{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Introduction \n",
    "## Customer Churn Prediction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Customer attrition or churn, is when customers stop doing business with a company. It can have a significant impact on a company's revenue and it's crucial for businesses to find out the reasons why customers are leaving and take steps to reduce the number of customers leaving. One way to do this is by identifying customer segments that are at risk of leaving, and implementing retention strategies to keep them. Also, by using data and machine learning techniques, companies can predict which customers are likely to leave in the future and take actions to keep them before they decide to leave.\n",
    "\n",
    "We are going to build a basic model for predicting customer churn using [Telco Customer Churn dataset](https://www.kaggle.com/blastchar/telco-customer-churn). We are using some classification algorithm to model customers who have left, using Python tools such as pandas for data manipulation and matplotlib for visualizations.\n",
    "\n",
    "\n",
    "Let's get started."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Steps Involved to Predict Customer Churn\n",
    "- Importing Libraries\n",
    "- Loading Dataset\n",
    "- Exploratory Data Analysis\n",
    "- Outliers using IQR method\n",
    "- Cleaning and Transforming Data\n",
    "    - One-hot Encoding\n",
    "    - Rearranging Columns\n",
    "    - Feature Scaling\n",
    "    - Feature Selection\n",
    "- Prediction using Logistic Regression\n",
    "- Prediction using Support Vector Classifier\n",
    "- Prediction using Decision Tree Classifier\n",
    "- Prediction using KNN Classifier"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Importing Libraries\n",
    "\n",
    "First of all, we will import knwon necessary libraries."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "#import platform\n",
    "import pandas as pd\n",
    "import sklearn\n",
    "import numpy as np\n",
    "#import graphviz\n",
    "import seaborn as sns\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt\n",
    "# import plotly.express as px\n",
    "# import plotly.graph_objects as go\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Loading Dataset\n",
    "We use pandas to read the dataset and preprocess it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7043, 21)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('WA_Fn-UseC_-Telco-Customer-Churn.csv')\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exploratory Data Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "scrolled": false
   },
   "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>...</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>...</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>29.85</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>...</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>56.95</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>...</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>53.85</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>...</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>42.30</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>...</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>70.70</td>\n",
       "      <td>151.65</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   customerID  gender  SeniorCitizen Partner Dependents  tenure PhoneService  \\\n",
       "0  7590-VHVEG  Female              0     Yes         No       1           No   \n",
       "1  5575-GNVDE    Male              0      No         No      34          Yes   \n",
       "2  3668-QPYBK    Male              0      No         No       2          Yes   \n",
       "3  7795-CFOCW    Male              0      No         No      45           No   \n",
       "4  9237-HQITU  Female              0      No         No       2          Yes   \n",
       "\n",
       "      MultipleLines InternetService OnlineSecurity  ... DeviceProtection  \\\n",
       "0  No phone service             DSL             No  ...               No   \n",
       "1                No             DSL            Yes  ...              Yes   \n",
       "2                No             DSL            Yes  ...               No   \n",
       "3  No phone service             DSL            Yes  ...              Yes   \n",
       "4                No     Fiber optic             No  ...               No   \n",
       "\n",
       "  TechSupport StreamingTV StreamingMovies        Contract PaperlessBilling  \\\n",
       "0          No          No              No  Month-to-month              Yes   \n",
       "1          No          No              No        One year               No   \n",
       "2          No          No              No  Month-to-month              Yes   \n",
       "3         Yes          No              No        One year               No   \n",
       "4          No          No              No  Month-to-month              Yes   \n",
       "\n",
       "               PaymentMethod MonthlyCharges  TotalCharges Churn  \n",
       "0           Electronic check          29.85         29.85    No  \n",
       "1               Mailed check          56.95        1889.5    No  \n",
       "2               Mailed check          53.85        108.15   Yes  \n",
       "3  Bank transfer (automatic)          42.30       1840.75    No  \n",
       "4           Electronic check          70.70        151.65   Yes  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.018231Z",
     "iopub.status.busy": "2021-11-09T03:52:43.017819Z",
     "iopub.status.idle": "2021-11-09T03:52:43.052282Z",
     "shell.execute_reply": "2021-11-09T03:52:43.051336Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.018175Z"
    }
   },
   "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>...</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>...</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>84.80</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>...</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>103.20</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>...</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>29.60</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>...</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>74.40</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>...</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>105.65</td>\n",
       "      <td>6844.5</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 21 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      customerID  gender  SeniorCitizen Partner Dependents  tenure  \\\n",
       "7038  6840-RESVB    Male              0     Yes        Yes      24   \n",
       "7039  2234-XADUH  Female              0     Yes        Yes      72   \n",
       "7040  4801-JZAZL  Female              0     Yes        Yes      11   \n",
       "7041  8361-LTMKD    Male              1     Yes         No       4   \n",
       "7042  3186-AJIEK    Male              0      No         No      66   \n",
       "\n",
       "     PhoneService     MultipleLines InternetService OnlineSecurity  ...  \\\n",
       "7038          Yes               Yes             DSL            Yes  ...   \n",
       "7039          Yes               Yes     Fiber optic             No  ...   \n",
       "7040           No  No phone service             DSL            Yes  ...   \n",
       "7041          Yes               Yes     Fiber optic             No  ...   \n",
