path: root/Data Prediction/Tele Churn/.ipynb_checkpoints/tele_churn-checkpoint.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "211755a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "# pip install matplotlib pandas seaborn missingno plotly scikit-learn xgboost catboost lightgbm"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "be0c7624-8210-4045-9033-2176cb5211ef",
   "metadata": {},
   "source": [
    "# Importing Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "3ce7f5d0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "        <script type=\"text/javascript\">\n",
       "        window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
       "        if (window.MathJax && window.MathJax.Hub && window.MathJax.Hub.Config) {window.MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
       "        if (typeof require !== 'undefined') {\n",
       "        require.undef(\"plotly\");\n",
       "        requirejs.config({\n",
       "            paths: {\n",
       "                'plotly': ['https://cdn.plot.ly/plotly-2.27.0.min']\n",
       "            }\n",
       "        });\n",
       "        require(['plotly'], function(Plotly) {\n",
       "            window._Plotly = Plotly;\n",
       "        });\n",
       "        }\n",
       "        </script>\n",
       "        "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import warnings\n",
    "warnings.simplefilter(action='ignore')\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import missingno as msno\n",
    "from plotly.offline import plot, iplot, init_notebook_mode\n",
    "init_notebook_mode(connected=True)\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "from sklearn.preprocessing import MinMaxScaler, LabelEncoder, StandardScaler, RobustScaler\n",
    "from sklearn.model_selection import GridSearchCV, cross_validate\n",
    "from sklearn.metrics import roc_auc_score,roc_curve, classification_report, confusion_matrix, accuracy_score\n",
    "from sklearn.metrics import RocCurveDisplay\n",
    "from sklearn.model_selection import train_test_split, cross_validate\n",
    "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, VotingClassifier, AdaBoostClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from xgboost import XGBClassifier\n",
    "from catboost import CatBoostClassifier\n",
    "from lightgbm import LGBMClassifier\n",
    "from sklearn.exceptions import ConvergenceWarning\n",
    "import tkinter\n",
    "from collections import Counter\n",
    "\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.max_rows', None)\n",
    "pd.set_option('display.float_format', lambda x: '%.3f' % x)\n",
    "pd.set_option('display.width', 500)\n",
    "\n",
    "# %matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a35dd24-0ced-4d2d-930c-064a0be81b50",
   "metadata": {},
   "source": [
    "# Loading Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "fe7fdda7",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1 = pd.read_csv(\"WA_Fn-UseC_-Telco-Customer-Churn.csv\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "147cc94e-f526-4f19-9101-caac1a7a8f4e",
   "metadata": {},
   "source": [
    "# Explorartory Data Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "eccab7dd-6d55-4d84-9ef2-10c8b9fefc93",
   "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>customerID</th>\n",
       "      <th>gender</th>\n",
       "      <th>SeniorCitizen</th>\n",
       "      <th>Partner</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>tenure</th>\n",
       "      <th>PhoneService</th>\n",
       "      <th>MultipleLines</th>\n",
       "      <th>InternetService</th>\n",
       "      <th>OnlineSecurity</th>\n",
       "      <th>OnlineBackup</th>\n",
       "      <th>DeviceProtection</th>\n",
       "      <th>TechSupport</th>\n",
       "      <th>StreamingTV</th>\n",
       "      <th>StreamingMovies</th>\n",
       "      <th>Contract</th>\n",
       "      <th>PaperlessBilling</th>\n",
       "      <th>PaymentMethod</th>\n",
       "      <th>MonthlyCharges</th>\n",
       "      <th>TotalCharges</th>\n",
       "      <th>Churn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7590-VHVEG</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>No</td>\n",
       "      <td>No phone service</td>\n",
       "      <td>DSL</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Month-to-month</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Electronic check</td>\n",
       "      <td>29.850</td>\n",
       "      <td>29.85</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5575-GNVDE</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>34</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>DSL</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>One year</td>\n",
       "      <td>No</td>\n",
       "      <td>Mailed check</td>\n",
       "      <td>56.950</td>\n",
       "      <td>1889.5</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3668-QPYBK</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>DSL</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Month-to-month</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Mailed check</td>\n",
       "      <td>53.850</td>\n",
       "      <td>108.15</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7795-CFOCW</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>45</td>\n",
       "      <td>No</td>\n",
       "      <td>No phone service</td>\n",
       "      <td>DSL</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>One year</td>\n",
       "      <td>No</td>\n",
       "      <td>Bank transfer (automatic)</td>\n",
       "      <td>42.300</td>\n",
       "      <td>1840.75</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9237-HQITU</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>2</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Fiber optic</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Month-to-month</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Electronic check</td>\n",
       "      <td>70.700</td>\n",
       "      <td>151.65</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   customerID  gender  SeniorCitizen Partner Dependents  tenure PhoneService     MultipleLines InternetService OnlineSecurity OnlineBackup DeviceProtection TechSupport StreamingTV StreamingMovies        Contract PaperlessBilling              PaymentMethod  MonthlyCharges TotalCharges Churn\n",
       "0  7590-VHVEG  Female              0     Yes         No       1           No  No phone service             DSL             No          Yes               No          No          No              No  Month-to-month              Yes           Electronic check          29.850        29.85    No\n",
       "1  5575-GNVDE    Male              0      No         No      34          Yes                No             DSL            Yes           No              Yes          No          No              No        One year               No               Mailed check          56.950       1889.5    No\n",
       "2  3668-QPYBK    Male              0      No         No       2          Yes                No             DSL            Yes          Yes               No          No          No              No  Month-to-month              Yes               Mailed check          53.850       108.15   Yes\n",
       "3  7795-CFOCW    Male              0      No         No      45           No  No phone service             DSL            Yes           No              Yes         Yes          No              No        One year               No  Bank transfer (automatic)          42.300      1840.75    No\n",
       "4  9237-HQITU  Female              0      No         No       2          Yes                No     Fiber optic             No           No               No          No          No              No  Month-to-month              Yes           Electronic check          70.700       151.65   Yes"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df1.copy()\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "072cc34f-b29e-41ae-998a-3796be0dcc86",
   "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>customerID</th>\n",
       "      <th>gender</th>\n",
       "      <th>SeniorCitizen</th>\n",
       "      <th>Partner</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>tenure</th>\n",
       "      <th>PhoneService</th>\n",
       "      <th>MultipleLines</th>\n",
       "      <th>InternetService</th>\n",
       "      <th>OnlineSecurity</th>\n",
       "      <th>OnlineBackup</th>\n",
       "      <th>DeviceProtection</th>\n",
       "      <th>TechSupport</th>\n",
       "      <th>StreamingTV</th>\n",
       "      <th>StreamingMovies</th>\n",
       "      <th>Contract</th>\n",
       "      <th>PaperlessBilling</th>\n",
       "      <th>PaymentMethod</th>\n",
       "      <th>MonthlyCharges</th>\n",
       "      <th>TotalCharges</th>\n",
       "      <th>Churn</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7038</th>\n",
       "      <td>6840-RESVB</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>24</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>DSL</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>One year</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Mailed check</td>\n",
       "      <td>84.800</td>\n",
       "      <td>1990.5</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7039</th>\n",
       "      <td>2234-XADUH</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>72</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Fiber optic</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>One year</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Credit card (automatic)</td>\n",
       "      <td>103.200</td>\n",
       "      <td>7362.9</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7040</th>\n",
       "      <td>4801-JZAZL</td>\n",
       "      <td>Female</td>\n",
       "      <td>0</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>No</td>\n",
       "      <td>No phone service</td>\n",
       "      <td>DSL</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Month-to-month</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Electronic check</td>\n",
       "      <td>29.600</td>\n",
       "      <td>346.45</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7041</th>\n",
       "      <td>8361-LTMKD</td>\n",
       "      <td>Male</td>\n",
       "      <td>1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>4</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Fiber optic</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Month-to-month</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Mailed check</td>\n",
       "      <td>74.400</td>\n",
       "      <td>306.6</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7042</th>\n",
       "      <td>3186-AJIEK</td>\n",
       "      <td>Male</td>\n",
       "      <td>0</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>66</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Fiber optic</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Two year</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Bank transfer (automatic)</td>\n",
       "      <td>105.650</td>\n",
       "      <td>6844.5</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      customerID  gender  SeniorCitizen Partner Dependents  tenure PhoneService     MultipleLines InternetService OnlineSecurity OnlineBackup DeviceProtection TechSupport StreamingTV StreamingMovies        Contract PaperlessBilling              PaymentMethod  MonthlyCharges TotalCharges Churn\n",
       "7038  6840-RESVB    Male              0     Yes        Yes      24          Yes               Yes             DSL            Yes           No              Yes         Yes         Yes             Yes        One year              Yes               Mailed check          84.800       1990.5    No\n",
       "7039  2234-XADUH  Female              0     Yes        Yes      72          Yes               Yes     Fiber optic             No          Yes              Yes          No         Yes             Yes        One year              Yes    Credit card (automatic)         103.200       7362.9    No\n",
       "7040  4801-JZAZL  Female              0     Yes        Yes      11           No  No phone service             DSL            Yes           No               No          No          No              No  Month-to-month              Yes           Electronic check          29.600       346.45    No\n",
       "7041  8361-LTMKD    Male              1     Yes         No       4          Yes               Yes     Fiber optic             No           No               No          No          No              No  Month-to-month              Yes               Mailed check          74.400        306.6   Yes\n",
       "7042  3186-AJIEK    Male              0      No         No      66          Yes                No     Fiber optic            Yes           No              Yes         Yes         Yes             Yes        Two year              Yes  Bank transfer (automatic)         105.650       6844.5    No"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "9c64a681",
   "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>SeniorCitizen</th>\n",
       "      <th>tenure</th>\n",
       "      <th>MonthlyCharges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>7043.000</td>\n",
       "      <td>7043.000</td>\n",
       "      <td>7043.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.162</td>\n",
       "      <td>32.371</td>\n",
       "      <td>64.762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.369</td>\n",
       "      <td>24.559</td>\n",
       "      <td>30.090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>18.250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000</td>\n",
       "      <td>9.000</td>\n",
       "      <td>35.500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000</td>\n",
       "      <td>29.000</td>\n",
       "      <td>70.350</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.000</td>\n",
       "      <td>55.000</td>\n",
       "      <td>89.850</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000</td>\n",
       "      <td>72.000</td>\n",
       "      <td>118.750</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       SeniorCitizen   tenure  MonthlyCharges\n",
       "count       7043.000 7043.000        7043.000\n",
       "mean           0.162   32.371          64.762\n",
       "std            0.369   24.559          30.090\n",
       "min            0.000    0.000          18.250\n",
       "25%            0.000    9.000          35.500\n",
       "50%            0.000   29.000          70.350\n",
       "75%            0.000   55.000          89.850\n",
       "max            1.000   72.000         118.750"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0d330dc4",
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>SeniorCitizen</th>\n",
       "      <td>7043.000</td>\n",
       "      <td>0.162</td>\n",
       "      <td>0.369</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>1.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tenure</th>\n",
       "      <td>7043.000</td>\n",
       "      <td>32.371</td>\n",
       "      <td>24.559</td>\n",
       "      <td>0.000</td>\n",
       "      <td>9.000</td>\n",
       "      <td>29.000</td>\n",
       "      <td>55.000</td>\n",
       "      <td>72.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MonthlyCharges</th>\n",
       "      <td>7043.000</td>\n",
       "      <td>64.762</td>\n",
       "      <td>30.090</td>\n",
       "      <td>18.250</td>\n",
       "      <td>35.500</td>\n",
       "      <td>70.350</td>\n",
       "      <td>89.850</td>\n",
       "      <td>118.750</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  count   mean    std    min    25%    50%    75%     max\n",
       "SeniorCitizen  7043.000  0.162  0.369  0.000  0.000  0.000  0.000   1.000\n",
       "tenure         7043.000 32.371 24.559  0.000  9.000 29.000 55.000  72.000\n",
       "MonthlyCharges 7043.000 64.762 30.090 18.250 35.500 70.350 89.850 118.750"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe().T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "a30694a2-5fec-4755-871a-ed37833b7c3c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7043, 21)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "f6e03abf-0d4e-4f82-b40d-a89f7cb5e102",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['customerID', 'gender', 'SeniorCitizen', 'Partner', 'Dependents', 'tenure', 'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies', 'Contract', 'PaperlessBilling', 'PaymentMethod', 'MonthlyCharges', 'TotalCharges', 'Churn'], dtype='object')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2962acc6-4b0b-4fab-96ba-1af16ddf8dcc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "customerID          0\n",
       "gender              0\n",
       "SeniorCitizen       0\n",
       "Partner             0\n",
       "Dependents          0\n",
       "tenure              0\n",
       "PhoneService        0\n",
       "MultipleLines       0\n",
       "InternetService     0\n",
       "OnlineSecurity      0\n",
       "OnlineBackup        0\n",
       "DeviceProtection    0\n",
       "TechSupport         0\n",
       "StreamingTV         0\n",
       "StreamingMovies     0\n",
       "Contract            0\n",
       "PaperlessBilling    0\n",
       "PaymentMethod       0\n",
       "MonthlyCharges      0\n",
       "TotalCharges        0\n",
       "Churn               0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "76760a8d-b933-47d6-8357-de5fad75fe1d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "09aeaead",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m******************** SHAPE ********************\u001b[0m\n",
      "(7043, 21)\n",
      "\u001b[1m******************** TYPES ********************\u001b[0m\n",
      "customerID           object\n",
      "gender               object\n",
      "SeniorCitizen         int64\n",
      "Partner              object\n",
      "Dependents           object\n",
      "tenure                int64\n",
      "PhoneService         object\n",
      "MultipleLines        object\n",
      "InternetService      object\n",
      "OnlineSecurity       object\n",
      "OnlineBackup         object\n",
      "DeviceProtection     object\n",
      "TechSupport          object\n",
      "StreamingTV          object\n",
      "StreamingMovies      object\n",
      "Contract             object\n",
      "PaperlessBilling     object\n",
      "PaymentMethod        object\n",
      "MonthlyCharges      float64\n",
      "TotalCharges         object\n",
      "Churn                object\n",
      "dtype: object\n",
      "\u001b[1m******************** NA ********************\u001b[0m\n",
      "customerID          0\n",
      "gender              0\n",
      "SeniorCitizen       0\n",
      "Partner             0\n",
      "Dependents          0\n",
      "tenure              0\n",
