Hackerearth-Customer-Churn-Rate/churn_rate_over_sampling_xgb_grid.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "Aj3i9EkUQBsF",
   "metadata": {
    "id": "Aj3i9EkUQBsF"
   },
   "outputs": [],
   "source": [
    ""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "6opPSpleQDwE",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "6opPSpleQDwE",
    "outputId": "b1ed81c1-faa1-4e79-bacb-88d917e0157c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
     ]
    }
   ],
   "source": [
    "from google.colab import drive\n",
    "drive.mount('/content/drive')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "bridal-arrangement",
   "metadata": {
    "id": "bridal-arrangement"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "pd.set_option('display.max_columns', 50000)\n",
    "import numpy as np\n",
    "import csv\n",
    "import json\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.preprocessing import normalize\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.model_selection import train_test_split\n",
    "import sklearn\n",
    "import datetime, os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "surprised-rings",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 343
    },
    "id": "surprised-rings",
    "outputId": "cc64db2e-bda4-497c-f38f-4afb4c28861e"
   },
   "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>customer_id</th>\n",
       "      <th>Name</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>security_no</th>\n",
       "      <th>region_category</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joining_date</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>referral_id</th>\n",
       "      <th>preferred_offer_types</th>\n",
       "      <th>medium_of_operation</th>\n",
       "      <th>internet_option</th>\n",
       "      <th>last_visit_time</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>complaint_status</th>\n",
       "      <th>feedback</th>\n",
       "      <th>churn_risk_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe4300490044003600300030003800</td>\n",
       "      <td>Pattie Morrisey</td>\n",
       "      <td>18</td>\n",
       "      <td>F</td>\n",
       "      <td>XW0DQ7H</td>\n",
       "      <td>Village</td>\n",
       "      <td>Platinum Membership</td>\n",
       "      <td>2017-08-17</td>\n",
       "      <td>No</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>?</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>16:08:02</td>\n",
       "      <td>17</td>\n",
       "      <td>300.63</td>\n",
       "      <td>53005.25</td>\n",
       "      <td>17.0</td>\n",
       "      <td>781.75</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Not Applicable</td>\n",
       "      <td>Products always in Stock</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440032003100300035003700</td>\n",
       "      <td>Traci Peery</td>\n",
       "      <td>32</td>\n",
       "      <td>F</td>\n",
       "      <td>5K0N3X1</td>\n",
       "      <td>City</td>\n",
       "      <td>Premium Membership</td>\n",
       "      <td>2017-08-28</td>\n",
       "      <td>?</td>\n",
       "      <td>CID21329</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>12:38:13</td>\n",
       "      <td>16</td>\n",
       "      <td>306.34</td>\n",
       "      <td>12838.38</td>\n",
       "      <td>10.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Quality Customer Care</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe4300490044003100390032003600</td>\n",
       "      <td>Merideth Mcmeen</td>\n",
       "      <td>44</td>\n",
       "      <td>F</td>\n",
       "      <td>1F2TCL3</td>\n",
       "      <td>Town</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2016-11-11</td>\n",
       "      <td>Yes</td>\n",
       "      <td>CID12313</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>22:53:21</td>\n",
       "      <td>14</td>\n",
       "      <td>516.16</td>\n",
       "      <td>21027.00</td>\n",
       "      <td>22.0</td>\n",
       "      <td>500.69</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved in Follow-up</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003000330031003600</td>\n",
       "      <td>Eufemia Cardwell</td>\n",
       "      <td>37</td>\n",
       "      <td>M</td>\n",
       "      <td>VJGJ33N</td>\n",
       "      <td>City</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2016-10-29</td>\n",
       "      <td>Yes</td>\n",
       "      <td>CID3793</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:57:50</td>\n",
       "      <td>11</td>\n",
       "      <td>53.27</td>\n",
       "      <td>25239.56</td>\n",
       "      <td>6.0</td>\n",
       "      <td>567.66</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Unsolved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440031003900350030003600</td>\n",
       "      <td>Meghan Kosak</td>\n",
       "      <td>31</td>\n",
       "      <td>F</td>\n",
       "      <td>SVZXCWB</td>\n",
       "      <td>City</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2017-09-12</td>\n",
       "      <td>No</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Credit/Debit Card Offers</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:46:44</td>\n",
       "      <td>20</td>\n",
       "      <td>113.13</td>\n",
       "      <td>24483.66</td>\n",
       "      <td>16.0</td>\n",
       "      <td>663.06</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id              Name  age gender  \\\n",
       "0      fffe4300490044003600300030003800   Pattie Morrisey   18      F   \n",
       "1  fffe43004900440032003100300035003700       Traci Peery   32      F   \n",