       "7042          Yes                No     Fiber optic            Yes  ...   \n",
       "\n",
       "     DeviceProtection TechSupport StreamingTV StreamingMovies        Contract  \\\n",
       "7038              Yes         Yes         Yes             Yes        One year   \n",
       "7039              Yes          No         Yes             Yes        One year   \n",
       "7040               No          No          No              No  Month-to-month   \n",
       "7041               No          No          No              No  Month-to-month   \n",
       "7042              Yes         Yes         Yes             Yes        Two year   \n",
       "\n",
       "     PaperlessBilling              PaymentMethod MonthlyCharges  TotalCharges  \\\n",
       "7038              Yes               Mailed check          84.80        1990.5   \n",
       "7039              Yes    Credit card (automatic)         103.20        7362.9   \n",
       "7040              Yes           Electronic check          29.60        346.45   \n",
       "7041              Yes               Mailed check          74.40         306.6   \n",
       "7042              Yes  Bank transfer (automatic)         105.65        6844.5   \n",
       "\n",
       "     Churn  \n",
       "7038    No  \n",
       "7039    No  \n",
       "7040    No  \n",
       "7041   Yes  \n",
       "7042    No  \n",
       "\n",
       "[5 rows x 21 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.079833Z",
     "iopub.status.busy": "2021-11-09T03:52:43.078995Z",
     "iopub.status.idle": "2021-11-09T03:52:43.090558Z",
     "shell.execute_reply": "2021-11-09T03:52:43.089462Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.079771Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7043, 21)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We have 2 types of features in the dataset: categorical (two or more values and without any order) and numerical. Most of the feature names are self-explanatory, except for:\n",
    " - Partner: whether the customer has a partner or not (Yes, No),\n",
    " - Dependents: whether the customer has dependents or not (Yes, No),\n",
    " - OnlineBackup: whether the customer has online backup or not (Yes, No, No internet service),\n",
    " - tenure: number of months the customer has stayed with the company,\n",
    " - MonthlyCharges: the amount charged to the customer monthly,\n",
    " - TotalCharges: the total amount charged to the customer.\n",
    " \n",
    "There are 7043 customers in the dataset and 19 features without customerID (non-informative) and Churn column (target variable). Most of the categorical features have 4 or less unique values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.093002Z",
     "iopub.status.busy": "2021-11-09T03:52:43.092646Z",
     "iopub.status.idle": "2021-11-09T03:52:43.101858Z",
     "shell.execute_reply": "2021-11-09T03:52:43.100608Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.092944Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "147903"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.055811Z",
     "iopub.status.busy": "2021-11-09T03:52:43.055339Z",
     "iopub.status.idle": "2021-11-09T03:52:43.065207Z",
     "shell.execute_reply": "2021-11-09T03:52:43.064137Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.055751Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "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"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Totalcharges is given as object datatype but it is float datatype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.067769Z",
     "iopub.status.busy": "2021-11-09T03:52:43.067117Z",
     "iopub.status.idle": "2021-11-09T03:52:43.076918Z",
     "shell.execute_reply": "2021-11-09T03:52:43.075769Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.067723Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['customerID', 'gender', 'SeniorCitizen', 'Partner', 'Dependents',\n",
       "       'tenure', 'PhoneService', 'MultipleLines', 'InternetService',\n",
       "       'OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport',\n",
       "       'StreamingTV', 'StreamingMovies', 'Contract', 'PaperlessBilling',\n",
       "       'PaymentMethod', 'MonthlyCharges', 'TotalCharges', 'Churn'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.105839Z",
     "iopub.status.busy": "2021-11-09T03:52:43.104115Z",
     "iopub.status.idle": "2021-11-09T03:52:43.143193Z",
     "shell.execute_reply": "2021-11-09T03:52:43.142163Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.105792Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7043 entries, 0 to 7042\n",
      "Data columns (total 21 columns):\n",
      " #   Column            Non-Null Count  Dtype  \n",
      "---  ------            --------------  -----  \n",
      " 0   customerID        7043 non-null   object \n",
      " 1   gender            7043 non-null   object \n",
      " 2   SeniorCitizen     7043 non-null   int64  \n",
      " 3   Partner           7043 non-null   object \n",
      " 4   Dependents        7043 non-null   object \n",
      " 5   tenure            7043 non-null   int64  \n",
      " 6   PhoneService      7043 non-null   object \n",
      " 7   MultipleLines     7043 non-null   object \n",
      " 8   InternetService   7043 non-null   object \n",
      " 9   OnlineSecurity    7043 non-null   object \n",
      " 10  OnlineBackup      7043 non-null   object \n",
      " 11  DeviceProtection  7043 non-null   object \n",
      " 12  TechSupport       7043 non-null   object \n",
      " 13  StreamingTV       7043 non-null   object \n",
      " 14  StreamingMovies   7043 non-null   object \n",
      " 15  Contract          7043 non-null   object \n",
      " 16  PaperlessBilling  7043 non-null   object \n",
      " 17  PaymentMethod     7043 non-null   object \n",
      " 18  MonthlyCharges    7043 non-null   float64\n",
      " 19  TotalCharges      7043 non-null   object \n",
      " 20  Churn             7043 non-null   object \n",
      "dtypes: float64(1), int64(2), object(18)\n",
      "memory usage: 1.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.176933Z",
     "iopub.status.busy": "2021-11-09T03:52:43.176295Z",
     "iopub.status.idle": "2021-11-09T03:52:43.202429Z",
     "shell.execute_reply": "2021-11-09T03:52:43.201454Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.176874Z"
    }
   },
   "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": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.205070Z",
     "iopub.status.busy": "2021-11-09T03:52:43.203846Z",
     "iopub.status.idle": "2021-11-09T03:52:43.233001Z",
     "shell.execute_reply": "2021-11-09T03:52:43.231899Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.205022Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Basic Data Cleaning: \n",
    "As we have already observered in above cell that Totalcharges is given as object datatype but it is float datatype. We will fix it here."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('O')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['TotalCharges'].dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.290044Z",
     "iopub.status.busy": "2021-11-09T03:52:43.289662Z",
     "iopub.status.idle": "2021-11-09T03:52:43.301523Z",
     "shell.execute_reply": "2021-11-09T03:52:43.300033Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.289998Z"
    }
   },
   "outputs": [],
   "source": [
    "df['TotalCharges'] = pd.to_numeric(df['TotalCharges'],errors = 'coerce')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dtype('float64')"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['TotalCharges'].dtype"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "categorical_features = [\n",