      "PhoneService        0\n",
      "MultipleLines       0\n",
      "InternetService     0\n",
      "OnlineSecurity      0\n",
      "OnlineBackup        0\n",
      "DeviceProtection    0\n",
      "TechSupport         0\n",
      "StreamingTV         0\n",
      "StreamingMovies     0\n",
      "Contract            0\n",
      "PaperlessBilling    0\n",
      "PaymentMethod       0\n",
      "MonthlyCharges      0\n",
      "TotalCharges        0\n",
      "Churn               0\n",
      "dtype: int64\n",
      "\u001b[1m******************** DUPLICATED VALUE ********************\u001b[0m\n",
      "0\n"
     ]
    }
   ],
   "source": [
    "def check_df(dataframe, head=10):\n",
    "    \n",
    "    print('\\033[1m' + 20*\"*\" + ' SHAPE ' + 20*\"*\" + '\\033[0m')\n",
    "    print(dataframe.shape)\n",
    "    \n",
    "    print('\\033[1m' + 20*\"*\" + ' TYPES ' + 20*\"*\" + '\\033[0m')\n",
    "    print(dataframe.dtypes)\n",
    "    \n",
    "    print('\\033[1m' + 20*\"*\" + ' NA ' + 20*\"*\" + '\\033[0m')\n",
    "    print(dataframe.isnull().sum())\n",
    "    \n",
    "    print('\\033[1m' + 20*\"*\" + ' DUPLICATED VALUE ' + 20*\"*\" + '\\033[0m')\n",
    "    print(dataframe.duplicated().sum())\n",
    "    \n",
    "check_df(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "09adc81e-77f4-4ebe-8f85-e0ea6da42b7c",
   "metadata": {},
   "source": [
    "### Data Cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "b2f45ccf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Making the necessary arrangements\n",
    "# Since we do not need the CustomerID variable, we omitted it from the dataset.\n",
    "df = df.drop(['customerID'], axis = 1)\n",
    "\n",
    "# We converted the Churn variable as we wanted to see it as 1/0 instead of yes/no.\n",
    "df[\"Churn\"] = df[\"Churn\"].replace({\"Yes\":1, \"No\":0})\n",
    "\n",
    "# We converted the TotalCharges variable to a numeric variable.\n",
    "df.TotalCharges = pd.to_numeric(df.TotalCharges, errors='coerce')\n",
    "\n",
    "# SeniorCitizen variable should be object not integer, we changed that too.\n",
    "df[\"SeniorCitizen\"] = df[\"SeniorCitizen\"].astype(\"O\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "f21e4206",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7043 entries, 0 to 7042\n",
      "Data columns (total 20 columns):\n",
      " #   Column            Non-Null Count  Dtype  \n",
      "---  ------            --------------  -----  \n",
      " 0   gender            7043 non-null   object \n",
      " 1   SeniorCitizen     7043 non-null   object \n",
      " 2   Partner           7043 non-null   object \n",
      " 3   Dependents        7043 non-null   object \n",
      " 4   tenure            7043 non-null   int64  \n",
      " 5   PhoneService      7043 non-null   object \n",
      " 6   MultipleLines     7043 non-null   object \n",
      " 7   InternetService   7043 non-null   object \n",
      " 8   OnlineSecurity    7043 non-null   object \n",
      " 9   OnlineBackup      7043 non-null   object \n",
      " 10  DeviceProtection  7043 non-null   object \n",
      " 11  TechSupport       7043 non-null   object \n",
      " 12  StreamingTV       7043 non-null   object \n",
      " 13  StreamingMovies   7043 non-null   object \n",
      " 14  Contract          7043 non-null   object \n",
      " 15  PaperlessBilling  7043 non-null   object \n",
      " 16  PaymentMethod     7043 non-null   object \n",
      " 17  MonthlyCharges    7043 non-null   float64\n",
      " 18  TotalCharges      7032 non-null   float64\n",
      " 19  Churn             7043 non-null   int64  \n",
      "dtypes: float64(2), int64(2), object(16)\n",
      "memory usage: 1.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "089edcff",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.02, 'Count of Target Variable per Category')"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAArQAAAI6CAYAAADWhNtyAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA8KElEQVR4nO3deXyNZ/7/8ffJdkJIIk1ijURQStA2SlU1bYXYq1OtGkboUDoYhtbQ+arSRZcZal+mlm6qtWurlNi6mFbV2qKW2NciIWpNrt8ffTg/RxJySBwXr+fjkccj57qvc9+fc18nvHPnuq/jMMYYAQAAAJby8XYBAAAAwPUg0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAihQFy5cUN++fRUVFSUfHx+1bNnS2yXdNmJiYtShQwePn7ds2TI5HA7NmDHjqn07dOigmJgYz4sDgHxEoAVugO3bt6tLly6KjY1VYGCggoODVbduXQ0fPlynT5/2dnmSpDFjxmjKlCn5vt9Jkybp7bffVqtWrfTee+/pH//4R7Y+U6ZMkcPhuOrXzRic8nreZs2aJYfDoXfffTfXPosWLZLD4dCIESPysUJcq2XLlulPf/qTSpQooYCAAEVGRqp58+aaNWuWx/v6/fff9fLLL2vZsmX5XygA+Xm7AOBW98UXX+jJJ5+U0+lU+/btFRcXp3Pnzumbb77RCy+8oJ9//lkTJkzwdpkaM2aMwsPDr+mK3pUsWbJEpUuX1rBhw3Lt89BDD+mDDz5wa+vUqZNq1aqlZ5991tVWpEiRfK0tP+T1vDVt2lQhISGaOnWqOnXqlGOfqVOnytfXV08//XS+1LZlyxb5+HDd4loMHDhQgwcPVsWKFdWlSxdFR0fr6NGjmj9/vp544gl99NFH+vOf/5zn/f3+++8aNGiQJOnhhx8uoKqB2xeBFihAqampevrppxUdHa0lS5aoZMmSrm3dunXTtm3b9MUXX3ixwoJ3+PBhhYaGXrFPbGysYmNj3dq6du2q2NhYtWvX7rprOHPmjAICArwa7pxOp1q1aqXJkydr//79KlWqlNv2M2fOaPbs2WrQoIEiIyOv+TjGGJ05c0aFChWS0+m83rJvSZeeo5zMmDFDgwcPVqtWrTR16lT5+/u7tr3wwgtauHChzp8/f6PKveF+//13FS5c2NtlAB7hV3egAL311lvKyMjQxIkT3cLsRRUqVFDPnj1djy9cuKBXXnlF5cuXl9PpVExMjF588UWdPXvW7XkOh0Mvv/xytv1dPmfy4p/yv/32W/Xu3VsREREKCgrS448/riNHjrg97+eff9by5ctdf96/2lWkU6dOqU+fPoqKipLT6VSlSpX073//W8YYSdLOnTvlcDi0dOlS/fzzz679XuufXI8dO6bnn39e1apVU5EiRRQcHKzGjRtr3bp1bv0uzv+cNm2a/u///k+lS5dW4cKFdeLECUnS9OnTVaVKFQUGBiouLk6zZ8/OcR5oVlaW3nnnHVWtWlWBgYEqXry4unTpouPHj1/zeWvXrp2ysrI0bdq0bNu++OILpaenq23btpKkyZMn69FHH1VkZKScTqeqVKmisWPHZnteTEyMmjVrpoULF6pmzZoqVKiQxo8f79p26fshr+fwoszMTL344osqUaKEgoKC1KJFC+3ZsyfX1+fJuctNhw4dVKRIEe3YsUNJSUkKCgpSqVKlNHjwYNd7y9PjXOkc5WTAgAEKCwvTpEmT3MLsRUlJSWrWrJkk6dy5c3rppZcUHx+vkJAQBQUFqV69elq6dKmr/86dOxURESFJGjRokOu9cunP8ObNm9WqVSuFhYUpMDBQNWvW1Lx587Ide/369UpISFChQoVUpkwZvfrqq5o8ebIcDod27tzp1nfMmDGqWrWqnE6nSpUqpW7duiktLc2tz8MPP6y4uDitXr1aDz30kAoXLqwXX3xRycnJCg8PzzG4N2zYUJUqVcr1/AFeYQAUmNKlS5vY2Ng8909OTjaSTKtWrczo0aNN+/btjSTTsmVLt36SzMCBA7M9Pzo62iQnJ7seT5482Ugy99xzj3n00UfNyJEjTZ8+fYyvr6956qmnXP1mz55typQpYypXrmw++OAD88EHH5ivvvoq1zqzsrLMo48+ahwOh+nUqZMZNWqUad68uZFkevXqZYwxJiMjw3zwwQemcuXKpkyZMq79Hjx4ME/nIigoyO21rFq1ypQvX97069fPjB8/3gwePNiULl3ahISEmH379rn6LV261EgyVapUMXfffbcZOnSoGTJkiDl16pT5/PPPjcPhMNWrVzdDhw41AwYMMMWKFTNxcXEmOjra7fidOnUyfn5+pnPnzmbcuHHmn//8pwkKCjL33XefOXfu3DWdt8zMTFOmTBkTHx+fbduf/vQnU7hwYXPy5EljjDH33Xef6dChgxk2bJgZOXKkadiwoZFkRo0a5fa86OhoU6FCBVOsWDHTr18/M27cOLN06VLXtus5h9WqVXOdq379+pnAwEBz5513mt9//93VNzk5+ZrOXW6Sk5NNYGCgqVixovnLX/5iRo0aZZo1a2YkmQEDBlzTca50ji7366+/GknmmWeeuWKdFx05csSULFnS9O7d24wdO9a89dZbplKlSsbf39+sWbPGGPPHz8LYsWONJPP444+73ivr1q0zxhizceNGExISYqpUqWLefPNNM2rUKPPQQw8Zh8NhZs2a5TrW3r17TVhYmLnjjjvMoEGDzL///W9TuXJlU6NGDSPJpKamuvoOHDjQSDKJiYlm5MiRpnv37sbX1zfbuUlISDAlSpQwERERpkePHmb8+PFmzpw5ZtGiRUaS+eyzz9xe74EDB4yvr68ZPHhwns4PcKMQaIECkp6ebiSZxx57LE/9165daySZTp06ubU///zzRpJZsmSJq83TQJuYmGiysrJc7f/4xz+Mr6+vSUtLc7VVrVrVJCQk5KnWOXPmGEnm1VdfdWtv1aqVcTgcZtu2ba62hIQEU7Vq1Tzt91KXB9ozZ86YzMxMtz6pqanG6XS6/ed6MYzFxsa6BS9jjKlWrZopU6aMKzQaY8yyZcuMJLdQ9vXXXxtJ5qOPPnJ7/oIFC7K1e3LejDHmhRdeMJLMli1bXG3p6ekmMDDQtGnTxtV2ee3GGJOUlJTtF6To6GgjySxYsCBb/8vfD56ew9KlS5sTJ0642j/99FMjyQwfPtzVdnmg9eTc5eTiL3U9evRwtWVlZZmmTZuagIAAc+TIEY+Pc6VzdLm5c+caSWbYsGFX7WuMMRcuXDBnz551azt+/LgpXry4Wyg+cuRIrj+39evXN9WqVTNnzpxxtWVlZZkHHnjAVKxY0dXWo0cP43A4XEHZGGOOHj1qwsLC3ALt4cOHTUBAgGnYsKHbeI8aNcpIMpMmTXK1JSQkGElm3LhxbjVd/OWrdevWbu1Dhw41DofD7Nix4+onB7iBmHIAFJCLf+IuWrRonvrPnz9fktS7d2+39j59+kjSdc21ffbZZ+VwOFyP69Wrp8zMTO3ateua9jd//nz5+vrq73//e7ZajTH68ssvr7nW3DidTtcc2MzMTB09elRFihRRpUqV9NNPP2Xrn5yc7DZHcv/+/dqwYYPat2/vdnNZQkKCqlWr5vbc6dOnKyQkRA0aNNBvv/3m+oqPj1eRIkXc/pzsqYtzgqdOnepqmzlzps6cOeOabiDJrfb09HT99ttvSkhI0I4dO5Senu62z3LlyikpKemqx/b0HLZv397t/duqVSuVLFnS9V7NSX6du+7du7u+dzgc6t69u86dO6fFixdf03Hyeo48/bn19fVVQECApD+mQBw7dkwXLlxQzZo1czynlzt27JiWLFmip556SidPnnS9jqNHjyopKUlbt27Vvn37JEkLFixQnTp1dPfdd7ueHxYW5va+kaTFixfr3Llz6tWrl9u88c6dOys4ODjbvyVOp1MdO3Z0a/Px8VHbtm01b948nTx50tX+0Ucf6YEHHlC5cuXydH6AG4VACxSQ4OBgSXL7z+BKdu3aJR8fH1WoUMGtvUSJEgoNDb3m8ClJZcuWdXtcrFgxScrTnMac7Nq1S6VKlcr2n/5dd93l2p7fsrKyNGzYMFWsWFFOp1Ph4eGKiIjQ+vXrswU8Sdn+w71Y0+XnN6e2rVu3Kj09XZGRkYqIiHD7ysjI0OHDh6/5dVSvXl1xcXH6+OOPXW1Tp05VeHi4W+D69ttvlZiYqKCgIIWGhioiIkIvvviiJOUYaPPC03NYsWJFt8cOh0MVKlTINlfzUvlx7nx8fLLdJHjnnXdKkuvYnh4nr+fI059bSXrvvfdUvXp1BQYG6o477lBERIRrTvTVbNu2TcYYDRgwINvrGDhwoCS5XsuuXbvy9P69+F6/fJ5rQECAYmNjs/18li5d2hXKL9W+fXudPn1as2fPlvTHqhmrV6/WX/7yl6u+LuBGY5UDoIAEBwerVKlS2rhxo0fPu/RKqqcyMzNzbPf19c2x3Vx2k83N7PXXX9eAAQP0zDPP6JVXXlFYWJh8fHzUq1cvZWVlZeuf2x3seZGVlaXIyEh99NFHOW6/eIPPtWrXrp369eunH3/8UWXKlNHSpUvVpUsX+fn98U/y9u3bVb9+fVWuXFlDhw5VVFSUAgICNH/+fA0bNizb683ra/X0HF6Lgj5313qcvJ6jypUrS5I2bNiQp/4ffvihOnTooJYtW+qFF15QZGSkfH19NWTIEG3fvv2qz7943p9//vlcryDnFGLzU27npkqVKoqPj9eHH36o9u3b68MPP1RAQICeeuqpAq0HuBYEWqAANWvWTBMmTNDKlStVp06dK/aNjo5WVlaWtm7d6rrSKUmHDh1SWlqaoqOjXW3FihXLdrfyuXPndODAgWuu1ZMgHR0drcWLF+vkyZNuV2k3b97s2p7fZsyYoUceeUQTJ050a09LS1N4ePhVn3+xpm3btmXbdnlb+fLltXjxYtWtW/eqQehafgFp06aN+vfvr6lTpyo6OlqZmZlufzb+7LPPdPbsWc2bN8/t6vr1THWQPD+HW7dudXtsjNG2bdtUvXr1XI/hybnLTVZWlnbs2OG6KitJv/76qyS5VqPIj+Pk5M4771SlSpU0d+5cDR8+/KprH8+YMUOxsbGuD8646OLV1Ytye59cvBLt7++vxMTEKx4rOjo6T+/fi+/1LVu2uF3pPnfunFJTU696nEu1b99evXv31oEDBzR16lQ1bdrU9Rce4GbClAOgAPXt21dBQUHq1KmTDh06lG379u3bNXz4cElSkyZNJEnvvPOOW5+hQ4dK+mNh/ovKly+vFStWuPWbMGFCrldo8yIoKChbSM5NkyZNlJmZqVGjRrm1Dxs2TA6HQ40bN77mOnLj6+ub7Yry9OnTXfMLr6ZUqVKKi4vT+++/r4yMDFf78uXLs12Ne+qpp5SZmalXXnkl234uXLjgdp48OW8XlS1bVvXq1dMnn3yiDz/8UOXKldMDDzzg2n7xivqlrzc9PV2TJ0/26DiX8/Qcvv/++25/ep8xY4YOHDhwxfH15NxdyaXvLWOMRo0aJX9/f9WvXz9fj5OTQYMG6ejRo+rUqZMuXLiQbftXX32lzz//XFLOY/X9999r5cqVbs+5uK7r5XVFRkbq4Ycf1vjx43P8hfTS5fWSkpK0cuVKrV271tV27NixbFepExMTFRAQoBEjRrjVNXHiRKWnp7v9W3I1bdq0kcPhUM+ePbVjx458WRcaKAhcoQUKUPny5TV16lS1bt1ad911l9snhX333XeaPn26a53QGjVqKDk5WRMmTFBaWpoSEhL0ww8/6L333lPLli31yCOPuPbbqVMnde3aVU888YQaNGigdevWaeHChXm6Upmb+Ph4jR07Vq+++qoqVKigyMhIPfroozn2bd68uR555BH961//0s6dO1WjRg199dVXmjt3rnr16qXy5ctfcx25adasmQYPHqyOHTvqgQce0IYNG/TRRx9lm2t5Ja+//roee+wx1a1bVx07dtTx48c1atQoxcXFuYXchIQEdenSRUOGDNHatWvVsGFD+fv7a+vWrZo+fbqGDx+uVq1aSfLsvF2qXbt2evbZZ7V//37961//ctvWsGFDBQQEqHnz5urSpYsyMjL03//+V5GRkdd1Fd7TcxgWFqYHH3xQHTt21KFDh/TOO++oQoUK6ty5c67H8OTc5SYwMFALFixQcnKyateurS+//FJffPGFXnzxRddUgvw4Tm5at26tDRs26LXXXtOaNWvUpk0b1yeFLViwQCkpKa6b+po1a6ZZs2bp8ccfV9OmTZWamqpx48apSpUqbu+pQoUKqUqVKvrkk0905513KiwsTHFxcYqLi9Po0aP14IMPqlq1aurcubNiY2N16NAhrVy5Unv37nWtE9y3b199+OGHatCggXr06KGgoCC9++67Klu2rI4dO+a6ChwREaH+/ftr0KBBatSokVq0aKEtW7ZozJgxuu+++zwKpREREWrUqJGmT5+u0NBQj8IwcEN5a3kF4Hby66+/ms6dO5uYmBgTEBBgihYtaurWrWtGjhzptlTP+fPnzaBBg0y5cuWMv7+/iYqKMv3793frY8wfS+r885//NOHh4aZw4cImKSnJbNu2Lddlu1atWuX2/IvLMl26FufBgwdN06ZNTdGiRY2kqy5FdfLkSfOPf/zDlCpVyvj7+5uKFSuat99+2215MGPyd9muPn36mJIlS5pChQqZunXrmpUrV5qEhAS3Wi++tunTp+e432nTppnKlSsbp9Np4uLizLx588wTTzxhKleunK3vhAkTTHx8vClUqJApWrSoqVatmunbt6/Zv3+/q4+n5+2iY8eOGafTaSSZX375Jdv2efPmmerVq5vAwEATExNj3nzzTTNp0qRs641GR0ebpk2b5niMnJbt8uQcfvzxx6Z///4mMjLSFCpUyDRt2tTs2rXL7Rg5rUOb13OXk+TkZBMUFGS2b99uGjZsaAoXLmyKFy9uBg4cmG3Jsbwe50rn6EpSUlLMY489ZiIjI42fn5+JiIgwzZs3N3PnznX1ycrKMq+//rqJjo42TqfT3HPPPebzzz/P8bx89913Jj4+3gQEBGRbwmv79u2mffv2pkSJEsbf39+ULl3aNGvWzMyYMcNtH2vWrDH16tUzTqfTlClTxgwZMsSMGDHCSMq2xvOoUaNM5cqVjb+/vylevLh57rnnzPHjx9365OXn8+Jybc8++2zeTx5wgzmMseiuEAAoAHfffbciIiK0aNEib5dy2+vQoYNmzJjhdnUTV9arVy+NHz9eGRkZud4Aej3mzp2rli1basWKFapXr16+7x/ID8yhBXDbOH/+fLY5kcuWLdO6deuu+lG/wM3g9OnTbo+PHj2qDz74QA8++GCBhFlJ+u9//6vY2Fg9+OCDBbJ/ID8whxbAbWPfvn1KTExUu3btVKpUKW3evFnjxo1TiRIl1LVrV2+XB1xVnTp19PDDD+uuu+7SoUOHNHHiRJ04cUIDBgzI92NNmzZN69ev1xdffKHhw4df15KCQEEj0AK4bRQrVkzx8fF69913deTIEQUFBalp06Z64403dMcdd3i7POCqmjRpohkzZmjChAlyOBy69957NXHiRD300EP5fqw2bdqoSJEi+utf/6q//e1v+b5/ID8xhxYAAABWYw4tAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsJqftwvwhqysLO3fv19FixaVw+HwdjkAAAC4jDFGJ0+eVKlSpeTjc+VrsLdloN2/f7+ioqK8XQYAAACuYs+ePSpTpswV+9yWgbZo0aKS/jhBwcHBXq4GAAAAlztx4oSioqJcue1KbstAe3GaQXBwMIEWAADgJpaX6aHcFAYAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAan7eLsCb4gYulI+zsLfLAG4JO99o6u0SAAC3Ka7QAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArGZloF2xYoWaN2+uUqVKyeFwaM6cOd4uCQAAAF5iZaA9deqUatSoodGjR3u7FAAAAHiZn7cLuBaNGzdW48aN89z/7NmzOnv2rOvxiRMnCqIsAAAAeIGVV2g9NWTIEIWEhLi+oqKivF0SAAAA8sltEWj79++v9PR019eePXu8XRIAAADyiZVTDjzldDrldDq9XQYAAAAKwG1xhRYAAAC3LgItAAAArGbllIOMjAxt27bN9Tg1NVVr165VWFiYypYt68XKAAAAcKNZGWh//PFHPfLII67HvXv3liQlJydrypQpXqoKAAAA3mBloH344YdljPF2GQAAALgJMIcWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGp+3i7AmzYOSlJwcLC3ywAAAMB14AotAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKtdU6C9cOGCFi9erPHjx+vkyZOSpP379ysjIyNfiwMAAACuxuMPVti1a5caNWqk3bt36+zZs2rQoIGKFi2qN998U2fPntW4ceMKok4AAAAgRx5foe3Zs6dq1qyp48ePq1ChQq72xx9/XCkpKflaHAAAAHA1Hl+h/frrr/Xdd98pICDArT0mJkb79u3Lt8IAAACAvPD4Cm1WVpYyMzOzte/du1dFixbNl6IAAACAvPI40DZs2FDvvPOO67HD4VBGRoYGDhyoJk2a5GdtAAAAwFU5jDHGkyfs3btXSUlJMsZo69atqlmzprZu3arw8HCtWLFCkZGRBVVrvjlx4oRCQkKUnp6u4OBgb5cDAACAy3iS1zwOtNIfy3ZNmzZN69evV0ZGhu699161bdvW7SaxmxmBFgAA4ObmSV7z+KYwSfLz81O7du2uqTgAAAAgP+Up0M6bNy/PO2zRosU1FwMAAAB4Kk+BtmXLlnnamcPhyHEFBAAAAKCg5CnQZmVlFXQdAAAAwDXxeNkuAAAA4GZyTYE2JSVFzZo1U/ny5VW+fHk1a9ZMixcvzu/aAAAAgKvyONCOGTNGjRo1UtGiRdWzZ0/17NlTwcHBatKkiUaPHl0QNQIAAAC58ngd2jJlyqhfv37q3r27W/vo0aP1+uuva9++fflaYEFgHVoAAICbmyd5zeMrtGlpaWrUqFG29oYNGyo9Pd3T3QEAAADXxeNA26JFC82ePTtb+9y5c9WsWbN8KQoAAADIqzwt2zVixAjX91WqVNFrr72mZcuWqU6dOpKk//3vf/r222/Vp0+fgqkSAAAAyEWe5tCWK1cubztzOLRjx47rLqqgMYcWAADg5uZJXsvTFdrU1NR8KQwAAADIb3ywAgAAAKyWpyu0l9u7d6/mzZun3bt369y5c27bhg4dmi+FAQAAAHnhcaBNSUlRixYtFBsbq82bNysuLk47d+6UMUb33ntvQdQIAAAA5MrjKQf9+/fX888/rw0bNigwMFAzZ87Unj17lJCQoCeffLIgagQAAABy5XGg3bRpk9q3by9J8vPz0+nTp1WkSBENHjxYb775Zr4XCAAAAFyJx4E2KCjINW+2ZMmS2r59u2vbb7/9ln+VAQAAAHng8Rza+++/X998843uuusuNWnSRH369NGGDRs0a9Ys3X///QVRIwAAAJArjwPt0KFDlZGRIUkaNGiQMjIy9Mknn6hixYqscAAAAIAbLk+fFHar4ZPCAAAAbm6e5DU+WAEAAABWy9OUg7CwMP36668KDw9XsWLF5HA4cu177NixfCsOAAAAuJo8Bdphw4apaNGikqR33nmnIOsBAAAAPJKnQJucnCxJunDhghwOh5KSklS8ePECLQwAAADIC4/m0Pr5+alr1646c+ZMQdUDAAAAeMTjm8Jq1aqlNWvWFEQtAAAAgMc8Xof2b3/7m/r06aO9e/cqPj5eQUFBbturV6+eb8UBAAAAV+PxOrQ+Ptkv6jocDhlj5HA4lJmZmW/FFRTWoQUAALi5eZLXPL5Cm5qaes2FAQAAAPnN40AbHR1dEHUAAAAA18TjQHvRL7/8ot27d+vcuXNu7S1atLjuogAAAIC88jjQ7tixQ48//rg2bNjgmjsryfXpYTbMoQUAAMCtw+Nlu3r27Kly5crp8OHDKly4sH7++WetWLFCNWvW1LJlywqgRAAAACB3Hl+hXblypZYsWaLw8HD5+PjIx8dHDz74oIYMGaK///3vrFELAACAG8rjK7SZmZkqWrSoJCk8PFz79++X9MfNYlu2bMnf6gAAAICr8PgKbVxcnNatW6dy5cqpdu3aeuuttxQQEKAJEyYoNja2IGoEAAAAcuVxoP2///s/nTp1SpI0ePBgNWvWTPXq1dMdd9yhTz75JN8LBAAAAK4kz4G2Zs2a6tSpk/785z+7Pq2hQoUK2rx5s44dO6ZixYq5VjoAAAAAbpQ8z6GtUaOG+vbtq5IlS6p9+/ZuKxqEhYURZgEAAOAVeQ60EydO1MGDBzV69Gjt3r1b9evXV4UKFfT6669r3759BVkjAAAAkCuPVjkoXLiwOnTooGXLlunXX3/V008/rfHjxysmJkZNmzbVrFmzCqpOAAAAIEcOc/Gjvq6RMUYzZ85Uly5dlJaWZsUnhZ04cUIhISFKT093zQcGAADAzcOTvObxKgeXWrZsmSZPnqyZM2fKz89PnTt3vp7dAQAAAB7zONDu3btXU6ZM0ZQpU7Rjxw7Vq1dPY8aM0ZNPPqlChQoVRI0AAABArvIcaD/99FNNmjRJKSkpioyMVHJysp555hlVqFChIOsDAAAArijPgbZdu3Zq2rSpZs+erSZNmsjHx+NPzQUAAADyXZ4D7d69exUZGVmQtQAAAAAey/NlVsIsAAAAbkbMGwAAAIDVCLQAAACwGoEWAAAAVvM40MbGxuro0aPZ2tPS0hQbG5svRQEAAAB55XGg3blzZ44fb3v27Fnt27cvX4oCAAAA8irPy3bNmzfP9f3ChQsVEhLiepyZmamUlBTFxMTka3EAAADA1eQ50LZs2VKS5HA4lJyc7LbN399fMTEx+s9//pOvxQEAAABXk+dAm5WVJUkqV66cVq1apfDw8AIrCgAAAMirPAfai1JTU13fnzlzRoGBgflaEAAAAOAJj28Ky8rK0iuvvKLSpUurSJEi2rFjhyRpwIABmjhxYr4XCAAAAFyJx4H21Vdf1ZQpU/TWW28pICDA1R4XF6d33303X4sDAAAArsbjQPv+++9rwoQJatu2rXx9fV3tNWrU0ObNm/O1OAAAAOBqPA60+/btU4UKFbK1Z2Vl6fz58/lSFAAAAJBXHgfaKlWq6Ouvv87WPmPGDN1zzz35UhQAAACQVx6vcvDSSy8pOTlZ+/btU1ZWlmbNmqUtW7bo/fff1+eff14QNQIAAAC58vgK7WOPPabPPvtMixcvVlBQkF566SVt2rRJn332mRo0aFAQNQIAAAC5chhjjLeLuNFOnDihkJAQpaenKzg42NvlAAAA4DKe5DWPr9ACAAAANxOP59AWK1ZMDocjW7vD4VBgYKAqVKigDh06qGPHjvlSIAAAAHAl13RT2GuvvabGjRurVq1akqQffvhBCxYsULdu3ZSamqrnnntOFy5cUOfOnfO9YAAAAOBSHgfab775Rq+++qq6du3q1j5+/Hh99dVXmjlzpqpXr64RI0YQaAEAAFDgPJ5Du3DhQiUmJmZrr1+/vhYuXChJatKkiXbs2HH91QEAAABX4XGgDQsL02effZat/bPPPlNYWJgk6dSpUypatOj1VwcAAABchcdTDgYMGKDnnntOS5cudc2hXbVqlebPn69x48ZJkhYtWqSEhIT8rRQAAADIwTWtQ/vtt99q1KhR2rJliySpUqVK6tGjhx544IF8L7AgsA4tAADAzc2TvObRFdrz58+rS5cuGjBggD7++OPrKhIAAADIDx7NofX399fMmTMLqhYAAADAYx7fFNayZUvNmTOnAEoBAAAAPOfxTWEVK1bU4MGD9e233yo+Pl5BQUFu2//+97/nW3EAAADA1Xh8U1i5cuVy35nDYcX6s9wUBgAAcHMrsJvCJCk1NfWaCwMAAADym8dzaAEAAICbicdXaCVp7969mjdvnnbv3q1z5865bRs6dGi+FAYAAADkhceBNiUlRS1atFBsbKw2b96suLg47dy5U8YY3XvvvQVRIwAAAJArj6cc9O/fX88//7w2bNigwMBAzZw5U3v27FFCQoKefPLJgqgRAAAAyJXHgXbTpk1q3769JMnPz0+nT59WkSJFNHjwYL355pv5XiAAAABwJR4H2qCgINe82ZIlS2r79u2ubb/99lv+VQYAAADkQZ4D7eDBg3Xq1Cndf//9+uabbyRJTZo0UZ8+ffTaa6/pmWee0f33319ghQIAAAA5yfMHK/j6+urAgQPKyMhQRkaGqlevrlOnTqlPnz767rvvVLFiRQ0dOlTR0dEFXfN144MVAAAAbm4F8sEKF3NvbGysqy0oKEjjxo27xjIBAACA6+fRHFqHw1FQdQAAAADXxKN1aO+8886rhtpjx45dV0EAAACAJzwKtIMGDVJISEhB1QIAAAB4zKNA+/TTTysyMrKgagEAAAA8luc5tMyfBQAAwM0oz4E2j6t7AQAAADdUnqccZGVlFWQdAAAAwDXx+KNvAQAAgJsJgRYAAABWI9ACAADAah4t23WriRu4UD7Owt4uAwAA4Ka3842m3i4hV1yhBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWM3aQDt69GjFxMQoMDBQtWvX1g8//ODtkgAAAOAFVgbaTz75RL1799bAgQP1008/qUaNGkpKStLhw4e9XRoAAABuMCsD7dChQ9W5c2d17NhRVapU0bhx41S4cGFNmjQpx/5nz57ViRMn3L4AAABwa7Au0J47d06rV69WYmKiq83Hx0eJiYlauXJljs8ZMmSIQkJCXF9RUVE3qlwAAAAUMOsC7W+//abMzEwVL17crb148eI6ePBgjs/p37+/0tPTXV979uy5EaUCAADgBvDzdgE3gtPplNPp9HYZAAAAKADWXaENDw+Xr6+vDh065NZ+6NAhlShRwktVAQAAwFusC7QBAQGKj49XSkqKqy0rK0spKSmqU6eOFysDAACAN1g55aB3795KTk5WzZo1VatWLb3zzjs6deqUOnbs6O3SAAAAcINZGWhbt26tI0eO6KWXXtLBgwd19913a8GCBdluFAMAAMCtz8pAK0ndu3dX9+7dvV0GAAAAvMy6ObQAAADApQi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsJqftwvwpo2DkhQcHOztMgAAAHAduEILAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBAABgNQItAAAArEagBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFjNz9sFeIMxRpJ04sQJL1cCAACAnFzMaRdz25XcloH26NGjkqSoqCgvVwIAAIArOXnypEJCQq7Y57YMtGFhYZKk3bt3X/UE4eZ14sQJRUVFac+ePQoODvZ2ObhGjOOtgXG8dTCWt4ZbYRyNMTp58qRKlSp11b63ZaD18flj6nBISIi1g4z/Lzg4mHG8BTCOtwbG8dbBWN4abB/HvF545KYwAAAAWI1ACwAAAKvdloHW6XRq4MCBcjqd3i4F14FxvDUwjrcGxvHWwVjeGm63cXSYvKyFAAAAANykbssrtAAAALh1EGgBAABgNQItAAAArEagBQAAgNVuy0A7evRoxcTEKDAwULVr19YPP/zg7ZJuWytWrFDz5s1VqlQpORwOzZkzx227MUYvvfSSSpYsqUKFCikxMVFbt25163Ps2DG1bdtWwcHBCg0N1V//+ldlZGS49Vm/fr3q1aunwMBARUVF6a233irol3ZbGTJkiO677z4VLVpUkZGRatmypbZs2eLW58yZM+rWrZvuuOMOFSlSRE888YQOHTrk1mf37t1q2rSpChcurMjISL3wwgu6cOGCW59ly5bp3nvvldPpVIUKFTRlypSCfnm3jbFjx6p69equhdjr1KmjL7/80rWdMbTTG2+8IYfDoV69ernaGMub38svvyyHw+H2VblyZdd2xvAy5jYzbdo0ExAQYCZNmmR+/vln07lzZxMaGmoOHTrk7dJuS/Pnzzf/+te/zKxZs4wkM3v2bLftb7zxhgkJCTFz5swx69atMy1atDDlypUzp0+fdvVp1KiRqVGjhvnf//5nvv76a1OhQgXTpk0b1/b09HRTvHhx07ZtW7Nx40bz8ccfm0KFCpnx48ffqJd5y0tKSjKTJ082GzduNGvXrjVNmjQxZcuWNRkZGa4+Xbt2NVFRUSYlJcX8+OOP5v777zcPPPCAa/uFCxdMXFycSUxMNGvWrDHz58834eHhpn///q4+O3bsMIULFza9e/c2v/zyixk5cqTx9fU1CxYsuKGv91Y1b94888UXX5hff/3VbNmyxbz44ovG39/fbNy40RjDGNrohx9+MDExMaZ69eqmZ8+ernbG8uY3cOBAU7VqVXPgwAHX15EjR1zbGUN3t12grVWrlunWrZvrcWZmpilVqpQZMmSIF6uCMSZboM3KyjIlSpQwb7/9tqstLS3NOJ1O8/HHHxtjjPnll1+MJLNq1SpXny+//NI4HA6zb98+Y4wxY8aMMcWKFTNnz5519fnnP/9pKlWqVMCv6PZ1+PBhI8ksX77cGPPHuPn7+5vp06e7+mzatMlIMitXrjTG/PHLjY+Pjzl48KCrz9ixY01wcLBr7Pr27WuqVq3qdqzWrVubpKSkgn5Jt61ixYqZd999lzG00MmTJ03FihXNokWLTEJCgivQMpZ2GDhwoKlRo0aO2xjD7G6rKQfnzp3T6tWrlZiY6Grz8fFRYmKiVq5c6cXKkJPU1FQdPHjQbbxCQkJUu3Zt13itXLlSoaGhqlmzpqtPYmKifHx89P3337v6PPTQQwoICHD1SUpK0pYtW3T8+PEb9GpuL+np6ZKksLAwSdLq1at1/vx5t7GsXLmyypYt6zaW1apVU/HixV19kpKSdOLECf3888+uPpfu42Iffn7zX2ZmpqZNm6ZTp06pTp06jKGFunXrpqZNm2Y734ylPbZu3apSpUopNjZWbdu21e7duyUxhjm5rQLtb7/9pszMTLfBlaTixYvr4MGDXqoKubk4Jlcar4MHDyoyMtJtu5+fn8LCwtz65LSPS4+B/JOVlaVevXqpbt26iouLk/THeQ4ICFBoaKhb38vH8mrjlFufEydO6PTp0wXxcm47GzZsUJEiReR0OtW1a1fNnj1bVapUYQwtM23aNP30008aMmRItm2MpR1q166tKVOmaMGCBRo7dqxSU1NVr149nTx5kjHMgZ+3CwBwa+nWrZs2btyob775xtul4BpUqlRJa9euVXp6umbMmKHk5GQtX77c22XBA3v27FHPnj21aNEiBQYGerscXKPGjRu7vq9evbpq166t6OhoffrppypUqJAXK7s53VZXaMPDw+Xr65vtLsBDhw6pRIkSXqoKubk4JlcarxIlSujw4cNu2y9cuKBjx4659clpH5ceA/mje/fu+vzzz7V06VKVKVPG1V6iRAmdO3dOaWlpbv0vH8urjVNufYKDg/kHPp8EBASoQoUKio+P15AhQ1SjRg0NHz6cMbTI6tWrdfjwYd17773y8/OTn5+fli9frhEjRsjPz0/FixdnLC0UGhqqO++8U9u2bePnMQe3VaANCAhQfHy8UlJSXG1ZWVlKSUlRnTp1vFgZclKuXDmVKFHCbbxOnDih77//3jVederUUVpamlavXu3qs2TJEmVlZal27dquPitWrND58+ddfRYtWqRKlSqpWLFiN+jV3NqMMerevbtmz56tJUuWqFy5cm7b4+Pj5e/v7zaWW7Zs0e7du93GcsOGDW6/oCxatEjBwcGqUqWKq8+l+7jYh5/fgpOVlaWzZ88yhhapX7++NmzYoLVr17q+atasqbZt27q+Zyztk5GRoe3bt6tkyZL8PObE23el3WjTpk0zTqfTTJkyxfzyyy/m2WefNaGhoW53AeLGOXnypFmzZo1Zs2aNkWSGDh1q1qxZY3bt2mWM+WPZrtDQUDN37lyzfv1689hjj+W4bNc999xjvv/+e/PNN9+YihUrui3blZaWZooXL27+8pe/mI0bN5pp06aZwoULs2xXPnruuedMSEiIWbZsmdsSM7///rurT9euXU3ZsmXNkiVLzI8//mjq1Klj6tSp49p+cYmZhg0bmrVr15oFCxaYiIiIHJeYeeGFF8ymTZvM6NGjrV1i5mbUr18/s3z5cpOammrWr19v+vXrZxwOh/nqq6+MMYyhzS5d5cAYxtIGffr0McuWLTOpqanm22+/NYmJiSY8PNwcPnzYGMMYXu62C7TGGDNy5EhTtmxZExAQYGrVqmX+97//ebuk29bSpUuNpGxfycnJxpg/lu4aMGCAKV68uHE6naZ+/fpmy5Ytbvs4evSoadOmjSlSpIgJDg42HTt2NCdPnnTrs27dOvPggw8ap9NpSpcubd54440b9RJvCzmNoSQzefJkV5/Tp0+bv/3tb6ZYsWKmcOHC5vHHHzcHDhxw28/OnTtN48aNTaFChUx4eLjp06ePOX/+vFufpUuXmrvvvtsEBASY2NhYt2Pg+jzzzDMmOjraBAQEmIiICFO/fn1XmDWGMbTZ5YGWsbz5tW7d2pQsWdIEBASY0qVLm9atW5tt27a5tjOG7hzGGOOda8MAAADA9but5tACAADg1kOgBQAAgNUItAAAALAagRYAAABWI9ACAADAagRaAAAAWI1ACwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKxGoAUAAIDVCLQAAACwGoEWAAAAViPQAgAAwGoEWgAAAFiNQAsAAACrEWgBwMsOHjyoHj16KDY2Vk6nU1FRUWrevLlSUlJuaB0Oh0Nz5sy5occEgPzg5+0CAOB2tnPnTtWtW1ehoaF6++23Va1aNZ0/f14LFy5Ut27dtHnzZm+XCAA3PYcxxni7CAC4XTVp0kTr16/Xli1bFBQU5LYtLS1NoaGh2r17t3r06KGUlBT5+PioUaNGGjlypIoXLy5J6tChg9LS0tyurvbq1Utr167VsmXLJEkPP/ywqlevrsDAQL377rsKCAhQ165d9fLLL0uSYmJitGvXLtfzo6OjtXPnzoJ86QCQb5hyAABecuzYMS1YsEDdunXLFmYlKTQ0VFlZWXrsscd07NgxLV++XIsWLdKOHTvUunVrj4/33nvvKSgoSN9//73eeustDR48WIsWLZIkrVq1SpI0efJkHThwwPUYAGzAlAMA8JJt27bJGKPKlSvn2iclJUUbNmxQamqqoqKiJEnvv/++qlatqlWrVum+++7L8/GqV6+ugQMHSpIqVqyoUaNGKSUlRQ0aNFBERISkP0J0iRIlruNVAcCNxxVaAPCSvMz42rRpk6KiolxhVpKqVKmi0NBQbdq0yaPjVa9e3e1xyZIldfjwYY/2AQA3IwItAHhJxYoV5XA4rvvGLx8fn2zh+Pz589n6+fv7uz12OBzKysq6rmMDwM2AQAsAXhIWFqakpCSNHj1ap06dyrY9LS1Nd911l/bs2aM9e/a42n/55RelpaWpSpUqkqSIiAgdOHDA7blr1671uB5/f39lZmZ6/DwA8DYCLQB40ejRo5WZmalatWpp5syZ2rp1qzZt2qQRI0aoTp06SkxMVLVq1dS2bVv99NNP+uGHH9S+fXslJCSoZs2akqRHH31UP/74o95//31t3bpVAwcO1MaNGz2uJSYmRikpKTp48KCOHz+e3y8VAAoMgRYAvCg2NlY//fSTHnnkEfXp00dxcXFq0KCBUlJSNHbsWDkcDs2dO1fFihXTQw89pMTERMXGxuqTTz5x7SMpKUkDBgxQ3759dd999+nkyZNq3769x7X85z//0aJFixQVFaV77rknP18mABQo1qEFAACA1bhCCwAAAKsRaAEAAGA1Ai0AAACsRqAFAACA1Qi0AAAAsBqBFgAAAFYj0AIAAMBqBFoAAABYjUALAAAAqxFoAQAAYDUCLQAAAKz2/wDot0s3QHmAzQAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df['Churn'].value_counts().plot(kind='barh', figsize=(8,6))\n",
    "plt.xlabel(\"Count\", labelpad=14)\n",
    "plt.ylabel(\"Target Variable\", labelpad=14)\n",
    "plt.title(\"Count of Target Variable per Category\", y=1.02)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "9eae1591",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Churn\n",
       "0    5174\n",
       "1    1869\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Churn'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "63180e4a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Churn\n",
       "0   73.463\n",
       "1   26.537\n",
       "Name: count, dtype: float64"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "100*df['Churn'].value_counts()/len(df['Churn'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "3048dfc6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7043 entries, 0 to 7042\n",
      "Data columns (total 20 columns):\n",
      " #   Column            Non-Null Count  Dtype  \n",
      "---  ------            --------------  -----  \n",
      " 0   gender            7043 non-null   object \n",
      " 1   SeniorCitizen     7043 non-null   object \n",
      " 2   Partner           7043 non-null   object \n",
      " 3   Dependents        7043 non-null   object \n",
      " 4   tenure            7043 non-null   int64  \n",
      " 5   PhoneService      7043 non-null   object \n",
      " 6   MultipleLines     7043 non-null   object \n",
      " 7   InternetService   7043 non-null   object \n",
      " 8   OnlineSecurity    7043 non-null   object \n",
      " 9   OnlineBackup      7043 non-null   object \n",
      " 10  DeviceProtection  7043 non-null   object \n",
      " 11  TechSupport       7043 non-null   object \n",
      " 12  StreamingTV       7043 non-null   object \n",
      " 13  StreamingMovies   7043 non-null   object \n",
      " 14  Contract          7043 non-null   object \n",
      " 15  PaperlessBilling  7043 non-null   object \n",
      " 16  PaymentMethod     7043 non-null   object \n",
      " 17  MonthlyCharges    7043 non-null   float64\n",
      " 18  TotalCharges      7032 non-null   float64\n",
      " 19  Churn             7043 non-null   int64  \n",
      "dtypes: float64(2), int64(2), object(16)\n",
      "memory usage: 1.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "54fbf0bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "gender               0\n",
       "SeniorCitizen        0\n",
       "Partner              0\n",
       "Dependents           0\n",
       "tenure               0\n",
       "PhoneService         0\n",
       "MultipleLines        0\n",
       "InternetService      0\n",
       "OnlineSecurity       0\n",
       "OnlineBackup         0\n",
       "DeviceProtection     0\n",
       "TechSupport          0\n",
       "StreamingTV          0\n",
       "StreamingMovies      0\n",
       "Contract             0\n",
       "PaperlessBilling     0\n",
       "PaymentMethod        0\n",
       "MonthlyCharges       0\n",
       "TotalCharges        11\n",
       "Churn                0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "8b1e531b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Observations: 7043\n",
      "Variables: 20\n",
      "cat_cols: 17\n",
      "num_cols: 3\n",
      "cat_but_car: 0\n",
      "num_but_cat: 1\n"
     ]
    }
   ],
   "source": [
    "def grab_col_names(dataframe, cat_th=10, car_th=20):\n",
    "    \"\"\"\n",
    "\n",
    "    It gives the names of categorical, numerical and categorical but cardinal variables in the data set.\n",
    "    Note: Categorical variables with numerical appearance are also included in categorical variables.\n",
    "\n",
    "    Parameters\n",
    "    ------\n",
    "            df: Dataframe\n",
    "                The dataframe from which variable names are to be retrieved\n",
    "        cat_th: int, optional\n",
    "                threshold value for numeric but categorical variables\n",
    "        car_th: int, optinal\n",
    "                threshold value for categorical but cardinal variables\n",
    "\n",
    "    Returns\n",
    "    ------\n",
    "        cat_cols: list\n",
    "                Categorical variable list\n",
    "        num_cols: list\n",
    "                Numeric variable list\n",
    "        cat_but_car: list\n",
    "                Categorical but cardinal variable list\n",
    "\n",
    "    Notes\n",
    "    ------\n",
    "        cat_cols + num_cols + cat_but_car = total number of variables\n",
    "        num_but_cat is inside cat_cols\n",
    "\n",
    "    \"\"\"\n",
    "\n",
    "    # cat_cols, cat_but_car\n",
    "    cat_cols = [col for col in dataframe.columns if dataframe[col].dtypes == \"O\"]\n",
    "    num_but_cat = [col for col in dataframe.columns if dataframe[col].nunique() < cat_th and\n",
    "                   dataframe[col].dtypes != \"O\"]\n",
    "    cat_but_car = [col for col in dataframe.columns if dataframe[col].nunique() > car_th and\n",
    "                   dataframe[col].dtypes == \"O\"]\n",
    "    cat_cols = cat_cols + num_but_cat\n",
    "    cat_cols = [col for col in cat_cols if col not in cat_but_car]\n",
    "\n",
    "    # num_cols\n",
    "    num_cols = [col for col in dataframe.columns if dataframe[col].dtypes != \"O\"]\n",
    "    num_cols = [col for col in num_cols if col not in num_but_cat]\n",
    "\n",
    "    print(f\"Observations: {dataframe.shape[0]}\")\n",
    "    print(f\"Variables: {dataframe.shape[1]}\")\n",
    "    print(f'cat_cols: {len(cat_cols)}')\n",
    "    print(f'num_cols: {len(num_cols)}')\n",
    "    print(f'cat_but_car: {len(cat_but_car)}')\n",
    "    print(f'num_but_cat: {len(num_but_cat)}')\n",
    "    return cat_cols, num_cols, cat_but_car\n",
    "\n",
    "cat_cols, num_cols, cat_but_car = grab_col_names(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "5831c338",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['tenure', 'MonthlyCharges', 'TotalCharges']"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "num_cols"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "02d09051",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['gender',\n",
       " 'SeniorCitizen',\n",
       " 'Partner',\n",
       " 'Dependents',\n",
       " 'PhoneService',\n",
       " 'MultipleLines',\n",
       " 'InternetService',\n",
       " 'OnlineSecurity',\n",
       " 'OnlineBackup',\n",
       " 'DeviceProtection',\n",
       " 'TechSupport',\n",
       " 'StreamingTV',\n",
       " 'StreamingMovies',\n",
       " 'Contract',\n",
       " 'PaperlessBilling',\n",
       " 'PaymentMethod',\n",
       " 'Churn']"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cat_cols"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c805c38",
   "metadata": {},
   "source": [
    "Data Visualization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "6bb2c162",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### gender ############################\n",
      "        gender  Ratio\n",
      "gender               \n",
      "Male      3555 50.476\n",
      "Female    3488 49.524\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### SeniorCitizen ############################\n",
      "               SeniorCitizen  Ratio\n",
      "SeniorCitizen                      \n",
      "0                       5901 83.785\n",
      "1                       1142 16.215\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### Partner ############################\n",
      "         Partner  Ratio\n",
      "Partner                \n",
      "No          3641 51.697\n",
      "Yes         3402 48.303\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### Dependents ############################\n",
      "            Dependents  Ratio\n",
      "Dependents                   \n",
      "No                4933 70.041\n",
      "Yes               2110 29.959\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### PhoneService ############################\n",
      "              PhoneService  Ratio\n",
      "PhoneService                     \n",
      "Yes                   6361 90.317\n",
      "No                     682  9.683\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### MultipleLines ############################\n",
      "                  MultipleLines  Ratio\n",
      "MultipleLines                         \n",
      "No                         3390 48.133\n",
      "Yes                        2971 42.184\n",
      "No phone service            682  9.683\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### InternetService ############################\n",
      "                 InternetService  Ratio\n",
      "InternetService                        \n",
      "Fiber optic                 3096 43.959\n",
      "DSL                         2421 34.375\n",
      "No                          1526 21.667\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### OnlineSecurity ############################\n",
      "                     OnlineSecurity  Ratio\n",
      "OnlineSecurity                            \n",
      "No                             3498 49.666\n",
      "Yes                            2019 28.667\n",
      "No internet service            1526 21.667\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### OnlineBackup ############################\n",
      "                     OnlineBackup  Ratio\n",
      "OnlineBackup                            \n",
      "No                           3088 43.845\n",
      "Yes                          2429 34.488\n",
      "No internet service          1526 21.667\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### DeviceProtection ############################\n",
      "                     DeviceProtection  Ratio\n",
      "DeviceProtection                            \n",
      "No                               3095 43.944\n",
      "Yes                              2422 34.389\n",
      "No internet service              1526 21.667\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### TechSupport ############################\n",
      "                     TechSupport  Ratio\n",
      "TechSupport                            \n",
      "No                          3473 49.311\n",
      "Yes                         2044 29.022\n",
      "No internet service         1526 21.667\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### StreamingTV ############################\n",
      "                     StreamingTV  Ratio\n",
      "StreamingTV                            \n",
      "No                          2810 39.898\n",
      "Yes                         2707 38.435\n",
      "No internet service         1526 21.667\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### StreamingMovies ############################\n",
      "                     StreamingMovies  Ratio\n",
      "StreamingMovies                            \n",
      "No                              2785 39.543\n",
      "Yes                             2732 38.790\n",
      "No internet service             1526 21.667\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### Contract ############################\n",
      "                Contract  Ratio\n",
      "Contract                       \n",
      "Month-to-month      3875 55.019\n",
      "Two year            1695 24.066\n",
      "One year            1473 20.914\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### PaperlessBilling ############################\n",
      "                  PaperlessBilling  Ratio\n",
      "PaperlessBilling                         \n",
      "Yes                           4171 59.222\n",
      "No                            2872 40.778\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### PaymentMethod ############################\n",
      "                           PaymentMethod  Ratio\n",
      "PaymentMethod                                  \n",
      "Electronic check                    2365 33.579\n",
      "Mailed check                        1612 22.888\n",
      "Bank transfer (automatic)           1544 21.922\n",
      "Credit card (automatic)             1522 21.610\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "##################### Churn ############################\n",
      "       Churn  Ratio\n",
      "Churn              \n",
      "0       5174 73.463\n",
      "1       1869 26.537\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def cat_summary(dataframe, col_name, plot = False):\n",
    "    print('#####################',col_name,'############################')\n",
    "    print(pd.DataFrame({col_name: dataframe[col_name].value_counts(),\n",
    "                       'Ratio':100 * dataframe[col_name].value_counts()/len(dataframe)}))\n",
    "    \n",
    "    if plot:\n",
    "        sns.countplot(x = dataframe[col_name], data = dataframe, edgecolor='black', color='#D9F9C4')\n",
    "        plt.show(block = True)\n",
    "        \n",
    "for col in cat_cols:\n",
    "    cat_summary(df, col, plot = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "03a89b6e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from plotly.subplots import make_subplots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "884f9b09",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.plotly.v1+json": {
       "config": {
        "plotlyServerURL": "https://plot.ly"
       },
       "data": [
        {
         "domain": {
          "x": [
           0,
           0.45
          ],
          "y": [
           0,
           1
          ]
         },
         "hole": 0.4,
         "hoverinfo": "label+percent+name",
         "labels": [
          "Male",
          "Female"
         ],
         "name": "Gender",
         "textfont": {
          "size": 16
         },
         "type": "pie",
         "values": [
          3555,
          3488
         ]
        },
        {
         "domain": {
          "x": [
           0.55,
           1
          ],
          "y": [
           0,
           1
          ]
         },
         "hole": 0.4,
         "hoverinfo": "label+percent+name",
         "labels": [
          "No",
          "Yes"
         ],
         "name": "Churn",
         "textfont": {
          "size": 16
         },
         "type": "pie",
         "values": [
          5174,
          1869
         ]
        }
       ],
       "layout": {
        "annotations": [
         {
          "font": {
           "size": 20
          },
          "showarrow": false,
          "text": "Gender",
          "x": 0.16,
          "y": 0.5
         },
         {
          "font": {
           "size": 20
          },
          "showarrow": false,
          "text": "Churn",
          "x": 0.84,
          "y": 0.5
         }
        ],
        "autosize": true,
        "template": {
         "data": {
          "bar": [
           {
            "error_x": {
             "color": "#2a3f5f"
            },
            "error_y": {
             "color": "#2a3f5f"
            },
            "marker": {
             "line": {
              "color": "#E5ECF6",
              "width": 0.5
             },
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "bar"
           }
          ],
          "barpolar": [
           {
            "marker": {
             "line": {
              "color": "#E5ECF6",
              "width": 0.5
             },
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "barpolar"
           }
          ],
          "carpet": [
           {
            "aaxis": {
             "endlinecolor": "#2a3f5f",
             "gridcolor": "white",
             "linecolor": "white",
             "minorgridcolor": "white",
             "startlinecolor": "#2a3f5f"
            },
            "baxis": {
             "endlinecolor": "#2a3f5f",
             "gridcolor": "white",
             "linecolor": "white",
             "minorgridcolor": "white",
             "startlinecolor": "#2a3f5f"
            },
            "type": "carpet"
           }
          ],
          "choropleth": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "choropleth"