       "2      fffe4300490044003100390032003600   Merideth Mcmeen   44      F   \n",
       "3  fffe43004900440036003000330031003600  Eufemia Cardwell   37      M   \n",
       "4  fffe43004900440031003900350030003600      Meghan Kosak   31      F   \n",
       "\n",
       "  security_no region_category  membership_category joining_date  \\\n",
       "0     XW0DQ7H         Village  Platinum Membership   2017-08-17   \n",
       "1     5K0N3X1            City   Premium Membership   2017-08-28   \n",
       "2     1F2TCL3            Town        No Membership   2016-11-11   \n",
       "3     VJGJ33N            City        No Membership   2016-10-29   \n",
       "4     SVZXCWB            City        No Membership   2017-09-12   \n",
       "\n",
       "  joined_through_referral referral_id     preferred_offer_types  \\\n",
       "0                      No    xxxxxxxx     Gift Vouchers/Coupons   \n",
       "1                       ?    CID21329     Gift Vouchers/Coupons   \n",
       "2                     Yes    CID12313     Gift Vouchers/Coupons   \n",
       "3                     Yes     CID3793     Gift Vouchers/Coupons   \n",
       "4                      No    xxxxxxxx  Credit/Debit Card Offers   \n",
       "\n",
       "  medium_of_operation internet_option last_visit_time  days_since_last_login  \\\n",
       "0                   ?           Wi-Fi        16:08:02                     17   \n",
       "1             Desktop     Mobile_Data        12:38:13                     16   \n",
       "2             Desktop           Wi-Fi        22:53:21                     14   \n",
       "3             Desktop     Mobile_Data        15:57:50                     11   \n",
       "4          Smartphone     Mobile_Data        15:46:44                     20   \n",
       "\n",
       "   avg_time_spent  avg_transaction_value avg_frequency_login_days  \\\n",
       "0          300.63               53005.25                     17.0   \n",
       "1          306.34               12838.38                     10.0   \n",
       "2          516.16               21027.00                     22.0   \n",
       "3           53.27               25239.56                      6.0   \n",
       "4          113.13               24483.66                     16.0   \n",
       "\n",
       "   points_in_wallet used_special_discount offer_application_preference  \\\n",
       "0            781.75                   Yes                          Yes   \n",
       "1               NaN                   Yes                           No   \n",
       "2            500.69                    No                          Yes   \n",
       "3            567.66                    No                          Yes   \n",
       "4            663.06                    No                          Yes   \n",
       "\n",
       "  past_complaint     complaint_status                  feedback  \\\n",
       "0             No       Not Applicable  Products always in Stock   \n",
       "1            Yes               Solved     Quality Customer Care   \n",
       "2            Yes  Solved in Follow-up              Poor Website   \n",
       "3            Yes             Unsolved              Poor Website   \n",
       "4            Yes               Solved              Poor Website   \n",
       "\n",
       "   churn_risk_score  \n",
       "0                 2  \n",
       "1                 1  \n",
       "2                 5  \n",
       "3                 5  \n",
       "4                 5  "
      ]
     },
     "execution_count": 50,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"./drive/MyDrive/dataset/train.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "micro-timothy",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "id": "micro-timothy",
    "outputId": "6b66786c-d6ae-4bd0-b275-54b2e23f2306"
   },
   "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>age</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>churn_risk_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>36992.000000</td>\n",
       "      <td>36992.000000</td>\n",
       "      <td>36992.000000</td>\n",
       "      <td>36992.000000</td>\n",
       "      <td>33549.000000</td>\n",
       "      <td>36992.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>37.118161</td>\n",
       "      <td>-41.915576</td>\n",
       "      <td>243.472334</td>\n",
       "      <td>29271.194003</td>\n",
       "      <td>686.882199</td>\n",
       "      <td>3.463397</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>15.867412</td>\n",
       "      <td>228.819900</td>\n",
       "      <td>398.289149</td>\n",
       "      <td>19444.806226</td>\n",
       "      <td>194.063624</td>\n",
       "      <td>1.409661</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>-999.000000</td>\n",
       "      <td>-2814.109110</td>\n",
       "      <td>800.460000</td>\n",
       "      <td>-760.661236</td>\n",
       "      <td>-1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>23.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>60.102500</td>\n",
       "      <td>14177.540000</td>\n",
       "      <td>616.150000</td>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>37.000000</td>\n",
       "      <td>12.000000</td>\n",
       "      <td>161.765000</td>\n",
       "      <td>27554.485000</td>\n",
       "      <td>697.620000</td>\n",
       "      <td>4.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>51.000000</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>356.515000</td>\n",
       "      <td>40855.110000</td>\n",
       "      <td>763.950000</td>\n",
       "      <td>5.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>64.000000</td>\n",