    "    \"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",
    "]\n",
    "numerical_features = [\"tenure\", \"MonthlyCharges\", \"TotalCharges\"]\n",
    "target = \"Churn\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.235534Z",
     "iopub.status.busy": "2021-11-09T03:52:43.234920Z",
     "iopub.status.idle": "2021-11-09T03:52:43.262979Z",
     "shell.execute_reply": "2021-11-09T03:52:43.261969Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.235471Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SeniorCitizen     1.833633\n",
       "tenure            0.239540\n",
       "MonthlyCharges   -0.220524\n",
       "TotalCharges      0.961642\n",
       "dtype: float64"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.skew(numeric_only= True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:52:43.269333Z",
     "iopub.status.busy": "2021-11-09T03:52:43.268524Z",
     "iopub.status.idle": "2021-11-09T03:52:43.287626Z",
     "shell.execute_reply": "2021-11-09T03:52:43.286653Z",
     "shell.execute_reply.started": "2021-11-09T03:52:43.269284Z"
    }
   },
   "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",
       "      <th>TotalCharges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>SeniorCitizen</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.016567</td>\n",
       "      <td>0.220173</td>\n",
       "      <td>0.102411</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>tenure</th>\n",
       "      <td>0.016567</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.247900</td>\n",
       "      <td>0.825880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>MonthlyCharges</th>\n",
       "      <td>0.220173</td>\n",
       "      <td>0.247900</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.651065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TotalCharges</th>\n",
       "      <td>0.102411</td>\n",
       "      <td>0.825880</td>\n",
       "      <td>0.651065</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                SeniorCitizen    tenure  MonthlyCharges  TotalCharges\n",
       "SeniorCitizen        1.000000  0.016567        0.220173      0.102411\n",
       "tenure               0.016567  1.000000        0.247900      0.825880\n",
       "MonthlyCharges       0.220173  0.247900        1.000000      0.651065\n",
       "TotalCharges         0.102411  0.825880        0.651065      1.000000"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.corr(numeric_only= True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature distribution"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We plot distributions for numerical and categorical features to check for outliers and compare feature distributions with target variable."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Numerical features distribution\n",
    "\n",
    "Numeric summarizing techniques (mean, standard deviation, etc.) don't show us spikes, shapes of distributions and it is hard to observe outliers with it. That is the reason we use histograms."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "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>count</th>\n",
       "      <td>7043.000000</td>\n",
       "      <td>7043.000000</td>\n",
       "      <td>7032.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>32.371149</td>\n",
       "      <td>64.761692</td>\n",
       "      <td>2283.300441</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>24.559481</td>\n",
       "      <td>30.090047</td>\n",
       "      <td>2266.771362</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>18.250000</td>\n",
       "      <td>18.800000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>35.500000</td>\n",
       "      <td>401.450000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>29.000000</td>\n",
       "      <td>70.350000</td>\n",
       "      <td>1397.475000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>55.000000</td>\n",
       "      <td>89.850000</td>\n",
       "      <td>3794.737500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>72.000000</td>\n",
       "      <td>118.750000</td>\n",
       "      <td>8684.800000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            tenure  MonthlyCharges  TotalCharges\n",
       "count  7043.000000     7043.000000   7032.000000\n",
       "mean     32.371149       64.761692   2283.300441\n",
       "std      24.559481       30.090047   2266.771362\n",
       "min       0.000000       18.250000     18.800000\n",
       "25%       9.000000       35.500000    401.450000\n",
       "50%      29.000000       70.350000   1397.475000\n",
       "75%      55.000000       89.850000   3794.737500\n",
       "max      72.000000      118.750000   8684.800000"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[numerical_features].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[<AxesSubplot: title={'center': 'tenure'}>,\n",
       "        <AxesSubplot: title={'center': 'MonthlyCharges'}>],\n",
       "       [<AxesSubplot: title={'center': 'TotalCharges'}>, <AxesSubplot: >]],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x700 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[numerical_features].hist(bins=30, figsize=(10, 7))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We look at distributions of numerical features in relation to the target variable. We can observe that the greater TotalCharges and tenure are the less is the probability of churn."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([<AxesSubplot: title={'center': 'tenure'}>,\n",
       "       <AxesSubplot: title={'center': 'MonthlyCharges'}>,\n",
       "       <AxesSubplot: title={'center': 'TotalCharges'}>], dtype=object)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1400x400 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(1, 3, figsize=(14, 4))\n",
    "df[df.Churn == \"No\"][numerical_features].hist(bins=30, color=\"blue\", alpha=0.5, ax=ax)\n",
    "df[df.Churn == \"Yes\"][numerical_features].hist(bins=30, color=\"red\", alpha=0.5, ax=ax)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Categorical feature distribution\n",
    "\n",
    "To analyze categorical features, we use bar charts. We observe that Senior citizens and customers without phone service are less represented in the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1900x1900 with 16 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ROWS, COLS = 4, 4\n",
    "fig, ax = plt.subplots(ROWS,COLS, figsize=(19,19))\n",
    "row, col = 0, 0,\n",
    "for i, categorical_feature in enumerate(categorical_features):\n",
    "    if col == COLS - 1:\n",
    "        row += 1\n",
    "    col = i % COLS\n",
    "    df[categorical_feature].value_counts().plot(kind='bar', ax=ax[row, col]).set_title(categorical_feature)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The next step is to look at categorical features in relation to the target variable. We do this only for contract feature. Users who have a month-to-month contract are more likely to churn than users with long term contracts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'churned')"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "feature = 'Contract'\n",
    "fig, ax = plt.subplots(1, 2, figsize=(12, 4))\n",
    "df[df.Churn == \"No\"][feature].value_counts().plot(kind='bar', ax=ax[0]).set_title('not churned')\n",
