabNm1gb28Pa2tr+Pv76/wz9qsU5HmvXr2Kbt26wc3NDZaWlihfvjx69uyJxMTEAj9v8+bNcerUKTx79kzdFxkZiZo1a6Jt27Y4cuQIsrKyNI4pFAo0a9YMQP6+ZgDp62/SpElwd3eHtbU1AgMDceHCBVSsWFHrLwkJCQkYNWoUPDw8YGFhgcqVK2PmzJkacegyZswYODk5QQih7hsxYgQUCgUWLFig7ouNjYVCoVDHmbsGuF+/fli8eDEAaJQF5Pbjjz/C29sbFhYWaNiwIY4dO/bS+ADghx9+QExMDL777juN5BcArKyssGrVKigUCkyZMuWV13rR9evXAUA9Li+ytLSEnZ1dga6XrUWLFhrXz3b//n0MGDAArq6usLCwQM2aNfHLL79oPf727dvo2LEjbGxs4OLigtGjR2P37t1aPyeyS5hOnDiBli1bwtraGl9++SUAIC0tDRMnTkTlypVhYWEBDw8PfPbZZ0hLS9N4rrCwMDRv3hwODg6wtbVFtWrV1NfItnDhQtSsWRPW1tYoXbo0fH19sXbtWvXxvGqAlyxZgpo1a8LCwgLu7u4YNmyY1s/k7Ndw4cIFBAYGwtraGuXKlcOsWbPy9V6TcWMCTAYvMTERjx8/1viIj49XHxdCoFOnTli9ejV69+6NqVOn4t69e+jbt+8bPe/AgQPVScXMmTPxxRdfwNLSUqP2eOnSpfD09MSXX36JOXPmwMPDAx9//LE6GQCAefPmoXz58vDx8cHq1auxevVqfPXVV3k+78qVK9G9e3colUpMnz4dgwYNwqZNm9C8eXOt/0AyMzMREhICJycnzJ49G/7+/pgzZw5+/PHHN3rt2VavXo127drB1tYWM2fOxNdff40LFy6gefPm6v/wunfvDoVCgfXr12s9fv369Xj77bdRunRpAMD+/fvRsmVLJCUlYeLEifj222+RkJCAoKAgHD16tECx5fd509PTERISgiNHjmDEiBFYvHgxBg8ejBs3buj8JelVmjdvDpVKhejoaHVfZGQk/Pz84Ofnh8TERJw7d07jmI+PD5ycnADk72sGkJL4yZMnw9fXF9999x2qVKmCkJAQpKSkaJyXmpoKf39//Pbbb/jggw+wYMECNGvWDOPGjcOYMWNe+lpatGiBJ0+eaPxCc+jQIZiYmODQoUMafYBUsqPLkCFD0Lp1awBQf42vXr1a45y1a9fiu+++w5AhQzB16lTcunULXbt2hUqlemmM27Ztg6WlJbp3767zuJeXF5o3b479+/dr/FLyKp6engCAX3/9VeMXgDeV/X2R/TUPSL9ANGnSBHv37sXw4cMxf/58VK5cGQMHDsS8efPU56WkpCAoKAh79+7FyJEj8dVXX+Hw4cP4/PPPdT5XfHw82rZti7p162LevHkIDAxEVlYWOnbsiNmzZ6NDhw5YuHAhOnfujO+//x49evRQP/b8+fNo37490tLSMGXKFMyZMwcdO3bU+GV0+fLlGDlyJGrUqIF58+Zh8uTJqFu3rsbXvi6TJk3CsGHD4O7ujjlz5qBbt2744Ycf8Pbbb2uN93///Yc2bdqgTp06mDNnDnx8fPD5559j586d+X3LyVgJIgO1YsUKAUDnh4WFhfq8LVu2CABi1qxZ6r6MjAzRokULAUCsWLFC3e/v7y/8/f21nqtv377C09NT3d6/f78AIEaOHKl1blZWlvrfqampWsdDQkJEpUqVNPpq1qyp83nDw8MFABEeHi6EECI9PV24uLiIt956Szx79kx93vbt2wUAMWHCBI2YAYgpU6ZoXLNevXqiQYMGWs+Vm7+/v6hZs2aex58+fSocHBzEoEGDNPpjYmKEvb29Rn/Tpk21nvPo0aMCgPj111+FENL7VqVKFRESEqL1Hnp5eYnWrVur+7LH/ubNmy99Dfl53lOnTgkAYsOGDS+9Vn6dP39eABDffPONEEIIlUolbGxsxKpVq4QQQri6uorFixcLIYRISkoSSqVS473Kz9dMTEyMMDU1FZ07d9Y4b9KkSQKA6Nu3r7rvm2++ETY2NuLKlSsa537xxRdCqVSKO3fu5Pla4uLiBACxZMkSIYQQCQkJwsTERLz77rvC1dVVfd7IkSOFo6Ojetxu3ryp9b01bNgwoeu/pOxznZycxJMnT9T9f/31lwAgtm3blmd8Qgjh4OAg6tSp89JzRo4cKQCIs2fPCiFyvq9eNuapqamiWrVqAoDw9PQU/fr1Ez///LOIjY196XNly36OX375RTx69Eg8ePBA7Nq1S1SuXFkoFApx9OhR9bkDBw4UZcuWFY8fP9a4Rs+ePYW9vb36a2LOnDkCgNiyZYv6nGfPngkfHx+NnxNCSN+/AMSyZcs0rrl69WphYmIiDh06pNG/bNkyAUBERkYKIYT4/vvvBQDx6NGjPF9jp06dXvozQgjt79W4uDhhbm4u3n77bZGZmak+b9GiRer3K/dryP5eFUKItLQ04ebmJrp16/bS5yXiDDAZvMWLFyMsLEzj48XZgR07dsDU1BQfffSRuk+pVBZ4UcyLNm7cCIVCgYkTJ2ode/FPu1ZWVup/Z89U+/v748aNG6/15/Xjx48jLi4OH3/8sUaNZbt27eDj44O///5b6zFDhw7VaLdo0QI3btwo8HPnFhYWhoSEBLz33nsas+9KpRKNGzfW2O2gR48eOHHihMaffdetWwcLCwt06tQJAHD69GlcvXoV77//PuLj49XXS0lJQatWrXDw4MFX/sk+t/w8r729PQBg9+7dSE1Nfe33I1v16tXh5OSkru09c+YMUlJS1PWnfn5+6lm0qKgoZGZmatT/5udrZt++fcjIyMDHH3+s8dy6vqY3bNiAFi1aoHTp0hrjFBwcjMzMTBw8eDDP1+Ls7AwfHx/1OZGRkVAqlRg7dixiY2Nx9epVANIMcPPmzXWWNeRXjx49NGZFs0sFXvW1+vTpU5QqVeql52QfT0pKync8VlZWiI6OxtixYwFIf3kZOHAgypYtixEjRmiVC+RlwIABcHZ2hru7O9q0aYPExESsXr0aDRs2BCD9hWrjxo3o0KEDhBAaYxQSEoLExEScPHkSALBr1y6UK1cOHTt2VF/f0tISgwYN0vncFhYW6N+/v0bfhg0bUL16dfj4+Gg8V1BQEACov28dHBwAAH/99Vee33cODg64d+9evkpVsu3duxfp6ekYNWoUTExyUpRBgwbBzs5O62eYra0tevfurW6bm5ujUaNGhfIzjAwbE2AyeI0aNUJwcLDGx4ur7G/fvo2yZcvC1tZW43HVqlV77ee8fv063N3d4ejo+NLzIiMjERwcDBsbGzg4OMDZ2VldQ/c6CXB2Pauu2H18fLTqXbNrk19UunRpjZrb15Wd/AQFBcHZ2VnjY8+ePYiLi1Of++6778LExATr1q0DIP2nv2HDBrRt21ZdS5l9vb59+2pd76effkJaWlqB37P8PK+XlxfGjBmDn376CWXKlEFISAgWL178WuMDSL8A+fn5qWt9IyMj4eLiot6V5MUEOPvziwlwfr5mssc5904njo6OGkkkIL2vu3bt0npPg4ODAUBjnHRp0aKFusTh0KFD8PX1ha+vLxwdHXHo0CEkJSXhzJkz6oT1dVWoUEGjnf06XvW1WqpUKTx9+vSl52Qff1WinJu9vT1mzZqFW7du4datW/j5559RrVo1LFq0CN98802+rjFhwgSEhYVh8+bN+OCDD5CYmKiR+D169AgJCQn48ccftcYoO3nNHqPbt2/D29tb6xeNvHa8KVeunNYOMlevXsX58+e1nqtq1aoaz9WjRw80a9YMH374IVxdXdGzZ0+sX79eIxn+/PPPYWtri0aNGqFKlSoYNmzYK+v18/oZZm5ujkqVKmn9DCtfvrzW6y2sn2Fk2LgLBFEBKBQKnfV+r7No7Pr162jVqhV8fHwwd+5ceHh4wNzcHDt27MD3339f4NnM11GUq6+z41+9erXO7ZxMTXN+/Li7u6NFixZYv349vvzySxw5cgR37tzBzJkzta733XffoW7dujqfM/cvMa+Sn+cFgDlz5qBfv37466+/sGfPHowcORLTp0/HkSNHUL58+QI9JyAltNu2bcO///6rrv/N5ufnh7Fjx+L+/fv4559/4O7ujkqVKgEomq+ZrKwstG7dOs8dB7ITn5e9luXLl+PGjRs4dOgQWrRoAYVCgebNm+PQoUNwd3dHVlbWGyfAeX2t6vp+fFH16tVx6tQppKWl5bnV1tmzZ2FmZoYqVaq8dnyenp4YMGAAunTpgkqVKmHNmjWYOnXqKx9Xq1Yt9S8bnTt3RmpqKgYNGoTmzZvDw8NDPaa9e/fOc11C7dq1XyvmF/+akC0rKwu1atXC3LlzdT7Gw8ND/diDBw8iPDwcf//9N3bt2oV169YhKCgIe/bsgVKpRPXq1XH58mVs374du3btwsaNG7FkyRJMmDABkydPfq2Yc3vdrwsiJsBk9Dw9PbFv3z4kJydrJFCXL1/WOrd06dI6/7SWe1bC29sbu3fvxpMnT/KcBd62bRvS0tKwdetWjdktXTdCyO+fjrMX5ly+fFn9J8tsly9fVh8vDtkr7l1cXNT/wb9Mjx498PHHH+Py5ctYt24drK2t0aFDB63r2dnZ5et6+fWq581Wq1Yt1KpVC+PHj8fhw4fRrFkzLFu2LF9JTm4v7gccGRmJUaNGqY81aNAAFhYWiIiIQHR0tHr/WiD/XzPZ43zt2jWNPbDj4+O1Zsa8vb2RnJz82u9pdmIbFhaGY8eO4YsvvgAgLXhbunQp3N3dYWNjgwYNGrz0Om9SHvEy7du3R1RUFDZs2KDxp/Jst27dwqFDhxAcHKwzISyo0qVLw9vbW2MhY0HMmDEDmzdvxrRp07Bs2TI4OzujVKlSyMzMfOUYeXp64sKFCxBCaLyf165dy/fze3t748yZM2jVqtUrx8TExAStWrVCq1atMHfuXHz77bf46quvEB4ero7VxsYGPXr0QI8ePZCeno6uXbti2rRpGDdunM6t8F78GZb9ix8ApKen4+bNm4X6vU/GjSUQZPRCQ0ORkZGhsZVUZmYmFi5cqHWut7c3Ll26hEePHqn7zpw5o/VnvW7dukEIoXOWI3tmInvm4sWZisTERKxYsULrMTY2NvnaccDX1xcuLi5YtmyZRg3izp07cfHiRbRr1+6V1ygsISEhsLOzw7fffqtzpf6L7yEgvWdKpRK///47NmzYgPbt28PGxkZ9vEGDBvD29sbs2bORnJz8yuvl16ueNykpCRkZGRqPqVWrFkxMTDTe4zt37uDSpUv5ek5fX19YWlpizZo1uH//vsYMsIWFBerXr4/FixcjJSVFo/whv18zrVq1gqmpqdb2aIsWLdKKpXv37oiKisLu3bu1jiUkJGi99ty8vLxQrlw5fP/991CpVOptwVq0aIHr16/jzz//RJMmTTRm/HXJfs9fZ2eNlxkyZAhcXFwwduxYrV9enz9/jv79+0MIgQkTJhToumfOnMHjx4+1+m/fvo0LFy68dgmVt7c3unXrhpUrVyImJgZKpRLdunXDxo0bdSbVL37dh4SE4P79+9i6dau67/nz51i+fHm+n7979+64f/++zsc8e/ZMvYvIkydPtI5n/2Um+/vixd12AKmMoUaNGhBC5Ll7R3BwMMzNzbFgwQKNr/Off/4ZiYmJxfozjAwbZ4DJ4O3cuVNnYuLn54dKlSqhQ4cOaNasGb744gvcunULNWrUwKZNm3TWeA4YMABz585FSEgIBg4ciLi4OCxbtgw1a9bUWEATGBiIPn36YMGCBbh69SratGmDrKwsHDp0CIGBgRg+fDjefvttmJubo0OHDhgyZAiSk5OxfPlyuLi44OHDhxrP26BBAyxduhRTp05F5cqV4eLiojXDCwBmZmaYOXMm+vfvD39/f7z33nuIjY3F/PnzUbFiRYwePboQ3tEcjx490jkD6uXlhV69emHp0qXo06cP6tevj549e8LZ2Rl37tzB33//jWbNmmkkZC4uLggMDMTcuXPx9OlTjS2XAGm26aeffkLbtm1Rs2ZN9O/fH+XKlcP9+/cRHh4OOzs7bNu2rcCv4VXPu3//fgwfPhzvvvsuqlatioyMDKxevVqdmGT74IMPcODAgXz96dXc3BwNGzbEoUOHYGFhoTU76ufnhzlz5gDQrP/N79eMq6srPvnkE/XWVG3atMGZM2ewc+dOlClTRmNmb+zYsdi6dSvat2+Pfv36oUGDBkhJScG///6LP//8E7du3UKZMmVe+npatGiBP/74A7Vq1VLX5tavXx82Nja4cuWK1o0idMl+D0aOHImQkBAolcpCufudk5MT/vzzT7Rr1w7169fXuhPctWvXMH/+fJ03wdi4caPOnx19+/ZFWFgYJk6ciI4dO6JJkyawtbXFjRs38MsvvyAtLe2N7mg3duxYrF+/HvPmzcOMGTMwY8YMhIeHo3Hjxhg0aBBq1KiBJ0+e4OTJk9i7d686GR0yZAgWLVqE9957D5988gnKli2LNWvWqGda8zPL3qdPH6xfvx5Dhw5FeHg4mjVrhszMTFy6dAnr16/H7t274evriylTpuDgwYNo164dPD09ERcXhyVLlqB8+fLqr9m3334bbm5uaNasGVxdXXHx4kUsWrQI7dq1y7Pe2tnZWb2FX5s2bdCxY0dcvnwZS5YsQcOGDXXO4hO9luLfeIKoeLxsGzTk2oIpPj5e9OnTR9jZ2Ql7e3vRp08f9fZXL54nhBC//fabqFSpkjA3Nxd169YVu3fv1toGTQhpK7XvvvtO+Pj4CHNzc+Hs7Czatm0rTpw4oT5n69atonbt2sLS0lJUrFhRzJw5U/zyyy9aW3jFxMSIdu3aiVKlSgkA6i3Rcm+Dlm3dunWiXr16wsLCQjg6OopevXqJe/fuaZzTt29fYWNjo/W+TZw4Ued2VLllb0Gk66NVq1bq88LDw0VISIiwt7cXlpaWwtvbW/Tr108cP35c65rLly8XAESpUqU0tnF70alTp0TXrl2Fk5OTsLCwEJ6enqJ79+5i37596nPyuw1afp73xo0bYsCAAcLb21tYWloKR0dHERgYKPbu3avz/civcePGCQDCz89P69imTZvU8WRkZGgcy+/XTEZGhvj666+Fm5ubsLKyEkFBQeLixYvCyclJDB06VOOaT58+FePGjROVK1cW5ubmokyZMsLPz0/Mnj1bpKenv/K1LF68WAAQH330kUZ/cHCwAKAxNkLo3gYtIyNDjBgxQjg7OwuFQqF+L7PP/e6777SeF4CYOHHiK+PLvs6gQYNEhQoVhJmZmShTpozo2LGj1nZfQuR8X+X1cejQIXHjxg0xYcIE0aRJE+Hi4iJMTU2Fs7OzaNeundi/f/8r43nVVmsBAQHCzs5OJCQkCCGEiI2NFcOGDRMeHh7CzMxMuLm5iVatWokff/xR43E3btwQ7dq1E1ZWVsLZ2Vn873//Exs3bhQAxJEjR9TnvWwbw/T0dDFz5kxRs2ZNYWFhIUqXLi0aNGggJk+eLBITE4UQQuzbt0906tRJuLu7C3Nzc+Hu7i7ee+89je30fvjhB9GyZUv196q3t7cYO3as+hpC5P29umjRIuHj4yPMzMyEq6ur+Oijj8R///2ncU5er0HXz2Oi3BRCsFKciMgYJCQkoHTp0pg6depLb6ZChmXevHkYPXo07t27h3LlyskdDpFeYA0wEZEB0nVXs+y7hum6nTcZhtzj/vz5c/zwww+oUqUKk1+iF7AGmIjIAK1btw4rV65EaGgobG1t8c8//+D333/H22+/rV6oRoana9euqFChAurWrYvExET89ttvuHTpEtasWSN3aER6hQkwEZEBql27NkxNTTFr1iwkJSWpF8a9zrZtVHKEhITgp59+wpo1a5CZmYkaNWrgjz/+0FrcSWTsZK0BPnjwIL777jucOHECDx8+xObNm9G5c2f18eTkZHzxxRfYsmUL4uPj4eXlhZEjR2rcuvX58+f43//+hz/++ANpaWkICQnBkiVL4OrqKsMrIiIiIiJ9J2sNcEpKCurUqYPFixfrPD5mzBjs2rULv/32Gy5evIhRo0Zh+PDhGnscjh49Gtu2bcOGDRtw4MABPHjwAF27di2ul0BEREREJYze7AKhUCi0ZoDfeust9OjRA19//bW6r0GDBmjbti2mTp2KxMREODs7Y+3atXjnnXcAAJcuXUL16tURFRWFJk2aFPfLICIiIiI9p9c1wH5+fti6dSsGDBgAd3d3RERE4MqVK/j+++8BACdOnIBKpdK4NaKPjw8qVKjw0gQ4LS1N4w5OWVlZePLkCZycnIrsdpxERERE9PqEEHj69Cnc3d1hYvJmRQx6nQAvXLgQgwcPRvny5WFqagoTExMsX74cLVu2BADExMTA3NwcDg4OGo9zdXVFTExMntedPn26zlvUEhEREZF+u3v3LsqXL/9G19D7BPjIkSPYunUrPD09cfDgQQwbNgzu7u4as74FNW7cOIwZM0bdTkxMRIUKFXDlyhU4OjoWRuikx1QqFcLDwxEYGAgzMzO5w6EixvE2Lhxv48LxNi5PnjxB1apV87yVdkHobQL87NkzfPnll9i8eTPatWsHQNrW5/Tp05g9ezaCg4Ph5uaG9PR0JCQkaMwCx8bGws3NLc9rW1hYwMLCQqvf0dERTk5Ohf5aSL+oVCpYW1vDycmJPzCNAMfbuHC8jQvH2zgVRrmq3t4JTqVSQaVSadV4KJVKZGVlAZAWxJmZmWHfvn3q45cvX8adO3fQtGnTYo2XiIiIiEoGWWeAk5OTce3aNXX75s2bOH36NBwdHVGhQgX4+/tj7NixsLKygqenJw4cOIBff/0Vc+fOBQDY29tj4MCBGDNmDBwdHWFnZ4cRI0agadOm3AGCiIiIiHSSNQE+fvw4AgMD1e3suty+ffti5cqV+OOPPzBu3Dj06tULT548gaenJ6ZNm6ZxI4zvv/8eJiYm6Natm8aNMIiIiIiIdJE1AQ4ICMDLtiF2c3PDihUrXnoNS0tLLF68OM+baRARUfHIzMyESqWSNQaVSgVTU1M8f/4cmZmZssZCRY/jbViUSiVMTU2LZUtavV0ER0REJUdycjLu3bv30kmN4iCEgJubG+7evct93Y0Ax9vwWFtbo2zZsjA3Ny/S52ECTEREbyQzMxP37t2DtbU1nJ2dZU1EsrKykJycDFtb2zfeKJ/0H8fbcAghkJ6ejkePHuHmzZuoUqVKkY4pE2AiInojKpUKQgg4OzvDyspK1liysrKQnp4OS0tLJkRGgONtWKysrGBmZobbt2+rx7Wo8KuFiIgKBf8ETURvqrh+kWECTERERERGhQkwERERERkVJsBEREQGZNKkSahbt67cYRDpNSbARERklPr16weFQgGFQgEzMzO4urqidevW+OWXX5CVlVWga61cuRIODg6FEldAQIA6LktLS9SoUaNAN3j69NNPsW/fvgI9Z8WKFTFv3rwCRqpfIiIioFAokJCQoNEfEBCAUaNGyRIT6S8mwEREpBcyM4HDh4EtW6TPxXFfgzZt2uDhw4e4desWdu7cicDAQHzyySdo3749MjIyij6APAwaNAgPHz7EhQsX0L17dwwbNgy///57vh5ra2sLJyenIo7Q+KSnp8sdAhUiJsBERCS7HTsAX1+gTRugVy/ps6+v1F+ULCws4ObmhnLlyqF+/fr48ssv8ddff2Hnzp1YuXKl+ry5c+eiVq1asLGxgYeHBz7++GMkJycDkGYe+/fvj8TERPXM7aRJkwAAq1evhq+vL0qVKgU3Nze8//77iIuLe2Vc1tbWcHNzQ6VKlTBp0iRUqVIFW7duBQDcuXMHnTp1gq2tLezs7NC9e3fExsaqH5u7BKJfv37o3LkzZs+ejbJly8LJyQnDhg1T37UvICAAt2/fxujRo9XxA8Dt27fRoUMHlC5dGjY2NqhZsyZ2vOGAREREoFGjRrCxsYGDgwOaNWuG27dvq49v27YNDRs2hKWlJcqUKYMuXbqoj73svbx16xYCAwMBAKVLl4ZCoUC/fv3Qr18/HDhwAPPnz1e/tlu3bgEAzp07h7Zt28LW1haurq7o06cPHj9+rH6+gIAADB8+HKNGjUKZMmUQEhLyRq+d9AsTYCIiktWOHUDv3sCVK4CFBVCqlPT5yhWpv6iT4NyCgoJQp04dbNq0Sd1nYmKCBQsW4Pz581i1ahX279+Pzz77DADg5+eHefPmwc7ODg8fPsTDhw/x6aefApD2SP7mm29w5swZbNmyBbdu3UK/fv0KHJOVlRXS09ORlZWFTp064cmTJzhw4ADCwsJw48YN9OjR46WPDw8Px/Xr1xEeHo5Vq1Zh5cqV6gR/06ZNKF++PKZMmaKOHwCGDRuGtLQ0HDx4EP/++y9mzpwJW1vbAseeLSMjA507d4a/vz/Onj2LqKgoDB48WJ1w//333+jSpQtCQ0Nx6tQp7Nu3D40aNVI/Xtd72b9/fwCAh4cHNm7cCAC4fPkyHj58iPnz52P+/Plo2rSpekb94cOH8PDwQEJCAoKCglCvXj0cP34cu3btQmxsLLp3764R86pVq2Bubo7IyEgsW7bstV876R/eCIOIiGSTmQl89RWQlgbY2QHZWwmbmEjtpCRg/HggJARQKosvLh8fH5w9e1bdfrGGtGLFipg6dSqGDh2KJUuWwNzcHPb29lAoFHBzc9O4zoABA9T/rlSpEhYsWICGDRuq7172KpmZmfj9999x9uxZDB48GPv27cO///6LmzdvwsPDAwDw66+/ombNmjh27BgaNmyo8zqlS5fGokWLoFQq4ePjg3bt2mHfvn0YNGgQHB0doVQq1TOr2e7cuYNu3bqhVq1a6vjfRFJSEhITE9G+fXt4e3sDAKpXr64+Pm3aNPTs2ROTJ09W99WpU0f975e9l3Z2dnB0dAQAuLi4aNRjm5ubq2fUsy1atAj16tXDt99+q+775Zdf4OHhgStXrqBq1aoAgCpVqmDWrFlv9LpJP3EGmIiIZBMdDVy/Dlhb5yS/2RQKqf/aNem84iSE0Lixx969e9GqVSuUK1cOpUqVQp8+fRAfH4/U1NSXXufEiRPo0KEDKlSogFKlSsHf3x+AlFy+zJIlS2BrawsrKysMGjQIo0ePxkcffYSLFy/Cw8NDnfwCQI0aNeDg4ICLFy/meb2aNWtC+cJvEGXLln1lKcbIkSMxdepUNGvWDBMnTtT4hSC3b7/9Fra2tuoPXa/P0dER/fr1Q0hICDp06ID58+erZ5sB4PTp02jVqlWez5HXe3nv3r2Xvg5dzpw5g/DwcI2YfXx8AADXr19Xn9egQYMCX5tKBibAREQkm7g4aRY4r9ldpVI6no+y2UJ18eJFeHl5AZDqS9u3b4/atWtj48aNOHHiBBYvXgzg5QujUlJSEBISAjs7O6xZswbHjh3D5s2bX/k4AOjVqxdOnz6NmzdvIiUlBXPnzn2jO2SZmZlptBUKxSt3uvjwww9x48YN9OnTB//++y98fX2xcOFCnecOHToUp0+fVn+4u7vrPG/FihWIioqCn58f1q1bh6pVq+LIkSMA8NLbaL/svcyuZS6I5ORkdOjQQSPm06dP4+rVq2jZsqX6PBsbmwJfm0oGJsBERCQbF5ecJFeX7OTYxaX4Ytq/fz/+/fdfdOvWDYA085iVlYU5c+agSZMmqFq1Kh48eKDxGHNzc2TmehGXLl1CfHw8ZsyYgRYtWsDHxydfC+AAwN7eHpUrV0a5cuU0Et/q1avj7t27uHv3rrrvwoULSEhIQI0aNV73JeuMH5Bqa4cOHYpNmzbhf//7H5YvX67z8Y6OjqhcubL6w9Q07wrLevXqYdy4cTh8+DDeeustrF27FgBQu3btPLdvy897aW5uDgBar0PXa6tfvz7Onz+PihUrasRduXJlJr1GggkwERHJpnFjwNsbSE0FhNA8JoTUX7mydF5RSEtLQ0xMDO7fv4+TJ0/i22+/RadOndC+fXt88MEHAIDKlStDpVJh4cKFuHHjBlavXq21IKpixYpITk7Gvn378PjxY6SmpqJChQowNzdXP27r1q345ptv3ije4OBg1KpVC7169cLJkydx9OhRfPDBB/D394evr+9rX7dixYo4ePAg7t+/r94JYdSoUdi9ezdu3ryJkydPIjw8XKNmt6Bu3ryJcePGISoqCrdv38aePXtw9epV9TUnTpyI33//HRMnTsTFixfVC+8A5Ou99PT0hEKhwPbt2/Ho0SP1Lh0VK1ZEdHQ0bt26hcePHyMrKwvDhg3DkydP8N577+HYsWO4fv06du/ejf79++v8RYAMDxNgIiKSjVIJTJsm7fqQlASoVEBWlvQ5KUnqnzq16BbA7dq1C2XLlkXFihXRpk0bhIeHY8GCBfjrr7/UNbN16tTB3LlzMXPmTLz11ltYs2YNpk+frnEdPz8/DB06FD169ICzszNmzZoFZ2dnrFy5Ehs2bECNGjUwY8YMzJ49+43iVSgU+Ouvv1C6dGm0bNkSwcHBqFSpEtatW/dG150yZQpu3boFb29vODs7A5BmUocNG4bq1aujTZs2qFq1aoFuyJGbtbU1Ll26hG7duqFq1aoYPHgwhg0bhiFDhgCQth3bsGEDtm7dirp16yIoKAhHjx4FgHy9l+XKlcPkyZPxxRdfwNXVFcOHDwcg3RhEqVSiRo0acHZ2xp07d+Du7o7IyEhkZmbi7bffRq1atTBq1Cg4ODi8UakJlRwKIXL/zm18kpKSYG9vj8ePH3PzcCOgUqmwY8cOhIaGatXFkeHheBe958+f4+bNm/Dy8oKlpeVrXWPHDmk3iOvXc8oeKleWkt/Q0PxfJysrC0lJSbCzs2MiYwQ43obnZT9P4uPjUaZMGSQmJsLOzu6NnofboBERkexCQ6WtzqKjpQVvLi5S2UNxbn1GRMaDCTAREekFpRLw85M7CiIyBvx7AREREREZFSbARERERGRUmAATERERkVFhAkxERERERoUJMBEREREZFSbARERERGRUmAATERERkVFhAkxERESFZuXKlXBwcJA7DFkEBARg1KhR6nbFihUxb968Yo/DmMcgv5gAExGR0bp79y4GDBgAd3d3mJubw9PTE5988gni4+M1zsud2OR24MABBAUFwdHREdbW1qhSpQr69u2L9PT0PB9TsWJFKBQKKBQKWFtbo1atWvjpp58K66XJpkePHrhy5YrcYeiFY8eOYfDgwfk6t6iS1kuXLkGhUODIkSMa/U2aNIGlpSWeP3+u7nv+/DksLS3x888/F3oc+oYJMBERGaUbN27A19cXV69exe+//45r165h2bJl2LdvH5o2bYonT57k6zoXLlxAmzZt4Ovri4MHD+Lff//FwoULYW5ujszMzJc+dsqUKXj48CHOnTuH3r17Y9CgQdi5c2dhvLw8vSwpLwxWVlZwcXEp0ucoSoX5/jg7O8Pa2rrQrvc6fHx84ObmhoiICHXf06dPcfLkSTg7O2skxlFRUUhLS0NQUJAMkRYvJsBERFS4hABSUuT5ECLfYQ4bNgzm5ubYs2cP/P39UaFCBbRt2xZ79+7F/fv38dVXX+XrOnv27IGbmxtmzZqFt956C97e3mjTpg2WL18OKyurlz62VKlScHNzQ6VKlfD555/D0dERYWFh6uMJCQn48MMP4ezsDDs7OwQFBeHMmTMa15g6dSpcXFxQqlQpfPjhh/jiiy9Qt25d9fF+/fqhc+fOmDZtGtzd3VGtWjUA0ux39+7d4eDgAEdHR3Tq1Am3bt1SPy4iIgKNGjWCjY0NHBwc0KxZM9y+fRsAcObMGQQGBqJUqVKws7NDgwYNcPz4cQC6ZzKXLl0Kb29vmJubo1q1ali9erXGcYVCgZ9++gldunRRz6Bv3bo1X+//y2S/9smTJ6vfw6FDh2okuQEBARg+fDhGjRqFMmXKICQkBABw7tw5tG3bFra2tnB1dUWfPn3w+PFj9eNSUlLwwQcfwNbWFmXLlsWcOXO0nj93CURCQgKGDBkCV1dXWFpa4q233sL27dsRERGB/v37IzExUf1XgUmTJgEA0tLS8Omnn6JcuXKwsbFB48aNNZJZQHrPK1SoAGtra3Tp0kXrLxiBgYEaj/nnn39QtWpVdOjQQaM/IiICnp6e8PLywrFjx9C6dWuUKVMG9vb28Pf3x8mTJzWue+nSJTRv3hyWlpaoUaMG9u7dC4VCgS1btqjPedXXmVyYABMRUeFKTQVsbeX5SE3NV4hPnjzB7t278fHHH2slqW5ubujVqxfWrVsHkY+E2s3NDQ8fPsTBgwdf6+0CgKysLGzcuBH//fcfzM3N1f3vvvsu4uLisHPnTpw4cQL169dHq1at1LPTa9aswbRp0zBz5kycOHECFSpUwNKlS7Wuv2/fPly+fBlhYWHYvn07VCoVQkJCUKpUKRw6dAiRkZGwtbVFmzZtkJ6ejoyMDHTu3Bn+/v44e/YsoqKiMHjwYCgUCgBAr169UL58eRw7dgwnTpzAF198ATMzM52vbfPmzfjkk0/wv//9D+fOncOQIUPQv39/hIeHa5w3efJkdO/eHWfPnkVoaCh69eqV71n4l9m3bx8uXryIiIgI/P7779i0aRMmT56scc6qVatgbm6OyMhILFu2DAkJCQgKCkK9evVw/Phx7Nq1C7Gxsejevbv6MWPHjsWBAwfw119/Yc+ePYiIiNBKEF+UlZWFtm3bIjIyEr/99hsuXLiAGTNmQKlUws/PD/PmzYOdnR0ePnyIhw8f4tNPPwUADB8+HFFRUfjjjz9w9uxZvPvuu2jTpg2uXr0KAIiOjsbAgQMxfPhwnD59GoGBgZg6darGcwcGBuKff/5BRkYGACA8PBwBAQHw9/fXGIfw8HAEBgYCkGaJ+/bti3/++QdHjhxBlSpVEBoaiqdPnwIAMjMz0blzZ1hbWyM6Oho//vij1i+Nr/o6k5UgkZiYKACIx48fyx0KFYP09HSxZcsWkZ6eLncoVAw43kXv2bNn4sKFC+LZs2dSR3KyENJcbLF/ZCYlif/++09kZma+NOYjR44IAGLz5s06j8+dO1cAELGxsUIIIfz9/cUnn3yi89yMjAzRr18/AUC4ubmJzp07i4ULF4rExMSXxuDp6SnMzc2FjY2NMDU1FQCEo6OjuHr1qhBCiEOHDgk7Ozvx/Plzjcd5e3uLH374QQghROPGjcWwYcM0jjdr1kzUqVNH3e7bt69wdXUVaWlp6r7Vq1eLatWqiaysLHVfWlqasLKyErt37xbx8fECgIiIiNAZe6lSpcTKlSt1HluxYoWwt7dXt/38/MSgQYM0znn33XdFaGioug1AjB8/Xt1OTk4WAMTOnTt1Pke2zMzMl4533759haOjo0hJSVH3LV26VNja2qof4+/vL+rVq6fxuG+++Ua8/fbbGn13794VAMTly5fF06dPhbm5uVi/fr36eHx8vLCystL4OvH09BTff/+9EEKI3bt3CxMTE3H58mWdseZ+34QQ4vbt20KpVIr79+9r9Ldq1UqMGzdOCCHEe++9p/FeCiFEjx49NK519epVAUAcPnxYCCFEw4YNxfr168WDBw+EhYWFePbsmUhNTRUWFhZi1apVOuPLzMwUpUqVEtu2bRNCCLFz505hamoqHj58qD4nLCxM4/vqVV9numj9PHnB48ePBYBXfm/lB2eAiYiocFlbA8nJ8nwUsN5SFKBkIi9KpRIrVqzAvXv3MGvWLJQrVw7ffvstatasiYcPH770sWPHjsXp06exf/9+NG7cGN9//z0qV64MQCozSE5OhpOTE2xtbdUfN2/exPXr1wEAly9fRqNGjTSumbsNALVq1dKYWT5z5gyuXbuGUqVKqa/r6OiI58+f4/r163B0dES/fv0QEhKCDh06YP78+RqvZcyYMfjwww8RHByMGTNmqOPR5eLFi2jWrJlGX7NmzXDx4kWNvtq1a6v/bWNjAzs7O8TFxem85rfffgtbW1vY2dmhfPnyuHPnTp7PX6dOHY063KZNmyI5ORl3795V9zVo0EDjMWfOnEF4eLjG++7j4wMAuH79Oq5fv4709HQ0btxY/RhHR0d1eYkup0+fRvny5VG1atU8z8nt33//RWZmJqpWraoRy4EDB9Tv+cWLFzXiyH6NL6pcuTLKly+PiIgIJCUl4dSpU/D390fZsmVRoUIFREVFqet/s2eAY2NjMWjQIFSpUgX29vaws7NDcnKy+r2+fPkyPDw84Obmpn6e3F97r/o6k5OprM9ORESGR6EAbGzkee6srHydVrlyZSgUCly8eBFdunTROn7x4kWULl0azs7O+X7qcuXKoU+fPujTpw+++eYbVK1aFcuWLdP6c/uLypQpg8qVK6Ny5crYsGEDatWqBV9fX9SoUQPJyckoW7asVr0ngALvFmCTazySk5PRoEEDrFmzRuvc7Ne8YsUKjBw5Ert27cK6deswfvx4hIWFoUmTJpg0aRLef/99/P3339i5cycmTpyIP/74Q+d7mV+5SygUCgWy8hjPoUOHonv37sjKykJycjLc3d1f+3kB3e9Phw4dMHPmTK1zy5Yti2vXrhX4OV5VD65LcnIylEolTpw4AaVSqXHM1ta2QNcKCAhAeHg4ateujSpVqqgXKmaXQQghULlyZXh4eAAA+vbti/j4eMyfPx+enp6wsLBA06ZNC1S6kJ+vM7lwBpiIiIyOk5MTWrdujSVLluDZs2cax2JiYrBmzRr06NFDXfNaUKVLl0bZsmWRkpKS78d4eHigR48eGDduHACgfv36iImJgampqTpJzv4oU6YMAKBatWo4duyYxnVyt3WpX78+rl69ChcXF61r29vbq8+rV68exo0bh8OHD+Ott97C2rVr1ceqVq2K0aNHY8+ePejatStWrFih87mqV6+OyMhIjb7IyEjUqFEjf2+MDo6Ojup4K1WqBFPTvOfzzpw5ozHGR44cga2trTrR06V+/fo4f/48KlasqPX+2NjYwNvbG2ZmZoiOjlY/5r///nvp9m+1a9fGvXv38jxH164h9erVQ2ZmJuLi4rTiyJ55rV69ukYc2a8xt8DAQBw+fBhhYWEICAhQ97ds2RIRERGIiIhQz/4C0hiNHDkSoaGhqFmzJiwsLDQWAVarVg13795FbGysui/3115+v87kwASYiIiM0qJFi5CWloaQkBAcPHgQd+/exa5du9C6dWuUK1cO06ZN0zj/0aNHOH36tMZHbGwsfvjhB3z00UfYs2cPrl+/jvPnz+Pzzz/H+fPn0aFDhwLF9Mknn2Dbtm04fvw4goOD0bRpU3Tu3Bl79uzBrVu3cPjwYXz11VfqHRdGjBiBn3/+GatWrcLVq1cxdepUnD179pWJe69evVCmTBl06tQJhw4dws2bNxEREYGRI0fi3r17uHnzJsaNG4eoqCjcvn0be/bswdWrV1G9enU8e/YMw4cPR0REBG7fvo3IyEgcO3YM1atX1/lcY8eOxcqVK7F06VJcvXoVc+fOxaZNm9SLvIpaeno6Bg4ciAsXLmDHjh2YOHEihg8fDhOTvFOgYcOG4cmTJ3jvvfdw7NgxXL9+Hbt370b//v2RmZkJW1tbDBw4EGPHjsX+/ftx7tw59OvX76XX9Pf3R8uWLdGtWzeEhYXh5s2b2LlzJ3bt2gVA2jEiOTkZ+/btw+PHj5GamoqqVauiV69e+OCDD7Bp0ybcvHkTR48exfTp0/H3338DgHqWfvbs2bh69SoWLVqkvuaLAgMDkZKSgl9++QX+/v4acUVHR+Po0aMaCXCVKlWwevVqXLx4EdHR0ejVq5fGLHbr1q3h7e2Nvn374uzZs4iMjMT48eMBQGOx5Mu+zmT1xlXEBoCL4IwLF0UZF4530XvZopXi9qpFUbndunVLvUjMzMxMeHh4iBEjRmj9f+Dv7y8AaH1888034uTJk6J3797Cy8tLWFhYCCcnJ9GyZUuxdevWlz73iwukXhQSEiLatm0rhBAiKSlJjBgxQri7u6vj69Wrl7hz5476/ClTpogyZcoIW1tbMWDAADFy5EjRpEkT9fG+ffuKTp06aT3Pw4cPxQcffCDKlCkjLCwsRKVKlcSgQYNEYmKiiImJEZ07dxZly5YV5ubmwtPTU0yYMEFkZmaKtLQ00bNnT+Hh4SHMzc2Fu7u7GD58uHr8dS3mWrJkiahUqZIwMzMTVatWFb/++qvGcehYkGhvby9WrFjx0vcwP4vgOnXqJCZMmCCcnJyEra2tGDRokMbCwrwWOF65ckV06dJFODg4CCsrK+Hj4yNGjRqlXtD19OlT0bt3b2FtbS1cXV3FrFmztK6Ve4zj4+NF//79hZOTk7C0tBRvvfWW2L59u/r40KFDhZOTkwAgJk6cKISQfoZNmDBBVKxYUZiZmYmyZcuKLl26iLNnz6of9/PPP4vy5csLKysr0aFDBzF79mytMciOB4DGwjUhhKhYsaIAIB48eKDuO3nypPD19RWWlpaiSpUqYsOGDVqv5+LFi6JZs2bC3Nxc+Pj4iG3btgkAYteuXepzXvZ1pktxLYJTCFEIKwBKuKSkJNjb2+Px48dwcnKSOxwqYiqVCjt27EBoaGie2/aQ4eB4F73nz5/j5s2b8PLygqWlpayxZGVlISkpCXZ2di+djTNkrVu3hpubm9Zeu4boVePdr18/JCQkaOxLS0UnMjISzZs3x7Vr1+Dt7f1a13jZz5P4+HiUKVMGiYmJsLOze6NYuQiOiIiohEpNTcWyZcsQEhICpVKJ33//HXv37tW4mQZRUdm8eTNsbW1RpUoVXLt2DZ988gmaNWv22slvcWICTEREVEIpFArs2LED06ZNw/Pnz1GtWjVs3LgRwcHBcodGRuDp06f4/PPPcefOHZQpUwbBwcE674inj5gAExERlVBWVlbYu3ev3GHorZUrV8odgkH74IMP8MEHH8gdxmsxzgIpIiIiIjJaTICJiKhQcE01Eb2p4vo5wgSYiIjeSPYdqgpyhygiIl1SU1MBaN8ZsLCxBpiIiN6IqakprK2t8ejRI5iZmcm6/VhWVhbS09Px/Plzo90GzZhwvA2HEAKpqamIi4uDg4OD1q2fCxsTYCIieiMKhQJly5bFzZs3cfv2bVljEULg2bNnsLKyeu3bGFPJwfE2PA4ODurbPBclJsBERPTGzM3NUaVKFdnLIFQqFQ4ePIiWLVvyxidGgONtWMzMzIp85jcbE2AiIioUJiYmst8JTqlUIiMjA5aWlkyIjADHm14XC2aIiIiIyKgwASYiIiIio8IEmIiIiIiMChNgIiIiIjIqTICJiIiIyKgwASYiIiIio8IEmIiIiIiMChNgIiIiKnEyM4HoaOnf0dFSm7RlZgKHDwNbtkif+T5JZE2ADx48iA4dOsDd3R0KhQJbtmzROufixYvo2LEj7O3tYWNjg4YNG+LOnTvq48+fP8ewYcPg5OQEW1tbdOvWDbGxscX4KoiIiKg47dgB+PoCXbtK7a5dpfaOHfLGpW+y36c2bYBevaTPfJ8ksibAKSkpqFOnDhYvXqzz+PXr19G8eXP4+PggIiICZ8+exddff61xp6HRo0dj27Zt2LBhAw4cOIAHDx6ga/Z3BBERERmUHTuA3r2BK1cACwupz8JCavfuzeQuW+73qVQpvk8vkvVWyG3btkXbtm3zPP7VV18hNDQUs2bNUvd5e3ur/52YmIiff/4Za9euRVBQEABgxYoVqF69Oo4cOYImTZoUXfBERERUrDIzga++AtLSADs7IPvux2ZmUjspCRg/HggJAZRKeWOVU+73SaGQ+k1M+D5lkzUBfpmsrCz8/fff+OyzzxASEoJTp07By8sL48aNQ+fOnQEAJ06cgEqlQnBwsPpxPj4+qFChAqKiovJMgNPS0pCWlqZuJyUlAQBUKhVUKlXRvSjSC9ljzLE2Dhxv48LxNmzR0cD9+4Cjo5T0WlhI45z92dQUuHcPiIoCGjeWM1J55X6fciup71Nhfl8rhBCi0K72BhQKBTZv3qxObmNiYlC2bFlYW1tj6tSpCAwMxK5du/Dll18iPDwc/v7+WLt2Lfr376+RzAJAo0aNEBgYiJkzZ+p8rkmTJmHy5Mla/WvXroW1tXWhvzYiIiIiejOpqal4//33kZiYCDs7uze6ll7PAANAp06dMHr0aABA3bp1cfjwYSxbtgz+/v6vfe1x48ZhzJgx6nZSUhI8PDwQGBgIJyenNwuc9J5KpUJYWBhat24NM12/GpNB4XgbF463YYuOlha8WVjkzADPmBGGL75ojbQ0M6hU0p/9N20qWTObhS33+5RbSX2f4uPjC+1aepsAlylTBqampqhRo4ZGf/Xq1fHPP/8AANzc3JCeno6EhAQ4ODioz4mNjYWbm1ue17awsIBFduX8C8zMzPgD04hwvI0Lx9u4cLwNU9OmQLly0kKuFycA09LM8OyZGZKSgGrVpPOMtbYV0H6fsmuAAUAIlNj3qTC/p/V2H2Bzc3M0bNgQly9f1ui/cuUKPD09AQANGjSAmZkZ9u3bpz5++fJl3LlzB02bNi3WeImIiKhoKZXAtGnSzGZSkjSTCUifk5Kk/qlTS1ZSVxR0vU9ZWXyfXiTrDHBycjKuXbumbt+8eROnT5+Go6MjKlSogLFjx6JHjx5o2bKlugZ427ZtiIiIAADY29tj4MCBGDNmDBwdHWFnZ4cRI0agadOm3AGCiIjIAIWGAr/9Ju1ycP++1JeWJs1oTp0qHSfN9+n6dWlnCKWS71M2WRPg48ePIzAwUN3Orsvt27cvVq5ciS5dumDZsmWYPn06Ro4ciWrVqmHjxo1o3ry5+jHff/89TExM0K1bN6SlpSEkJARLliwp9tdCRERExSM0VNrCKyoKiI+XallL2p/zi0P2+xQdDcTFAS4uUs0v3yeZE+CAgAC8ahOKAQMGYMCAAXket7S0xOLFi/O8mQYREREZHqVSSuZ27GBS9zJKJeDnJ3cU+kdva4CJiIiIiIoCE2AiIiIiMipMgImIiIjIqDABJiIiIiKjwgSYiIiIiIwKE2AiIiIiMipMgImIiIjIqDABJiIiIiKjwgSYiIiIyJCtWwcMGSJ3FHpF1jvBEREREVERCgwEIiKkf3/wAdCsmazh6AsmwERERESGRqUCzM01+3hPZDWWQBAREREZkgcPtJPfjAxAoZAnHj3EBJiIiIjIUBw4AJQrl9Pu2BEQAlAq5YtJDzEBJiIiIjIEM2cCAQE57YULgb/+ki0cfcYaYCIiIqKSrlUrYP/+nHZUFNCkiXzx6DkmwEREREQlla7FbnFxgLOzPPGUECyBICIiIiqJHj7UvdiNye8rMQEmIiIiKmkOHgTc3XPa7dtzsVsBMAEmIiIiKklmzwb8/XPa8+cD27bJF08JxBpgIiIiopKidWtg796cdmQkb3DxGpgAExEREem7jAzAzEyzLzYWcHGRJ54SjiUQRERERPosJkY7+VWpmPy+ASbARERERPrqn3+AsmVz2qGh0mI3U/4R/00wASYiIiLSR3PnAi1a5LS//x74+2/54jEg/PWBiIiISN+0aQPs3p3TPnQIaN5cvngMDBNgIiIiIn2ha7FbTAzg6ipPPAaKJRBERERE+iA2VvdiNya/hY4JMBEREZHcDh8G3Nxy2m+/zcVuRYgJMBEREZGc5s8HmjXLac+Zo1n/S4WOv1YQERERyaV9e82dHQ4cAFq2lC8eI8EEmIiIiKi46Vrs9vChZhkEFRkmwERERETF6dEj7bu4qVSs9y1GrAEmIiIiKi5RUZrJb6tWXOwmAybARERERMVh4ULAzy+n/d13wN698sVjxPjrBhEREVFR69gR2LYtp83FbrJiAkxERERUVDIztcsb7t8H3N3liYcAMAEmIiIiKhq6Frulp2vv/kDFjjXARERERIUtOloz+Q0IkBa7MfnVC0yAiYiIiArT4sVAkyY57RkzgPBw+eIhLSyBICIiIiosXboAW7bktMPDpdlf0itMgImIiIjeFBe7lShMgImIiIjexOPHgLOzZh8Xu+k11gATERERva6jRzWT3xYtuNitBGACTERERPQ6li0DGjfOaX/7LXDwoHzxUL6xBIKIiIiooN59F/jzz5z2vn1AUJB88VCBMAEmIiIiyq+sLECp1Oy7excoX16eeOi1MAEmIiIiyo/4eKBMGc2+tDTA3FyeeOi1sQaYiIiI6FWOHdNMfv38pMVuTH5LJCbARERERC/z449Ao0Y57W++ASIj5YuH3hhLIIiIiIjy0qMHsH59TjssDAgOli8eKhRMgImIiIhyy8oCLCyAjIycPi52MxhMgImIiIhe9OQJ4OSk2cfFbgaFNcBERERE2U6c0Ex+GzfmYjcDxASYiIiICAB++gnw9c1pT5oEHDkiWzhUdFgCQURERPTee8Aff+S0d+8G3n5bvnioSDEBJiIiIuOVlQVYW0s1vtlu3wYqVJAvJipyTICJiIjIOP33H+DoqNn3/Lm0+wMZNNYAExERkfE5dUoz+fX1lRa7Mfk1CrImwAcPHkSHDh3g7u4OhUKBLVu25Hnu0KFDoVAoMG/ePI3+J0+eoFevXrCzs4ODgwMGDhyI5OTkog2ciIiISq5ffgHq189pT5gg3eqYjIasCXBKSgrq1KmDxYsXv/S8zZs348iRI3B3d9c61qtXL5w/fx5hYWHYvn07Dh48iMGDBxdVyERERFSS9e4NDByY0965E5g8Wb54SBay1gC3bdsWbdu2fek59+/fx4gRI7B79260a9dO49jFixexa9cuHDt2DL7/v23JwoULERoaitmzZ+tMmImIiMgIZWUBtrbAs2c5fbduAZ6esoVE8tHrRXBZWVno06cPxo4di5o1a2odj4qKgoODgzr5BYDg4GCYmJggOjoaXbp00XndtLQ0pL2w2jMpKQkAoFKpoFKpCvlVkL7JHmOOtXHgeBsXjrdxyfd4JyTAzMVF87FPn0r1vvxaKTEK8/tarxPgmTNnwtTUFCNHjtR5PCYmBi65vqBNTU3h6OiImJiYPK87ffp0TNbx547w8HBYW1u/WdBUYoSFhckdAhUjjrdx4Xgbl5eNt92NGwgcM0bdTqhUCQfmzgX27SuO0KgQpaamFtq19DYBPnHiBObPn4+TJ09CoVAU6rXHjRuHMS98MyQlJcHDwwOBgYFwyn3vbzI4KpUKYWFhaN26NczMzOQOh4oYx9u4cLyNy6vGW/HrrzB94f/7zC++gM2UKQgtziCp0MTHxxfatfQ2AT506BDi4uJQ4YWNqDMzM/G///0P8+bNw61bt+Dm5oa4uDiNx2VkZODJkydwc3PL89oWFhaw0LHNiZmZGX9gGhGOt3HheBsXjrdx0TneH3wArF6d0/77byhDQ6Es3tCoEBXm97TeJsB9+vRBcHCwRl9ISAj69OmD/v37AwCaNm2KhIQEnDhxAg0aNAAA7N+/H1lZWWjcuHGxx0xEREQyEwKwswNe3BL15k2gYkXZQiL9I2sCnJycjGvXrqnbN2/exOnTp+Ho6IgKFSpolSOYmZnBzc0N1apVAwBUr14dbdq0waBBg7Bs2TKoVCoMHz4cPXv25A4QRERExiYxEXBw0Ox79gywtJQlHNJfsu4DfPz4cdSrVw/16tUDAIwZMwb16tXDhAkT8n2NNWvWwMfHB61atUJoaCiaN2+OH3/8sahCJiIiIn109qxm8lunjjQbzOSXdJB1BjggIABCiHyff+vWLa0+R0dHrF27thCjIiIiopJEsXq15s0tvvwSmDZNvoBI7+ltDTARERHRq9RbsACm+/fndGzfDuS6cRZRbkyAiYiIqOTJyoKZuTkqvNh3/TpQqZJcEVEJwgSYiIiISpZHj4BcN8JCaipgZSVPPFTiyLoIjoiIiKhA9u/XSn5V6elMfqlAmAATERFRyfD550CrVupmVv36+GvLFvnioRKLCTARERHpP1dXYNasnPZ33yHzyBH54qESjTXAREREpL+EAExyzdcdOwb4+gIqlTwxUYnHBJiIiIj0k67FbomJ0q2Oid4ASyCIiIhI/4SHaye/WVlMfqlQMAEmIiIi/fLll0BQUE47+7bGCoV8MZFBYQkEERER6Q93d+Dhw5z2zJnAZ5/JFw8ZJCbAREREJD9di92io4FGjeSJhwwaE2AiIiKSV3w8UKaMZl9CAmBvL0s4ZPhYA0xERETyOXBAO/nNymLyS0WKCTARERHJ4+uvgYCAnHbNmlzsRsWCJRBERERU/Dw9gTt3ctrffguMGydfPGRUmAATERFR8dG12C0qCmjSRJ54yCgxASYiIqLi8eQJ4OSk2ffff4CDgyzhkPFiDTAREREVvUOHtJPfrCwmvyQLJsBERERUtCZNAlq2zGlXq8bFbiQrlkAQERFR0fH2Bm7cyGl/8w0wfrx88RCBCTAREREVBV2L3SIjAT8/eeIhegETYCIiIipc//0HODpq9j15ApQuLU88RLmwBpiIiIgKT2SkdvKblcXkl/QKE2AiIiIqHFOmAM2b57QrV+ZiN9JLTICJiIjozVWrBkycmNOeNAm4elW2cIhehjXARERE9Pp0LXb75x+gWTN54iHKBybARERE9HoSErRre7nYjUoAlkAQERFRwUVFaSe6XOxGJQQTYCIiIiqYadM09/P19ORiNypRmAATERFR/tWooXkntwkTgFu3ZAuH6HWwBpiIiIheTdditwMHgJYt5YmH6A0wASYiIqKXS0wEHBw0++LjtW94QVRCsASCiIiI8hYdrZ38ZmUx+aUSjQkwERER6TZjBtCkSU67XDkudiODwASYiIiItNWuDYwbl9P+8kvg3j354iEqRKwBJiIiohy6FruFhwMBAbKEQ1QUmAATERGRJCkJsLfX7Hv0CChTRp54iIoISyCIiIgIOH5cO/nNymLySwaJCTAREZGx++47oGHDnLabGxe7kUFjAkxERGTM6tcHPvssp/3558DDh/LFQ1QMWANMRERkrHLP8O7fDwQGyhMLUTFiAkxERGRsnj4F7Ow0++LiAGdneeIhKmYsgSAiIjImJ05oJ79ZWUx+yagwASYiIjIWc+cCvr457TJluNiNjBITYCIiImPQsCHwv//ltD/9VNrjl8gIsQaYiIjI0OWe4Q0LA4KD5YmFSA8wASYiIjJUyclAqVKafbGxgIuLPPEQ6QmWQBARERmiU6e0k9/MTCa/RGACTEREZHjmz5ducJHNwUFa7GbC//aJACbAREREhsXPDxg1Kqc9ejTw33+yhUOkj1gDTEREZChyL3bbvRt4+215YiHSY0yAiYiISjpdi91iYgBXV3niIdJzLIEgIiIqyc6c0b3YjckvUZ6YABMREZVUixYBdevmtEuV4mI3onzgdwgREVFJ1LIlMGJETnvkSCApSb54iEoQ1gATERGVNLkXu+3cCbRpk6+HZmYC0dFAXJy0JXDjxoBSWQQxEukxWWeADx48iA4dOsDd3R0KhQJbtmxRH1OpVPj8889Rq1Yt2NjYwN3dHR988AEePHigcY0nT56gV69esLOzg4ODAwYOHIjk5ORifiVERETFICVFO/l98CDfye+OHYCvr3R6r17SZ19fqZ/ImMiaAKekpKBOnTpYvHix1rHU1FScPHkSX3/9NU6ePIlNmzbh8uXL6Nixo8Z5vXr1wvnz5xEWFobt27fj4MGDGDx4cHG9BCIiouJx9ixga6vZl5kJlC2br4fv2AH07g1cuQJYWEjlwhYWUrt3bybBZFxkLYFo27Yt2rZtq/OYvb09wsLCNPoWLVqERo0a4c6dO6hQoQIuXryIXbt24dixY/D19QUALFy4EKGhoZg9ezbc3d2L/DUQEREVuSVLgGHDctqWlsCzZ/l+eGYm8NVXQFoaYGeXM4lsYiK1k5KA8eOBkBCWQ5BxKFE1wImJiVAoFHBwcAAAREVFwcHBQZ38AkBwcDBMTEwQHR2NLl266LxOWloa0tLS1O2k/180oFKpoFKpiu4FkF7IHmOOtXHgeBsXQxxvZevWMDlwQN3O/OgjZM2fDxTgNUZHA/fvA46OgJmZ9nFTU+DePSAqSqoJLikMcbwpb4U5ziUmAX7+/Dk+//xzvPfee7CzswMAxMTEwMXFReM8U1NTODo6IiYmJs9rTZ8+HZMnT9bqDw8Ph7W1deEGTnor918YyLBxvI2LoYx3p86dNdpR48cj7jWLdpcvf/U58fElsxTCUMabXi41NbXQrlUiEmCVSoXu3btDCIGlS5e+8fXGjRuHMWPGqNtJSUnw8PBAYGAgnJyc3vj6pN9UKhXCwsLQunVrmOmaCiGDwvE2LgYz3qmpMPv/v3ZmU926Bd/XLO2Ljga6dpVqfnW9LSqVVB6xaVPJmwE2iPGmfImPjy+0a+l9Apyd/N6+fRv79+9Xz/4CgJubG+Li4jTOz8jIwJMnT+Dm5pbnNS0sLGBhYaHVb2Zmxm8gI8LxNi4cb+NSosf73DmgVi3NvowMmL1BcW7TpkC5ctKCtxdrgAHpvhlJSUC1atJ5JbEGuESPN+VbYY6xXt8IIzv5vXr1Kvbu3as1O9u0aVMkJCTgxIkT6r79+/cjKysLjUvSr7BEREQA8MMPmsmvUillqG+YlSqVwLRp0gxwUpI045uVJX1OSpL6p04tmckv0euQNQFOTk7G6dOncfr0aQDAzZs3cfr0ady5cwcqlQrvvPMOjh8/jjVr1iAzMxMxMTGIiYlBeno6AKB69epo06YNBg0ahKNHjyIyMhLDhw9Hz549uQMEERGVLMHBwNChOe2hQ4GMjEK7fGgo8NtvQNWqUrnD06fS52rVpP7Q0EJ7KiK9J2sJxPHjxxEYGKhuZ9fl9u3bF5MmTcLWrVsBAHVfvM85pMVqAQEBAIA1a9Zg+PDhaNWqFUxMTNCtWzcsWLCgWOInIiIqFLlvbrF1K9ChQ6E/TWiotNUZ7wRHxk7WBDggIABCiDyPv+xYNkdHR6xdu7YwwyIiIioez54BuXcfundPKtgtIkol4OdXZJcnKhH0ugaYiIjIYF24oJ38ZmQUafJLRBImwERERMVt+XKgZk3NvkJY7EZE+cMEmIiIqDi1aQMMHpzT/vBDKfklomKj9/sAExERGYzci922bAE6dZIlFCJjxgSYiIioqD1/DlhZafbduQN4eMgTD5GRYwkEERFRUbp4UTv5VamY/BLJiAkwERFRUfnlF6BGDc0+IQBT/gGWSE5MgImIiIpCaCgwcGBOu18/LnYj0hP8FZSIiKiw5V7stmkT0KWLPLEQkRYmwERERIUlLQ2wtNTsu30bqFBBnniISCeWQBARERWGy5e1k1+ViskvkR5iAkxERPSmVq0CfHw0+7jYjUhvMQEmIiJ6Ex07SgvcsvXpw8VuRHqOv5oSERG9rtyL3TZsAN55R55YiCjfmAATEREVlK7FbrduAZ6esoRDRAXDEggiIqKCuHpVO/lNT2fyS1SCMAEmIiLKr48+AqpW1ewTAjAzkyceInotLIEgIiLKj9z1vu+/D6xZI08sRPRGOANMRET0KrmT38mTmfwSlWCcASYiIspLaipgY6PZd+QI0LixPPEQUaHgDDAREZEukZHaye+zZ0x+iQwAE2AiIqLchg0DmjfX7BNCe/cHIiqRWAJBRET0otz1vgDv7EZkYDgDTERElC138jtsGJNfIgPEGWAiIqJnzwBra82+yEjAz0+eeIioSDEBJiIi4xYVpZ3opqYCVlbyxENERY4lEEREZLxGjtROfoVg8ktk4DgDTERExomL3YiMFmeAiYjI+OROfgcPZvJLZEQ4A0xERMbj+XPt8oZDh7T3/CUig8YEmIiIjMPRo9p3cUtJ0d79gYgMHksgiIjI8I0erZ38CsHkl8hIcQaYiIgMGxe7EVEunAEmIiLDlTv5HTCAyS8RcQaYiIgMUFoaYG6u2RcRAfj7yxIOEekXzgATEZFBsb92DWalSml2Jicz+SUiNc4AExGRwTD54gsEzJ2r2cmSByLKhQkwEREZBoUCytx9TH6JSAeWQBARUcmXa7FbVu/eTH6JKE9MgImIqORKT9dKfiOnTEHmL7/IFBARlQRMgImIqGQ6dQqwsNDoUsXH43Ht2jIFREQlBRNgIiIqeb78EqhfX7NPCCD37g9ERDpwERwREZUsvLMbEb0hzgATEVHJkTv5ff99Jr9EVGCcASYiIv2nUmnf2W3PHqB1a3niIaISjQkwERHptzNngLp1NfsSEwE7O1nCIaKSjyUQRESkv77+Wjv5FYLJLxG9Ec4AExGRfuJiNyIqIpwBJiIi/ZM7+e3enckvERUazgATEZH+0LXYbdcuICREnniIyCAxASYiIv1w7hxQq5ZmX0ICYG8vSzhEZLhYAkFERPKbMkU7+RWCyS8RFQnOABMRkbzMzaXShxex3peIihBngImISD4KhWby26ULk18iKnKcASYiouKXkQGYmWn2bd8OtGsnTzxEZFSYABMRUfG6cAGoWVOz77//AAcHWcIhIuPDEggiIio+336rnfwKUWKS38xM4PBhYMsW6XNmptwREdHr4AwwEREVDxsbIDVVs68E1fvu2AF89RVw/bqU+CqVgLc3MG0aEBoqd3REVBCyzgAfPHgQHTp0gLu7OxQKBbZs2aJxXAiBCRMmoGzZsrCyskJwcDCuXr2qcc6TJ0/Qq1cv2NnZwcHBAQMHDkRycnIxvgoiInolhUIz+W3fvsQlv717A1euABYWQKlS0ucrV6T+HTvkjpCICkLWBDglJQV16tTB4sWLdR6fNWsWFixYgGXLliE6Oho2NjYICQnB8+fP1ef06tUL58+fR1hYGLZv346DBw9i8ODBxfUSiIjoZTIztW9rvHUrsG2bPPG8hsxMaeY3LQ2ws5PW7pmYSJ/t7KT+8eNZDkFUkshaAtG2bVu0bdtW5zEhBObNm4fx48ejU6dOAIBff/0Vrq6u2LJlC3r27ImLFy9i165dOHbsGHx9fQEACxcuRGhoKGbPng13d3ed105LS0NaWpq6nZSUBABQqVRQ5d6LkgxO9hhzrI0Dx1tGly7BrHZtjS5VTAzg6Ki9728hKYrxjo4G7t+Xws69cQUAmJoC9+4BUVFA48aF9rSUD/z+Ni6FOc4KIfTjb1AKhQKbN29G586dAQA3btyAt7c3Tp06hbp166rP8/f3R926dTF//nz88ssv+N///of//vtPfTwjIwOWlpbYsGEDunTpovO5Jk2ahMmTJ2v1r127FtbW1oX6uoiIjFHlTZtQ89dfNfr+ylXmRkRUEKmpqXj//feRmJgIOzu7N7qW3i6Ci4mJAQC4urpq9Lu6uqqPxcTEwMXFReO4qakpHB0d1efoMm7cOIwZM0bdTkpKgoeHBwIDA+Hk5FRYL4H0lEqlQlhYGFq3bg0zXdM5ZFA43sXP1MUFioQEjT5VejqKY51YUYx3dDTQtatU86vrkiqVVAaxaRNngIsbv7+NS3x8fKFdS28T4KJkYWEBCwsLrX4zMzN+AxkRjrdx4XgXk9z1viEhwK5dKO53vjDHu2lToFw5acGbnZ3mSxQCSEoCqlWTzlMqC+UpqYD4/W0cCnOM9XYfYDc3NwBAbGysRn9sbKz6mJubG+Li4jSOZ2Rk4MmTJ+pziIioGOha7LZ5M7BrlzzxFCKlUtrqzMJCSnZVKiArS/qclCT1T53K5JeoJNHbBNjLywtubm7Yt2+fui8pKQnR0dFo2rQpAKBp06ZISEjAiRMn1Ofs378fWVlZaMy/QxERFY8rV6SVYC96/Bj4/zUdhiA0FPjtN6BqVanc4elT6XO1alI/9wEmKllkLYFITk7GtWvX1O2bN2/i9OnTcHR0RIUKFTBq1ChMnToVVapUgZeXF77++mu4u7urF8pVr14dbdq0waBBg7Bs2TKoVCoMHz4cPXv2zHMHCCIiKkRz5gCffqrZpx9rqwtdaKhU0REdDcTFAS4uUs0vZ36JSh5ZE+Djx48jMDBQ3c5emNa3b1+sXLkSn332GVJSUjB48GAkJCSgefPm2LVrFywtLdWPWbNmDYYPH45WrVrBxMQE3bp1w4IFC4r9tRARGR0XF+DRI80+A01+symVgJ+f3FEQ0ZuSNQEOCAjAy3ZhUygUmDJlCqZMmZLnOY6Ojli7dm1RhEdERHnJXe/bqhWwd688sRARFZDe1gATEZEeysrSTn43bGDyS0QlSr4T4IyMjFeec+HChTcKhoiI9Ni1a9oFr3FxwDvvyBMPEdFryncC3KtXr5cev3DhAoKCgt44ICIi0kPz5wNVqmj2CQE4O8sTDxHRG8h3AhwVFYWhQ4fqPHbx4kUEBQXBjysDiIgMT7lywKhRmn0GvtiNiAxbvhPg3bt3Y+PGjfjyyy81+i9duoSgoCA0adIEGzZsKPQAiYhIRgoF8OBBTrtlSya/RFTi5XsXiOrVq2PHjh1o1aoVHB0d8emnn+LSpUsIDAxEw4YN8eeff0LJzRCJiAxDVpZ2ve8ffwA9esgTDxFRISrQNmgNGzbEli1b0L59eyQnJ2P58uVo0KAB/vzzT5jmvgsQERGVTDduAN7emn0xMYCrqzzxEBEVsgJvgxYUFIS1a9di2rRpqFu3LjZv3gxzc/OiiI2IiIrbokXayW9WFpNfIjIo+Z62LV26NBS59n48dOgQXHP9UHzy5EnhREZERMWrYkXg9m3NPtb7EpEByncCPG/evCIMg4iIZJX75hZNmgBRUfLEQkRUxPKdAPft27co4yAiIjnoWuy2Zg3w/vvyxENEVAy4co2IyFjdugV4eWn2PXwIuLnJEg4RUXEp8CI4IiIyAEuXaie/WVlMfonIKHAGmIjI2FStCly9qtnHxW5EZEQ4A0xEZEwUCs3kt2FDJr9EZHReOwFOT0/H5cuXkZGRUZjxEBFRURBCe6eHX38Fjh6VJx4iIhkVOAFOTU3FwIEDYW1tjZo1a+LOnTsAgBEjRmDGjBmFHiAREb2hO3cAk1w/7u/fB/r0kSceIiKZFTgBHjduHM6cOYOIiAhYWlqq+4ODg7Fu3bpCDY6IiN7Q8uWAp6dmX1YW4O4uTzxERHqgwIvgtmzZgnXr1qFJkyYad4arWbMmrl+/XqjBERHRG6hRA7h4UbOP9b5ERAWfAX706BFcXFy0+lNSUrRulUxERDJRKDST37p1mfwSEf2/AifAvr6++Pvvv9Xt7KT3p59+QtOmTQsvMiIiKjhdi91WrABOnZInHiIiPVTgEohvv/0Wbdu2xYULF5CRkYH58+fjwoULOHz4MA4cOFAUMRIRUX7cuwd4eGj23b0LlC8vTzxERHqqwDPAzZs3x+nTp5GRkYFatWphz549cHFxQVRUFBo0aFAUMRIR0ausWKGd/GZlMfklItLhte4E5+3tjeXLlxd2LERE9Drq1AHOntXsY70vEVGeCpwAJyUl6exXKBSwsLCAubn5GwdFRET5lLvet2ZN4Nw5eWIhIiohClwC4eDggNKlS2t9ODg4wMrKCp6enpg4cSKysrKKIl4iIgJ0L3ZbvpzJLxFRPhR4BnjlypX46quv0K9fPzRq1AgAcPToUaxatQrjx4/Ho0ePMHv2bFhYWODLL78s9ICJiIzegwdAuXKafbdvAxUqyBMPEVEJU+AEeNWqVZgzZw66d++u7uvQoQNq1aqFH374Afv27UOFChUwbdo0JsBERIVt1SqgXz/Nvqws7dlgIiLKU4FLIA4fPox69epp9derVw9RUVEApJ0i7ty58+bRERFRDl9f7eRXVykEERG9VIETYA8PD/z8889a/T///DM8/n8Lnvj4eJQuXfrNoyMiIolCAZw4kdOuWpU7PRARvaYCl0DMnj0b7777Lnbu3ImGDRsCAI4fP45Lly7hzz//BAAcO3YMPXr0KNxIiYiMkRCASa65imXLgCFD5ImHiMgAFDgB7tixIy5fvowffvgBly9fBgC0bdsWW7ZsQcWKFQEAH330UaEGSURklBITAQcHzb5btwBPTzmiISIyGK91I4yKFSti+vTphR0LERFli44GmjTR7ONiNyKiQvFaCTAApKam4s6dO0hPT9for1279hsHRURk1GbMAMaNy2mXKwfcuydfPEREBqbACfCjR4/Qv39/7Ny5U+fxzMzMNw6KiMho1a4N/PtvTvvLL4Fp0+SLh4jIABV4F4hRo0YhISEB0dHRsLKywq5du7Bq1SpUqVIFW7duLYoYiYgMX/Z2Zi8mv+HhTH6JiIpAgWeA9+/fj7/++gu+vr4wMTGBp6cnWrduDTs7O0yfPh3t2rUrijiJiAxXUhJgb6/Z9+gRUKaMPPEQERm4As8Ap6SkwMXFBQBQunRpPHr0CABQq1YtnDx5snCjIyIydMeOaSe/WVlMfomIilCBE+Bq1aqptz+rU6cOfvjhB9y/fx/Lli1D2bJlCz1AIiKD9d13QKNGOW1XV97ZjYioGBS4BOKTTz7Bw4cPAQATJ05EmzZtsGbNGpibm2PlypWFHR8RkWGqXx84dSqn/dlnwMyZ8sVDRGRE8p0A37x5E15eXujdu7e6r0GDBrh9+zYuXbqEChUqoAz/ZEdE9Gq5Z3j37QOCguSJhYjICOU7Afb29oanpycCAwMRFBSEgIAAlC9fHtbW1qhfv35RxkhEZBiePgXs7DT74uIAZ2d54iEiMlL5ToD379+PiIgIRERE4Pfff0d6ejoqVaqEoKAgBAYGIjAwEK6urkUZKxFRyXX8ONCwoWYf7+xGRCSLfCfAAQEBCAgIAAA8f/4chw8fVifEq1atgkqlgo+PD86fP19UsRIRlUxz5wL/+19O28kJePxYvniIiIzca90K2dLSEkFBQWjevDkCAwOxc+dO/PDDD7h06VJhx0dEVLI1bCjN/mb79FNp9wciIpJNgRLg9PR0HDlyBOHh4YiIiEB0dDQ8PDzQsmVLLFq0CP7+/kUVJxFRyZO7vCEsDAgOlicWIiJSy3cCHBQUhOjoaHh5ecHf3x9DhgzB2rVrufcvEVFuyclAqVKafbGxwP/fRIiIiOSV7xthHDp0CE5OTggKCkKrVq3QunVrJr9ERLmdPKmd/GZmMvklItIj+U6AExIS8OOPP8La2hozZ86Eu7s7atWqheHDh+PPP/9U3xKZiMhozZsHNGiQ07a3l+7sZlLgm24SEVERyvdPZRsbG7Rp0wYzZsxAdHQ0Hj9+jFmzZsHa2hqzZs1C+fLl8dZbbxVlrERE+qtpU2D06Jz2qFFAQoJc0RAR0Uu81i4QgJQQOzo6wtHREaVLl4apqSkuXrxYmLEREZUMuRe77doFhITIEwsREb1SvhPgrKwsHD9+HBEREQgPD0dkZCRSUlJQrlw5BAYGYvHixQgMDCzKWImI9IuuxW4PHwJubvLEQ0RE+ZLvBNjBwQEpKSlwc3NDYGAgvv/+ewQEBMDb27so4yMi0k+nTwP16mn2ZWay3peIqATIdwL83XffITAwEFWrVi3KeIiI9N/ChcDIkTltGxtpNpiIiEqEfCfAQ4YMKco4iIhKhhYtgH/+yWmPGAEsWCBfPEREVGCvvQiOiMjo5F7stmMH0LatPLEQEdFrYwJMRPQqKSmAra1m34MHAG8GRERUIun1ao3MzEx8/fXX8PLygpWVFby9vfHNN99ACKE+RwiBCRMmoGzZsrCyskJwcDCuXr0qY9REZFDOntVOfjMzmfwSEZVgep0Az5w5E0uXLsWiRYtw8eJFzJw5E7NmzcLChQvV58yaNQsLFizAsmXLEB0dDRsbG4SEhOD58+cyRk5EBmHJEqBOnZy2pSXv7EZEZAD0+qf44cOH0alTJ7Rr1w4VK1bEO++8g7fffhtHjx4FIM3+zps3D+PHj0enTp1Qu3Zt/Prrr3jw4AG2bNkib/BEVLIFBADDhuW0P/4YePZMtnCIiKjw6HUNsJ+fH3788UdcuXIFVatWxZkzZ/DPP/9g7ty5AICbN28iJiYGwcHB6sfY29ujcePGiIqKQs+ePXVeNy0tDWlpaep2UlISAEClUkGlUhXhKyJ9kD3GHGvj8DrjbWZurtHO2LIFIjQU4NeM3uP3t3HheBuXwhxnvU6Av/jiCyQlJcHHxwdKpRKZmZmYNm0aevXqBQCIiYkBALi6umo8ztXVVX1Ml+nTp2Py5Mla/eHh4bC2ti7EV0D6LCwsTO4QqBjlZ7yVaWlo36OHRt/uX37Bc0Da8YFKDH5/GxeOt3FITU0ttGvpdQK8fv16rFmzBmvXrkXNmjVx+vRpjBo1Cu7u7ujbt+9rX3fcuHEYM2aMup2UlAQPDw8EBgbCycmpMEInPaZSqRAWFobWrVvDzMxM7nCoiOV7vM+dg1n9+pqPffYMQUplEUdIhYnf38aF421c4uPjC+1aep0Ajx07Fl988YW6lKFWrVq4ffs2pk+fjr59+8LNzQ0AEBsbi7IvrMiOjY1F3bp187yuhYUFLCwstPrNzMz4DWREON7G5aXj/cMPwNChOW2lEsjIAL86Si5+fxsXjrdxKMwx1utFcKmpqTDJtdpaqVQiKysLAODl5QU3Nzfs27dPfTwpKQnR0dFo2rRpscZKRCVUq1aaye+QIUBGhnzxEBFRkdPrGeAOHTpg2rRpqFChAmrWrIlTp05h7ty5GDBgAABAoVBg1KhRmDp1KqpUqQIvLy98/fXXcHd3R+fOneUNnoj0X+47u/31F9CxozyxEBFRsdHrBHjhwoX4+uuv8fHHHyMuLg7u7u4YMmQIJkyYoD7ns88+Q0pKCgYPHoyEhAQ0b94cu3btgqWlpYyRE5Fee/YMyL3g9e5doHx5eeIhIqJipdcJcKlSpTBv3jzMmzcvz3MUCgWmTJmCKVOmFF9gRFRyXbgA1Kyp2ZeRIdX9EhGRUdDrGmAiokK1fLl28isEk18iIiPDBJiIjIKyXTtg8OCcjg8/lJJfIiIyOnpdAkFEVBg65V4Uu2UL0KmTHKEQEZEeYAJMRIYrM1Prtsa4cwfw8JAnHiIi0gtMgInIMCUlAbnu7AaVCjDljz0iImPHGmAiMjw3bwJ+fsD16wCAJ9WqQZWezuSXiIgAcAaYiAzNoUNA167A48dA2bLI2LgRh+LiECp3XEREpDc4A0xEhmPFCunWxo8fS+UPx45B+PrKHRUREekZJsBEVPJlZgJjxwIDBkh1vu+8I80Elysnd2RERKSHmAATUcn29CnQuTMwe7bU/vprYN067VsdExER/T/WABNRyXXrFtChA3DuHGBhIZVAvPee3FEREZGeYwJMRCXTP/9Ii90ePQLc3IC//gIaNZI7KiIiKgFYAkFEJc+qVdJit0ePgHr1gGPHmPwSEVG+MQEmopIjMxP47DOgXz8gPR3o1k1a7Fa+vNyRERFRCcIEmIhKhqdPpZKH776T2uPHA+vXAzY28sZFREQlDmuAiUj/3b4tLXb7919psdsvvwDvvy93VEREVEIxASYi/Xb4MNClCxAXB7i6SovdGjeWOyoiIirBWAJBRPrr11+BwEAp+a1bV1rsxuSXiIjeEBNgItI/WVnAF18AfftKi926dJG2PfPwkDsyIiIyAEyAiUi/JCdLi91mzpTaX34J/PknF7sREVGhYQ0wEemPO3ekxW5nz0qL3X76CejdW+6oiIjIwDABJiL9EBUFdO4s1fu6uABbtgBNm8odFRERGSAmwEQkv99+AwYOlOp969QBtm4FKlSQOyq9kJkJREfn/F7QuDGgVModFRFRycYaYCKST1aWVOPbp4+U/HbuLC12Y/ILANixA/D1Bdq0AXr1kj77+kr9RET0+pgAE5E8kpOlWxlPny61x40DNm4EbG3ljUtP7NghlT9fuSKVQ5cqJX2+ckXqZxJMRPT6mAATUfG7cwdo3lyq8zU3l/b7/fZbwIQ/kgCp7OGrr4C0NMDODjAzk94aMzOpnZYm3Qk6M1PuSImISib+b0NExevIEaBRI+DMGamoNTxcKoEgteho4Pp1wNoaUCg0jykUUv+1a9J5RERUcEyAiaj4rF0LBAQAsbFA7drA0aOAn5/cUemduDhpdjevxW5KpXQ8Lq544yIiMhRMgImo6GVlSX/T79VL+vt9x45AZCTg6Sl3ZHrJxSUnydUlOzl2cSneuIiIDAUTYCIqWikpwDvvSDW+APD558DmzVzs9hKNGwPe3kBqKiCE5jEhpP7KlaXziIio4JgAE1HRuXtXWuy2ebO02G3VKmDGDC52ewWlEpg2Tdr1ISkJUKmkSXSVSmpbWABTp3I/YCKi18X/hYioaERHAw0bAqdPA87OwP79wAcfyB1ViREaKt0fpGpVqWrk6VPpc7VqUn9oqNwREhGVXLwTHBEVvt9/B/r3lzK2WrWkO7tVrCh3VCVOaCgQEsI7wRERFTYmwERUeLKygIkTpb/PA0CHDsCaNdJdHOi1KJXcKIOIqLAxASaiwpGSAvTtK93NDQA++0xa+MbpSiIi0jNMgInozd27J21tduqUdLuyH38E+vWTOyoiIiKdmAAT0Zs5ehTo1AmIiQHKlJF2fGjeXO6oiIiI8sRdIIjo9f3xB+DvLyW/b70lJcNMfomISM8xASaigste7Pbee8Dz50C7dtKd3by85I6MiIjolZgAE1HBpKYCPXoAU6ZI7U8/Bf76C7CzkzcuHTIzpS3EAOlzXrcWJiIi48IEmIjy7/59oGVL4M8/pcVuv/wCfPedXu70sGMH4OsLdO0qtbt2ldo7dsgbFxERyY8JMBHlz7Fj0p3dTpyQFrvt2yfd7EIP7dgB9O4NXLki3TYYkD5fuSL1MwkmIjJuTICJ6NXWr5dmfh8+BGrWlBa7tWghd1Q6ZWYCX30l3YTOzk6aqAakz3Z2Uv/48SyHICIyZkyAiShvQgCTJkk1v8+fS/fmPXxYrxe7RUcD168D1taAQqF5TKGQ+q9dy6kNJiIi48N9gIlIt9RUqcRh/XqpPWYMMGuWXtb7viguTprdzStMpVI6HhdXvHEREZH+YAJMRNru3wc6dwaOH5dqB5YuBQYOlDuqfHFxyUlyTXT8jSs7OXZxKf7YiIhIP7AEgog0HT8ONGokfXZyAvbuLTHJLwA0bgx4e0sT2EJoHhNC6q9cWTqPiIiMExNgIsqRvdjtwQOgRg1psVvLlnJHVSBKJTBtmrTrQ1ISoFJJ/SqV1LawAKZO1ftKDiIiKkJMgIlImhqdMkVa7PbsGdC2rbTYrVIluSN7LaGhwG+/AVWrSrs+ANLnatWk/tBQeeMjIiJ5sQaYyNg9ewYMGAD88YfUHj1ab29uURChoUBICBAVBcTHA5s2AU2blviXRUREhYAzwETG7MEDwN9fSn5NTYHly4G5cw0mS1Qqc2p9Gzc2mJdFRERviDPARMbq5EmgY0dpxwdHR2DjRiAgQO6oiIiIihxngImM0Z9/As2bS8lv9erSYjcmv0REZCSYABMZEyGAb74B3n1Xqv3NLpL19pY7MiIiomLDEggiY5F7sdsnnwCzZ0u1v0REREaE//MRGYOHD6U7ux09KiW8ixcDgwfLHRUREZEsmAATGbpTp6TFbvfuSYvd/vwTCAyUOyoiIiLZ6H0N8P3799G7d284OTnBysoKtWrVwvHjx9XHhRCYMGECypYtCysrKwQHB+Pq1asyRkykRzZtkha73bsH+PgA0dFMfomIyOjpdQL833//oVmzZjAzM8POnTtx4cIFzJkzB6VLl1afM2vWLCxYsADLli1DdHQ0bGxsEBISgufPn8sYOZHMhJDuB9ytG5CamrPYrXJluSMjIiKSnV6XQMycORMeHh5YsWKFus/Ly0v9byEE5s2bh/Hjx6NTp04AgF9//RWurq7YsmULevbsWewxE8nu2TPgww+BtWul9siRwJw5XOxGRET0//T6f8StW7ciJCQE7777Lg4cOIBy5crh448/xqBBgwAAN2/eRExMDIKDg9WPsbe3R+PGjREVFZVnApyWloa0tDR1OykpCQCgUqmgUqmK8BWRPsgeY4Mc65gYKN95ByZHj0IolciaPx9ZgwdLM8KG+HrzwaDHm7RwvI0Lx9u4FOY463UCfOPGDSxduhRjxozBl19+iWPHjmHkyJEwNzdH3759ERMTAwBwdXXVeJyrq6v6mC7Tp0/H5MmTtfrDw8NhbW1duC+C9FZYWJjcIRQquxs30Pjbb2H2+DHSbW1x7LPP8Lh8eWDHDrlD0wuGNt70chxv48LxNg6pqamFdi2FEEIU2tUKmbm5OXx9fXH48GF138iRI3Hs2DFERUXh8OHDaNasGR48eICyZcuqz+nevTsUCgXWrVun87q6ZoA9PDzw8OFDODk5Fd0LIr2gUqkQFhaG1q1bw8zMTO5wCoViyxYo+/WDIjUVompVZGzeDFSpIndYesEQx5vyxvE2Lhxv4xIfH4+yZcsiMTERdnZ2b3QtvZ4BLlu2LGrUqKHRV716dWzcuBEA4ObmBgCIjY3VSIBjY2NRt27dPK9rYWEBCwsLrX4zMzN+AxkRgxhvIYDp04GvvpLarVtDsX49zBwcZA1LHxnEeFO+cbyNC8fbOBTmGOv1LhDNmjXD5cuXNfquXLkCT09PANKCODc3N+zbt099PCkpCdHR0WjatGmxxkpU7J4/B/r0yUl+hw+Xyh2Y/BIREb2UXs8Ajx49Gn5+fvj222/RvXt3HD16FD/++CN+/PFHAIBCocCoUaMwdepUVKlSBV5eXvj666/h7u6Ozp07yxs8UVGKjZXu7HbkCKBUAgsXAh99JHdUREREJYJeJ8ANGzbE5s2bMW7cOEyZMgVeXl6YN28eevXqpT7ns88+Q0pKCgYPHoyEhAQ0b94cu3btgqWlpYyRExWhM2eADh2Au3el2d4NG4AXdkIhIiKil9PrBBgA2rdvj/bt2+d5XKFQYMqUKZgyZUoxRkUkky1bgN69gZQUoGpVYNs26TMRERHlm17XABPR/xMCmDED6NpVSn6Dg6XyBya/REREBcYEmEjfPX8O9O0LjBsnJcLDhkmL3V64JTgRERHln96XQBAZtdhYoEsXICpKWuw2f76UABMREdFrYwJMpK/OnpUWu925Iy12W78eaN1a7qiIiIhKPJZAEOmjrVsBPz8p+a1SRar3ZfJLRERUKJgAk1HJzASio6V/R0dLbb0iBDBrlrTHb0oK0KqVlPxWqyZ3ZERERAaDCTAZjR07AF9faSMFQPrs6yv164W0NKBfP+Dzz6VE+KOPgJ07AUdHuSMjIiIyKEyAySjs2CFtn3vlCmBhIfVZWEjt3r31IAmOi5Nme3/9VVrstmgRsGQJwHvbExERFTomwGTwMjOBr76SJljt7HJySjMzqZ2WBowfL2M5xNmzQKNGQGQkYG8vZePc6YGIiKjIMAEmgxcdDVy/DlhbAwqF5jGFQuq/di2nNrhYbdsGNGsG3L4NVK4s1fu+/bYMgRARERkPJsBk8OLipNldpVL3caVSOh4XV4xBCQF89x3QqROQnAwEBkoZuI9PMQZBRERknJgAk8FzcclJcnXJTo5dXIopoLQ0YMAA4LPPpER4yBBg924udiMiIiomTIDJ4DVuDHh7A6mpUr75IiGk/sqVpfOK3KNHQHAwsHIlYGICLFgALF3KxW5ERETFiAkwGTylEpg2Tdr1ISkJUKmkfpVKaltYAFOn5l0iUWjOnZMWu/3zj7T6bscOYMQI7cJkIiIiKlJMgMkohIYCv/0GVK0qVSAA0udq1aT+0NAiDmD7dqBpU+DWLWk6+sgRICSkiJ+UiIiIdDGVOwCi4hIaKuWcUVFAfDywaZOUkxbpzK8QwNy5wNix0r8DAoA//wScnIrwSYmIiOhlOANMRkWpzKn1bdy4iJPf9HRg4EDg00+l5HfQIGmxG5NfIiIiWXEGmKgoPHoEdOsGHDokLXabOxcYOZL1vkRERHqACTBRYTt3DujQQar3tbMD1q0D2rSROyoiIiL6fyyBICpMf/8N+PlJyW+lSlLBMZNfIiIivcIEmKgwZC9269ABePoU8PeX7uxWo4bckREREVEuTICJ3lR6urTA7X//kxLhDz8E9uwBypSROzIiIiLSgTXARG/i8WNpsdvBg9JitzlzgE8+4WI3IiIiPcYEmOh1XbgglTzcuAGUKiUtdmvbVu6oiIiI6BVYAkH0OnbulO6iceMG4OUlLXZj8ktERFQiMAEmKgghgO+/B9q3B5KSgBYtgKNHgZo15Y6MiIiI8okJMFF+pacDQ4YAY8YAWVnAgAHA3r1c7EZERFTCsAaYKD/i46XFbgcOSAvcZs8GRo/mYjciIqISiAkw0atcvCgtdrt+XVrs9vvvQLt2ckdFREREr4kJMNHL7NoF9Ogh1ft6eQHbtrHel4iIqIRjDTCRLkIA8+dLM71JSUDz5tKd3Zj8EhERlXhMgIlyU6mAoUOBUaOkxW79+0uL3Zyd5Y6MiIiICgFLIIheFB8PvPMOEBEhLXCbNUu6xTEXuxERERkMJsBE2S5dkvb3vX4dsLWVFru1by93VERERFTImAATAcCePUD37kBiIlCxIrB1K1CrltxRERERURFgDTAZNyGAhQul2xgnJgLNmkmL3Zj8EhERGSwmwGS8VCrgo4+AkSOlxW59+wL79gEuLnJHRkREREWIJRBklMyePoWyfXsgPFxa4DZzJvDpp1zsRkREZASYAJPRUfz9NwI/+QQmT55Ii93WrAE6dpQ7LCIiIiomLIEg4/L55zDt0gVWT55AeHgAkZFMfomIiIwMZ4DJeNSoAVy8qG5m7N4Ns+rVZQyIiIiI5MAZYDJ8z55Jtb0vJL9/r10LVK4sY1BEREQkFybAZNhu3ACsrXPajo5QpaUh48U+IiIiMipMgMlwbd8OeHvntPv3l251zJ0eiIiIjBoTYDJM48YBHTrktH/9FfjlF/niISIiIr3BRXBkeGrVAs6dy2mfOQPUri1fPERERKRXmACT4Xj+HLCy0uxLSADs7WUJh4iIiPQTSyDIMNy8qZn82tlJtzdm8ktERES5MAGmku/vv4FKlXLaH3wAJCZysRsRERHpxASYSravvgLat89pr1wJrFolWzhERESk/1gDTCVX3brSArdsp08DderIFQ0RERGVEEyAqeTRtdjtv/8ABwdZwiEiIqKShSUQVLLcuqWZ/NrYAJmZTH6JiIgo35gAU8mxcyfg5ZXT7t0bSE4GTPhlTERERPnHzIFKhgkTgNDQnPbPPwOrV8sXDxEREZVYrAEm/degAXDyZE775EmgXj354iEiIqISjQkw6a+0NMDSUrPvyROgdGl54iEiIiKDwATYAGRmAtHRQFwc4OICNG4MKJVyR/WGbt8GKlbMaVtZsd6XiIiICkWJyiZmzJgBhUKBUaNGqfueP3+OYcOGwcnJCba2tujWrRtiY2PlC7KY7dgB+PoCbdoAvXpJn319pf4Sa/duzeT3vfeA1FQmv0RERFQoSkxGcezYMfzwww+oXbu2Rv/o0aOxbds2bNiwAQcOHMCDBw/QtWtXmaIsXjt2SBshXLkCWFgApUpJn69ckfpLZBI8caKUxWdbvhxYu1a+eIiIiMjglIgEODk5Gb169cLy5ctR+oX6z8TERPz888+YO3cugoKC0KBBA6xYsQKHDx/GkSNHZIy46GVmSncBTksD7OwAMzNpgtTMTGqnpQHjx0vnlRiNGgFTpuS0T5wAPvxQvniIiIjIIJWIGuBhw4ahXbt2CA4OxtSpU9X9J06cgEqlQnBwsLrPx8cHFSpUQFRUFJo0aaLzemlpaUhLS1O3k5KSAAAqlQoqlaqIXkXhio4G7t8HHB2lpDc3U1Pg3j0gKkqqCdZraWkwK1VKo0sVEyO9uCIYj+wxLiljTW+G421cON7GheNtXApznPU+Af7jjz9w8uRJHDt2TOtYTEwMzM3N4ZDrLmCurq6IiYnJ85rTp0/H5MmTtfrDw8NhbW39xjEXl+XLX31OfLx+l0JYPXqEtwcNUrczTU2xff16oBhm8MPCwor8OUh/cLyNC8fbuHC8jUNqamqhXUuvE+C7d+/ik08+QVhYGCxzb4f1BsaNG4cxY8ao20lJSfDw8EBgYCCcnJwK7XmKUnQ00LWrVPOrawZYpZLKIDZt0t8ZYMXevTB9IfnNevddZK1Zg9CXPKYwqFQqhIWFoXXr1jDT9eaRQeF4GxeOt3HheBuX+Pj4QruWXifAJ06cQFxcHOrXr6/uy8zMxMGDB7Fo0SLs3r0b6enpSEhI0JgFjo2NhZubW57XtbCwgIWFhVa/mZlZifkGatoUKFdOWvBmZwcoFDnHhACSkoBq1aTz9HJLtClTpAVv2X74ASaDBxdrUXpJGm96cxxv48LxNi4cb+NQmGOs1wlwq1at8O+//2r09e/fHz4+Pvj888/h4eEBMzMz7Nu3D926dQMAXL58GXfu3EHTpk3lCLnYKJXAtGnSbg9JSYC1tdSXmSntGGZhAUydqqfJb9OmmiUOx45Je7cRERERFQO9ToBLlSqFt956S6PPxsYGTk5O6v6BAwdizJgxcHR0hJ2dHUaMGIGmTZvmuQDOkISGAr/9Ju0Gcf26lPwqldLM79Sp0nG9kp4uZeYvevwYKCFlJ0RERGQY9DoBzo/vv/8eJiYm6NatG9LS0hASEoIlS5bIHVaxCQ0FQkJKwJ3g7t0DPDxy2iYmUqEyb25BRERExazEJcAREREabUtLSyxevBiLFy+WJyA9oFQCfn5yR/ESe/cCrVvntN99F1i/Xr54iIiIyKhx+o2K1rRpmsnvsmVMfomIiEhWJW4GmEqQZs2Aw4dz2kePAg0byhcPEREREZgAU1HQtdjt0SOgTBl54iEiIiJ6AUsgqHDdv6+d/GZkMPklIiIivcEEmApPeDhQvnxOu0sX6a4cerclBRERERkzJsBUOKZPB4KCctqLF0v3YSYiIiLSM6wBpjfn7w8cPJjTjo4GGjWSLx4iIiKil2ACTK9PpQLMzTX74uIAZ2d54iEiIiLKB5ZA0Ot58EA7+c3IYPJLREREeo8JMBXcgQNAuXI57Y4dudiNiIiISgwmwFQwM2cCAQE57YULgb/+ki0cIiIiooJiDTDlX1CQtNVZtqgooEkT+eIhIiIieg1MgOnVuNiNiIiIDAhLIOjlHj7kYjciIiIyKEyAKW8HDwLu7jntdu242I2IiIhKPCbApNvs2dINLrLNnw9s3y5fPERERESFhDXApK11a2Dv3px2ZCTg5ydfPERERESFiAkw5cjIAMzMNPtiYwEXF3niISIiIioCLIEgSUyMdvKrUjH5JSIiIoPDBJiAQ4eAsmVz2m3aSIvdTPkHAiIiIjI8TICN3dy5QMuWmu2dO+WLh4iIiKiIcYrPmLVpA+zendM+dAho3ly+eIiIiIiKARNgY6RrsVtMDODqKk88RERERMWIJRDGJjZW92I3Jr9ERERkJJgAG5PISMDNLafdujUXuxEREZHRYQJsLObP16zvnT0b2LNHvniIiIiIZMKpP2PQvj3w99857QMHNHd+ICIiIjIiTIANma7Fbg8fapZBEBERERkZJsCGKi5Oe2GbSsV6XyIiIjJ6rAE2RIcPaya/rVpxsRsRERHR/2MCbGgWLACaNctpz5wJ7N0rXzxEREREeoZTgoakY0dg27acdkQE4O8vWzhERERE+ogJsKH4/nvN5Pf+fcDdXb54iIiIiPQUE2BD8exZzr/T07V3fyAiIiIiAKwBNhzjxgH//SctdmPyS0RERJQnJsCGQqEAHBzkjoKIiIhI7zEBJiIiIiKjwgSYiIiIiIwKE2AiIiIiMipMgImIiIjIqDABJiIiIiKjwgSYiIiIiIwKE2AiIiIiMipMgImIiIjIqDABJiIiIiKjwgSYiIiIiIwKE2AiIiIiMipMgImIiIjIqDABJiIiIiKjwgSYiIiIiIwKE2AiIiIiMipMgImIiIjIqDABJiIiIiKjwgSYiIiIiIwKE2AiIiIiMipMgImIiIjIqDABJiIiIiKjovcJ8PTp09GwYUOUKlUKLi4u6Ny5My5fvqxxzvPnzzFs2DA4OTnB1tYW3bp1Q2xsrEwRExEREZE+0/sE+MCBAxg2bBiOHDmCsLAwqFQqvP3220hJSVGfM3r0aGzbtg0bNmzAgQMH8ODBA3Tt2lXGqImIiIhIX5nKHcCr7Nq1S6O9cuVKuLi44MSJE2jZsiUSExPx888/Y+3atQgKCgIArFixAtWrV8eRI0fQpEkTOcImIiIiIj2l9wlwbomJiQAAR0dHAMCJEyegUqkQHBysPsfHxwcVKlRAVFSUzgQ4LS0NaWlp6nZSUhIAQKVSQaVSFWX4pAeyx5hjbRw43saF421cON7GpTDHuUQlwFlZWRg1ahSaNWuGt956CwAQExMDc3NzODg4aJzr6uqKmJgYndeZPn06Jk+erNUfHh4Oa2vrQo+b9FNYWJjcIVAx4ngbF463ceF4G4fU1NRCu1aJSoCHDRuGc+fO4Z9//nmj64wbNw5jxoxRt5OSkuDh4YHAwEA4OTm9aZik51QqFcLCwtC6dWuYmZnJHQ4VMY63ceF4GxeOt3GJj48vtGuVmAR4+PDh2L59Ow4ePIjy5cur+93c3JCeno6EhASNWeDY2Fi4ubnpvJaFhQUsLCy0+s3MzPgNZEQ43saF421cON7GheNtHApzjPV+FwghBIYPH47Nmzdj//798PLy0jjeoEEDmJmZYd++feq+y5cv486dO2jatGlxh0tEREREek7vZ4CHDRuGtWvX4q+//kKpUqXUdb329vawsrKCvb09Bg4ciDFjxsDR0RF2dnYYMWIEmjZtyh0giIiIiEiL3ifAS5cuBQAEBARo9K9YsQL9+vUDAPxfe/cfU9V9/3H8BcgFpcpPFVD5oRR/VLBEB8Mf6AIR2sn8FYPOpGjVpa3WKrFa24k1zpnZuP6KnavrxD9EnZl2W7eyWBR/FbVqiXWhzDIc3QqCvyMoMPh8/+jXk95ebFXAK5znIznJvZ9zzue87/nkk756/ZzL66+/Lk9PT02fPl0NDQ1KT0/XO++884ArBQAAQGfw0AdgY8z3HuPr66tNmzZp06ZND6AiAAAAdGYP/RpgAAAAoD0RgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArBGAAAADYCgEYAAAAtkIABgAAgK0QgAEAAGArXSYAb9q0SVFRUfL19VVSUpJOnDjh7pIAAADwEOoSAXjXrl3KycnR6tWrdfr0aY0YMULp6emqqalxd2kAAAB4yHSJAPzrX/9aCxYs0Ny5czVs2DBt3rxZPXr00O9//3t3lwYAAICHTDd3F9BWjY2NOnXqlFauXGm1eXp6Ki0tTcXFxa2e09DQoIaGBuv9tWvXJEmXL1/u2GLxUGhqalJ9fb0uXbokb29vd5eDDsZ42wvjbS+Mt73czmnGmDb31ekD8MWLF9Xc3Ky+ffs6tfft21eff/55q+esX79ea9ascWmPjY3tkBoBAADQPi5duiR/f/829dHpA/D9WLlypXJycqz3V69eVWRkpCorK9t8Q/Hwu379ugYMGKAvv/xSvXr1cnc56GCMt70w3vbCeNvLtWvXFBERoaCgoDb31ekDcEhIiLy8vHThwgWn9gsXLig0NLTVc3x8fOTj4+PS7u/vzwSykV69ejHeNsJ42wvjbS+Mt714erb9EbZO/xCcw+HQyJEjVVhYaLW1tLSosLBQycnJbqwMAAAAD6NO/w2wJOXk5Cg7O1ujRo1SYmKi3njjDdXV1Wnu3LnuLg0AAAAPmS4RgLOyslRbW6vc3FxVV1fr8ccfV0FBgcuDcXfi4+Oj1atXt7osAl0P420vjLe9MN72wnjbS3uOt4dpj9+SAAAAADqJTr8GGAAAALgXBGAAAADYCgEYAAAAtkIABgAAgK3YPgBv2rRJUVFR8vX1VVJSkk6cOOHuktABXn31VXl4eDhtQ4YMcXdZaEeHDh1SZmamwsPD5eHhoffff99pvzFGubm5CgsLU/fu3ZWWlqZz5865p1i02feN95w5c1zmfEZGhnuKRZusX79eP/jBD9SzZ0/16dNHU6ZMUVlZmdMxt27d0sKFCxUcHKxHHnlE06dPd/kDWegc7ma8J0yY4DK/n3nmmXu6jq0D8K5du5STk6PVq1fr9OnTGjFihNLT01VTU+Pu0tABHnvsMVVVVVnbkSNH3F0S2lFdXZ1GjBihTZs2tbp/w4YNeuutt7R582YdP35cfn5+Sk9P161btx5wpWgP3zfekpSRkeE053fs2PEAK0R7OXjwoBYuXKhjx45p3759ampq0sSJE1VXV2cds3TpUv3lL3/R7t27dfDgQX311VeaNm2aG6vG/bqb8ZakBQsWOM3vDRs23NuFjI0lJiaahQsXWu+bm5tNeHi4Wb9+vRurQkdYvXq1GTFihLvLwAMiyezdu9d639LSYkJDQ81rr71mtV29etX4+PiYHTt2uKFCtKdvj7cxxmRnZ5vJkye7pR50rJqaGiPJHDx40Bjz9Vz29vY2u3fvto4pLS01kkxxcbG7ykQ7+fZ4G2PM+PHjzQsvvNCmfm37DXBjY6NOnTqltLQ0q83T01NpaWkqLi52Y2XoKOfOnVN4eLgGDhyo2bNnq7Ky0t0l4QGpqKhQdXW103z39/dXUlIS870LKyoqUp8+fTR48GA9++yzunTpkrtLQju4du2aJCkoKEiSdOrUKTU1NTnN7yFDhigiIoL53QV8e7xv2759u0JCQjR8+HCtXLlS9fX199Rvl/hLcPfj4sWLam5udvlrcX379tXnn3/upqrQUZKSkpSXl6fBgwerqqpKa9as0bhx43T27Fn17NnT3eWhg1VXV0tSq/P99j50LRkZGZo2bZqio6NVXl6ul19+WU888YSKi4vl5eXl7vJwn1paWrRkyRKNGTNGw4cPl/T1/HY4HAoICHA6lvnd+bU23pL005/+VJGRkQoPD9eZM2e0YsUKlZWVac+ePXfdt20DMOzliSeesF7Hx8crKSlJkZGR+sMf/qB58+a5sTIAHWHmzJnW67i4OMXHx2vQoEEqKipSamqqGytDWyxcuFBnz57lGQ6buNN4/+xnP7Nex8XFKSwsTKmpqSovL9egQYPuqm/bLoEICQmRl5eXy1OiFy5cUGhoqJuqwoMSEBCg2NhYffHFF+4uBQ/A7TnNfLevgQMHKiQkhDnfiS1atEgffPCBDhw4oP79+1vtoaGhamxs1NWrV52OZ353bnca79YkJSVJ0j3Nb9sGYIfDoZEjR6qwsNBqa2lpUWFhoZKTk91YGR6EGzduqLy8XGFhYe4uBQ9AdHS0QkNDneb79evXdfz4cea7TfznP//RpUuXmPOdkDFGixYt0t69e7V//35FR0c77R85cqS8vb2d5ndZWZkqKyuZ353Q9413a0pKSiTpnua3rZdA5OTkKDs7W6NGjVJiYqLeeOMN1dXVae7cue4uDe1s2bJlyszMVGRkpL766iutXr1aXl5emjVrlrtLQzu5ceOG0//9V1RUqKSkREFBQYqIiNCSJUv0i1/8Qo8++qiio6O1atUqhYeHa8qUKe4rGvftu8Y7KChIa9as0fTp0xUaGqry8nItX75cMTExSk9Pd2PVuB8LFy5Ufn6+/vSnP6lnz57Wul5/f391795d/v7+mjdvnnJychQUFKRevXrp+eefV3Jysn74wx+6uXrcq+8b7/LycuXn5+vJJ59UcHCwzpw5o6VLlyolJUXx8fF3f6E2/YZEF/D222+biIgI43A4TGJiojl27Ji7S0IHyMrKMmFhYcbhcJh+/fqZrKws88UXX7i7LLSjAwcOGEkuW3Z2tjHm659CW7Vqlenbt6/x8fExqamppqyszL1F475913jX19ebiRMnmt69extvb28TGRlpFixYYKqrq91dNu5Da+MsyWzdutU65ubNm+a5554zgYGBpkePHmbq1KmmqqrKfUXjvn3feFdWVpqUlBQTFBRkfHx8TExMjHnxxRfNtWvX7uk6Hv9/MQAAAMAWbLsGGAAAAPZEAAYAAICtEIABAABgKwRgAAAA2AoBGAAAALZCAAYAAICtEIABAABgKwRgAAAA2AoBGAAkeXh46P3333d3GZozZ44t/jxzXl6eAgICXNpTUlKUn5/fpr4bGxsVFRWlkydPtqkfAF0XARhAlzJnzhx5eHi4bBkZGe4uzcn58+fl4eGhkpISp/Y333xTeXl5HX79hyXwf9Of//xnXbhwQTNnzmxTPw6HQ8uWLdOKFSvaqTIAXQ0BGECXk5GRoaqqKqdtx44d7i7rrvj7+7f6zagdvPXWW5o7d648Pe//P02NjY2SpNmzZ+vIkSP6xz/+0V7lAehCCMAAuhwfHx+FhoY6bYGBgdb+c+fOKSUlRb6+vho2bJj27dvndH5RUZE8PDx09epVq62kpEQeHh46f/681Xb06FFNmDBBPXr0UGBgoNLT03XlyhVJUkFBgcaOHauAgAAFBwdr0qRJKi8vt86Njo6WJCUkJMjDw0MTJkyQ5LoEoqGhQYsXL1afPn3k6+ursWPH6pNPPnGptbCwUKNGjVKPHj00evRolZWVteke/u53v9PQoUPl6+urIUOG6J133rH2jR492uXb1draWnl7e+vQoUNW3cuWLVO/fv3k5+enpKQkFRUV3fF6tbW12r9/vzIzM622p59+WpMmTXI6rqmpSX369NF7770nSZowYYIWLVqkJUuWKCQkROnp6ZKkwMBAjRkzRjt37mzTfQDQNRGAAdhKS0uLpk2bJofDoePHj2vz5s339U/lJSUlSk1N1bBhw1RcXKwjR44oMzNTzc3NkqS6ujrl5OTo5MmTKiwslKenp6ZOnaqWlhZJ0okTJyRJH330kaqqqrRnz55Wr7N8+XL98Y9/1LZt23T69GnFxMQoPT1dly9fdjrulVde0caNG3Xy5El169ZNTz/99D1/ptu2b9+u3NxcrVu3TqWlpfrlL3+pVatWadu2bZK+/nZ1586dMsZY5+zatUvh4eEaN26cJGnRokUqLi7Wzp07debMGc2YMUMZGRk6d+5cq9c8cuSIevTooaFDh1pt8+fPV0FBgaqqqqy2Dz74QPX19crKyrLatm3bJofDoaNHj2rz5s1We2Jiog4fPnzf9wFAF2YAoAvJzs42Xl5exs/Pz2lbt26dMcaYv//976Zbt27mv//9r3XOhx9+aCSZvXv3GmOMOXDggJFkrly5Yh3z6aefGkmmoqLCGGPMrFmzzJgxY+66rtraWiPJfPbZZ8YYYyoqKowk8+mnn7rUP3nyZGOMMTdu3DDe3t5m+/bt1v7GxkYTHh5uNmzY4FTrRx99ZB3z17/+1UgyN2/evGM93/y83zZo0CCTn5/v1LZ27VqTnJxsjDGmpqbGdOvWzRw6dMjan5ycbFasWGGMMebf//638fLycrrHxhiTmppqVq5caYwxZuvWrcbf39/a9/rrr5uBAwe61DJs2DDzq1/9ynqfmZlp5syZY70fP368SUhIaPVzvPnmmyYqKqrVfQDsrZv7ojcAdIwf/ehH+s1vfuPUFhQUJEkqLS3VgAEDFB4ebu1LTk6+52uUlJRoxowZd9x/7tw55ebm6vjx47p48aL1zW9lZaWGDx9+V9coLy9XU1OTxowZY7V5e3srMTFRpaWlTsfGx8dbr8PCwiRJNTU1ioiIuOvPJH39zXV5ebnmzZunBQsWWO3/+9//5O/vL0nq3bu3Jk6cqO3bt2vcuHGqqKhQcXGxfvvb30qSPvvsMzU3Nys2Ntap74aGBgUHB7d63Zs3b8rX19elff78+Xr33Xe1fPlyXbhwQR9++KH279/vdMzIkSNb7bN79+6qr6+/+w8PwDYIwAC6HD8/P8XExNz3+bcfwjLf+Cf+pqYmp2O6d+/+nX1kZmYqMjJSW7ZsUXh4uFpaWjR8+HDrIa325u3tbb328PCQJCt034sbN25IkrZs2aKkpCSnfV5eXtbr2bNna/HixXr77beVn5+vuLg4xcXFWX14eXnp1KlTTudI0iOPPNLqdUNCQqz109/01FNP6aWXXlJxcbE+/vhjRUdHW8ssbvPz82u1z8uXL6t3797f84kB2BFrgAHYytChQ/Xll186rSs9duyY0zG3Q9M3j/n2z5XFx8ersLCw1WtcunRJZWVl+vnPf67U1FQNHTrUJdw5HA5JstYMt2bQoEHW2tbbmpqa9Mknn2jYsGHf8SnvX9++fRUeHq5//etfiomJcdpuP7gnSZMnT9atW7dUUFCg/Px8zZ4929qXkJCg5uZm1dTUuPQRGhra6nUTEhJUXV3tcp+Cg4M1ZcoUbd26VXl5eZo7d+5df5azZ88qISHhHu8AADvgG2AAXU5DQ4Oqq6ud2rp166aQkBClpaUpNjZW2dnZeu2113T9+nW98sorTsfGxMRowIABevXVV7Vu3Tr985//1MaNG52OWblypeLi4vTcc8/pmWeekcPh0IEDBzRjxgwFBQUpODhY7777rsLCwlRZWamXXnrJ6fw+ffqoe/fuKigoUP/+/eXr62stMbjNz89Pzz77rF588UUFBQUpIiJCGzZsUH19vebNm9fm+1RRUeES7B999FGtWbNGixcvlr+/vzIyMtTQ0KCTJ0/qypUrysnJsWqbMmWKVq1apdLSUs2aNcvqIzY2VrNnz9ZTTz2ljRs3KiEhQbW1tSosLFR8fLx+/OMfu9SSkJCgkJAQHT161OWXH+bPn69JkyapublZ2dnZd/35Dh8+rLVr197DHQFgG+5ehAwA7Sk7O9tIctkGDx5sHVNWVmbGjh1rHA6HiY2NNQUFBS4PhR05csTExcUZX19fM27cOLN7926nh+CMMaaoqMiMHj3a+Pj4mICAAJOenm49OLdv3z4zdOhQ4+PjY+Lj401RUZHLNbZs2WIGDBhgPD09zfjx4636bz8EZ4wxN2/eNM8//7wJCQkxPj4+ZsyYMebEiRPW/rt5YK81rd0jSebw4cPGGGO2b99uHn/8ceNwOExgYKBJSUkxe/bscerjb3/7m5FkUlJSXPpvbGw0ubm5Jioqynh7e5uwsDAzdepUc+bMGWOM60NwxhizfPlyM3PmTJe+WlpaTGRkpHnyySdd9o0fP9688MILLu0ff/yxCQgIMPX19Xe8BwDsy8OYbyxyAwDATaqrq/XYY4/p9OnTioyMtNpv3Lihfv36aevWrZo2bdpd9ZWVlaURI0bo5Zdf7qhyAXRirAEGADwUQkND9d5776myslLS1w/x1dTUaO3atQoICNBPfvKTu+qnsbFRcXFxWrp0aUeWC6AT4xtgAMBD6fz584qOjlb//v2Vl5en1NRUd5cEoIsgAAMAAMBWWAIBAAAAWyEAAwAAwFYIwAAAALAVAjAAAABshQAMAAAAWyEAAwAAwFYIwAAAALAVAjAAAABs5f8Are3PhLP5FWkAAAAASUVORK5CYII=", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "plt.figure(\n", + " figsize=(8, 8)\n", + ")\n", + "\n", + "plt.scatter(\n", + " educationWageDf[\"Education\"],\n", + " educationWageDf[\"Wage\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.plot(\n", + " educationWageDf[\"Education\"],\n", + " educationWageDf[\"predictedWage\"],\n", + " color='red',\n", + " label='OLS Regression - predictedWage'\n", + ")\n", + "plt.title('Education Level vs. Wage with OLS Regression')\n", + "plt.xlabel('Education Level(yr)')\n", + "plt.ylabel('Wage K')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "plt.gca().set_xlim([0, 25])\n", + "plt.gca().set_ylim([0, 180])\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "trx50k1tBX0s" + }, + "source": [ + "# Another way" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "5G0wXkAFIxMd", + "outputId": "638eddd9-db57-42f7-e702-2d99e4ce18c7" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(array([20, 18, 12, 16, 10, 23, 2, 5]),\n", + " array([160, 120, 70, 100, 65, 160, 40, 55]))" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "X = np.array([20, 18, 12, 16, 10, 23, 2, 5])\n", + "y = np.array([160, 120, 70 , 100, 65, 160, 40, 55])\n", + "X, y" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "id": "YTcd15wbK9AA" + }, + "outputs": [], + "source": [ + "X = sm.add_constant(X)" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Oksgjk2MKjL_", + "outputId": "05fff372-2217-40d5-ddae-6ae6f716f54a" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[ 1., 20.],\n", + " [ 1., 18.],\n", + " [ 1., 12.],\n", + " [ 1., 16.],\n", + " [ 1., 10.],\n", + " [ 1., 23.],\n", + " [ 1., 2.],\n", + " [ 1., 5.]])" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "X" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "id": "foBX_PxyJJj8" + }, + "outputs": [], + "source": [ + "model = sm.OLS(y, X).fit()\n" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Da-TIkZpJMBB", + "outputId": "d5c347b5-2c1b-49bc-84cf-ecab21cef3f8" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: y R-squared: 0.906\n", + "Model: OLS Adj. R-squared: 0.890\n", + "Method: Least Squares F-statistic: 57.64\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 0.000272\n", + "Time: 01:23:11 Log-Likelihood: -32.114\n", + "No. Observations: 8 AIC: 68.23\n", + "Df Residuals: 6 BIC: 68.39\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 16.1358 11.887 1.357 0.223 -12.950 45.221\n", + "x1 6.0464 0.796 7.592 0.000 4.098 7.995\n", + "==============================================================================\n", + "Omnibus: 0.619 Durbin-Watson: 0.926\n", + "Prob(Omnibus): 0.734 Jarque-Bera (JB): 0.522\n", + "Skew: 0.213 Prob(JB): 0.770\n", + "Kurtosis: 1.823 Cond. No. 32.5\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/jasonjafari/gitHub/ml_models_deployments/venv/lib/python3.12/site-packages/scipy/stats/_axis_nan_policy.py:531: UserWarning: kurtosistest only valid for n>=20 ... continuing anyway, n=8\n", + " res = hypotest_fun_out(*samples, **kwds)\n" + ] + } + ], + "source": [ + "print(model.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "8Evg53IMJQQD", + "outputId": "817500b1-4734-4d83-9347-ef1bdcd1ee7c" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Coefficients: [16.13576159 6.04635762]\n" + ] + } + ], + "source": [ + "print(\"Coefficients:\", model.params)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Csteg6CiOiSv", + "outputId": "e3469200-48c1-4c56-8e46-fbdc0aac986b" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 46.36754967, 106.83112583])" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictions = model.predict([[1, 5], [1, 15]])\n", + "predictions" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "id": "xxZNODO1PC1m" + }, + "outputs": [], + "source": [ + "def predicWage(intercept, slope, yearsOfExperience):\n", + " return intercept + (slope * yearsOfExperience)" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "8lYfVWyNPdLc", + "outputId": "7db3e8e0-1425-4179-dfc9-c48c5167cd4e" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "46.367549668874176" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predicWage(model.params[0], model.params[1], 5)" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "YnJzK9USPkcC", + "outputId": "01b40693-ade3-433a-de93-bc848a19506a" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "106.83112582781453" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predicWage(model.params[0], model.params[1], 15)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "UxR96NeFLG9p" + }, + "source": [ + "# Another way" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "id": "y6-07nV0JoBa" + }, + "outputs": [], + "source": [ + "from sklearn.linear_model import LinearRegression" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "DJKKcxAFBlZi", + "outputId": "accbbe8f-e428-4dd1-83f6-9da8c3eb4fff" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EducationWagepredictedWage
020160137.062914
118120124.970199
2127088.692053
316100112.877483
4106576.599338
523160155.201987
