{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "htcWC_rahuEO"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import statsmodels.formula.api as smf\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "nMp4vGhHh24o"
   },
   "outputs": [],
   "source": [
    "rawBostonData = pd.read_csv('../Dataset/Boston.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "rinZvyYSh5E1"
   },
   "outputs": [],
   "source": [
    "rawBostonData = rawBostonData.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "66P7Nrqrh7R3"
   },
   "outputs": [],
   "source": [
    "rawBostonData = rawBostonData.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "SvaVeiVYh9bI"
   },
   "outputs": [],
   "source": [
    "renamedBostonData = rawBostonData.rename(columns = {'CRIM':'crimeRatePerCapita',\n",
    " ' ZN ':'landOver25K_sqft',\n",
    " 'INDUS ':'non-retailLandProptn',\n",
    " 'CHAS':'riverDummy',\n",
    " 'NOX':'nitrixOxide_pp10m',\n",
    " 'RM':'AvgNo.RoomsPerDwelling',\n",
    " 'AGE':'ProptnOwnerOccupied',\n",
    " 'DIS':'weightedDist',\n",
    " 'RAD':'radialHighwaysAccess',\n",
    " 'TAX':'propTaxRate_per10K',\n",
    " 'PTRATIO':'pupilTeacherRatio',\n",
    " 'LSTAT':'pctLowerStatus',\n",
    " 'MEDV':'medianValue_Ks'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "2bdQ0pNxh_ux"
   },
   "outputs": [],
   "source": [
    "X = renamedBostonData.drop('crimeRatePerCapita', axis = 1)\n",
    "y = renamedBostonData[['crimeRatePerCapita']]\n",
    "seed = 10 \n",
    "test_data_size = 0.3 \n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = test_data_size, random_state = seed)\n",
    "train_data = pd.concat([X_train, y_train], axis = 1)\n",
    "test_data = pd.concat([X_test, y_test], axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "pS55MGThiChz"
   },
   "outputs": [],
   "source": [
    "logLinearModel = smf.ols(formula='np.log(crimeRatePerCapita) ~ medianValue_Ks', data=train_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "T2EmISCBkr1t"
   },
   "outputs": [],
   "source": [
    "logLinearModResult = logLinearModel.fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 442
    },
    "colab_type": "code",
    "id": "n-D9pwOSkthe",
    "outputId": "4a111658-9370-491c-d38b-d480f783e8b8"
   },
   "outputs": [],
   "source": [
    "print(logLinearModResult.summary())"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Activity2_01.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}