    "df[df.Churn == \"Yes\"][feature].value_counts().plot(kind='bar', ax=ax[1]).set_title('churned')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Target variable distribution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'churned')"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "df[target].value_counts().plot(kind='bar').set_title('churned')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Target variable distribution shows that we are dealing with an imbalanced problem as there are many more non-churned as compare to churned users. The model would achieve high accuracy as it would mostly predict majority class - users who didn't churn in our example.\n",
    "\n",
    "Few things we can do to minimize the influence of imbalanced dataset:\n",
    "- resample data,\n",
    "- collect more samples,\n",
    "- use precision and recall as accuracy metrics."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Outliers Analysis with IQR Method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:14.876626Z",
     "iopub.status.busy": "2021-11-09T03:53:14.875430Z",
     "iopub.status.idle": "2021-11-09T03:53:14.900303Z",
     "shell.execute_reply": "2021-11-09T03:53:14.899071Z",
     "shell.execute_reply.started": "2021-11-09T03:53:14.876576Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "No outliers in tenure\n",
      "No outliers in MonthlyCharges\n"
     ]
    }
   ],
   "source": [
    "x = ['tenure','MonthlyCharges']\n",
    "def count_outliers(data,col):\n",
    "        q1 = data[col].quantile(0.25,interpolation='nearest')\n",
    "        q2 = data[col].quantile(0.5,interpolation='nearest')\n",
    "        q3 = data[col].quantile(0.75,interpolation='nearest')\n",
    "        q4 = data[col].quantile(1,interpolation='nearest')\n",
    "        IQR = q3 -q1\n",
    "        global LLP\n",
    "        global ULP\n",
    "        LLP = q1 - 1.5*IQR\n",
    "        ULP = q3 + 1.5*IQR\n",
    "        if data[col].min() > LLP and data[col].max() < ULP:\n",
    "            print(\"No outliers in\",i)\n",
    "        else:\n",
    "            print(\"There are outliers in\",i)\n",
    "            x = data[data[col]<LLP][col].size\n",
    "            y = data[data[col]>ULP][col].size\n",
    "            a.append(i)\n",
    "            print('Count of outliers are:',x+y)\n",
    "global a\n",
    "a = []\n",
    "for i in x:\n",
    "    count_outliers(df,i)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Cleaning and Transforming Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:14.902614Z",
     "iopub.status.busy": "2021-11-09T03:53:14.902166Z",
     "iopub.status.idle": "2021-11-09T03:53:14.911726Z",
     "shell.execute_reply": "2021-11-09T03:53:14.910394Z",
     "shell.execute_reply.started": "2021-11-09T03:53:14.902565Z"
    }
   },
   "outputs": [],
   "source": [
    "df.drop(['customerID'],axis = 1,inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:14.914366Z",
     "iopub.status.busy": "2021-11-09T03:53:14.914012Z",
     "iopub.status.idle": "2021-11-09T03:53:14.952158Z",
     "shell.execute_reply": "2021-11-09T03:53:14.951160Z",
     "shell.execute_reply.started": "2021-11-09T03:53:14.914319Z"
    }
   },
   "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>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>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>29.85</td>\n",
       "      <td>29.85</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\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>56.95</td>\n",
       "      <td>1889.50</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\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>53.85</td>\n",
       "      <td>108.15</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\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>42.30</td>\n",
       "      <td>1840.75</td>\n",
       "      <td>No</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\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>70.70</td>\n",
       "      <td>151.65</td>\n",
       "      <td>Yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender  SeniorCitizen Partner Dependents  tenure PhoneService  \\\n",
       "0  Female              0     Yes         No       1           No   \n",
       "1    Male              0      No         No      34          Yes   \n",
       "2    Male              0      No         No       2          Yes   \n",
       "3    Male              0      No         No      45           No   \n",
       "4  Female              0      No         No       2          Yes   \n",
       "\n",
       "      MultipleLines InternetService OnlineSecurity OnlineBackup  \\\n",
       "0  No phone service             DSL             No          Yes   \n",
       "1                No             DSL            Yes           No   \n",
       "2                No             DSL            Yes          Yes   \n",
       "3  No phone service             DSL            Yes           No   \n",
       "4                No     Fiber optic             No           No   \n",
       "\n",
       "  DeviceProtection TechSupport StreamingTV StreamingMovies        Contract  \\\n",
       "0               No          No          No              No  Month-to-month   \n",
       "1              Yes          No          No              No        One year   \n",
       "2               No          No          No              No  Month-to-month   \n",
       "3              Yes         Yes          No              No        One year   \n",
       "4               No          No          No              No  Month-to-month   \n",
       "\n",
       "  PaperlessBilling              PaymentMethod  MonthlyCharges  TotalCharges  \\\n",
       "0              Yes           Electronic check           29.85         29.85   \n",
       "1               No               Mailed check           56.95       1889.50   \n",
       "2              Yes               Mailed check           53.85        108.15   \n",
       "3               No  Bank transfer (automatic)           42.30       1840.75   \n",
       "4              Yes           Electronic check           70.70        151.65   \n",
       "\n",
       "  Churn  \n",
       "0    No  \n",
       "1    No  \n",
       "2   Yes  \n",
       "3    No  \n",
       "4   Yes  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Dropped customerID because it is not needed"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### On Hot Encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:14.954613Z",
     "iopub.status.busy": "2021-11-09T03:53:14.953998Z",
     "iopub.status.idle": "2021-11-09T03:53:15.014837Z",
     "shell.execute_reply": "2021-11-09T03:53:15.013920Z",
     "shell.execute_reply.started": "2021-11-09T03:53:14.954564Z"
    }
   },
   "outputs": [],
   "source": [
    "df1=pd.get_dummies(data=df,columns=['gender', 'Partner', 'Dependents', \n",
    "       'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity',\n",
    "       'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV',\n",
    "       'StreamingMovies', 'Contract', 'PaperlessBilling', 'PaymentMethod', 'Churn'], drop_first=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "scrolled": true
   },
   "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",
       "      <th>TotalCharges</th>\n",
       "      <th>gender_Male</th>\n",
       "      <th>Partner_Yes</th>\n",
       "      <th>Dependents_Yes</th>\n",
       "      <th>PhoneService_Yes</th>\n",
       "      <th>MultipleLines_No phone service</th>\n",
       "      <th>MultipleLines_Yes</th>\n",
       "      <th>...</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>PaperlessBilling_Yes</th>\n",