           }
          ],
          "contour": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "contour"
           }
          ],
          "contourcarpet": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "contourcarpet"
           }
          ],
          "heatmap": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "heatmap"
           }
          ],
          "heatmapgl": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "heatmapgl"
           }
          ],
          "histogram": [
           {
            "marker": {
             "pattern": {
              "fillmode": "overlay",
              "size": 10,
              "solidity": 0.2
             }
            },
            "type": "histogram"
           }
          ],
          "histogram2d": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "histogram2d"
           }
          ],
          "histogram2dcontour": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "histogram2dcontour"
           }
          ],
          "mesh3d": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "type": "mesh3d"
           }
          ],
          "parcoords": [
           {
            "line": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "parcoords"
           }
          ],
          "pie": [
           {
            "automargin": true,
            "type": "pie"
           }
          ],
          "scatter": [
           {
            "fillpattern": {
             "fillmode": "overlay",
             "size": 10,
             "solidity": 0.2
            },
            "type": "scatter"
           }
          ],
          "scatter3d": [
           {
            "line": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatter3d"
           }
          ],
          "scattercarpet": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattercarpet"
           }
          ],
          "scattergeo": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattergeo"
           }
          ],
          "scattergl": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattergl"
           }
          ],
          "scattermapbox": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scattermapbox"
           }
          ],
          "scatterpolar": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterpolar"
           }
          ],
          "scatterpolargl": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterpolargl"
           }
          ],
          "scatterternary": [
           {
            "marker": {
             "colorbar": {
              "outlinewidth": 0,
              "ticks": ""
             }
            },
            "type": "scatterternary"
           }
          ],
          "surface": [
           {
            "colorbar": {
             "outlinewidth": 0,
             "ticks": ""
            },
            "colorscale": [
             [
              0,
              "#0d0887"
             ],
             [
              0.1111111111111111,
              "#46039f"
             ],
             [
              0.2222222222222222,
              "#7201a8"
             ],
             [
              0.3333333333333333,
              "#9c179e"
             ],
             [
              0.4444444444444444,
              "#bd3786"
             ],
             [
              0.5555555555555556,
              "#d8576b"
             ],
             [
              0.6666666666666666,
              "#ed7953"
             ],
             [
              0.7777777777777778,
              "#fb9f3a"
             ],
             [
              0.8888888888888888,
              "#fdca26"
             ],
             [
              1,
              "#f0f921"
             ]
            ],
            "type": "surface"
           }
          ],
          "table": [
           {
            "cells": {
             "fill": {
              "color": "#EBF0F8"
             },
             "line": {
              "color": "white"
             }
            },
            "header": {
             "fill": {
              "color": "#C8D4E3"
             },
             "line": {
              "color": "white"
             }
            },
            "type": "table"
           }
          ]
         },
         "layout": {
          "annotationdefaults": {
           "arrowcolor": "#2a3f5f",
           "arrowhead": 0,
           "arrowwidth": 1
          },
          "autotypenumbers": "strict",
          "coloraxis": {
           "colorbar": {
            "outlinewidth": 0,
            "ticks": ""
           }
          },
          "colorscale": {
           "diverging": [
            [
             0,
             "#8e0152"
            ],
            [
             0.1,
             "#c51b7d"
            ],
            [
             0.2,
             "#de77ae"
            ],
            [
             0.3,
             "#f1b6da"
            ],
            [
             0.4,
             "#fde0ef"
            ],
            [
             0.5,
             "#f7f7f7"
            ],
            [
             0.6,
             "#e6f5d0"
            ],
            [
             0.7,
             "#b8e186"
            ],
            [
             0.8,
             "#7fbc41"
            ],
            [
             0.9,
             "#4d9221"
            ],
            [
             1,
             "#276419"
            ]
           ],
           "sequential": [
            [
             0,
             "#0d0887"
            ],
            [
             0.1111111111111111,
             "#46039f"
            ],
            [
             0.2222222222222222,
             "#7201a8"
            ],
            [
             0.3333333333333333,
             "#9c179e"
            ],
            [
             0.4444444444444444,
             "#bd3786"
            ],
            [
             0.5555555555555556,
             "#d8576b"
            ],
            [
             0.6666666666666666,
             "#ed7953"
            ],
            [
             0.7777777777777778,
             "#fb9f3a"
            ],
            [
             0.8888888888888888,
             "#fdca26"
            ],
            [
             1,
             "#f0f921"
            ]
           ],
           "sequentialminus": [
            [
             0,
             "#0d0887"
            ],
            [
             0.1111111111111111,
             "#46039f"
            ],
            [
             0.2222222222222222,
             "#7201a8"
            ],
            [
             0.3333333333333333,
             "#9c179e"
            ],
            [
             0.4444444444444444,
             "#bd3786"
            ],
            [
             0.5555555555555556,
             "#d8576b"
            ],
            [
             0.6666666666666666,
             "#ed7953"
            ],
            [
             0.7777777777777778,
             "#fb9f3a"
            ],
            [
             0.8888888888888888,
             "#fdca26"
            ],
            [
             1,
             "#f0f921"
            ]
           ]
          },
          "colorway": [
           "#636efa",
           "#EF553B",
           "#00cc96",
           "#ab63fa",
           "#FFA15A",
           "#19d3f3",
           "#FF6692",
           "#B6E880",
           "#FF97FF",
           "#FECB52"
          ],
          "font": {
           "color": "#2a3f5f"
          },
          "geo": {
           "bgcolor": "white",
           "lakecolor": "white",
           "landcolor": "#E5ECF6",
           "showlakes": true,
           "showland": true,
           "subunitcolor": "white"
          },
          "hoverlabel": {
           "align": "left"
          },
          "hovermode": "closest",
          "mapbox": {
           "style": "light"
          },
          "paper_bgcolor": "white",
          "plot_bgcolor": "#E5ECF6",
          "polar": {
           "angularaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "bgcolor": "#E5ECF6",
           "radialaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           }
          },
          "scene": {
           "xaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           },
           "yaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           },
           "zaxis": {
            "backgroundcolor": "#E5ECF6",
            "gridcolor": "white",
            "gridwidth": 2,
            "linecolor": "white",
            "showbackground": true,
            "ticks": "",
            "zerolinecolor": "white"
           }
          },
          "shapedefaults": {
           "line": {
            "color": "#2a3f5f"
           }
          },
          "ternary": {
           "aaxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "baxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           },
           "bgcolor": "#E5ECF6",
           "caxis": {
            "gridcolor": "white",
            "linecolor": "white",
            "ticks": ""
           }
          },
          "title": {
           "x": 0.05
          },
          "xaxis": {
           "automargin": true,
           "gridcolor": "white",
           "linecolor": "white",
           "ticks": "",
           "title": {
            "standoff": 15
           },
           "zerolinecolor": "white",
           "zerolinewidth": 2
          },
          "yaxis": {
           "automargin": true,
           "gridcolor": "white",
           "linecolor": "white",
           "ticks": "",
           "title": {
            "standoff": 15
           },
           "zerolinecolor": "white",
           "zerolinewidth": 2
          }
         }
        },
        "title": {
         "text": "Gender and Churn Distributions"
        }
       }
      },
      "image/png": "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",
      "text/html": [
       "<div>                            <div id=\"7a0eaf5e-0716-4e9a-b957-5391a4585b92\" class=\"plotly-graph-div\" style=\"height:525px; width:100%;\"></div>            <script type=\"text/javascript\">                require([\"plotly\"], function(Plotly) {                    window.PLOTLYENV=window.PLOTLYENV || {};                                    if (document.getElementById(\"7a0eaf5e-0716-4e9a-b957-5391a4585b92\")) {                    Plotly.newPlot(                        \"7a0eaf5e-0716-4e9a-b957-5391a4585b92\",                        [{\"labels\":[\"Male\",\"Female\"],\"name\":\"Gender\",\"values\":[3555,3488],\"type\":\"pie\",\"domain\":{\"x\":[0.0,0.45],\"y\":[0.0,1.0]},\"textfont\":{\"size\":16},\"hole\":0.4,\"hoverinfo\":\"label+percent+name\"},{\"labels\":[\"No\",\"Yes\"],\"name\":\"Churn\",\"values\":[5174,1869],\"type\":\"pie\",\"domain\":{\"x\":[0.55,1.0],\"y\":[0.0,1.0]},\"textfont\":{\"size\":16},\"hole\":0.4,\"hoverinfo\":\"label+percent+name\"}],                        {\"template\":{\"data\":{\"histogram2dcontour\":[{\"type\":\"histogram2dcontour\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"choropleth\":[{\"type\":\"choropleth\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"histogram2d\":[{\"type\":\"histogram2d\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"heatmap\":[{\"type\":\"heatmap\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"heatmapgl\":[{\"type\":\"heatmapgl\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"contourcarpet\":[{\"type\":\"contourcarpet\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"contour\":[{\"type\":\"contour\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"surface\":[{\"type\":\"surface\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"},\"colorscale\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]]}],\"mesh3d\":[{\"type\":\"mesh3d\",\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}],\"scatter\":[{\"fillpattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2},\"type\":\"scatter\"}],\"parcoords\":[{\"type\":\"parcoords\",\"line\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterpolargl\":[{\"type\":\"scatterpolargl\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"bar\":[{\"error_x\":{\"color\":\"#2a3f5f\"},\"error_y\":{\"color\":\"#2a3f5f\"},\"marker\":{\"line\":{\"color\":\"#E5ECF6\",\"width\":0.5},\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"bar\"}],\"scattergeo\":[{\"type\":\"scattergeo\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterpolar\":[{\"type\":\"scatterpolar\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"histogram\":[{\"marker\":{\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"histogram\"}],\"scattergl\":[{\"type\":\"scattergl\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatter3d\":[{\"type\":\"scatter3d\",\"line\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}},\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scattermapbox\":[{\"type\":\"scattermapbox\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scatterternary\":[{\"type\":\"scatterternary\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"scattercarpet\":[{\"type\":\"scattercarpet\",\"marker\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}}}],\"carpet\":[{\"aaxis\":{\"endlinecolor\":\"#2a3f5f\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"minorgridcolor\":\"white\",\"startlinecolor\":\"#2a3f5f\"},\"baxis\":{\"endlinecolor\":\"#2a3f5f\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"minorgridcolor\":\"white\",\"startlinecolor\":\"#2a3f5f\"},\"type\":\"carpet\"}],\"table\":[{\"cells\":{\"fill\":{\"color\":\"#EBF0F8\"},\"line\":{\"color\":\"white\"}},\"header\":{\"fill\":{\"color\":\"#C8D4E3\"},\"line\":{\"color\":\"white\"}},\"type\":\"table\"}],\"barpolar\":[{\"marker\":{\"line\":{\"color\":\"#E5ECF6\",\"width\":0.5},\"pattern\":{\"fillmode\":\"overlay\",\"size\":10,\"solidity\":0.2}},\"type\":\"barpolar\"}],\"pie\":[{\"automargin\":true,\"type\":\"pie\"}]},\"layout\":{\"autotypenumbers\":\"strict\",\"colorway\":[\"#636efa\",\"#EF553B\",\"#00cc96\",\"#ab63fa\",\"#FFA15A\",\"#19d3f3\",\"#FF6692\",\"#B6E880\",\"#FF97FF\",\"#FECB52\"],\"font\":{\"color\":\"#2a3f5f\"},\"hovermode\":\"closest\",\"hoverlabel\":{\"align\":\"left\"},\"paper_bgcolor\":\"white\",\"plot_bgcolor\":\"#E5ECF6\",\"polar\":{\"bgcolor\":\"#E5ECF6\",\"angularaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"radialaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"}},\"ternary\":{\"bgcolor\":\"#E5ECF6\",\"aaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"baxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"},\"caxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\"}},\"coloraxis\":{\"colorbar\":{\"outlinewidth\":0,\"ticks\":\"\"}},\"colorscale\":{\"sequential\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]],\"sequentialminus\":[[0.0,\"#0d0887\"],[0.1111111111111111,\"#46039f\"],[0.2222222222222222,\"#7201a8\"],[0.3333333333333333,\"#9c179e\"],[0.4444444444444444,\"#bd3786\"],[0.5555555555555556,\"#d8576b\"],[0.6666666666666666,\"#ed7953\"],[0.7777777777777778,\"#fb9f3a\"],[0.8888888888888888,\"#fdca26\"],[1.0,\"#f0f921\"]],\"diverging\":[[0,\"#8e0152\"],[0.1,\"#c51b7d\"],[0.2,\"#de77ae\"],[0.3,\"#f1b6da\"],[0.4,\"#fde0ef\"],[0.5,\"#f7f7f7\"],[0.6,\"#e6f5d0\"],[0.7,\"#b8e186\"],[0.8,\"#7fbc41\"],[0.9,\"#4d9221\"],[1,\"#276419\"]]},\"xaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\",\"title\":{\"standoff\":15},\"zerolinecolor\":\"white\",\"automargin\":true,\"zerolinewidth\":2},\"yaxis\":{\"gridcolor\":\"white\",\"linecolor\":\"white\",\"ticks\":\"\",\"title\":{\"standoff\":15},\"zerolinecolor\":\"white\",\"automargin\":true,\"zerolinewidth\":2},\"scene\":{\"xaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2},\"yaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2},\"zaxis\":{\"backgroundcolor\":\"#E5ECF6\",\"gridcolor\":\"white\",\"linecolor\":\"white\",\"showbackground\":true,\"ticks\":\"\",\"zerolinecolor\":\"white\",\"gridwidth\":2}},\"shapedefaults\":{\"line\":{\"color\":\"#2a3f5f\"}},\"annotationdefaults\":{\"arrowcolor\":\"#2a3f5f\",\"arrowhead\":0,\"arrowwidth\":1},\"geo\":{\"bgcolor\":\"white\",\"landcolor\":\"#E5ECF6\",\"subunitcolor\":\"white\",\"showland\":true,\"showlakes\":true,\"lakecolor\":\"white\"},\"title\":{\"x\":0.05},\"mapbox\":{\"style\":\"light\"}}},\"title\":{\"text\":\"Gender and Churn Distributions\"},\"annotations\":[{\"showarrow\":false,\"text\":\"Gender\",\"x\":0.16,\"y\":0.5,\"font\":{\"size\":20}},{\"showarrow\":false,\"text\":\"Churn\",\"x\":0.84,\"y\":0.5,\"font\":{\"size\":20}}]},                        {\"responsive\": true}                    ).then(function(){\n",
       "                            \n",
       "var gd = document.getElementById('7a0eaf5e-0716-4e9a-b957-5391a4585b92');\n",
       "var x = new MutationObserver(function (mutations, observer) {{\n",
       "        var display = window.getComputedStyle(gd).display;\n",
       "        if (!display || display === 'none') {{\n",
       "            console.log([gd, 'removed!']);\n",
       "            Plotly.purge(gd);\n",
       "            observer.disconnect();\n",
       "        }}\n",
       "}});\n",
       "\n",
       "// Listen for the removal of the full notebook cells\n",
       "var notebookContainer = gd.closest('#notebook-container');\n",
       "if (notebookContainer) {{\n",
       "    x.observe(notebookContainer, {childList: true});\n",
       "}}\n",
       "\n",
       "// Listen for the clearing of the current output cell\n",
       "var outputEl = gd.closest('.output');\n",
       "if (outputEl) {{\n",
       "    x.observe(outputEl, {childList: true});\n",
       "}}\n",
       "\n",
       "                        })                };                });            </script>        </div>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "g_labels = ['Male', 'Female']\n",
    "c_labels = ['No', 'Yes']\n",
    "# Create subplots: use 'domain' type for Pie subplot\n",
    "fig = make_subplots(rows=1, cols=2, specs=[[{'type':'domain'}, {'type':'domain'}]])\n",
    "fig.add_trace(go.Pie(labels=g_labels, values=df['gender'].value_counts(), name=\"Gender\"),\n",
    "              1, 1)\n",
    "fig.add_trace(go.Pie(labels=c_labels, values=df['Churn'].value_counts(), name=\"Churn\"),\n",
    "              1, 2)\n",
    "\n",
    "# Use `hole` to create a donut-like pie chart\n",
    "fig.update_traces(hole=.4, hoverinfo=\"label+percent+name\", textfont_size=16)\n",
    "\n",
    "fig.update_layout(\n",
    "    title_text=\"Gender and Churn Distributions\",\n",
    "    # Add annotations in the center of the donut pies.\n",
    "    annotations=[dict(text='Gender', x=0.16, y=0.5, font_size=20, showarrow=False),\n",
    "                 dict(text='Churn', x=0.84, y=0.5, font_size=20, showarrow=False)])\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "153ebb4d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   7043.000\n",
      "mean      32.371\n",
      "std       24.559\n",
      "min        0.000\n",
      "5%         1.000\n",
      "10%        2.000\n",
      "20%        6.000\n",
      "30%       12.000\n",
      "40%       20.000\n",
      "50%       29.000\n",