       "      <td>26.000000</td>\n",
       "      <td>3235.578521</td>\n",
       "      <td>99914.050000</td>\n",
       "      <td>2069.069761</td>\n",
       "      <td>5.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                age  days_since_last_login  avg_time_spent  \\\n",
       "count  36992.000000           36992.000000    36992.000000   \n",
       "mean      37.118161             -41.915576      243.472334   \n",
       "std       15.867412             228.819900      398.289149   \n",
       "min       10.000000            -999.000000    -2814.109110   \n",
       "25%       23.000000               8.000000       60.102500   \n",
       "50%       37.000000              12.000000      161.765000   \n",
       "75%       51.000000              16.000000      356.515000   \n",
       "max       64.000000              26.000000     3235.578521   \n",
       "\n",
       "       avg_transaction_value  points_in_wallet  churn_risk_score  \n",
       "count           36992.000000      33549.000000      36992.000000  \n",
       "mean            29271.194003        686.882199          3.463397  \n",
       "std             19444.806226        194.063624          1.409661  \n",
       "min               800.460000       -760.661236         -1.000000  \n",
       "25%             14177.540000        616.150000          3.000000  \n",
       "50%             27554.485000        697.620000          4.000000  \n",
       "75%             40855.110000        763.950000          5.000000  \n",
       "max             99914.050000       2069.069761          5.000000  "
      ]
     },
     "execution_count": 51,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "democratic-passion",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "democratic-passion",
    "outputId": "9946f925-2c1d-419e-d5db-ebcddf0c0d49"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 36992 entries, 0 to 36991\n",
      "Data columns (total 25 columns):\n",
      " #   Column                        Non-Null Count  Dtype  \n",
      "---  ------                        --------------  -----  \n",
      " 0   customer_id                   36992 non-null  object \n",
      " 1   Name                          36992 non-null  object \n",
      " 2   age                           36992 non-null  int64  \n",
      " 3   gender                        36992 non-null  object \n",
      " 4   security_no                   36992 non-null  object \n",
      " 5   region_category               31564 non-null  object \n",
      " 6   membership_category           36992 non-null  object \n",
      " 7   joining_date                  36992 non-null  object \n",
      " 8   joined_through_referral       36992 non-null  object \n",
      " 9   referral_id                   36992 non-null  object \n",
      " 10  preferred_offer_types         36704 non-null  object \n",
      " 11  medium_of_operation           36992 non-null  object \n",
      " 12  internet_option               36992 non-null  object \n",
      " 13  last_visit_time               36992 non-null  object \n",
      " 14  days_since_last_login         36992 non-null  int64  \n",
      " 15  avg_time_spent                36992 non-null  float64\n",
      " 16  avg_transaction_value         36992 non-null  float64\n",
      " 17  avg_frequency_login_days      36992 non-null  object \n",
      " 18  points_in_wallet              33549 non-null  float64\n",
      " 19  used_special_discount         36992 non-null  object \n",
      " 20  offer_application_preference  36992 non-null  object \n",
      " 21  past_complaint                36992 non-null  object \n",
      " 22  complaint_status              36992 non-null  object \n",
      " 23  feedback                      36992 non-null  object \n",
      " 24  churn_risk_score              36992 non-null  int64  \n",
      "dtypes: float64(3), int64(3), object(19)\n",
      "memory usage: 7.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "typical-bunch",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "typical-bunch",
    "outputId": "1a4937e7-694a-4890-b8dc-8b5c280b4a56"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "F          18490\n",
      "M          18443\n",
      "Unknown       59\n",
      "Name: gender, dtype: int64\n",
      "--------------------------------------------------\n",
      "Town       14128\n",
      "City       12737\n",
      "Village     4699\n",
      "Name: region_category, dtype: int64\n",
      "--------------------------------------------------\n",
      "Basic Membership       7724\n",
      "No Membership          7692\n",
      "Gold Membership        6795\n",
      "Silver Membership      5988\n",
      "Premium Membership     4455\n",
      "Platinum Membership    4338\n",
      "Name: membership_category, dtype: int64\n",
      "--------------------------------------------------\n",
      "No     15839\n",
      "Yes    15715\n",
      "?       5438\n",
      "Name: joined_through_referral, dtype: int64\n",
      "--------------------------------------------------\n",
      "Gift Vouchers/Coupons       12349\n",
      "Credit/Debit Card Offers    12274\n",
      "Without Offers              12081\n",
      "Name: preferred_offer_types, dtype: int64\n",
      "--------------------------------------------------\n",
      "Desktop       13913\n",
      "Smartphone    13876\n",
      "?              5393\n",
      "Both           3810\n",
      "Name: medium_of_operation, dtype: int64\n",
      "--------------------------------------------------\n",
      "Wi-Fi          12413\n",
      "Mobile_Data    12343\n",
      "Fiber_Optic    12236\n",
      "Name: internet_option, dtype: int64\n",