       "      <th>PaymentMethod_Credit card (automatic)</th>\n",
       "      <th>PaymentMethod_Electronic check</th>\n",
       "      <th>PaymentMethod_Mailed check</th>\n",
       "      <th>Churn_Yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>29.85</td>\n",
       "      <td>29.85</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>56.95</td>\n",
       "      <td>1889.50</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>53.85</td>\n",
       "      <td>108.15</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>45</td>\n",
       "      <td>42.30</td>\n",
       "      <td>1840.75</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>70.70</td>\n",
       "      <td>151.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 31 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   SeniorCitizen  tenure  MonthlyCharges  TotalCharges  gender_Male  \\\n",
       "0              0       1           29.85         29.85            0   \n",
       "1              0      34           56.95       1889.50            1   \n",
       "2              0       2           53.85        108.15            1   \n",
       "3              0      45           42.30       1840.75            1   \n",
       "4              0       2           70.70        151.65            0   \n",
       "\n",
       "   Partner_Yes  Dependents_Yes  PhoneService_Yes  \\\n",
       "0            1               0                 0   \n",
       "1            0               0                 1   \n",
       "2            0               0                 1   \n",
       "3            0               0                 0   \n",
       "4            0               0                 1   \n",
       "\n",
       "   MultipleLines_No phone service  MultipleLines_Yes  ...  StreamingTV_Yes  \\\n",
       "0                               1                  0  ...                0   \n",
       "1                               0                  0  ...                0   \n",
       "2                               0                  0  ...                0   \n",
       "3                               1                  0  ...                0   \n",
       "4                               0                  0  ...                0   \n",
       "\n",
       "   StreamingMovies_No internet service  StreamingMovies_Yes  \\\n",
       "0                                    0                    0   \n",
       "1                                    0                    0   \n",
       "2                                    0                    0   \n",
       "3                                    0                    0   \n",
       "4                                    0                    0   \n",
       "\n",
       "   Contract_One year  Contract_Two year  PaperlessBilling_Yes  \\\n",
       "0                  0                  0                     1   \n",
       "1                  1                  0                     0   \n",
       "2                  0                  0                     1   \n",
       "3                  1                  0                     0   \n",
       "4                  0                  0                     1   \n",
       "\n",
       "   PaymentMethod_Credit card (automatic)  PaymentMethod_Electronic check  \\\n",
       "0                                      0                               1   \n",
       "1                                      0                               0   \n",
       "2                                      0                               0   \n",
       "3                                      0                               0   \n",
       "4                                      0                               1   \n",
       "\n",
       "   PaymentMethod_Mailed check  Churn_Yes  \n",
       "0                           0          0  \n",
       "1                           1          0  \n",
       "2                           1          1  \n",
       "3                           0          0  \n",
       "4                           0          1  \n",
       "\n",
       "[5 rows x 31 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['SeniorCitizen', 'tenure', 'MonthlyCharges', 'TotalCharges',\n",
       "       'gender_Male', 'Partner_Yes', 'Dependents_Yes', 'PhoneService_Yes',\n",
       "       'MultipleLines_No phone service', 'MultipleLines_Yes',\n",
       "       'InternetService_Fiber optic', 'InternetService_No',\n",
       "       'OnlineSecurity_No internet service', 'OnlineSecurity_Yes',\n",
       "       'OnlineBackup_No internet service', 'OnlineBackup_Yes',\n",
       "       'DeviceProtection_No internet service', 'DeviceProtection_Yes',\n",
       "       'TechSupport_No internet service', 'TechSupport_Yes',\n",
       "       'StreamingTV_No internet service', 'StreamingTV_Yes',\n",
       "       'StreamingMovies_No internet service', 'StreamingMovies_Yes',\n",
       "       'Contract_One year', 'Contract_Two year', 'PaperlessBilling_Yes',\n",
       "       'PaymentMethod_Credit card (automatic)',\n",
       "       'PaymentMethod_Electronic check', 'PaymentMethod_Mailed check',\n",
       "       'Churn_Yes'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Rearranging Columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "_kg_hide-input": true,
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.018322Z",
     "iopub.status.busy": "2021-11-09T03:53:15.017423Z",
     "iopub.status.idle": "2021-11-09T03:53:15.028617Z",
     "shell.execute_reply": "2021-11-09T03:53:15.027469Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.018273Z"
    }
   },
   "outputs": [],
   "source": [
    "df1 = df1[['SeniorCitizen', 'tenure', 'MonthlyCharges', 'TotalCharges',\n",
    "        'gender_Male', 'Partner_Yes', 'Dependents_Yes',\n",
    "       'PhoneService_Yes', 'MultipleLines_No phone service',\n",
    "       'MultipleLines_Yes', 'InternetService_Fiber optic',\n",
    "       'InternetService_No', 'OnlineSecurity_No internet service',\n",
    "       'OnlineSecurity_Yes', 'OnlineBackup_No internet service',\n",
    "       'OnlineBackup_Yes', 'DeviceProtection_No internet service',\n",
    "       'DeviceProtection_Yes', 'TechSupport_No internet service',\n",
    "       'TechSupport_Yes', 'StreamingTV_No internet service', 'StreamingTV_Yes',\n",
    "       'StreamingMovies_No internet service', 'StreamingMovies_Yes',\n",
    "       'Contract_One year', 'Contract_Two year', 'PaperlessBilling_Yes',\n",
    "       'PaymentMethod_Credit card (automatic)',\n",
    "       'PaymentMethod_Electronic check', 'PaymentMethod_Mailed check','Churn_Yes']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.031710Z",
     "iopub.status.busy": "2021-11-09T03:53:15.030868Z",
     "iopub.status.idle": "2021-11-09T03:53:15.064625Z",
     "shell.execute_reply": "2021-11-09T03:53:15.063618Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.031661Z"
    }
   },
   "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",
       "      <th>TotalCharges</th>\n",
       "      <th>gender_Male</th>\n",
       "      <th>Partner_Yes</th>\n",
       "      <th>Dependents_Yes</th>\n",
       "      <th>PhoneService_Yes</th>\n",
       "      <th>MultipleLines_No phone service</th>\n",
       "      <th>MultipleLines_Yes</th>\n",
       "      <th>...</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>PaperlessBilling_Yes</th>\n",
       "      <th>PaymentMethod_Credit card (automatic)</th>\n",
       "      <th>PaymentMethod_Electronic check</th>\n",
       "      <th>PaymentMethod_Mailed check</th>\n",
