chore: bump version to 1.0.13

.gitignore

@@ -10,3 +10,4 @@ build/
 node_modules
 
 ~~
+~~*

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
 ```

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

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

mlModelSaver/mlModelSaver.py

@@ -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

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": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Sales</th>\n",
+       "      <th>Temperature</th>\n",
+       "      <th>Advertising</th>\n",
+       "      <th>Discount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>17235</td>\n",
+       "      <td>33</td>\n",
+       "      <td>15</td>\n",
+       "      <td>5.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>19854</td>\n",
+       "      <td>42</td>\n",
+       "      <td>25</td>\n",
+       "      <td>5.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>45786</td>\n",
+       "      <td>58</td>\n",
+       "      <td>40</td>\n",
+       "      <td>10.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>49745</td>\n",
+       "      <td>67</td>\n",
+       "      <td>70</td>\n",
+       "      <td>20.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>65894</td>\n",
+       "      <td>73</td>\n",
+       "      <td>75</td>\n",
+       "      <td>20.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "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": [
+       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x12e499550>"
+      ]
+     },
+     "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
+}

notebooks/.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

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": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Sales</th>\n",
+       "      <th>Temperature</th>\n",
+       "      <th>Advertising</th>\n",
+       "      <th>Discount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>17235</td>\n",
+       "      <td>33</td>\n",
+       "      <td>15</td>\n",
+       "      <td>5.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>19854</td>\n",
+       "      <td>42</td>\n",
+       "      <td>25</td>\n",
+       "      <td>5.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>45786</td>\n",
+       "      <td>58</td>\n",
+       "      <td>40</td>\n",
+       "      <td>10.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>49745</td>\n",
+       "      <td>67</td>\n",
+       "      <td>70</td>\n",
+       "      <td>20.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>65894</td>\n",
+       "      <td>73</td>\n",
+       "      <td>75</td>\n",
+       "      <td>20.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "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": [
+       "<statsmodels.regression.linear_model.RegressionResultsWrapper at 0x12e499550>"
+      ]
+     },
+     "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
+}

notebooks/Readme.md

@@ -0,0 +1,4 @@
+```
+pip install jupyterlab
+pip install notebook
+```

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": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>A</th>\n",
+       "      <th>B</th>\n",
+       "      <th>C</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "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": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>A</th>\n",
+       "      <th>B</th>\n",
+       "      <th>C</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>4</td>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "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
+}

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
+}

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",

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",
+            "modelName": "salaryBasedOnGpaMisStatistics",
-            "description": "Predict Salary based on GPA MIS Statistics for sallaryMisDf",
+            "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']

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

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