624028.228477
755546.367550
\n", + "
" + ], + "text/plain": [ + " Education Wage predictedWage\n", + "0 20 160 137.062914\n", + "1 18 120 124.970199\n", + "2 12 70 88.692053\n", + "3 16 100 112.877483\n", + "4 10 65 76.599338\n", + "5 23 160 155.201987\n", + "6 2 40 28.228477\n", + "7 5 55 46.367550" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "id": "0GMyNZTyB0tz" + }, + "outputs": [], + "source": [ + "educationWageLiniarRgressionModel2 = LinearRegression()" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "CMrTd4NsC3Am", + "outputId": "adb114b3-4853-4d1e-8982-c5aa615236da" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(0 20\n", + " 1 18\n", + " 2 12\n", + " 3 16\n", + " 4 10\n", + " 5 23\n", + " 6 2\n", + " 7 5\n", + " Name: Education, dtype: int64,\n", + " pandas.core.series.Series)" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageDf[\"Education\"], type(educationWageDf[\"Education\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Flw3PPJKC0eI", + "outputId": "c7fd107a-295e-4e74-ac0d-fab8794f9da5" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "( Education\n", + " 0 20\n", + " 1 18\n", + " 2 12\n", + " 3 16\n", + " 4 10\n", + " 5 23\n", + " 6 2\n", + " 7 5,\n", + " pandas.core.frame.DataFrame)" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "educationWageDf[[\"Education\"]], type(educationWageDf[[\"Education\"]])" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": { + "id": "ox_p7rYYB8nA" + }, + "outputs": [], + "source": [ + "educationWageLiniarRgressionModel2Fit = educationWageLiniarRgressionModel2.fit(\n", + " educationWageDf[[\"Education\"]],\n", + " educationWageDf[\"Wage\"]\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "RxNZRBlhKpu5", + "outputId": "97fd2df3-121e-487d-89bd-eca5dccc3d5e" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Intercept: 16.135761589403984\n", + "Coefficient: 6.046357615894038\n" + ] + } + ], + "source": [ + "# Print the intercept and coefficient\n", + "print(\"Intercept:\", educationWageLiniarRgressionModel2Fit.intercept_)\n", + "print(\"Coefficient:\", educationWageLiniarRgressionModel2Fit.coef_[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "xtqZ6ZRaQBgK", + "outputId": "7d2b6a50-998f-48e6-f711-4a245490e924" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/Users/jasonjafari/gitHub/ml_models_deployments/venv/lib/python3.12/site-packages/sklearn/base.py:493: UserWarning: X does not have valid feature names, but LinearRegression was fitted with feature names\n", + " warnings.warn(\n" + ] + }, + { + "data": { + "text/plain": [ + "array([ 46.36754967, 106.83112583])" + ] + }, + "execution_count": 39, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictions1 = educationWageLiniarRgressionModel2Fit.predict(np.array([[5], [15]]))\n", + "predictions1" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "e2cyeBEUhzx6" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "BVJslxRTiCxx" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ssUOw-bWQTMP", + "outputId": "a7f58e83-9a5f-4b68-cca9-95ab76e917ec" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "46.367549668874176" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predicWage(educationWageLiniarRgressionModel2Fit.intercept_, educationWageLiniarRgressionModel2Fit.coef_[0], 5)" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "8cM6wdOdQYGK", + "outputId": "cfbd9022-bc83-4292-eac3-d24493fc1aa7" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "106.83112582781456" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predicWage(educationWageLiniarRgressionModel2Fit.intercept_, educationWageLiniarRgressionModel2Fit.coef_[0], 15)" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "uurMTqQpDi_A", + "outputId": "cd798e3d-1556-438f-d1ad-3b8d7acbd09f" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EducationWagepredictedWagepredictedWage2
020160137.062914137.062914
118120124.970199124.970199
2127088.69205388.692053
316100112.877483112.877483
4106576.59933876.599338
523160155.201987155.201987
624028.22847728.228477
755546.36755046.367550
\n", + "
" + ], + "text/plain": [ + " Education Wage predictedWage predictedWage2\n", + "0 20 160 137.062914 137.062914\n", + "1 18 120 124.970199 124.970199\n", + "2 12 70 88.692053 88.692053\n", + "3 16 100 112.877483 112.877483\n", + "4 10 65 76.599338 76.599338\n", + "5 23 160 155.201987 155.201987\n", + "6 2 40 28.228477 28.228477\n", + "7 5 55 46.367550 46.367550" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedWage2 = educationWageLiniarRgressionModel2Fit.predict(educationWageDf[[\"Education\"]])\n", + "educationWageDf['predictedWage2'] = predictedWage2\n", + "educationWageDf" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 718 + }, + "id": "30mmVCEuD4sx", + "outputId": "61e0c28a-6809-4a89-c670-ed767aaa7e60" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "plt.figure(\n", + " figsize=(8, 8)\n", + ")\n", + "\n", + "plt.scatter(\n", + " educationWageDf[\"Education\"],\n", + " educationWageDf[\"Wage\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.plot(\n", + " educationWageDf[\"Education\"],\n", + " educationWageDf[\"predictedWage\"],\n", + " color='red',\n", + " label='OLS Regression - predictedWage'\n", + ")\n", + "plt.plot(\n", + " educationWageDf[\"Education\"],\n", + " educationWageDf[\"predictedWage2\"],\n", + " color='black',\n", + " label='sklearn Regression - predictedWage'\n", + ")\n", + "plt.title('Education Level vs. Wage with OLS Regression')\n", + "plt.xlabel('Education Level(yr)')\n", + "plt.ylabel('Wage K')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "plt.gca().set_xlim([0, 25])\n", + "plt.gca().set_ylim([0, 180])\n", + "\n", + "\n", + "equation = f'Wage = {educationWageLiniarRgressionModel2Fit.coef_[0]:.2f} * Education + {educationWageLiniarRgressionModel2Fit.intercept_:.2f}'\n", + "\n", + "\n", + "plt.text(\n", + " 10, 120,\n", + " equation,\n", + " horizontalalignment='center',\n", + " verticalalignment='center',\n", + " fontsize=12,\n", + " color=\"green\",\n", + " bbox=dict(facecolor='white', alpha=0.5)\n", + ")\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "lNvoCcWRL1tW" + }, + "source": [ + "# Real dataset" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "id": "KHPW5DNvMUdz" + }, + "outputs": [], + "source": [ + "import pandas as pd" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "gIC1S6uQQi_t" + }, + "source": [ + "Download it from [here](https://www.dropbox.com/scl/fi/1sc8ojfezlbrcaje42w0n/College.xlsx?rlkey=i3starhohiwkua8ekbjk3nb92&st=yd75jyvp&dl=0)" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": { + "id": "Ksf536HkMQu5" + }, + "outputs": [], + "source": [ + "# collegeDf = pd.read_excel(\"./College.xlsx\")\n", + "collegeDf = pd.read_excel(\"https://www.dropbox.com/scl/fi/sqdbxs8c9r55s2qleal8t/College.xlsx?rlkey=c751oujzls8oxzwd0l89pcv5k&dl=1\")" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "Rjwma_7DNFzP", + "outputId": "ca99f39a-2b5b-44ac-e6dd-54fd610608f2" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SchoolEarningsCostGradDebtCity
0St. Ambrose C (NC)448002292062881
1Albion College (Albion, MI)451002342973920
2Alfred University (Alfred, NY)423001956763870
3Allegheny College (Meadville, PA)492002514778920
4Beloit College (Beloit, WI)379002197978931
\n", + "
" + ], + "text/plain": [ + " School Earnings Cost Grad Debt City\n", + "0 St. Ambrose C (NC) 44800 22920 62 88 1\n", + "1 Albion College (Albion, MI) 45100 23429 73 92 0\n", + "2 Alfred University (Alfred, NY) 42300 19567 63 87 0\n", + "3 Allegheny College (Meadville, PA) 49200 25147 78 92 0\n", + "4 Beloit College (Beloit, WI) 37900 21979 78 93 1" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 47, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "E9I8JZkuqHYJ", + "outputId": "83499364-5b7d-4615-edba-1fb31b20a078" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SchoolEarningsCostGradDebtCity
111Whittier College (Whittier, CA)451003318167860
112Widener University (Chester, PA)517002738756830
113Willamette University (Salem, OR)492003031278931
114Winthrop University (Rock Hill, SC)361001531154761
115Wittenberg University (Springfield, OH)427002661664901
\n", + "
" + ], + "text/plain": [ + " School Earnings Cost Grad Debt \\\n", + "111 Whittier College (Whittier, CA) 45100 33181 67 86 \n", + "112 Widener University (Chester, PA) 51700 27387 56 83 \n", + "113 Willamette University (Salem, OR) 49200 30312 78 93 \n", + "114 Winthrop University (Rock Hill, SC) 36100 15311 54 76 \n", + "115 Wittenberg University (Springfield, OH) 42700 26616 64 90 \n", + "\n", + " City \n", + "111 0 \n", + "112 0 \n", + "113 1 \n", + "114 1 \n", + "115 1 " + ] + }, + "execution_count": 47, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf.tail()" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "RVAeXlkzNSWi", + "outputId": "68e3246c-2621-492a-f989-6c8fe1de217d" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "(116, 6)" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "l-IUyXkCNXTx", + "outputId": "7e9963da-781e-4580-a2c5-3699e3b3d136" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "696" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf.size" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "8qveUcTkNav_", + "outputId": "c0972bb4-1577-43d6-b871-bf1d11436829" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EarningsCostGradDebtCity
count116.000000116.000000116.000000116.000000116.000000
mean46477.58620725251.68965565.68103488.4051720.508621
std7341.8761525387.15285811.7647966.8384820.502095
min32300.0000009938.00000032.00000052.0000000.000000
25%42300.00000021674.25000059.00000086.0000000.000000
50%45150.00000024957.50000067.00000090.0000001.000000
75%51000.00000029489.75000075.00000093.0000001.000000
max74900.00000035159.00000086.00000098.0000001.000000
\n", + "