       "      <th>Churn_Yes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>29.85</td>\n",
       "      <td>29.85</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>34</td>\n",
       "      <td>56.95</td>\n",
       "      <td>1889.50</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>53.85</td>\n",
       "      <td>108.15</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>45</td>\n",
       "      <td>42.30</td>\n",
       "      <td>1840.75</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>70.70</td>\n",
       "      <td>151.65</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 31 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   SeniorCitizen  tenure  MonthlyCharges  TotalCharges  gender_Male  \\\n",
       "0              0       1           29.85         29.85            0   \n",
       "1              0      34           56.95       1889.50            1   \n",
       "2              0       2           53.85        108.15            1   \n",
       "3              0      45           42.30       1840.75            1   \n",
       "4              0       2           70.70        151.65            0   \n",
       "\n",
       "   Partner_Yes  Dependents_Yes  PhoneService_Yes  \\\n",
       "0            1               0                 0   \n",
       "1            0               0                 1   \n",
       "2            0               0                 1   \n",
       "3            0               0                 0   \n",
       "4            0               0                 1   \n",
       "\n",
       "   MultipleLines_No phone service  MultipleLines_Yes  ...  StreamingTV_Yes  \\\n",
       "0                               1                  0  ...                0   \n",
       "1                               0                  0  ...                0   \n",
       "2                               0                  0  ...                0   \n",
       "3                               1                  0  ...                0   \n",
       "4                               0                  0  ...                0   \n",
       "\n",
       "   StreamingMovies_No internet service  StreamingMovies_Yes  \\\n",
       "0                                    0                    0   \n",
       "1                                    0                    0   \n",
       "2                                    0                    0   \n",
       "3                                    0                    0   \n",
       "4                                    0                    0   \n",
       "\n",
       "   Contract_One year  Contract_Two year  PaperlessBilling_Yes  \\\n",
       "0                  0                  0                     1   \n",
       "1                  1                  0                     0   \n",
       "2                  0                  0                     1   \n",
       "3                  1                  0                     0   \n",
       "4                  0                  0                     1   \n",
       "\n",
       "   PaymentMethod_Credit card (automatic)  PaymentMethod_Electronic check  \\\n",
       "0                                      0                               1   \n",
       "1                                      0                               0   \n",
       "2                                      0                               0   \n",
       "3                                      0                               0   \n",
       "4                                      0                               1   \n",
       "\n",
       "   PaymentMethod_Mailed check  Churn_Yes  \n",
       "0                           0          0  \n",
       "1                           1          0  \n",
       "2                           1          1  \n",
       "3                           0          0  \n",
       "4                           0          1  \n",
       "\n",
       "[5 rows x 31 columns]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7043, 31)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.067076Z",
     "iopub.status.busy": "2021-11-09T03:53:15.066454Z",
     "iopub.status.idle": "2021-11-09T03:53:15.080022Z",
     "shell.execute_reply": "2021-11-09T03:53:15.078954Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.067027Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.impute import SimpleImputer\n",
    "\n",
    "# The imputer will replace missing values with the mean of the non-missing values for the respective columns\n",
    "\n",
    "imputer = SimpleImputer(missing_values=np.nan, strategy=\"mean\")\n",
    "\n",
    "df1.TotalCharges = imputer.fit_transform(df1[\"TotalCharges\"].values.reshape(-1, 1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature Scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.082462Z",
     "iopub.status.busy": "2021-11-09T03:53:15.082111Z",
     "iopub.status.idle": "2021-11-09T03:53:15.103525Z",
     "shell.execute_reply": "2021-11-09T03:53:15.102463Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.082399Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler.fit(df1.drop(['Churn_Yes'],axis = 1))\n",
    "scaled_features = scaler.transform(df1.drop('Churn_Yes',axis = 1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Feature Selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.106000Z",
     "iopub.status.busy": "2021-11-09T03:53:15.105329Z",
     "iopub.status.idle": "2021-11-09T03:53:15.116525Z",
     "shell.execute_reply": "2021-11-09T03:53:15.115285Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.105952Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X = scaled_features\n",
    "Y = df1['Churn_Yes']\n",
    "X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size = 0.3,random_state=44)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prediction using Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.228616Z",
     "iopub.status.busy": "2021-11-09T03:53:42.227007Z",
     "iopub.status.idle": "2021-11-09T03:53:42.319319Z",
     "shell.execute_reply": "2021-11-09T03:53:42.318141Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.228565Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 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-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 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-1 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-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 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-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 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-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 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-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</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-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import classification_report,accuracy_score ,confusion_matrix\n",
    "\n",
    "logmodel = LogisticRegression()\n",
    "logmodel.fit(X_train,Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.328549Z",
     "iopub.status.busy": "2021-11-09T03:53:42.325493Z",
     "iopub.status.idle": "2021-11-09T03:53:42.338505Z",
     "shell.execute_reply": "2021-11-09T03:53:42.337265Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.328497Z"
    }
   },
   "outputs": [],
   "source": [
    "predLR = logmodel.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, ..., 0, 0, 0], dtype=uint8)"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predLR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "5616    0\n",
