{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "GalWZL42gUJL"
   },
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import matplotlib as mpl\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import statsmodels.formula.api as smf\n",
    "import statsmodels.graphics.api as smg\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import patsy\n",
    "from statsmodels.graphics.correlation import plot_corr\n",
    "from sklearn.model_selection import train_test_split\n",
    "plt.style.use('seaborn')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "6_lKgFqPgeyk"
   },
   "outputs": [],
   "source": [
    "rawBostonData = pd.read_csv('../Dataset/Boston.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "yB1hG1WKglOM",
    "outputId": "2030133d-d616-4059-f647-da075e03ed12"
   },
   "outputs": [],
   "source": [
    "rawBostonData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "1krtNoLygsJx"
   },
   "outputs": [],
   "source": [
    "rawBostonData = rawBostonData.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Eyxd8QXwgw_d"
   },
   "outputs": [],
   "source": [
    "rawBostonData = rawBostonData.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 238
    },
    "colab_type": "code",
    "id": "1Z62CWO_gzc5",
    "outputId": "8868804a-e4f7-41fa-c07f-6b759bd63eb5"
   },
   "outputs": [],
   "source": [
    "list(rawBostonData.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 241
    },
    "colab_type": "code",
    "id": "EB7FBISzg2yx",
    "outputId": "92c8bde0-5493-442a-ee48-8eefdc48aaba"
   },
   "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'})\n",
    "renamedBostonData.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 323
    },
    "colab_type": "code",
    "id": "N_cmLg_5g56i",
    "outputId": "f11f011c-9d31-4ff5-a03b-e380356fc2a3"
   },
   "outputs": [],
   "source": [
    "renamedBostonData.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 452
    },
    "colab_type": "code",
    "id": "X8khkdpjgv-K",
    "outputId": "478bc4de-75c2-413b-dc1c-7156d8bd7c82"
   },
   "outputs": [],
   "source": [
    "renamedBostonData.describe(include=[np.number]).T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "oO_etrVcg-gV"
   },
   "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": {
     "base_uri": "https://localhost:8080/",
     "height": 793
    },
    "colab_type": "code",
    "id": "dwCbKxJqhBee",
    "outputId": "d1604316-dc31-4a5f-af82-75cfc8b70faf"
   },
   "outputs": [],
   "source": [
    "corrMatrix = train_data.corr(method = 'pearson')\n",
    "xnames=list(train_data.columns)\n",
    "ynames=list(train_data.columns)\n",
    "plot_corr(corrMatrix, xnames=xnames, ynames=ynames,\\\n",
    "          title=None, normcolor=False, cmap='RdYlBu_r')"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise2.01.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
}