" + ], + "text/plain": [ + " Earnings Cost Grad Debt City\n", + "count 116.000000 116.000000 116.000000 116.000000 116.000000\n", + "mean 46477.586207 25251.689655 65.681034 88.405172 0.508621\n", + "std 7341.876152 5387.152858 11.764796 6.838482 0.502095\n", + "min 32300.000000 9938.000000 32.000000 52.000000 0.000000\n", + "25% 42300.000000 21674.250000 59.000000 86.000000 0.000000\n", + "50% 45150.000000 24957.500000 67.000000 90.000000 1.000000\n", + "75% 51000.000000 29489.750000 75.000000 93.000000 1.000000\n", + "max 74900.000000 35159.000000 86.000000 98.000000 1.000000" + ] + }, + "execution_count": 50, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 696 + }, + "id": "HPJ285H3Jx7p", + "outputId": "e11e0599-a20f-4a65-e83c-a7182c072d08" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plotting\n", + "plt.figure(\n", + " figsize=(8, 8)\n", + ")\n", + "\n", + "plt.scatter(\n", + " collegeDf[\"Cost\"],\n", + " collegeDf[\"Earnings\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "plt.xlabel('Cost')\n", + "plt.ylabel('Earnings')\n", + "plt.legend()\n", + "plt.grid(True)\n", + "\n", + "\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Puh0-DhgKp9i", + "outputId": "97c984fb-f216-4db1-8a61-e0a266ed5981" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "( const Cost\n", + " 0 1.0 22920\n", + " 1 1.0 23429\n", + " 2 1.0 19567\n", + " 3 1.0 25147\n", + " 4 1.0 21979\n", + " .. ... ...\n", + " 111 1.0 33181\n", + " 112 1.0 27387\n", + " 113 1.0 30312\n", + " 114 1.0 15311\n", + " 115 1.0 26616\n", + " \n", + " [116 rows x 2 columns],\n", + " pandas.core.frame.DataFrame)" + ] + }, + "execution_count": 52, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sm.add_constant(collegeDf['Cost']), type(sm.add_constant(collegeDf['Cost']))" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "id": "54YBn53VNxQk" + }, + "outputs": [], + "source": [ + "earningOthersOlsModelFit1 = sm.OLS(\n", + " collegeDf[\"Earnings\"],\n", + " sm.add_constant(collegeDf['Cost'])\n", + ").fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "KbZxiP7zNyoY", + "outputId": "291d7bcc-2c3e-4ca6-8ab7-76b4af854f1a" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Earnings R-squared: 0.277\n", + "Model: OLS Adj. R-squared: 0.270\n", + "Method: Least Squares F-statistic: 43.61\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.33e-09\n", + "Time: 01:23:12 Log-Likelihood: -1177.9\n", + "No. Observations: 116 AIC: 2360.\n", + "Df Residuals: 114 BIC: 2365.\n", + "Df Model: 1 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 2.838e+04 2802.417 10.125 0.000 2.28e+04 3.39e+04\n", + "Cost 0.7169 0.109 6.604 0.000 0.502 0.932\n", + "==============================================================================\n", + "Omnibus: 11.840 Durbin-Watson: 1.841\n", + "Prob(Omnibus): 0.003 Jarque-Bera (JB): 19.875\n", + "Skew: 0.437 Prob(JB): 4.83e-05\n", + "Kurtosis: 4.830 Cond. No. 1.24e+05\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 1.24e+05. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "print(earningOthersOlsModelFit1.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 55, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"earningOthersOlsModelFit1\",\n", + " \"model\": earningOthersOlsModelFit1,\n", + " \"description\": \"predict Earnings based on Cost\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Cost\",\n", + " \"type\": \"float\"\n", + " }\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Earnings\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 424 + }, + "id": "Efg5OIl6KwDz", + "outputId": "880870cb-c2d4-4ff1-ad77-5103fd8a1083" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SchoolEarningsCostGradDebtCitypredictedEarning1
0St. Ambrose C (NC)44800229206288144806.067625
1Albion College (Albion, MI)45100234297392045170.954503
2Alfred University (Alfred, NY)42300195676387042402.402200
3Allegheny College (Meadville, PA)49200251477892046402.537324
4Beloit College (Beloit, WI)37900219797893144131.492866
........................
111Whittier College (Whittier, CA)45100331816786052161.871659
112Widener University (Chester, PA)51700273875683048008.326334
113Willamette University (Salem, OR)49200303127893150105.171359
114Winthrop University (Rock Hill, SC)36100153115476139351.403080
115Wittenberg University (Springfield, OH)42700266166490147455.619492
\n", + "

116 rows × 7 columns

\n", + "
" + ], + "text/plain": [ + " School Earnings Cost Grad Debt \\\n", + "0 St. Ambrose C (NC) 44800 22920 62 88 \n", + "1 Albion College (Albion, MI) 45100 23429 73 92 \n", + "2 Alfred University (Alfred, NY) 42300 19567 63 87 \n", + "3 Allegheny College (Meadville, PA) 49200 25147 78 92 \n", + "4 Beloit College (Beloit, WI) 37900 21979 78 93 \n", + ".. ... ... ... ... ... \n", + "111 Whittier College (Whittier, CA) 45100 33181 67 86 \n", + "112 Widener University (Chester, PA) 51700 27387 56 83 \n", + "113 Willamette University (Salem, OR) 49200 30312 78 93 \n", + "114 Winthrop University (Rock Hill, SC) 36100 15311 54 76 \n", + "115 Wittenberg University (Springfield, OH) 42700 26616 64 90 \n", + "\n", + " City predictedEarning1 \n", + "0 1 44806.067625 \n", + "1 0 45170.954503 \n", + "2 0 42402.402200 \n", + "3 0 46402.537324 \n", + "4 1 44131.492866 \n", + ".. ... ... \n", + "111 0 52161.871659 \n", + "112 0 48008.326334 \n", + "113 1 50105.171359 \n", + "114 1 39351.403080 \n", + "115 1 47455.619492 \n", + "\n", + "[116 rows x 7 columns]" + ] + }, + "execution_count": 56, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedEarning1 = earningOthersOlsModelFit1.predict(sm.add_constant(collegeDf[\"Cost\"]))\n", + "collegeDf['predictedEarning1'] = predictedEarning1\n", + "collegeDf" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 676 + }, + "id": "HWPp6ZYeLA3W", + "outputId": "45e4214b-e148-4726-a4ca-a4fb1b4dfdbe" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plt.figure(\n", + " figsize=(8, 8)\n", + ")\n", + "\n", + "plt.scatter(\n", + " collegeDf[\"Cost\"],\n", + " collegeDf[\"Earnings\"],\n", + " color='blue',\n", + " alpha=0.9,\n", + " label='Data Points - scatter',\n", + ")\n", + "\n", + "\n", + "plt.plot(\n", + " collegeDf[\"Cost\"],\n", + " collegeDf[\"predictedEarning1\"],\n", + " color='red',\n", + " label='OLS 1'\n", + ")\n", + "\n", + "plt.legend()\n", + "\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 424 + }, + "id": "VO6Yv3bgLyRv", + "outputId": "601d0a87-b32e-4957-bfdf-7b0749986842" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SchoolEarningsCostGradDebtCitypredictedEarning1
0St. Ambrose C (NC)44800229206288144806.067625
1Albion College (Albion, MI)45100234297392045170.954503
2Alfred University (Alfred, NY)42300195676387042402.402200
3Allegheny College (Meadville, PA)49200251477892046402.537324
4Beloit College (Beloit, WI)37900219797893144131.492866
........................
111Whittier College (Whittier, CA)45100331816786052161.871659
112Widener University (Chester, PA)51700273875683048008.326334
113Willamette University (Salem, OR)49200303127893150105.171359
114Winthrop University (Rock Hill, SC)36100153115476139351.403080
115Wittenberg University (Springfield, OH)42700266166490147455.619492
\n", + "

116 rows × 7 columns

\n", + "
" + ], + "text/plain": [ + " School Earnings Cost Grad Debt \\\n", + "0 St. Ambrose C (NC) 44800 22920 62 88 \n", + "1 Albion College (Albion, MI) 45100 23429 73 92 \n", + "2 Alfred University (Alfred, NY) 42300 19567 63 87 \n", + "3 Allegheny College (Meadville, PA) 49200 25147 78 92 \n", + "4 Beloit College (Beloit, WI) 37900 21979 78 93 \n", + ".. ... ... ... ... ... \n", + "111 Whittier College (Whittier, CA) 45100 33181 67 86 \n", + "112 Widener University (Chester, PA) 51700 27387 56 83 \n", + "113 Willamette University (Salem, OR) 49200 30312 78 93 \n", + "114 Winthrop University (Rock Hill, SC) 36100 15311 54 76 \n", + "115 Wittenberg University (Springfield, OH) 42700 26616 64 90 \n", + "\n", + " City predictedEarning1 \n", + "0 1 44806.067625 \n", + "1 0 45170.954503 \n", + "2 0 42402.402200 \n", + "3 0 46402.537324 \n", + "4 1 44131.492866 \n", + ".. ... ... \n", + "111 0 52161.871659 \n", + "112 0 48008.326334 \n", + "113 1 50105.171359 \n", + "114 1 39351.403080 \n", + "115 1 47455.619492 \n", + "\n", + "[116 rows x 7 columns]" + ] + }, + "execution_count": 58, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 437 + }, + "id": "at1I6sLoMJFu", + "outputId": "aec4f9c8-b2c0-48ff-f8ab-7f19585e8c84" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fig = plt.figure()\n", + "ax = plt.axes(projection =\"3d\")\n", + "\n", + "# Creating plot\n", + "ax.scatter3D(\n", + " collegeDf[\"Cost\"],\n", + " collegeDf[\"Grad\"],\n", + " collegeDf[\"Earnings\"],\n", + " color = \"green\"\n", + ")\n", + "plt.title(\"Cost,Grad -> Earnings\")\n", + "ax.set_xlabel('Cost')\n", + "ax.set_ylabel('Grad')\n", + "ax.set_zlabel('Earnings')\n", + "\n", + "# show plot\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "HzQFLcchNaDt", + "outputId": "5d676c4e-e4d2-4837-bcc1-98179415a3f0" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "( Cost Grad\n", + " 0 22920 62\n", + " 1 23429 73\n", + " 2 19567 63\n", + " 3 25147 78\n", + " 4 21979 78\n", + " .. ... ...\n", + " 111 33181 67\n", + " 112 27387 56\n", + " 113 30312 78\n", + " 114 15311 54\n", + " 115 26616 64\n", + " \n", + " [116 rows x 2 columns],\n", + " pandas.core.frame.DataFrame)" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf[['Cost', 'Grad']], type(collegeDf[['Cost', 'Grad']])" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "qBInUi_bsQ_x", + "outputId": "4235806e-71bb-41bd-d28b-f8ea2407c20a" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "( const Cost Grad\n", + " 0 1.0 22920 62\n", + " 1 1.0 23429 73\n", + " 2 1.0 19567 63\n", + " 3 1.0 25147 78\n", + " 4 1.0 21979 78\n", + " .. ... ... ...\n", + " 111 1.0 33181 67\n", + " 112 1.0 27387 56\n", + " 113 1.0 30312 78\n", + " 114 1.0 15311 54\n", + " 115 1.0 26616 64\n", + " \n", + " [116 rows x 3 columns],\n", + " pandas.core.frame.DataFrame)" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "sm.add_constant(collegeDf[['Cost', 'Grad']]), type(sm.add_constant(collegeDf[['Cost', 'Grad']]))" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "id": "PEQQ-E8dNQ9x" + }, + "outputs": [], + "source": [ + "earningOthersOlsModelFit2 = sm.OLS(\n", + " collegeDf[\"Earnings\"],\n", + " sm.add_constant(collegeDf[['Cost', 'Grad']])\n", + ").fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 63, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ETve670aOTNZ", + "outputId": "1d740ca1-fab3-4fdd-c574-052947d82800" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Earnings R-squared: 0.398\n", + "Model: OLS Adj. R-squared: 0.387\n", + "Method: Least Squares F-statistic: 37.37\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 3.50e-13\n", + "Time: 01:23:13 Log-Likelihood: -1167.2\n", + "No. Observations: 116 AIC: 2340.\n", + "Df Residuals: 113 BIC: 2349.\n", + "Df Model: 2 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 1.798e+04 3366.727 5.341 0.000 1.13e+04 2.47e+04\n", + "Cost 0.5131 0.108 4.741 0.000 0.299 0.728\n", + "Grad 236.6049 49.563 4.774 0.000 138.412 334.798\n", + "==============================================================================\n", + "Omnibus: 22.086 Durbin-Watson: 1.997\n", + "Prob(Omnibus): 0.000 Jarque-Bera (JB): 33.660\n", + "Skew: 0.904 Prob(JB): 4.91e-08\n", + "Kurtosis: 4.923 Cond. No. 1.63e+05\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 1.63e+05. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "print(earningOthersOlsModelFit2.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 64, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 64, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"earningOthersOlsModelFit2\",\n", + " \"model\": earningOthersOlsModelFit2,\n", + " \"description\": \"predict Earnings based on Cost and Grad\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Cost\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"Grad\",\n", + " \"type\": \"int\"\n", + " },\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Earnings\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 424 + }, + "id": "Dn6EX65kOdtu", + "outputId": "f13fe9be-487f-4717-ebf6-7158d8753fa3" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SchoolEarningsCostGradDebtCitypredictedEarning1predictedEarning2
0St. Ambrose C (NC)44800229206288144806.06762544410.232770
1Albion College (Albion, MI)45100234297392045170.95450347274.057585
2Alfred University (Alfred, NY)42300195676387042402.40220042926.395289
3Allegheny College (Meadville, PA)49200251477892046402.53732449338.597282
4Beloit College (Beloit, WI)37900219797893144131.49286647713.079376
...........................