       "2937    0\n",
       "1355    0\n",
       "5441    1\n",
       "3333    0\n",
       "       ..\n",
       "2797    1\n",
       "412     0\n",
       "174     0\n",
       "5761    0\n",
       "5895    0\n",
       "Name: Churn_Yes, Length: 2113, dtype: uint8"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.348885Z",
     "iopub.status.busy": "2021-11-09T03:53:42.344785Z",
     "iopub.status.idle": "2021-11-09T03:53:42.381860Z",
     "shell.execute_reply": "2021-11-09T03:53:42.380863Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.348824Z"
    },
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.84      0.90      0.87      1557\n",
      "           1       0.65      0.53      0.58       556\n",
      "\n",
      "    accuracy                           0.80      2113\n",
      "   macro avg       0.74      0.71      0.73      2113\n",
      "weighted avg       0.79      0.80      0.79      2113\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(Y_test, predLR))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1200x400 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# calculate the classification report\n",
    "report = classification_report(Y_test, predLR, target_names=['Churn_No', 'Churn_Yes'])\n",
    "\n",
    "# split the report into lines\n",
    "lines = report.split('\\n')\n",
    "\n",
    "# split each line into parts\n",
    "parts = [line.split() for line in lines[2:-5]]\n",
    "\n",
    "# extract the metrics for each class\n",
    "class_metrics = dict()\n",
    "for part in parts:\n",
    "    class_metrics[part[0]] = {'precision': float(part[1]), 'recall': float(part[2]), 'f1-score': float(part[3]), 'support': int(part[4])}\n",
    "\n",
    "# create a bar chart for each metric\n",
    "fig, ax = plt.subplots(1, 4, figsize=(12, 4))\n",
    "metrics = ['precision', 'recall', 'f1-score', 'support']\n",
    "for i, metric in enumerate(metrics):\n",
    "    ax[i].bar(class_metrics.keys(), [class_metrics[key][metric] for key in class_metrics.keys()])\n",
    "    ax[i].set_title(metric)\n",
    "\n",
    "# display the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "confusion_matrix_LR = confusion_matrix(Y_test, predLR)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 480x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# create a heatmap of the matrix using matshow()\n",
    "\n",
    "plt.matshow(confusion_matrix(Y_test, predLR))\n",
    "\n",
    "# add labels for the x and y axes\n",
    "plt.xlabel('Predicted Class')\n",
    "plt.ylabel('Actual Class')\n",
    "\n",
    "for i in range(2):\n",
    "    for j in range(2):\n",
    "        plt.text(j, i, confusion_matrix_LR[i, j], ha='center', va='center')\n",
    "\n",
    "\n",
    "# Add custom labels for x and y ticks\n",
    "plt.xticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.yticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.390863Z",
     "iopub.status.busy": "2021-11-09T03:53:42.388123Z",
     "iopub.status.idle": "2021-11-09T03:53:42.405849Z",
     "shell.execute_reply": "2021-11-09T03:53:42.404464Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.390782Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8062880324543611"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "logmodel.score(X_train, Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8002839564600095"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(Y_test, predLR)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prediction using Support Vector Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.527574Z",
     "iopub.status.busy": "2021-11-09T03:53:42.526756Z",
     "iopub.status.idle": "2021-11-09T03:53:43.842686Z",
     "shell.execute_reply": "2021-11-09T03:53:43.841678Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.527527Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC\n",
    "\n",
    "svc = SVC()\n",
    "svc.fit(X_train, Y_train)\n",
    "y_pred_svc = svc.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:43.862493Z",
     "iopub.status.busy": "2021-11-09T03:53:43.861822Z",
     "iopub.status.idle": "2021-11-09T03:53:43.877207Z",
     "shell.execute_reply": "2021-11-09T03:53:43.876226Z",
     "shell.execute_reply.started": "2021-11-09T03:53:43.862445Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.83      0.92      0.87      1557\n",
      "           1       0.67      0.48      0.56       556\n",
      "\n",
      "    accuracy                           0.80      2113\n",
      "   macro avg       0.75      0.70      0.71      2113\n",
      "weighted avg       0.79      0.80      0.79      2113\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(Y_test, y_pred_svc))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:43.844696Z",
     "iopub.status.busy": "2021-11-09T03:53:43.844279Z",
     "iopub.status.idle": "2021-11-09T03:53:43.858729Z",
     "shell.execute_reply": "2021-11-09T03:53:43.857478Z",
     "shell.execute_reply.started": "2021-11-09T03:53:43.844652Z"
    }
   },
   "outputs": [],
   "source": [
    "confusion_matrix_svc = confusion_matrix(Y_test, y_pred_svc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 480x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# create a heatmap of the matrix using matshow()\n",
    "\n",
    "plt.matshow(confusion_matrix_svc)\n",
    "\n",
    "# add labels for the x and y axes\n",
    "plt.xlabel('Predicted Class')\n",
    "plt.ylabel('Actual Class')\n",
    "\n",
    "for i in range(2):\n",
    "    for j in range(2):\n",
    "        plt.text(j, i, confusion_matrix_svc[i, j], ha='center', va='center')\n",
    "\n",
    "        \n",
    "# Add custom labels for x and y ticks\n",
    "plt.xticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.yticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8170385395537525"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svc.score(X_train,Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:43.879144Z",
     "iopub.status.busy": "2021-11-09T03:53:43.878814Z",
     "iopub.status.idle": "2021-11-09T03:53:43.885927Z",
     "shell.execute_reply": "2021-11-09T03:53:43.884870Z",
     "shell.execute_reply.started": "2021-11-09T03:53:43.879102Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8012304779933743"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(Y_test, y_pred_svc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Prediction using Decision Tree Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.414719Z",
     "iopub.status.busy": "2021-11-09T03:53:42.412027Z",
     "iopub.status.idle": "2021-11-09T03:53:42.465457Z",
     "shell.execute_reply": "2021-11-09T03:53:42.464395Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.414670Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "dtc = DecisionTreeClassifier()\n",
    "\n",
    "dtc.fit(X_train, Y_train)\n",
    "y_pred_dtc = dtc.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.485884Z",
     "iopub.status.busy": "2021-11-09T03:53:42.485243Z",
     "iopub.status.idle": "2021-11-09T03:53:42.506139Z",
     "shell.execute_reply": "2021-11-09T03:53:42.505038Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.485837Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.81      0.80      0.81      1557\n",
      "           1       0.47      0.48      0.47       556\n",
      "\n",
      "    accuracy                           0.72      2113\n",
      "   macro avg       0.64      0.64      0.64      2113\n",
      "weighted avg       0.72      0.72      0.72      2113\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(Y_test, y_pred_dtc))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.468239Z",