      "60%       40.000\n",
      "70%       50.000\n",
      "80%       60.000\n",
      "90%       69.000\n",
      "95%       72.000\n",
      "99%       72.000\n",
      "max       72.000\n",
      "Name: tenure, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   7043.000\n",
      "mean      64.762\n",
      "std       30.090\n",
      "min       18.250\n",
      "5%        19.650\n",
      "10%       20.050\n",
      "20%       25.050\n",
      "30%       45.850\n",
      "40%       58.830\n",
      "50%       70.350\n",
      "60%       79.100\n",
      "70%       85.500\n",
      "80%       94.250\n",
      "90%      102.600\n",
      "95%      107.400\n",
      "99%      114.729\n",
      "max      118.750\n",
      "Name: MonthlyCharges, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "count   7032.000\n",
      "mean    2283.300\n",
      "std     2266.771\n",
      "min       18.800\n",
      "5%        49.605\n",
      "10%       84.600\n",
      "20%      267.070\n",
      "30%      551.995\n",
      "40%      944.170\n",
      "50%     1397.475\n",
      "60%     2048.950\n",
      "70%     3141.130\n",
      "80%     4475.410\n",
      "90%     5976.640\n",
      "95%     6923.590\n",
      "99%     8039.883\n",
      "max     8684.800\n",
      "Name: TotalCharges, dtype: float64\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def num_summary(dataframe, numerical_col, plot=False):\n",
    "    quantiles = [0.05, 0.10, 0.20, 0.30, 0.40, 0.50, 0.60, 0.70, 0.80, 0.90, 0.95, 0.99]\n",
    "    print(dataframe[numerical_col].describe(quantiles).T)\n",
    "\n",
    "    if plot:\n",
    "        dataframe[numerical_col].hist(bins=20, alpha=0.4, color='b')\n",
    "        plt.xlabel(numerical_col)\n",
    "        plt.title(numerical_col)\n",
    "        plt.show(block=True)\n",
    "        \n",
    "for col in num_cols:\n",
    "    num_summary(df, col, plot=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 203,
   "id": "ff85677a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        CHURN_MEAN\n",
      "gender            \n",
      "Female       0.269\n",
      "Male         0.262\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "               CHURN_MEAN\n",
      "SeniorCitizen            \n",
      "0                   0.236\n",
      "1                   0.417\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "         CHURN_MEAN\n",
      "Partner            \n",
      "No            0.330\n",
      "Yes           0.197\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "            CHURN_MEAN\n",
      "Dependents            \n",
      "No               0.313\n",
      "Yes              0.155\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "              CHURN_MEAN\n",
      "PhoneService            \n",
      "No                 0.249\n",
      "Yes                0.267\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                  CHURN_MEAN\n",
      "MultipleLines               \n",
      "No                     0.250\n",
      "No phone service       0.249\n",
      "Yes                    0.286\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                 CHURN_MEAN\n",
      "InternetService            \n",
      "DSL                   0.190\n",
      "Fiber optic           0.419\n",
      "No                    0.074\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                     CHURN_MEAN\n",
      "OnlineSecurity                 \n",
      "No                        0.418\n",
      "No internet service       0.074\n",
      "Yes                       0.146\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                     CHURN_MEAN\n",
      "OnlineBackup                   \n",
      "No                        0.399\n",
      "No internet service       0.074\n",
      "Yes                       0.215\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                     CHURN_MEAN\n",
      "DeviceProtection               \n",
      "No                        0.391\n",
      "No internet service       0.074\n",
      "Yes                       0.225\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                     CHURN_MEAN\n",
      "TechSupport                    \n",
      "No                        0.416\n",
      "No internet service       0.074\n",
      "Yes                       0.152\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                     CHURN_MEAN\n",
      "StreamingTV                    \n",
      "No                        0.335\n",
      "No internet service       0.074\n",
      "Yes                       0.301\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                     CHURN_MEAN\n",
      "StreamingMovies                \n",
      "No                        0.337\n",
      "No internet service       0.074\n",
      "Yes                       0.299\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                CHURN_MEAN\n",
      "Contract                  \n",
      "Month-to-month       0.427\n",
      "One year             0.113\n",
      "Two year             0.028\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                  CHURN_MEAN\n",
      "PaperlessBilling            \n",
      "No                     0.163\n",
      "Yes                    0.336\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "                           CHURN_MEAN\n",
      "PaymentMethod                        \n",
      "Bank transfer (automatic)       0.167\n",
      "Credit card (automatic)         0.152\n",
      "Electronic check                0.453\n",
      "Mailed check                    0.191\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n",
      "       CHURN_MEAN\n",
      "Churn            \n",
      "0           0.000\n",
      "1           1.000\n",
      "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n"
     ]
    }
   ],
   "source": [
    "def target_summary_with_cat(dataframe,target,categorical_col):\n",
    "    print(pd.DataFrame({\"CHURN_MEAN\": dataframe.groupby(categorical_col)[target].mean()}))\n",
    "    print(\"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\")\n",
    "\n",
    "for col in cat_cols:\n",
    "    target_summary_with_cat(df,\"Churn\",col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 204,
   "id": "cd0bef79",
   "metadata": {},
   "outputs": [],
   "source": [
    "def outlier_thresholds(dataframe, col_name, q1=0.05, q3=0.95):\n",
    "    quartile1 = dataframe[col_name].quantile(q1)\n",
    "    quartile3 = dataframe[col_name].quantile(q3)\n",
    "    interquantile_range = quartile3 - quartile1\n",
    "    up_limit = quartile3 + 1.5 * interquantile_range\n",
    "    low_limit = quartile1 - 1.5 * interquantile_range\n",
    "    return low_limit, up_limit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 205,
   "id": "3a1bd489",
   "metadata": {},
   "outputs": [],
   "source": [
    "def check_outlier(dataframe, col_name):\n",
    "    low_limit, up_limit = outlier_thresholds(dataframe, col_name)\n",
    "    if dataframe[(dataframe[col_name] > up_limit) | (dataframe[col_name] < low_limit)].any(axis=None):\n",
    "        return True\n",
    "    else:\n",
    "        return False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 206,
   "id": "4b42d8eb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tenure False\n",
      "MonthlyCharges False\n",
      "TotalCharges False\n"
     ]
    }
   ],
   "source": [
    "for col in num_cols:\n",
    "    print(col, check_outlier(df, col))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 207,
   "id": "0e5ca3eb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              n_miss  ratio\n",
      "TotalCharges      11  0.160\n"
     ]
    }
   ],
   "source": [
    "def missing_values_table(dataframe, na_name=False):\n",
    "    na_columns = [col for col in dataframe.columns if dataframe[col].isnull().sum() > 0]\n",
    "\n",
    "    n_miss = dataframe[na_columns].isnull().sum().sort_values(ascending=False)\n",
    "    ratio = (dataframe[na_columns].isnull().sum() / dataframe.shape[0] * 100).sort_values(ascending=False)\n",
    "    missing_df = pd.concat([n_miss, np.round(ratio, 2)], axis=1, keys=['n_miss', 'ratio'])\n",
    "    print(missing_df, end=\"\\n\")\n",
    "\n",
    "    if na_name:\n",
    "        return na_columns\n",
    "\n",
    "missing_values_table(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 208,
   "id": "6f73eb78",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 208,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Filling in missing values with the median\n",
    "\n",
    "df[\"TotalCharges\"].fillna(df[\"TotalCharges\"].median(), inplace=True)\n",
    "\n",
    "df['TotalCharges'].isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 209,
   "id": "137afb24",
   "metadata": {
    "lines_to_next_cell": 2
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: >"
      ]
     },
     "execution_count": 209,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(df[['tenure', 'MonthlyCharges', 'TotalCharges','Churn']].corr())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8d5436d7-9833-4e97-a620-0dbbcd219b58",
   "metadata": {},
   "source": [
    "IT IS LOGICAL THAT THERE IS A HIGH CORRELATION BETWEEN TENURE AND TOTALCHARGES BECAUSE AS THE TENURE, I.e., TOTAL SERVICE PROVIDED MONTH INCREASES, THE AMOUNT COLLECTED ALSO INCREASES."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 210,
   "id": "2aa3d5f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc[((df[\"gender\"] == \"Male\") & (df[\"SeniorCitizen\"]== 1)),\"SENIOR/YOUNG_GENDER\"] = \"senior_male\"\n",
    "df.loc[((df[\"gender\"] == \"Female\") & (df[\"SeniorCitizen\"]== 0)),\"SENIOR/YOUNG_GENDER\"] =\"young_male\"\n",
    "df.loc[((df[\"gender\"] == \"Male\") & (df[\"SeniorCitizen\"]== 1)),\"SENIOR/YOUNG_GENDER\"] =\"senior_female\"\n",
    "df.loc[((df[\"gender\"] == \"Female\") & (df[\"SeniorCitizen\"]== 0)),\"SENIOR/YOUNG_GENDER\"] =\"young_female\"\n",
    "\n",
    "\n",
    "df.loc[((df[\"gender\"] == \"Male\") & (df[\"TechSupport\"] == \"No\")),\"GENDER_SUPPORT\"] = \"no_sup_male\"\n",
    "df.loc[((df[\"gender\"] == \"Female\") & (df[\"TechSupport\"] == \"No\")),\"GENDER_SUPPORT\"] = \"no_sup_female\"\n",
    "\n",
    "\n",
    "df.loc[((df[\"Contract\"] == \"Month-to-month\")\n",
    "       & (df[\"PaymentMethod\"] == \"Electronic check\")\n",
    "       & (df[\"gender\"] == \"Male\")),\"GENDER_EC_MONTH\"] = \"male_ec_month\"\n",
    "\n",
    "df.loc[((df[\"Contract\"] == \"Month-to-month\")\n",
    "       & (df[\"PaymentMethod\"] == \"Electronic check\")\n",
    "       & (df[\"gender\"] == \"Female\")),\"GENDER_EC_MONTH\"] = \"female_ec_month\"\n",
    "\n",
    "\n",
    "df.loc[((df[\"OnlineSecurity\"] == \"No\") & (df[\"gender\"] == \"Female\")), \"GENDER_SECURITY\"] = \"no_sec_female\"\n",
    "df.loc[((df[\"OnlineSecurity\"] == \"Yes\") & (df[\"gender\"] == \"Female\")),\"GENDER_SECURITY\"] = \"yes_sec_female\"\n",
    "df.loc[((df[\"OnlineSecurity\"] == \"No\") & (df[\"gender\"] == \"Male\")),\"GENDER_SECURITY\"] = \"no_sec_male\"\n",
    "df.loc[((df[\"OnlineSecurity\"] == \"Yes\") & (df[\"gender\"] == \"Male\")),\"GENDER_SECURITY\"] = \"yes_sec_male\"\n",
    "\n",
    "\n",
    "df.loc[((df[\"InternetService\"] == \"Fiber optic\")\n",
    "       & (df[\"gender\"] == \"Male\")\n",
    "       & (df[\"Dependents\"] == \"No\")),\"GENDER_FIB_DEP\"] = \"male_fib_dep_no\"\n",
    "\n",
    "df.loc[((df[\"InternetService\"] == \"Fiber optic\")\n",
    "       & (df[\"gender\"] == \"Female\")\n",
    "       & (df[\"Dependents\"] == \"No\")),\"GENDER_FIB_DEP\"] = \"female_fib_dep_no\"\n",
    "\n",
    "df.loc[(df[\"tenure\"]>=0) & (df[\"tenure\"]<=12),\"NEW_TENURE_YEAR\"] = \"0-1 Year\"\n",
    "df.loc[(df[\"tenure\"]>12) & (df[\"tenure\"]<=24),\"NEW_TENURE_YEAR\"] = \"1-2 Year\"\n",
    "df.loc[(df[\"tenure\"]>24) & (df[\"tenure\"]<=36),\"NEW_TENURE_YEAR\"] = \"2-3 Year\"\n",
    "df.loc[(df[\"tenure\"]>36) & (df[\"tenure\"]<=48),\"NEW_TENURE_YEAR\"] = \"3-4 Year\"\n",
    "df.loc[(df[\"tenure\"]>48) & (df[\"tenure\"]<=60),\"NEW_TENURE_YEAR\"] = \"4-5 Year\"\n",
    "df.loc[(df[\"tenure\"]>60) & (df[\"tenure\"]<=72),\"NEW_TENURE_YEAR\"] = \"5-6 Year\"\n",
    "\n",
    "\n",
    "df.loc[((df[\"Partner\"] == \"No\") & (df[\"Contract\"] == \"Month-to-month\")),\"PARTNER_CONTR\"] = \"no_partner_month\"\n",
    "df.loc[((df[\"Partner\"] == \"Yes\") & (df[\"Contract\"] == \"Month-to-month\")),\"PARTNER_CONTR\"] = \"yes_partner_month\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 211,
   "id": "39b74b87",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Observations: 7043\n",
      "Variables: 27\n",
      "cat_cols: 24\n",
      "num_cols: 3\n",
      "cat_but_car: 0\n",
      "num_but_cat: 1\n"
     ]
    }
   ],
   "source": [
    "cat_cols, num_cols, cat_but_car = grab_col_names(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 212,
   "id": "ed4b3bb8",
   "metadata": {},
   "outputs": [],
   "source": [
    "le = LabelEncoder()\n",
    "\n",
    "binary_cols = [col for col in df.columns if df[col].dtype not in [int, float]\n",
    "               and df[col].nunique() == 2]\n",
    "\n",
    "def label_encoder(dataframe, binary_col):\n",
    "    labelencoder = LabelEncoder()\n",
    "    dataframe[binary_col] = labelencoder.fit_transform(dataframe[binary_col])\n",
    "    return dataframe\n",
    "\n",
    "\n",
    "for col in binary_cols:\n",
    "    df = label_encoder(df, col)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 213,
   "id": "2ef6b00b",
   "metadata": {},
   "outputs": [],
   "source": [
    "def one_hot_encoder(dataframe, categorical_cols, drop_first=True):\n",
    "    dataframe = pd.get_dummies(dataframe, columns=categorical_cols, drop_first=drop_first)\n",
    "    return dataframe\n",
    "\n",
    "ohe_cols = [col for col in df.columns if 30 >= df[col].nunique() > 2]\n",
    "df = one_hot_encoder(df, ohe_cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 214,
   "id": "27af7c78",
   "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>tenure</th>\n",
       "      <th>MonthlyCharges</th>\n",
       "      <th>TotalCharges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-1.277</td>\n",
       "      <td>-1.160</td>\n",
       "      <td>-0.994</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.066</td>\n",
       "      <td>-0.260</td>\n",
       "      <td>-0.173</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-1.237</td>\n",
       "      <td>-0.363</td>\n",
       "      <td>-0.960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.514</td>\n",
       "      <td>-0.747</td>\n",
       "      <td>-0.195</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-1.237</td>\n",
       "      <td>0.197</td>\n",
       "      <td>-0.940</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   tenure  MonthlyCharges  TotalCharges\n",
       "0  -1.277          -1.160        -0.994\n",
       "1   0.066          -0.260        -0.173\n",
       "2  -1.237          -0.363        -0.960\n",
       "3   0.514          -0.747        -0.195\n",
       "4  -1.237           0.197        -0.940"
      ]
     },
     "execution_count": 214,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scaler = StandardScaler()\n",
    "df[num_cols] = scaler.fit_transform(df[num_cols])\n",
    "\n",
    "df[num_cols].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "id": "d2dd691f",
   "metadata": {},
   "outputs": [],
   "source": [
    "y = df[\"Churn\"]\n",
    "X = df.drop([\"Churn\"], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "id": "7036f544",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 226,
   "id": "ce93de41-cf13-4b1f-bbc6-cf35402a3720",
   "metadata": {},
   "outputs": [],
   "source": [
    "def base_models(X, y, scoring=\"roc_auc\"):\n",
    "    print(\"Base Models....\")\n",
    "    classifiers = [('LR', LogisticRegression()),\n",
    "                   ('KNN', KNeighborsClassifier()),\n",
    "                   (\"CART\", DecisionTreeClassifier()),\n",
    "                   (\"RF\", RandomForestClassifier()),\n",
    "                   ('Adaboost', AdaBoostClassifier()),\n",
    "                   ('GBM', GradientBoostingClassifier()),\n",
    "                   ('XGBoost', XGBClassifier(use_label_encoder=False, eval_metric='logloss')),\n",
    "                   ('LightGBM', LGBMClassifier()),\n",
    "                   ]\n",
    "\n",
    "    for name, classifier in classifiers:\n",
    "        cv_results = cross_validate(classifier, X, y, cv=3, scoring=scoring)\n",
    "        print(f\"{scoring}: {round(cv_results['test_score'].mean(), 4)} ({name}) \")\n",
    "\n",
    "base_models(X, y, scoring=\"accuracy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "id": "e412726e",
   "metadata": {},
   "outputs": [],
   "source": [
    "knn_params = {\"n_neighbors\": range(2, 50)}\n",
    "\n",
    "cart_params = {'max_depth': range(1, 20),\n",
    "               \"min_samples_split\": range(2, 30)}\n",
    "\n",
    "rf_params = {\"max_depth\": [8, 15, None],\n",
    "             \"max_features\": [5, 7, \"auto\"],\n",
    "             \"min_samples_split\": [15, 20],\n",
    "             \"n_estimators\": [200, 300]}\n",
    "\n",
    "xgboost_params = {\"learning_rate\": [0.1, 0.01],\n",
    "                  \"max_depth\": [5, 8],\n",
    "                  \"n_estimators\": [100, 200]}\n",
    "\n",
    "lightgbm_params = {\"learning_rate\": [0.01, 0.1],\n",
    "                   \"n_estimators\": [300, 500]}\n",
    "\n",
    "\n",
    "classifiers = [('KNN', KNeighborsClassifier(), knn_params),\n",
    "               (\"CART\", DecisionTreeClassifier(), cart_params),\n",
    "               (\"RF\", RandomForestClassifier(), rf_params),\n",
    "               ('XGBoost', XGBClassifier(use_label_encoder=False, eval_metric='logloss'), xgboost_params),\n",
    "               ('LightGBM', LGBMClassifier(), lightgbm_params)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 233,
   "id": "6568b4b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "def hyperparameter_optimization(X, y, cv=3, scoring=\"roc_auc\"):\n",
    "    print(\"Hyperparameter Optimization....\")\n",
    "    best_models = {}\n",
    "    for name, classifier, params in classifiers:\n",
    "        print(f\"########## {name} ##########\")\n",
    "        cv_results = cross_validate(classifier, X, y, cv=cv, scoring=scoring)\n",
    "        print(f\"{scoring} (Before): {round(cv_results['test_score'].mean(), 4)}\")\n",
    "\n",
    "        gs_best = GridSearchCV(classifier, params, cv=cv, n_jobs=-1, verbose=False).fit(X, y)\n",
    "        final_model = classifier.set_params(**gs_best.best_params_)\n",
    "\n",
    "        cv_results = cross_validate(final_model, X, y, cv=cv, scoring=scoring)\n",
    "        print(f\"{scoring} (After): {round(cv_results['test_score'].mean(), 4)}\")\n",
    "        print(f\"{name} best params: {gs_best.best_params_}\", end=\"\\n\\n\")\n",
