{
 "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
}