     "iopub.status.busy": "2021-11-09T03:53:42.467658Z",
     "iopub.status.idle": "2021-11-09T03:53:42.483494Z",
     "shell.execute_reply": "2021-11-09T03:53:42.482335Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.468197Z"
    }
   },
   "outputs": [],
   "source": [
    "confusion_matrix_dtc = confusion_matrix(Y_test, y_pred_dtc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 480x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# create a heatmap of the matrix using matshow()\n",
    "\n",
    "plt.matshow(confusion_matrix_dtc)\n",
    "\n",
    "# add labels for the x and y axes\n",
    "plt.xlabel('Predicted Class')\n",
    "plt.ylabel('Actual Class')\n",
    "\n",
    "for i in range(2):\n",
    "    for j in range(2):\n",
    "        plt.text(j, i, confusion_matrix_dtc[i, j], ha='center', va='center')\n",
    "\n",
    "\n",
    "# Add custom labels for x and y ticks\n",
    "plt.xticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.yticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9987829614604462"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dtc.score(X_train,Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:42.512579Z",
     "iopub.status.busy": "2021-11-09T03:53:42.511696Z",
     "iopub.status.idle": "2021-11-09T03:53:42.524237Z",
     "shell.execute_reply": "2021-11-09T03:53:42.523090Z",
     "shell.execute_reply.started": "2021-11-09T03:53:42.512525Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.718409843823947"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(Y_test, y_pred_dtc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prediction using KNN Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.119418Z",
     "iopub.status.busy": "2021-11-09T03:53:15.118718Z",
     "iopub.status.idle": "2021-11-09T03:53:15.188313Z",
     "shell.execute_reply": "2021-11-09T03:53:15.187419Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.119360Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 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-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 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-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 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-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 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-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier(n_neighbors=30)</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-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">KNeighborsClassifier</label><div class=\"sk-toggleable__content\"><pre>KNeighborsClassifier(n_neighbors=30)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "KNeighborsClassifier(n_neighbors=30)"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "knn = KNeighborsClassifier(n_neighbors = 30)\n",
    "knn.fit(X_train,Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.190286Z",
     "iopub.status.busy": "2021-11-09T03:53:15.189853Z",
     "iopub.status.idle": "2021-11-09T03:53:15.800866Z",
     "shell.execute_reply": "2021-11-09T03:53:15.799696Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.190238Z"
    }
   },
   "outputs": [],
   "source": [
    "pred_knn = knn.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.840171Z",
     "iopub.status.busy": "2021-11-09T03:53:15.839811Z",
     "iopub.status.idle": "2021-11-09T03:53:40.333004Z",
     "shell.execute_reply": "2021-11-09T03:53:40.332162Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.840125Z"
    }
   },
   "outputs": [],
   "source": [
    "error_rate= []\n",
    "for i in range(1,40):\n",
    "    knn = KNeighborsClassifier(n_neighbors = i)\n",
    "    knn.fit(X_train,Y_train)\n",
    "    pred_i = knn.predict(X_test)\n",
    "    error_rate.append(np.mean(pred_i != Y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:40.334926Z",
     "iopub.status.busy": "2021-11-09T03:53:40.334639Z",
     "iopub.status.idle": "2021-11-09T03:53:40.729899Z",
     "shell.execute_reply": "2021-11-09T03:53:40.728891Z",
     "shell.execute_reply.started": "2021-11-09T03:53:40.334874Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Error Rate')"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize = (10,6))\n",
    "plt.plot(range(1,40),error_rate,color = 'blue',linestyle = '--',marker = 'o',markerfacecolor='red',markersize = 10)\n",
    "plt.title('Error Rate vs K')\n",
    "plt.xlabel('K')\n",
    "plt.ylabel('Error Rate')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.820436Z",
     "iopub.status.busy": "2021-11-09T03:53:15.820173Z",
     "iopub.status.idle": "2021-11-09T03:53:15.838086Z",
     "shell.execute_reply": "2021-11-09T03:53:15.837096Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.820382Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.84      0.88      0.86      1557\n",
      "           1       0.62      0.55      0.58       556\n",
      "\n",
      "    accuracy                           0.79      2113\n",
      "   macro avg       0.73      0.71      0.72      2113\n",
      "weighted avg       0.79      0.79      0.79      2113\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(classification_report(Y_test,pred_knn))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:15.803343Z",
     "iopub.status.busy": "2021-11-09T03:53:15.803004Z",
     "iopub.status.idle": "2021-11-09T03:53:15.818621Z",
     "shell.execute_reply": "2021-11-09T03:53:15.817622Z",
     "shell.execute_reply.started": "2021-11-09T03:53:15.803297Z"
    }
   },
   "outputs": [],
   "source": [
    "confusion_matrix_knn = confusion_matrix(Y_test,pred_knn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 480x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# create a heatmap of the matrix using matshow()\n",
    "\n",
    "plt.matshow(confusion_matrix_knn)\n",
    "\n",
    "# add labels for the x and y axes\n",
    "plt.xlabel('Predicted Class')\n",
    "plt.ylabel('Actual Class')\n",
    "\n",
    "for i in range(2):\n",
    "    for j in range(2):\n",
    "        plt.text(j, i, confusion_matrix_knn[i, j], ha='center', va='center')\n",
    "\n",
    "# Add custom labels for x and y ticks\n",
    "plt.xticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.yticks([0, 1], [\"Not Churned\", \"Churned\"])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8008113590263691"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "knn.score(X_train,Y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2021-11-09T03:53:40.732823Z",
     "iopub.status.busy": "2021-11-09T03:53:40.731412Z",
     "iopub.status.idle": "2021-11-09T03:53:42.225267Z",
     "shell.execute_reply": "2021-11-09T03:53:42.224304Z",
     "shell.execute_reply.started": "2021-11-09T03:53:40.732768Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.792238523426408"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(Y_test, pred_knn)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Conclusion\n",
    "So, Thank you for sticking with me until the end. If you are interested in learning more about this dataset, you can explore other machine learning classification models such as Ada Boost Classifier, Gradient Boosting Classifier, Stochastic Gradient Boosting (SGB) Classifier, Cat Boost Classifier and XGB Boost Classifier. Additionally, you can try tuning the model's hyperparameters using techniques like GridSearchCV. I am not going into detail about those topics, but if you are interested, feel free to explore them further.  "
   ]
  }
 ],
 "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}