    "        best_models[name] = final_model\n",
    "    return best_models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 234,
   "id": "23ff2b58",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Base Models....\n",
      "roc_auc: 0.8403 (LR) \n",
      "roc_auc: 0.7827 (KNN) \n",
      "roc_auc: 0.6498 (CART) \n",
      "roc_auc: 0.8182 (RF) \n",
      "roc_auc: 0.8371 (Adaboost) \n",
      "roc_auc: 0.8383 (GBM) \n",
      "roc_auc: 0.8114 (XGBoost) \n",
      "roc_auc: 0.8356 (CatBoost) \n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 998, number of negative: 2758\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000621 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265708 -> initscore=-1.016508\n",
      "[LightGBM] [Info] Start training from score -1.016508\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000553 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000501 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "roc_auc: 0.8262 (LightGBM) \n",
      "Hyperparameter Optimization....\n",
      "########## KNN ##########\n",
      "roc_auc (Before): 0.7827\n",
      "roc_auc (After): 0.8246\n",
      "KNN best params: {'n_neighbors': 26}\n",
      "\n",
      "########## CART ##########\n",
      "roc_auc (Before): 0.6471\n",
      "roc_auc (After): 0.8081\n",
      "CART best params: {'max_depth': 4, 'min_samples_split': 2}\n",
      "\n",
      "########## RF ##########\n",
      "roc_auc (Before): 0.816\n",
      "roc_auc (After): 0.8391\n",
      "RF best params: {'max_depth': 15, 'max_features': 5, 'min_samples_split': 20, 'n_estimators': 300}\n",
      "\n",
      "########## XGBoost ##########\n",
      "roc_auc (Before): 0.8114\n",
      "roc_auc (After): 0.8362\n",
      "XGBoost best params: {'learning_rate': 0.1, 'max_depth': 5, 'n_estimators': 100}\n",
      "\n",
      "########## LightGBM ##########\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 998, number of negative: 2758\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001389 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265708 -> initscore=-1.016508\n",
      "[LightGBM] [Info] Start training from score -1.016508\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000611 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000637 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "roc_auc (Before): 0.8262\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 1496, number of negative: 4138\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000679 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 5634, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265531 -> initscore=-1.017418\n",
      "[LightGBM] [Info] Start training from score -1.017418\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 998, number of negative: 2758\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000629 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265708 -> initscore=-1.016508\n",
      "[LightGBM] [Info] Start training from score -1.016508\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000625 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.000640 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "roc_auc (After): 0.8388\n",
      "LightGBM best params: {'learning_rate': 0.01, 'n_estimators': 300}\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def fit_models(X,y):\n",
    "    base_models(X, y)\n",
    "    best_models = hyperparameter_optimization(X, y)\n",
    "    return best_models\n",
    "\n",
    "best_models = fit_models(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 235,
   "id": "4b9313a7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 1496, number of negative: 4138\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001857 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 5634, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265531 -> initscore=-1.017418\n",
      "[LightGBM] [Info] Start training from score -1.017418\n"
     ]
    }
   ],
   "source": [
    "lgbm_model = best_models['LightGBM'].fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 236,
   "id": "b1554003",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.84      0.92      0.88      1036\n",
      "           1       0.68      0.51      0.58       373\n",
      "\n",
      "    accuracy                           0.81      1409\n",
      "   macro avg       0.76      0.71      0.73      1409\n",
      "weighted avg       0.80      0.81      0.80      1409\n",
      "\n"
     ]
    }
   ],
   "source": [
    "y_pred = lgbm_model.predict(X_test)\n",
    "y_prob = lgbm_model.predict_proba(X_test)[:, 1]\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 237,
   "id": "d3d93aca",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lgbm_roc_auc = roc_auc_score(y_test, y_prob)\n",
    "fpr, tpr, thresholds = roc_curve(y_test, y_prob)\n",
    "plt.figure()\n",
    "\n",
    "plt.plot([0,1],[0,1],'r--')\n",
    "plt.plot(fpr, tpr, marker='.', label='LGBM')\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title(\"LGBM ROC\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 238,
   "id": "e4af4a2b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1])"
      ]
     },
     "execution_count": 238,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.columns\n",
    "random_user = X.sample(1, random_state = 42)\n",
    "lgbm_model.predict(random_user)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 239,
   "id": "4d3cba12",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x1000 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Observing the variables that affect the success of our model\n",
    "\n",
    "def plot_importance(model, features, num=len(X), save=False):\n",
    "    feature_imp = pd.DataFrame({'Value': model.feature_importances_, 'Feature': features.columns})\n",
    "    plt.figure(figsize=(10, 10))\n",
    "    sns.set(font_scale=1)\n",
    "    sns.barplot(x=\"Value\", y=\"Feature\", data=feature_imp.sort_values(by=\"Value\",\n",
    "                                                                      ascending=False)[0:num])\n",
    "    plt.title('Features')\n",
    "    plt.tight_layout()\n",
    "    plt.show()\n",
    "    if save:\n",
    "        plt.savefig('importances.png')\n",
    "\n",
    "plot_importance(lgbm_model, X_train, num=35)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 240,
   "id": "36ff6f7c",
   "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>gender</th>\n",
       "      <th>SeniorCitizen</th>\n",
       "      <th>Partner</th>\n",
       "      <th>Dependents</th>\n",
       "      <th>tenure</th>\n",
       "      <th>PhoneService</th>\n",
       "      <th>PaperlessBilling</th>\n",
       "      <th>MonthlyCharges</th>\n",
       "      <th>TotalCharges</th>\n",
       "      <th>Churn</th>\n",
       "      <th>MultipleLines_No phone service</th>\n",
       "      <th>MultipleLines_Yes</th>\n",
       "      <th>InternetService_Fiber optic</th>\n",
       "      <th>InternetService_No</th>\n",
       "      <th>OnlineSecurity_No internet service</th>\n",
       "      <th>OnlineSecurity_Yes</th>\n",
       "      <th>OnlineBackup_No internet service</th>\n",
       "      <th>OnlineBackup_Yes</th>\n",
       "      <th>DeviceProtection_No internet service</th>\n",
       "      <th>DeviceProtection_Yes</th>\n",
       "      <th>TechSupport_No internet service</th>\n",
       "      <th>TechSupport_Yes</th>\n",
       "      <th>StreamingTV_No internet service</th>\n",
       "      <th>StreamingTV_Yes</th>\n",
       "      <th>StreamingMovies_No internet service</th>\n",
       "      <th>StreamingMovies_Yes</th>\n",
       "      <th>Contract_One year</th>\n",
       "      <th>Contract_Two year</th>\n",
       "      <th>PaymentMethod_Credit card (automatic)</th>\n",
       "      <th>PaymentMethod_Electronic check</th>\n",
       "      <th>PaymentMethod_Mailed check</th>\n",
       "      <th>SENIOR/YOUNG_GENDER_senior_female</th>\n",
       "      <th>SENIOR/YOUNG_GENDER_young_female</th>\n",
       "      <th>GENDER_SUPPORT_no_sup_female</th>\n",
       "      <th>GENDER_SUPPORT_no_sup_male</th>\n",
       "      <th>GENDER_EC_MONTH_male_ec_month</th>\n",
       "      <th>GENDER_EC_MONTH_nan</th>\n",
       "      <th>GENDER_SECURITY_no_sec_female</th>\n",
       "      <th>GENDER_SECURITY_no_sec_male</th>\n",
       "      <th>GENDER_SECURITY_yes_sec_female</th>\n",
       "      <th>GENDER_SECURITY_yes_sec_male</th>\n",
       "      <th>GENDER_FIB_DEP_male_fib_dep_no</th>\n",
       "      <th>GENDER_FIB_DEP_nan</th>\n",
       "      <th>NEW_TENURE_YEAR_1-2 Year</th>\n",
       "      <th>NEW_TENURE_YEAR_2-3 Year</th>\n",
       "      <th>NEW_TENURE_YEAR_3-4 Year</th>\n",
       "      <th>NEW_TENURE_YEAR_4-5 Year</th>\n",
       "      <th>NEW_TENURE_YEAR_5-6 Year</th>\n",
       "      <th>PARTNER_CONTR_no_partner_month</th>\n",
       "      <th>PARTNER_CONTR_yes_partner_month</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.277</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-1.160</td>\n",
       "      <td>-0.994</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.066</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.260</td>\n",
       "      <td>-0.173</td>\n",
       "      <td>0</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.237</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.363</td>\n",
       "      <td>-0.960</td>\n",
       "      <td>1</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.514</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.747</td>\n",
       "      <td>-0.195</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-1.237</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.197</td>\n",
       "      <td>-0.940</td>\n",
       "      <td>1</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender  SeniorCitizen  Partner  Dependents  tenure  PhoneService  PaperlessBilling  MonthlyCharges  TotalCharges  Churn  MultipleLines_No phone service  MultipleLines_Yes  InternetService_Fiber optic  InternetService_No  OnlineSecurity_No internet service  OnlineSecurity_Yes  OnlineBackup_No internet service  OnlineBackup_Yes  DeviceProtection_No internet service  DeviceProtection_Yes  TechSupport_No internet service  TechSupport_Yes  StreamingTV_No internet service  StreamingTV_Yes  \\\n",
       "0       0              0        1           0  -1.277             0                 1          -1.160        -0.994      0                            True              False                        False               False                               False               False                             False              True                                 False                 False                            False            False                            False            False   \n",
       "1       1              0        0           0   0.066             1                 0          -0.260        -0.173      0                           False              False                        False               False                               False                True                             False             False                                 False                  True                            False            False                            False            False   \n",
       "2       1              0        0           0  -1.237             1                 1          -0.363        -0.960      1                           False              False                        False               False                               False                True                             False              True                                 False                 False                            False            False                            False            False   \n",
       "3       1              0        0           0   0.514             0                 0          -0.747        -0.195      0                            True              False                        False               False                               False                True                             False             False                                 False                  True                            False             True                            False            False   \n",
       "4       0              0        0           0  -1.237             1                 1           0.197        -0.940      1                           False              False                         True               False                               False               False                             False             False                                 False                 False                            False            False                            False            False   \n",
       "\n",
       "   StreamingMovies_No internet service  StreamingMovies_Yes  Contract_One year  Contract_Two year  PaymentMethod_Credit card (automatic)  PaymentMethod_Electronic check  PaymentMethod_Mailed check  SENIOR/YOUNG_GENDER_senior_female  SENIOR/YOUNG_GENDER_young_female  GENDER_SUPPORT_no_sup_female  GENDER_SUPPORT_no_sup_male  GENDER_EC_MONTH_male_ec_month  GENDER_EC_MONTH_nan  GENDER_SECURITY_no_sec_female  GENDER_SECURITY_no_sec_male  GENDER_SECURITY_yes_sec_female  GENDER_SECURITY_yes_sec_male  \\\n",
       "0                                False                False              False              False                                  False                            True                       False                              False                              True                          True                       False                          False                False                           True                        False                           False                         False   \n",
       "1                                False                False               True              False                                  False                           False                        True                              False                             False                         False                        True                          False                 True                          False                        False                           False                          True   \n",
       "2                                False                False              False              False                                  False                           False                        True                              False                             False                         False                        True                          False                 True                          False                        False                           False                          True   \n",
       "3                                False                False               True              False                                  False                           False                       False                              False                             False                         False                       False                          False                 True                          False                        False                           False                          True   \n",
       "4                                False                False              False              False                                  False                            True                       False                              False                              True                          True                       False                          False                False                           True                        False                           False                         False   \n",
       "\n",
       "   GENDER_FIB_DEP_male_fib_dep_no  GENDER_FIB_DEP_nan  NEW_TENURE_YEAR_1-2 Year  NEW_TENURE_YEAR_2-3 Year  NEW_TENURE_YEAR_3-4 Year  NEW_TENURE_YEAR_4-5 Year  NEW_TENURE_YEAR_5-6 Year  PARTNER_CONTR_no_partner_month  PARTNER_CONTR_yes_partner_month  \n",
       "0                           False                True                     False                     False                     False                     False                     False                           False                             True  \n",
       "1                           False                True                     False                      True                     False                     False                     False                           False                            False  \n",
       "2                           False                True                     False                     False                     False                     False                     False                            True                            False  \n",
       "3                           False                True                     False                     False                      True                     False                     False                           False                            False  \n",
       "4                           False               False                     False                     False                     False                     False                     False                            True                            False  "
      ]
     },
     "execution_count": 240,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 241,
   "id": "0d76e6a0",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix, recall_score, precision_score, f1_score, accuracy_score, roc_auc_score\n",
    "from sklearn.metrics import classification_report\n",
    "from sklearn.metrics import ConfusionMatrixDisplay, roc_auc_score, RocCurveDisplay"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "83e60cf2",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "from sklearn.ensemble import BaggingClassifier\n",
    "from sklearn.naive_bayes import BernoulliNB\n",
    "from sklearn.calibration import CalibratedClassifierCV\n",
    "from sklearn.naive_bayes import CategoricalNB\n",
    "from sklearn.multioutput import ClassifierChain\n",
    "from sklearn.naive_bayes import ComplementNB\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.dummy import DummyClassifier\n",
    "from sklearn.tree import ExtraTreeClassifier\n",
    "from sklearn.ensemble import ExtraTreesClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.gaussian_process import GaussianProcessClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "from sklearn.ensemble import HistGradientBoostingClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.semi_supervised import LabelPropagation\n",
    "from sklearn.semi_supervised import LabelSpreading\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "from sklearn.svm import LinearSVC\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.linear_model import LogisticRegressionCV\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.multioutput import MultiOutputClassifier\n",