111Whittier College (Whittier, CA)45100331816786052161.87165950858.231896
112Widener University (Chester, PA)51700273875683048008.32633445282.645045
113Willamette University (Salem, OR)49200303127893150105.17135951988.786671
114Winthrop University (Rock Hill, SC)36100153115476139351.40308038613.174391
115Wittenberg University (Springfield, OH)42700266166490147455.61949246779.880175
\n", + "

116 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " School Earnings Cost Grad Debt \\\n", + "0 St. Ambrose C (NC) 44800 22920 62 88 \n", + "1 Albion College (Albion, MI) 45100 23429 73 92 \n", + "2 Alfred University (Alfred, NY) 42300 19567 63 87 \n", + "3 Allegheny College (Meadville, PA) 49200 25147 78 92 \n", + "4 Beloit College (Beloit, WI) 37900 21979 78 93 \n", + ".. ... ... ... ... ... \n", + "111 Whittier College (Whittier, CA) 45100 33181 67 86 \n", + "112 Widener University (Chester, PA) 51700 27387 56 83 \n", + "113 Willamette University (Salem, OR) 49200 30312 78 93 \n", + "114 Winthrop University (Rock Hill, SC) 36100 15311 54 76 \n", + "115 Wittenberg University (Springfield, OH) 42700 26616 64 90 \n", + "\n", + " City predictedEarning1 predictedEarning2 \n", + "0 1 44806.067625 44410.232770 \n", + "1 0 45170.954503 47274.057585 \n", + "2 0 42402.402200 42926.395289 \n", + "3 0 46402.537324 49338.597282 \n", + "4 1 44131.492866 47713.079376 \n", + ".. ... ... ... \n", + "111 0 52161.871659 50858.231896 \n", + "112 0 48008.326334 45282.645045 \n", + "113 1 50105.171359 51988.786671 \n", + "114 1 39351.403080 38613.174391 \n", + "115 1 47455.619492 46779.880175 \n", + "\n", + "[116 rows x 8 columns]" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedEarning2 = earningOthersOlsModelFit2.predict(\n", + " sm.add_constant(collegeDf[['Cost', 'Grad']])\n", + ")\n", + "collegeDf['predictedEarning2'] = predictedEarning2\n", + "collegeDf" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "id": "wZw7IpfVRHJx" + }, + "outputs": [], + "source": [ + "# if 'google.colab' in str(get_ipython()):\n", + "# get_ipython().run_line_magic('matplotlib', 'inline')\n", + "\n", + "# %matplotlib notebook\n", + "# # %matplotlib notebook\n", + "%matplotlib inline" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 437 + }, + "id": "vSt3zKpiPYfJ", + "outputId": "45febe98-0078-49ec-9de6-f4bf941cf957" + }, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Extracting coefficients\n", + "intercept = earningOthersOlsModelFit2.params['const']\n", + "coef_cost = earningOthersOlsModelFit2.params['Cost']\n", + "coef_grad = earningOthersOlsModelFit2.params['Grad']\n", + "\n", + "# Create 3D grid for plotting\n", + "cost_range = np.linspace(collegeDf['Cost'].min(), collegeDf['Cost'].max(), 100)\n", + "grad_range = np.linspace(collegeDf['Grad'].min(), collegeDf['Grad'].max(), 100)\n", + "cost_grid, grad_grid = np.meshgrid(cost_range, grad_range)\n", + "\n", + "# Calculate predicted earnings for each combination of cost and grad\n", + "earnings_predicted = intercept + coef_cost * cost_grid + coef_grad * grad_grid\n", + "\n", + "\n", + "\n", + "\n", + "fig = plt.figure()\n", + "ax = plt.axes(projection =\"3d\")\n", + "\n", + "# Scatter plot of the actual data points\n", + "ax.scatter(collegeDf['Cost'], collegeDf['Grad'], collegeDf['Earnings'], color='blue', label='Actual Earnings')\n", + "\n", + "# Plotting the fitted plane\n", + "ax.plot_surface(cost_grid, grad_grid, earnings_predicted, color='red', alpha=0.5, label='Fitted Plane')\n", + "\n", + "# Labeling axes\n", + "ax.set_xlabel('Cost')\n", + "ax.set_ylabel('Grad')\n", + "ax.set_zlabel('Earnings')\n", + "\n", + "\n", + "\n", + "plt.title('Cost and Grad vs. Earnings with Fitted Plane')\n", + "\n", + "# Rotating the plot\n", + "# ax.view_init(elev=0, azim=0) # Set the elevation and azimuth angles\n", + "plt.show()\n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 424 + }, + "id": "FMzTsqooWmsR", + "outputId": "f6aa23e3-fced-4a19-b113-3d0e471b768f" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SchoolEarningsCostGradDebtCitypredictedEarning1predictedEarning2
0St. Ambrose C (NC)44800229206288144806.06762544410.232770
1Albion College (Albion, MI)45100234297392045170.95450347274.057585
2Alfred University (Alfred, NY)42300195676387042402.40220042926.395289
3Allegheny College (Meadville, PA)49200251477892046402.53732449338.597282
4Beloit College (Beloit, WI)37900219797893144131.49286647713.079376
...........................
111Whittier College (Whittier, CA)45100331816786052161.87165950858.231896
112Widener University (Chester, PA)51700273875683048008.32633445282.645045
113Willamette University (Salem, OR)49200303127893150105.17135951988.786671
114Winthrop University (Rock Hill, SC)36100153115476139351.40308038613.174391
115Wittenberg University (Springfield, OH)42700266166490147455.61949246779.880175
\n", + "

116 rows × 8 columns

\n", + "
" + ], + "text/plain": [ + " School Earnings Cost Grad Debt \\\n", + "0 St. Ambrose C (NC) 44800 22920 62 88 \n", + "1 Albion College (Albion, MI) 45100 23429 73 92 \n", + "2 Alfred University (Alfred, NY) 42300 19567 63 87 \n", + "3 Allegheny College (Meadville, PA) 49200 25147 78 92 \n", + "4 Beloit College (Beloit, WI) 37900 21979 78 93 \n", + ".. ... ... ... ... ... \n", + "111 Whittier College (Whittier, CA) 45100 33181 67 86 \n", + "112 Widener University (Chester, PA) 51700 27387 56 83 \n", + "113 Willamette University (Salem, OR) 49200 30312 78 93 \n", + "114 Winthrop University (Rock Hill, SC) 36100 15311 54 76 \n", + "115 Wittenberg University (Springfield, OH) 42700 26616 64 90 \n", + "\n", + " City predictedEarning1 predictedEarning2 \n", + "0 1 44806.067625 44410.232770 \n", + "1 0 45170.954503 47274.057585 \n", + "2 0 42402.402200 42926.395289 \n", + "3 0 46402.537324 49338.597282 \n", + "4 1 44131.492866 47713.079376 \n", + ".. ... ... ... \n", + "111 0 52161.871659 50858.231896 \n", + "112 0 48008.326334 45282.645045 \n", + "113 1 50105.171359 51988.786671 \n", + "114 1 39351.403080 38613.174391 \n", + "115 1 47455.619492 46779.880175 \n", + "\n", + "[116 rows x 8 columns]" + ] + }, + "execution_count": 68, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "collegeDf" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "id": "fyEd2awfWvHR" + }, + "outputs": [], + "source": [ + "earningOthersOlsModelFit3 = sm.OLS(\n", + " collegeDf[\"Earnings\"],\n", + " sm.add_constant(collegeDf[['Cost', 'Grad','Debt']])\n", + ").fit()" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from functions.exportModel import exportModel\n", + "exportModel({\n", + " \"modelName\": \"earningOthersOlsModelFit3\",\n", + " \"model\": earningOthersOlsModelFit3,\n", + " \"description\": \"predict Earnings based on Cost, Grad and Debt\",\n", + " \"modelType\": \"sm.OLS\",\n", + " \"baseRelativePath\": \"..\",\n", + " \"inputs\": [\n", + " {\n", + " \"name\": \"const\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Cost\",\n", + " \"type\": \"float\"\n", + " },\n", + " {\n", + " \"name\": \"Grad\",\n", + " \"type\": \"int\"\n", + " },\n", + " {\n", + " \"name\": \"Debt\",\n", + " \"type\": \"int\"\n", + " },\n", + " ],\n", + " \"output\": {\n", + " \"name\": \"Earnings\",\n", + " \"type\": \"float\"\n", + " }\n", + "})" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "vmMvLc-nW1i0", + "outputId": "7d40fdab-a57f-40c3-c6e1-ad4d0733f87f" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Earnings R-squared: 0.402\n", + "Model: OLS Adj. R-squared: 0.386\n", + "Method: Least Squares F-statistic: 25.12\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 1.67e-12\n", + "Time: 01:23:13 Log-Likelihood: -1166.8\n", + "No. Observations: 116 AIC: 2342.\n", + "Df Residuals: 112 BIC: 2353.\n", + "Df Model: 3 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 1.182e+04 7735.631 1.528 0.129 -3507.686 2.71e+04\n", + "Cost 0.5050 0.109 4.644 0.000 0.290 0.720\n", + "Grad 192.6664 70.194 2.745 0.007 53.585 331.747\n", + "Debt 104.6573 118.283 0.885 0.378 -129.706 339.020\n", + "==============================================================================\n", + "Omnibus: 20.823 Durbin-Watson: 1.998\n", + "Prob(Omnibus): 0.000 Jarque-Bera (JB): 31.211\n", + "Skew: 0.862 Prob(JB): 1.67e-07\n", + "Kurtosis: 4.867 Cond. No. 3.74e+05\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 3.74e+05. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "print(earningOthersOlsModelFit3.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "-hrTLW63W8Dd", + "outputId": "9e03fe28-fe75-4dff-c322-ffbec2b5848d" + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " OLS Regression Results \n", + "==============================================================================\n", + "Dep. Variable: Earnings R-squared: 0.398\n", + "Model: OLS Adj. R-squared: 0.387\n", + "Method: Least Squares F-statistic: 37.37\n", + "Date: Sun, 09 Jun 2024 Prob (F-statistic): 3.50e-13\n", + "Time: 01:23:13 Log-Likelihood: -1167.2\n", + "No. Observations: 116 AIC: 2340.\n", + "Df Residuals: 113 BIC: 2349.\n", + "Df Model: 2 \n", + "Covariance Type: nonrobust \n", + "==============================================================================\n", + " coef std err t P>|t| [0.025 0.975]\n", + "------------------------------------------------------------------------------\n", + "const 1.798e+04 3366.727 5.341 0.000 1.13e+04 2.47e+04\n", + "Cost 0.5131 0.108 4.741 0.000 0.299 0.728\n", + "Grad 236.6049 49.563 4.774 0.000 138.412 334.798\n", + "==============================================================================\n", + "Omnibus: 22.086 Durbin-Watson: 1.997\n", + "Prob(Omnibus): 0.000 Jarque-Bera (JB): 33.660\n", + "Skew: 0.904 Prob(JB): 4.91e-08\n", + "Kurtosis: 4.923 Cond. No. 1.63e+05\n", + "==============================================================================\n", + "\n", + "Notes:\n", + "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", + "[2] The condition number is large, 1.63e+05. This might indicate that there are\n", + "strong multicollinearity or other numerical problems.\n" + ] + } + ], + "source": [ + "print(earningOthersOlsModelFit2.summary())" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 424 + }, + "id": "BgNn0qPaYGK7", + "outputId": "2e79d89c-f027-4414-cd90-febe5b2ef9ef" + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SchoolEarningsCostGradDebtCitypredictedEarning1predictedEarning2predictedEarning3
0St. Ambrose C (NC)44800229206288144806.06762544410.23277044548.538177
1Albion College (Albion, MI)45100234297392045170.95450347274.05758547343.527426
2Alfred University (Alfred, NY)42300195676387042402.40220042926.39528942943.384593
3Allegheny College (Meadville, PA)49200251477892046402.53732449338.59728249174.396984
4Beloit College (Beloit, WI)37900219797893144131.49286647713.07937647679.311039
..............................
111Whittier College (Whittier, CA)45100331816786052161.87165950858.23189650484.047251
112Widener University (Chester, PA)51700273875683048008.32633445282.64504545124.951685
113Willamette University (Salem, OR)49200303127893150105.17135951988.78667151887.221654
114Winthrop University (Rock Hill, SC)36100153115476139351.40308038613.17439137909.006123
115Wittenberg University (Springfield, OH)42700266166490147455.61949246779.88017547009.552838
\n", + "

116 rows × 9 columns

\n", + "
" + ], + "text/plain": [ + " School Earnings Cost Grad Debt \\\n", + "0 St. Ambrose C (NC) 44800 22920 62 88 \n", + "1 Albion College (Albion, MI) 45100 23429 73 92 \n", + "2 Alfred University (Alfred, NY) 42300 19567 63 87 \n", + "3 Allegheny College (Meadville, PA) 49200 25147 78 92 \n", + "4 Beloit College (Beloit, WI) 37900 21979 78 93 \n", + ".. ... ... ... ... ... \n", + "111 Whittier College (Whittier, CA) 45100 33181 67 86 \n", + "112 Widener University (Chester, PA) 51700 27387 56 83 \n", + "113 Willamette University (Salem, OR) 49200 30312 78 93 \n", + "114 Winthrop University (Rock Hill, SC) 36100 15311 54 76 \n", + "115 Wittenberg University (Springfield, OH) 42700 26616 64 90 \n", + "\n", + " City predictedEarning1 predictedEarning2 predictedEarning3 \n", + "0 1 44806.067625 44410.232770 44548.538177 \n", + "1 0 45170.954503 47274.057585 47343.527426 \n", + "2 0 42402.402200 42926.395289 42943.384593 \n", + "3 0 46402.537324 49338.597282 49174.396984 \n", + "4 1 44131.492866 47713.079376 47679.311039 \n", + ".. ... ... ... ... \n", + "111 0 52161.871659 50858.231896 50484.047251 \n", + "112 0 48008.326334 45282.645045 45124.951685 \n", + "113 1 50105.171359 51988.786671 51887.221654 \n", + "114 1 39351.403080 38613.174391 37909.006123 \n", + "115 1 47455.619492 46779.880175 47009.552838 \n", + "\n", + "[116 rows x 9 columns]" + ] + }, + "execution_count": 73, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "predictedEarning3 = earningOthersOlsModelFit3.predict(\n", + " sm.add_constant(collegeDf[['Cost', 'Grad', 'Debt']])\n", + ")\n", + "collegeDf['predictedEarning3'] = predictedEarning3\n", + "collegeDf" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git a/package.json b/package.json index 0e6d9fc..5cafdce 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "mlModelSaver", - "version": "1.0.12", + "version": "1.0.13", "description": "Make life easier for save and serving ml models", "main": "index.js", "repository": "git@github.com:smartdev-ca/mlModelSaver.git", diff --git a/pytests/test_mlModelSaver.py b/pytests/test_mlModelSaver.py index 8493047..13ac61c 100644 --- a/pytests/test_mlModelSaver.py +++ b/pytests/test_mlModelSaver.py @@ -8,7 +8,7 @@ sys.path.insert( os.path.abspath( os.path.join( os.path.dirname(__file__), - '../mlModelSaver' + '..' ) ) ) @@ -21,7 +21,7 @@ def test_ensureCLassInstance(): "modelsFolder": "test_modelsFolder" }) assert mlModelSaverInstance1.baseRelativePath == "test_baseRelativePath" - assert mlModelSaverInstance1.modelsFolder == "test_modelsFolder" + assert mlModelSaverInstance1.modelsFolder == "test_baseRelativePath/test_modelsFolder" tesSupportedModels = mlModelSaverInstance1.showSupportedModels() assert tesSupportedModels == ['sm.OLS'] @@ -31,22 +31,25 @@ def test_OLS_LinearRegression(): import numpy as np import pandas as pd import statsmodels.api as sm + from helpers import add_constant_column salaryMisDf = pd.read_excel("./datasets/Salary_MIS.xlsx") salaryBasedOnGpaMisStatistics = sm.OLS( salaryMisDf["Salary"], - sm.add_constant(salaryMisDf[["GPA", "MIS", "Statistics"]]) + add_constant_column(salaryMisDf[["GPA", "MIS", "Statistics"]]) ) salaryBasedOnGpaMisStatisticsFit = salaryBasedOnGpaMisStatistics.fit() mlModelSaverInstance2 = MlModelSaver({ "baseRelativePath": ".", - "modelsFolder": "~~tmp/models" + "modelsFolder": "~~tmp/testModels" }) - mlModelSaverInstance2.exportModel( + + + loadedModel = mlModelSaverInstance2.exportModel( salaryBasedOnGpaMisStatisticsFit, { - "modelName": "salaryBasedOnGpaMisStatisticsFit", - "description": "Predict Salary based on GPA MIS Statistics for sallaryMisDf", + "modelName": "salaryBasedOnGpaMisStatistics", + "description": "Predict Salary based on GPA MIS Statistics for salaryMisDf", "modelType": "sm.OLS", "inputs": [ { @@ -62,7 +65,8 @@ def test_OLS_LinearRegression(): "type": "binary" } ], - "output": [ + "transformer": add_constant_column, + "outputs": [ { "name": "Salary", "type": "int" @@ -70,4 +74,9 @@ def test_OLS_LinearRegression(): ] } ) - assert 2 == 2 + from mlModelSaver import check_file_exists + assert check_file_exists("./~~tmp/testModels/salaryBasedOnGpaMisStatistics.pkl") == True + testData = salaryMisDf[["GPA", "MIS", "Statistics"]].iloc[0:2] + predictedValueWithLoadedModel = loadedModel.mlModelSavePredict(testData, 'normal') + assert predictedValueWithLoadedModel == [{'Salary': 73.9924679451542}, {'Salary': 69.55525482441558}] + assert list(mlModelSaverInstance2.cachedModels.keys()) == ['salaryBasedOnGpaMisStatistics'] diff --git a/requirements.txt b/requirements.txt index 43ec90f..7a4a2c9 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,42 +1,138 @@ +anyio==4.4.0 +appnope==0.1.4 +argon2-cffi==23.1.0 +argon2-cffi-bindings==21.2.0 +arrow==1.3.0 +asttokens==2.4.1 +async-lru==2.0.4 +attrs==23.2.0 autopep8==2.2.0 +Babel==2.15.0 +beautifulsoup4==4.12.3 +bleach==6.1.0 certifi==2024.6.2 +cffi==1.16.0 charset-normalizer==3.3.2 +comm==0.2.2 +contourpy==1.2.1 +cycler==0.12.1 +debugpy==1.8.1 +decorator==5.1.1 +defusedxml==0.7.1 docutils==0.21.2 et-xmlfile==1.1.0 +executing==2.0.1 +fastjsonschema==2.20.0 +fonttools==4.53.0 +fqdn==1.5.1 +h11==0.14.0 +httpcore==1.0.5 +httpx==0.27.0 idna==3.7 importlib_metadata==7.1.0 iniconfig==2.0.0 +ipykernel==6.29.4 +ipython==8.25.0 +ipywidgets==8.1.3 +isoduration==20.11.0 jaraco.classes==3.4.0 jaraco.context==5.3.0 jaraco.functools==4.0.1 +jedi==0.19.1 +Jinja2==3.1.4 +json5==0.9.25 +jsonpointer==3.0.0 +jsonschema==4.22.0 +jsonschema-specifications==2023.12.1 +jupyter==1.0.0 +jupyter-console==6.6.3 +jupyter-events==0.10.0 +jupyter-lsp==2.2.5 +jupyter_client==8.6.2 +jupyter_core==5.7.2 +jupyter_server==2.14.1 +jupyter_server_terminals==0.5.3 +jupyterlab==4.2.2 +jupyterlab_pygments==0.3.0 +jupyterlab_server==2.27.2 +jupyterlab_widgets==3.0.11 keyring==25.2.1 +kiwisolver==1.4.5 markdown-it-py==3.0.0 +MarkupSafe==2.1.5 +matplotlib==3.9.0 +matplotlib-inline==0.1.7 mdurl==0.1.2 +mistune==3.0.2 +mlModelSaver==1.0.12 more-itertools==10.3.0 +nbclient==0.10.0 +nbconvert==7.16.4 +nbformat==5.10.4 +nest-asyncio==1.6.0 nh3==0.2.17 +notebook==7.2.1 +notebook_shim==0.2.4 numpy==1.26.4 openpyxl==3.1.4 +overrides==7.7.0 packaging==24.1 pandas==2.2.2 +pandocfilters==1.5.1 +parso==0.8.4 patsy==0.5.6 +pexpect==4.9.0 +pillow==10.3.0 pkginfo==1.11.1 +platformdirs==4.2.2 pluggy==1.5.0 +prometheus_client==0.20.0 +prompt_toolkit==3.0.47 +psutil==5.9.8 +ptyprocess==0.7.0 +pure-eval==0.2.2 pycodestyle==2.11.1 +pycparser==2.22 Pygments==2.18.0 +pyparsing==3.1.2 pytest==8.2.2 python-dateutil==2.9.0.post0 +python-json-logger==2.0.7 pytz==2024.1 +PyYAML==6.0.1 +pyzmq==26.0.3 +qtconsole==5.5.2 +QtPy==2.4.1 readme_renderer==43.0 +referencing==0.35.1 requests==2.32.3 requests-toolbelt==1.0.0 +rfc3339-validator==0.1.4 rfc3986==2.0.0 +rfc3986-validator==0.1.1 rich==13.7.1 +rpds-py==0.18.1 scipy==1.13.1 +Send2Trash==1.8.3 setuptools==70.0.0 six==1.16.0 +sniffio==1.3.1 +soupsieve==2.5 +stack-data==0.6.3 statsmodels==0.14.2 +terminado==0.18.1 +tinycss2==1.3.0 +tornado==6.4.1 +traitlets==5.14.3 twine==5.1.0 +types-python-dateutil==2.9.0.20240316 tzdata==2024.1 +uri-template==1.3.0 urllib3==2.2.1 +wcwidth==0.2.13 +webcolors==24.6.0 +webencodings==0.5.1 +websocket-client==1.8.0 wheel==0.43.0 +widgetsnbextension==4.0.11 zipp==3.19.2 diff --git a/setup.py b/setup.py index 53ac16e..0ebaba9 100644 --- a/setup.py +++ b/setup.py @@ -2,7 +2,7 @@ from setuptools import setup, find_packages setup( name='mlModelSaver', - version='1.0.12', + version='1.0.13', packages=find_packages(), description='Make life easier for saving and serving ML models', long_description=open('DOCS.md').read(), # Assumes you have a README.md file