    "from sklearn.naive_bayes import MultinomialNB\n",
    "from sklearn.neighbors import NearestCentroid\n",
    "from sklearn.svm import NuSVC\n",
    "from sklearn.multiclass import OneVsOneClassifier\n",
    "from sklearn.multiclass import OneVsRestClassifier\n",
    "from sklearn.multiclass import OutputCodeClassifier\n",
    "from sklearn.linear_model import PassiveAggressiveClassifier\n",
    "from sklearn.linear_model import Perceptron\n",
    "from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis\n",
    "from sklearn.neighbors import RadiusNeighborsClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.linear_model import RidgeClassifier\n",
    "from sklearn.linear_model import RidgeClassifierCV\n",
    "from sklearn.linear_model import SGDClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.ensemble import StackingClassifier\n",
    "\n",
    "from xgboost import XGBClassifier\n",
    "from catboost import CatBoostClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "90253f99",
   "metadata": {},
   "outputs": [],
   "source": [
    "estimators = []\n",
    "estimators.append(('AdaBoostClassifier', AdaBoostClassifier(random_state=13) ))\n",
    "estimators.append(('Bagging Classifier', BaggingClassifier(random_state=13) ))\n",
    "estimators.append(('Bernoulli NB', BernoulliNB() ))\n",
    "estimators.append(('Decision Tree Classifier', DecisionTreeClassifier(random_state=13) ))\n",
    "estimators.append(('Dummy Classifier', DummyClassifier(random_state=13) ))\n",
    "estimators.append(('Extra Tree Classifier', ExtraTreeClassifier(random_state=13) ))\n",
    "estimators.append(('Extra Trees Classifier', ExtraTreesClassifier(random_state=13) ))\n",
    "estimators.append(('Gaussian NB', GaussianNB() ))\n",
    "estimators.append(('Gaussian Process Classifier', GaussianProcessClassifier(random_state=13) ))\n",
    "estimators.append(('Gradient Boosting Classifier', GradientBoostingClassifier(random_state=13) ))\n",
    "estimators.append(('Hist Gradient Boosting Classifier', HistGradientBoostingClassifier(random_state=13) ))\n",
    "estimators.append(('KNN', KNeighborsClassifier() ))\n",
    "#estimators.append(('Label Propagation', LabelPropagation() ))\n",
    "#estimators.append(('Label Spreading', LabelSpreading() ))\n",
    "estimators.append(('LogisticRegression', LogisticRegression(max_iter=1000, random_state=13)))\n",
    "estimators.append(('Logistic Regression CV', LogisticRegressionCV(max_iter=1000, random_state=13) ))\n",
    "estimators.append(('MLPClassifier', MLPClassifier(max_iter=2000,random_state=13) ))\n",
    "estimators.append(('Nearest Centroid', NearestCentroid() ))\n",
    "estimators.append(('Passive Aggressive Classifier', PassiveAggressiveClassifier(random_state=13) ))\n",
    "estimators.append(('Perceptron', Perceptron(random_state=13) ))\n",
    "#estimators.append(('RadiusNeighborsClassifier', RadiusNeighborsClassifier(radius=3) ))\n",
    "estimators.append(('RandomForest', RandomForestClassifier(max_depth= 10, min_samples_leaf= 1, min_samples_split= 3, n_estimators= 170, random_state=13) ))\n",
    "estimators.append(('Ridge Classifier', RidgeClassifier(random_state=13) ))\n",
    "estimators.append(('Ridge Classifier CV', RidgeClassifierCV() ))\n",
    "estimators.append(('SGDClassifier', SGDClassifier(random_state=13) ))\n",
    "estimators.append(('SVC', SVC(random_state=13)))\n",
    "estimators.append(('XGB', XGBClassifier(random_state=13) ))\n",
    "estimators.append(('CatBoost', CatBoostClassifier(logging_level='Silent', random_state=13) ))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 243,
   "id": "feedc6f5-137a-441f-8fb8-f7870ea8c2b0",
   "metadata": {},
   "outputs": [],
   "source": [
    "XGB = XGBClassifier(random_state=13)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 244,
   "id": "2a7010bc",
   "metadata": {
    "lines_to_next_cell": 2
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Stacking classifier training Accuracy: 0.81\n",
      "Stacking classifier test Accuracy: 0.79\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import StackingClassifier\n",
    "SC = StackingClassifier(estimators=estimators,final_estimator=XGB,cv=6)\n",
    "SC.fit(X_train, y_train)\n",
    "y_pred = SC.predict(X_test)\n",
    "\n",
    "print(f\"\\nStacking classifier training Accuracy: {SC.score(X_train, y_train):0.2f}\")\n",
    "print(f\"Stacking classifier test Accuracy: {SC.score(X_test, y_test):0.2f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 245,
   "id": "370db6f1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[932 104]\n",
      " [185 188]]\n"
     ]
    }
   ],
   "source": [
    "SC_Recall = recall_score(y_test, y_pred)\n",
    "SC_Precision = precision_score(y_test, y_pred)\n",
    "SC_f1 = f1_score(y_test, y_pred)\n",
    "SC_accuracy = accuracy_score(y_test, y_pred)\n",
    "SC_roc_auc = roc_auc_score(y_test, y_pred)\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 246,
   "id": "f9ec6524",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing col-wise multi-threading, the overhead of testing was 0.002649 seconds.\n",
      "You can set `force_col_wise=true` to remove the overhead.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 998, number of negative: 2758\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.002687 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265708 -> initscore=-1.016508\n",
      "[LightGBM] [Info] Start training from score -1.016508\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.004307 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.008726 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 998, number of negative: 2758\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.002564 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265708 -> initscore=-1.016508\n",
      "[LightGBM] [Info] Start training from score -1.016508\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing col-wise multi-threading, the overhead of testing was 0.003598 seconds.\n",
      "You can set `force_col_wise=true` to remove the overhead.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.007005 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001559 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 998, number of negative: 2758\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.002142 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265708 -> initscore=-1.016508\n",
      "[LightGBM] [Info] Start training from score -1.016508\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 998, number of negative: 2758\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.006682 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265708 -> initscore=-1.016508\n",
      "[LightGBM] [Info] Start training from score -1.016508\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001670 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "[LightGBM] [Warning] Found whitespace in feature_names, replace with underlines\n",
      "[LightGBM] [Info] Number of positive: 997, number of negative: 2759\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001828 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 676\n",
      "[LightGBM] [Info] Number of data points in the train set: 3756, number of used features: 49\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.265442 -> initscore=-1.017873\n",
      "[LightGBM] [Info] Start training from score -1.017873\n",
      "Cross Validation Recall scores are: [0.49832776 0.4548495  0.48160535 0.49666667 0.44147157]\n",
      "Average Cross Validation Recall score:  0.4745841694537347\n",
      "Cross Validation Recall standard deviation:  0.025429279829347458\n"
     ]
    }
   ],
   "source": [
    "from statistics import stdev\n",
    "from sklearn.model_selection import cross_val_score\n",
    "score = cross_val_score(SC, X_train, y_train, cv=5, scoring='recall', error_score=\"raise\")\n",
    "SC_cv_score = score.mean()\n",
    "SC_cv_stdev = stdev(score)\n",
    "print('Cross Validation Recall scores are: {}'.format(score))\n",
    "print('Average Cross Validation Recall score: ', SC_cv_score)\n",
    "print('Cross Validation Recall standard deviation: ', SC_cv_stdev)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 247,
   "id": "2c2cc07a",
   "metadata": {
    "lines_to_next_cell": 2
   },
   "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>Model</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>ROC-AUC Score</th>\n",
       "      <th>Avg CV Recall</th>\n",
       "      <th>Standard Deviation of CV Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Random Forest</td>\n",
       "      <td>0.504</td>\n",
       "      <td>0.644</td>\n",
       "      <td>0.565</td>\n",
       "      <td>0.795</td>\n",
       "      <td>0.702</td>\n",
       "      <td>0.475</td>\n",
       "      <td>0.025</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Model  Recall  Precision  F1 Score  Accuracy  ROC-AUC Score  Avg CV Recall  Standard Deviation of CV Recall\n",
       "0  Random Forest   0.504      0.644     0.565     0.795          0.702          0.475                            0.025"
      ]
     },
     "execution_count": 247,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ndf = [(SC_Recall, SC_Precision, SC_f1, SC_accuracy, SC_roc_auc, SC_cv_score, SC_cv_stdev)]\n",
    "\n",
    "SC_score = pd.DataFrame(data = ndf, columns=['Recall','Precision','F1 Score', 'Accuracy', 'ROC-AUC Score', 'Avg CV Recall', 'Standard Deviation of CV Recall'])\n",
    "SC_score.insert(0, 'Model', 'Random Forest')\n",
    "SC_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 248,
   "id": "b03513af",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "No artists with labels found to put in legend.  Note that artists whose label start with an underscore are ignored when legend() is called with no argument.\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "y_proba = SC.predict_proba(X_test)\n",
    "\n",
    "from sklearn.metrics import roc_curve\n",
    "from sklearn.metrics import RocCurveDisplay\n",
    "def plot_auc_roc_curve(y_test, y_pred):\n",
    "    fpr, tpr, _ = roc_curve(y_test, y_pred)\n",
    "    roc_display = RocCurveDisplay(fpr=fpr, tpr=tpr).plot()\n",
    "    roc_display.figure_.set_size_inches(5,5)\n",
    "    plt.plot([0, 1], [0, 1], color = 'g')\n",
    "plot_auc_roc_curve(y_test, y_proba[:, 1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 249,
   "id": "0037e48d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import precision_recall_curve\n",
    "from sklearn.metrics import PrecisionRecallDisplay\n",
    "\n",
    "display = PrecisionRecallDisplay.from_estimator(\n",
    "    SC, X_test, y_test, name=\"Average precision\")\n",
    "_ = display.ax_.set_title(\"Stacking Classifier\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d0d4761d",
   "metadata": {},
   "source": [
    "# Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 250,
   "id": "3c07cd30",
   "metadata": {},
   "outputs": [],
   "source": [
    "rf = RandomForestClassifier(random_state=13)\n",
    "rf.fit(X_train, y_train)\n",
    "y_pred = rf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 251,
   "id": "8ca4e27d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[932 104]\n",
      " [191 182]]\n"
     ]
    }
   ],
   "source": [
    "rf_Recall = recall_score(y_test, y_pred)\n",
    "rf_Precision = precision_score(y_test, y_pred)\n",
    "rf_f1 = f1_score(y_test, y_pred)\n",
    "rf_accuracy = accuracy_score(y_test, y_pred)\n",
    "rf_roc_auc = roc_auc_score(y_test, y_pred)\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 252,
   "id": "054732e8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.83      0.90      0.86      1036\n",
      "           1       0.64      0.49      0.55       373\n",
      "\n",
      "    accuracy                           0.79      1409\n",
      "   macro avg       0.73      0.69      0.71      1409\n",
      "weighted avg       0.78      0.79      0.78      1409\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 253,
   "id": "624052f4",
   "metadata": {
    "lines_to_next_cell": 2
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross Validation Recall scores are: [0.54180602 0.46488294 0.4548495  0.48333333 0.44816054]\n",
      "Average Cross Validation Recall score:  0.47860646599777035\n",
      "Cross Validation Recall standard deviation:  0.037736620837502725\n"
     ]
    }
   ],
   "source": [
    "from statistics import stdev\n",
    "score = cross_val_score(rf, X_train, y_train, cv=5, scoring='recall', error_score=\"raise\")\n",
    "rf_cv_score = score.mean()\n",
    "rf_cv_stdev = stdev(score)\n",
    "print('Cross Validation Recall scores are: {}'.format(score))\n",
    "print('Average Cross Validation Recall score: ', rf_cv_score)\n",
    "print('Cross Validation Recall standard deviation: ', rf_cv_stdev)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 254,
   "id": "412d998b",
   "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>Model</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>ROC-AUC Score</th>\n",
       "      <th>Avg CV Recall</th>\n",
       "      <th>Standard Deviation of CV Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Random Forest</td>\n",
       "      <td>0.488</td>\n",
       "      <td>0.636</td>\n",
       "      <td>0.552</td>\n",
       "      <td>0.791</td>\n",
       "      <td>0.694</td>\n",
       "      <td>0.479</td>\n",
       "      <td>0.038</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Model  Recall  Precision  F1 Score  Accuracy  ROC-AUC Score  Avg CV Recall  Standard Deviation of CV Recall\n",
       "0  Random Forest   0.488      0.636     0.552     0.791          0.694          0.479                            0.038"
      ]
     },
     "execution_count": 254,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ndf = [(rf_Recall, rf_Precision, rf_f1, rf_accuracy, rf_roc_auc, rf_cv_score, rf_cv_stdev)]\n",
    "\n",
    "rf_score = pd.DataFrame(data = ndf, columns=['Recall','Precision','F1 Score', 'Accuracy', 'ROC-AUC Score', 'Avg CV Recall', 'Standard Deviation of CV Recall'])\n",
    "rf_score.insert(0, 'Model', 'Random Forest')\n",
    "rf_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 255,
   "id": "0af8cb24",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "params = {\n",
    "    'n_estimators': [130], # 'n_estimators': [120,130,150,170,190,200],\n",
    "    'max_depth': [14],  # 'max_depth': [8,10,12,14,15],\n",
    "    'min_samples_split': [3], # 'min_samples_split': [3,4,5,6],\n",
    "    'min_samples_leaf': [2], # 'min_samples_leaf': [1,2,3],\n",
    "    'random_state': [13]\n",
    "}\n",
    "\n",
    "grid_rf = GridSearchCV(rf, param_grid=params, cv=5, scoring='recall').fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 256,
   "id": "1fe87c68",
   "metadata": {
    "lines_to_next_cell": 2
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best parameters: {'max_depth': 14, 'min_samples_leaf': 2, 'min_samples_split': 3, 'n_estimators': 130, 'random_state': 13}\n",
      "Best score: 0.4993333333333333\n"
     ]
    }
   ],
   "source": [
    "print('Best parameters:', grid_rf.best_params_)\n",
    "print('Best score:', grid_rf.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 257,
   "id": "7a958c1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = grid_rf.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 258,
   "id": "f29dc0be",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[934 102]\n",
      " [186 187]]\n"
     ]
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test, y_pred)\n",
    "\n",
    "grid_rf_Recall = recall_score(y_test, y_pred)\n",
    "grid_rf_Precision = precision_score(y_test, y_pred)\n",
    "grid_rf_f1 = f1_score(y_test, y_pred)\n",
    "grid_rf_accuracy = accuracy_score(y_test, y_pred)\n",
    "grid_roc_auc = roc_auc_score(y_test, y_pred)\n",
    "\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 259,
   "id": "16d5376c",
   "metadata": {},
   "outputs": [],
   "source": [
    "score2 = cross_val_score(grid_rf, X_train, y_train, cv=5, scoring='recall')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 260,
   "id": "122ed69d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross Validation Recall scores are: [0.55518395 0.48160535 0.50501672 0.49666667 0.45819398]\n",
      "Average Cross Validation Recall score:  0.4993333333333333\n",
      "Cross Validation Recall standard deviation:  0.035935465636409585\n"
     ]
    }
   ],
   "source": [
    "grid_cv_score = score2.mean()\n",
    "grid_cv_stdev = stdev(score2)\n",
    "\n",
    "print('Cross Validation Recall scores are: {}'.format(score2))\n",
    "print('Average Cross Validation Recall score: ', grid_cv_score)\n",
    "print('Cross Validation Recall standard deviation: ', grid_cv_stdev)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 261,
   "id": "d942d9b1",
   "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>Model</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>ROC-AUC Score</th>\n",
       "      <th>Avg CV Recall</th>\n",
       "      <th>Standard Deviation of CV Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Random Forest after tuning</td>\n",
       "      <td>0.501</td>\n",
       "      <td>0.647</td>\n",
       "      <td>0.565</td>\n",
       "      <td>0.796</td>\n",
       "      <td>0.701</td>\n",
       "      <td>0.499</td>\n",
       "      <td>0.036</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        Model  Recall  Precision  F1 Score  Accuracy  ROC-AUC Score  Avg CV Recall  Standard Deviation of CV Recall\n",
       "0  Random Forest after tuning   0.501      0.647     0.565     0.796          0.701          0.499                            0.036"
      ]
     },
     "execution_count": 261,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ndf2 = [(grid_rf_Recall, grid_rf_Precision, grid_rf_f1, grid_rf_accuracy, grid_roc_auc, grid_cv_score, grid_cv_stdev)]\n",
    "\n",
    "grid_score = pd.DataFrame(data = ndf2, columns=\n",
    "                        ['Recall','Precision','F1 Score', 'Accuracy', 'ROC-AUC Score', 'Avg CV Recall', 'Standard Deviation of CV Recall'])\n",
    "grid_score.insert(0, 'Model', 'Random Forest after tuning')\n",
    "grid_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 276,
   "id": "9b414130",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-3 {color: black;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">XGBClassifier</label><div class=\"sk-toggleable__content\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
       "              colsample_bylevel=None, colsample_bynode=None,\n",
       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "              gamma=None, grow_policy=None, importance_type=None,\n",
       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "              num_parallel_tree=None, random_state=None, ...)"
      ]
     },
     "execution_count": 276,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from xgboost import XGBClassifier\n",
    "XGBC = XGBClassifier()\n",
    "XGBC.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 277,
   "id": "f7a6efc4",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = XGBC.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 278,
   "id": "81bb3cc1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[923 113]\n",
      " [178 195]]\n"
     ]
    }
   ],
   "source": [
    "XGBC_Recall = recall_score(y_test, y_pred)\n",
    "XGBC_Precision = precision_score(y_test, y_pred)\n",
    "XGBC_f1 = f1_score(y_test, y_pred)\n",
    "XGBC_accuracy = accuracy_score(y_test, y_pred)\n",
    "XGBC_roc_auc = roc_auc_score(y_test, y_pred)\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 279,
   "id": "2f2067f9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross Validation Recall scores are: [0.59197324 0.47157191 0.48160535 0.51       0.46488294]\n",
      "Average Cross Validation Recall score:  0.5040066889632107\n",
      "Cross Validation Recall standard deviation:  0.05210215243353261\n"
     ]
    }
   ],
   "source": [
    "score = cross_val_score(XGBC, X_train, y_train, cv=5, scoring='recall', error_score=\"raise\")\n",
    "XGBC_cv_score = score.mean()\n",
    "XGBC_cv_stdev = stdev(score)\n",
    "print('Cross Validation Recall scores are: {}'.format(score))\n",
    "print('Average Cross Validation Recall score: ', XGBC_cv_score)\n",
    "print('Cross Validation Recall standard deviation: ', XGBC_cv_stdev)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 280,
   "id": "fec008f5",
   "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>Model</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>ROC-AUC Score</th>\n",
       "      <th>Avg CV Recall</th>\n",
       "      <th>Standard Deviation of CV Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>XGBC</td>\n",
       "      <td>0.523</td>\n",
       "      <td>0.633</td>\n",
       "      <td>0.573</td>\n",
       "      <td>0.793</td>\n",
       "      <td>0.707</td>\n",
       "      <td>0.504</td>\n",
       "      <td>0.052</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Model  Recall  Precision  F1 Score  Accuracy  ROC-AUC Score  Avg CV Recall  Standard Deviation of CV Recall\n",
       "0  XGBC   0.523      0.633     0.573     0.793          0.707          0.504                            0.052"
      ]
     },
     "execution_count": 280,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ndf = [(XGBC_Recall, XGBC_Precision, XGBC_f1, XGBC_accuracy, XGBC_roc_auc, XGBC_cv_score, XGBC_cv_stdev)]\n",
    "\n",
    "XGBC_score = pd.DataFrame(data = ndf, columns=['Recall','Precision','F1 Score', 'Accuracy', 'ROC-AUC Score', 'Avg CV Recall', 'Standard Deviation of CV Recall'])\n",
    "XGBC_score.insert(0, 'Model', 'XGBC')\n",
    "XGBC_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 281,
   "id": "4ebcab97",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Step 1: Searching for the optimum parameters for the learning rate and the number of estimators:\n",
    "params = {'learning_rate': [0.01], #[0.0001, 0.001, 0.01, 0.1, 0.2, 0.3],\n",
    "              'subsample': [0.8],\n",
    "              'colsample_bytree': [0.8],\n",
    "              'n_estimators': [450] #range(50,500,50),\n",
    "              }\n",
    "\n",
    "grid_xgb = GridSearchCV(XGBC, param_grid=params, cv=5, scoring='recall').fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 282,
   "id": "7db0ea58",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best parameters: {'colsample_bytree': 0.8, 'learning_rate': 0.01, 'n_estimators': 450, 'subsample': 0.8}\n",
      "Best score: 0.5033311036789299\n"
     ]
    }
   ],
   "source": [
    "print('Best parameters:', grid_xgb.best_params_)\n",
    "print('Best score:', grid_xgb.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 283,
   "id": "79870788",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Step 2: Searching for the optimum parameters for max_depth and min_child_weight:\n",
    "params = {'max_depth': [7], #range(3,10,2),\n",
    "              'learning_rate': [0.01],\n",
    "              'subsample': [0.8],\n",
    "              'colsample_bytree': [0.8],\n",
    "              # 'colsample_bylevel': np.arange(0.5, 1.0, 0.1),\n",
    "              'min_child_weight': [5], #range(1,6,2),\n",
    "              'n_estimators': [450],\n",
    "              # 'num_class': [10]\n",
    "              }\n",
    "\n",
    "grid_xgb = GridSearchCV(XGBC, param_grid=params, cv=5, scoring='recall').fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 284,
   "id": "ff199016",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best parameters: {'colsample_bytree': 0.8, 'learning_rate': 0.01, 'max_depth': 7, 'min_child_weight': 5, 'n_estimators': 450, 'subsample': 0.8}\n",
      "Best score: 0.5086845039018952\n"
     ]
    }
   ],
   "source": [
    "print('Best parameters:', grid_xgb.best_params_)\n",
    "print('Best score:', grid_xgb.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 285,
   "id": "ef5bb817",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = grid_xgb.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 286,
   "id": "6f9f6f7a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[942  94]\n",
      " [175 198]]\n"
     ]
    }
   ],
   "source": [
    "grid_xgb_Recall = recall_score(y_test, y_pred)\n",
    "grid_xgb_Precision = precision_score(y_test, y_pred)\n",
    "grid_xgb_f1 = f1_score(y_test, y_pred)\n",
    "grid_xgb_accuracy = accuracy_score(y_test, y_pred)\n",
    "grid_xgb_roc_auc = roc_auc_score(y_test, y_pred)\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 287,
   "id": "2dbc1aa2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross Validation Recall scores are: [0.56521739 0.47826087 0.5083612  0.51666667 0.47491639]\n",
      "Average Cross Validation Recall score:  0.5086845039018952\n",
      "Cross Validation Recall standard deviation:  0.036488594052819415\n"
     ]
    }
   ],
   "source": [
    "score = cross_val_score(grid_xgb, X_train, y_train, cv=5, scoring='recall', error_score=\"raise\")\n",
    "grid_xgb_cv_score = score.mean()\n",
    "grid_xgb_cv_stdev = stdev(score)\n",
    "print('Cross Validation Recall scores are: {}'.format(score))\n",
    "print('Average Cross Validation Recall score: ', grid_xgb_cv_score)\n",
    "print('Cross Validation Recall standard deviation: ', grid_xgb_cv_stdev)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 288,
   "id": "b5281a58",
   "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>Model</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>ROC-AUC Score</th>\n",
       "      <th>Avg CV Recall</th>\n",
       "      <th>Standard Deviation of CV Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Tuned XGBC</td>\n",
       "      <td>0.531</td>\n",
       "      <td>0.678</td>\n",
       "      <td>0.595</td>\n",
       "      <td>0.809</td>\n",
       "      <td>0.720</td>\n",
       "      <td>0.509</td>\n",
       "      <td>0.036</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Model  Recall  Precision  F1 Score  Accuracy  ROC-AUC Score  Avg CV Recall  Standard Deviation of CV Recall\n",
       "0  Tuned XGBC   0.531      0.678     0.595     0.809          0.720          0.509                            0.036"
      ]
     },
     "execution_count": 288,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ndf = [(grid_xgb_Recall, grid_xgb_Precision, grid_xgb_f1, grid_xgb_accuracy, grid_xgb_roc_auc, grid_xgb_cv_score, grid_xgb_cv_stdev)]\n",
    "\n",
    "grid_xgb_score = pd.DataFrame(data = ndf, columns=['Recall','Precision','F1 Score', 'Accuracy', 'ROC-AUC Score', 'Avg CV Recall', 'Standard Deviation of CV Recall'])\n",
    "grid_xgb_score.insert(0, 'Model', 'Tuned XGBC')\n",
    "grid_xgb_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 289,
   "id": "add7f3cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import VotingClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 290,
   "id": "d869a158",
   "metadata": {},
   "outputs": [],
   "source": [
    "VC_hard = VotingClassifier(estimators = estimators, voting ='hard')\n",
    "VC_hard.fit(X_train, y_train)\n",
    "y_pred = VC_hard.predict(X_test)\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 291,
   "id": "331fd46a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[940  96]\n",
      " [171 202]]\n"
     ]
    }
   ],
   "source": [
    "VC_hard_Recall = recall_score(y_test, y_pred)\n",
    "VC_hard_Precision = precision_score(y_test, y_pred)\n",
    "VC_hard_f1 = f1_score(y_test, y_pred)\n",
    "VC_hard_accuracy = accuracy_score(y_test, y_pred)\n",
    "VC_hard_roc_auc = roc_auc_score(y_test, y_pred)\n",
    "\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 292,
   "id": "02646d21",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Cross Validation Recall scores are: [0.55183946 0.47826087 0.49832776 0.50666667 0.46153846]\n",
      "Average Cross Validation Recall score:  0.4993266443701227\n",
      "Cross Validation Recall standard deviation:  0.03422054809235207\n"
     ]
    }
   ],
   "source": [
    "score = cross_val_score(VC_hard, X_train, y_train, cv=5, scoring='recall', error_score=\"raise\")\n",
    "VC_hard_cv_score = score.mean()\n",
    "VC_hard_cv_stdev = stdev(score)\n",
    "print('Cross Validation Recall scores are: {}'.format(score))\n",
    "print('Average Cross Validation Recall score: ', VC_hard_cv_score)\n",
    "print('Cross Validation Recall standard deviation: ', VC_hard_cv_stdev)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 293,
   "id": "39e6c535",
   "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>Model</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>ROC-AUC Score</th>\n",
       "      <th>Avg CV Recall</th>\n",
       "      <th>Standard Deviation of CV Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Voting Clasifier - Hard Voting</td>\n",
       "      <td>0.542</td>\n",
       "      <td>0.678</td>\n",
       "      <td>0.602</td>\n",
       "      <td>0.811</td>\n",
       "      <td>0.724</td>\n",
       "      <td>0.499</td>\n",
       "      <td>0.034</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            Model  Recall  Precision  F1 Score  Accuracy  ROC-AUC Score  Avg CV Recall  Standard Deviation of CV Recall\n",
       "0  Voting Clasifier - Hard Voting   0.542      0.678     0.602     0.811          0.724          0.499                            0.034"
      ]
     },
     "execution_count": 293,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ndf = [(VC_hard_Recall, VC_hard_Precision, VC_hard_f1, VC_hard_accuracy, VC_hard_roc_auc, VC_hard_cv_score, VC_hard_cv_stdev)]\n",
    "\n",
    "VC_hard_score = pd.DataFrame(data = ndf, columns=['Recall','Precision','F1 Score', 'Accuracy', 'ROC-AUC Score', 'Avg CV Recall', 'Standard Deviation of CV Recall'])\n",
    "VC_hard_score.insert(0, 'Model', 'Voting Clasifier - Hard Voting')\n",
    "VC_hard_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 294,
   "id": "cb402589",
   "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>Model</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1 Score</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>ROC-AUC Score</th>\n",
       "      <th>Avg CV Recall</th>\n",
       "      <th>Standard Deviation of CV Recall</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Tuned XGBC</td>\n",
       "      <td>0.531</td>\n",
       "      <td>0.678</td>\n",
       "      <td>0.595</td>\n",
       "      <td>0.809</td>\n",
       "      <td>0.720</td>\n",
       "      <td>0.509</td>\n",
       "      <td>0.036</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>XGBC</td>\n",
       "      <td>0.523</td>\n",
       "      <td>0.633</td>\n",
       "      <td>0.573</td>\n",
       "      <td>0.793</td>\n",
       "      <td>0.707</td>\n",
       "      <td>0.504</td>\n",
       "      <td>0.052</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Random Forest after tuning</td>\n",
       "      <td>0.501</td>\n",
       "      <td>0.647</td>\n",
       "      <td>0.565</td>\n",
       "      <td>0.796</td>\n",
       "      <td>0.701</td>\n",
       "      <td>0.499</td>\n",
       "      <td>0.036</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Voting Clasifier - Hard Voting</td>\n",
       "      <td>0.542</td>\n",
       "      <td>0.678</td>\n",
       "      <td>0.602</td>\n",
       "      <td>0.811</td>\n",
       "      <td>0.724</td>\n",
       "      <td>0.499</td>\n",
       "      <td>0.034</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Random Forest</td>\n",
       "      <td>0.488</td>\n",
       "      <td>0.636</td>\n",
       "      <td>0.552</td>\n",
       "      <td>0.791</td>\n",
       "      <td>0.694</td>\n",
       "      <td>0.479</td>\n",
       "      <td>0.038</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            Model  Recall  Precision  F1 Score  Accuracy  ROC-AUC Score  Avg CV Recall  Standard Deviation of CV Recall\n",
       "3                      Tuned XGBC   0.531      0.678     0.595     0.809          0.720          0.509                            0.036\n",
       "2                            XGBC   0.523      0.633     0.573     0.793          0.707          0.504                            0.052\n",
       "1      Random Forest after tuning   0.501      0.647     0.565     0.796          0.701          0.499                            0.036\n",
       "4  Voting Clasifier - Hard Voting   0.542      0.678     0.602     0.811          0.724          0.499                            0.034\n",
       "0                   Random Forest   0.488      0.636     0.552     0.791          0.694          0.479                            0.038"
      ]
     },
     "execution_count": 294,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predictions = pd.concat([rf_score, grid_score, XGBC_score, grid_xgb_score, VC_hard_score], ignore_index=True, sort=False)\n",
    "predictions.sort_values(by=['Avg CV Recall'], ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "271760f6",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "No artists with labels found to put in legend.  Note that artists whose label start with an underscore are ignored when legend() is called with no argument.\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 500x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "y_proba = grid_xgb.predict_proba(X_test)\n",
    "\n",
    "from sklearn.metrics import roc_curve\n",
    "from sklearn.metrics import RocCurveDisplay\n",
    "def plot_auc_roc_curve(y_test, y_pred):\n",
    "    fpr, tpr, _ = roc_curve(y_test, y_pred)\n",
    "    roc_display = RocCurveDisplay(fpr=fpr, tpr=tpr).plot()\n",
    "    roc_display.figure_.set_size_inches(5,5)\n",
    "    plt.plot([0, 1], [0, 1], color = 'g')\n",
    "plot_auc_roc_curve(y_test, y_proba[:, 1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "9aa7016b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import precision_recall_curve\n",
    "from sklearn.metrics import PrecisionRecallDisplay\n",
    "\n",
    "display = PrecisionRecallDisplay.from_estimator(\n",
    "    grid_xgb, X_test, y_test, name=\"Average precision\")\n",
    "_ = display.ax_.set_title(\"Tuned XGBoost\")"
   ]
  }
 ],
 "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}