      "--------------------------------------------------\n",
      "Yes    20342\n",
      "No     16650\n",
      "Name: used_special_discount, dtype: int64\n",
      "--------------------------------------------------\n",
      "Yes    20440\n",
      "No     16552\n",
      "Name: offer_application_preference, dtype: int64\n",
      "--------------------------------------------------\n",
      "No     18602\n",
      "Yes    18390\n",
      "Name: past_complaint, dtype: int64\n",
      "--------------------------------------------------\n",
      "Not Applicable              18602\n",
      "Unsolved                     4644\n",
      "Solved                       4619\n",
      "Solved in Follow-up          4577\n",
      "No Information Available     4550\n",
      "Name: complaint_status, dtype: int64\n",
      "--------------------------------------------------\n",
      "Poor Product Quality        6350\n",
      "No reason specified         6290\n",
      "Too many ads                6279\n",
      "Poor Website                6271\n",
      "Poor Customer Service       6252\n",
      "Reasonable Price            1417\n",
      "User Friendly Website       1391\n",
      "Products always in Stock    1382\n",
      "Quality Customer Care       1360\n",
      "Name: feedback, dtype: int64\n",
      "--------------------------------------------------\n",
      "Error                  3522\n",
      "13.0                   1394\n",
      "19.0                   1365\n",
      "8.0                    1361\n",
      "14.0                   1355\n",
      "                       ... \n",
      "-18.461323191094202       1\n",
      "40.60196525026183         1\n",
      "-11.291393510762461       1\n",
      "-9.953600217853655        1\n",
      "-6.9611034041953275       1\n",
      "Name: avg_frequency_login_days, Length: 1654, dtype: int64\n",
      "--------------------------------------------------\n",
      " 3    10424\n",
      " 4    10185\n",
      " 5     9827\n",
      " 2     2741\n",
      " 1     2652\n",
      "-1     1163\n",
      "Name: churn_risk_score, dtype: int64\n",
      "--------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "def valueCounts(df):\n",
    "    print(df[\"gender\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"region_category\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"membership_category\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"joined_through_referral\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"preferred_offer_types\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"medium_of_operation\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"internet_option\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"used_special_discount\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"offer_application_preference\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"past_complaint\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"complaint_status\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"feedback\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"avg_frequency_login_days\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    print(df[\"churn_risk_score\"].value_counts())\n",
    "    print(\"-\"*50)\n",
    "    \n",
    "valueCounts(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "gorgeous-jimmy",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "gorgeous-jimmy",
    "outputId": "648f1abb-203a-40a8-d1dd-4a3e2cb59cb1"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 54,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().values.any()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "packed-plaza",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "packed-plaza",
    "outputId": "e92f5c47-c1b8-430c-db68-2c91ec2ed5f3"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "customer_id                        0\n",
       "Name                               0\n",
       "age                                0\n",
       "gender                             0\n",
       "security_no                        0\n",
       "region_category                 5428\n",
       "membership_category                0\n",
       "joining_date                       0\n",
       "joined_through_referral            0\n",
       "referral_id                        0\n",
       "preferred_offer_types            288\n",
       "medium_of_operation                0\n",
       "internet_option                    0\n",
       "last_visit_time                    0\n",
       "days_since_last_login              0\n",
       "avg_time_spent                     0\n",
       "avg_transaction_value              0\n",
       "avg_frequency_login_days           0\n",
       "points_in_wallet                3443\n",
       "used_special_discount              0\n",
       "offer_application_preference       0\n",
       "past_complaint                     0\n",
       "complaint_status                   0\n",
       "feedback                           0\n",
       "churn_risk_score                   0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 55,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "cloudy-northeast",
   "metadata": {
    "id": "cloudy-northeast"
   },
   "outputs": [],
   "source": [
    "# setting target wrong value -1 to 1 assuming sign issue, \n",
    "df['churn_risk_score'] = df['churn_risk_score'].apply(lambda x:1 if x == -1 else x)\n",
    "df['churn_risk_score'] = df['churn_risk_score'].apply(lambda x:x-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "figured-commerce",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "figured-commerce",
    "outputId": "18aeb6a3-67dd-426c-e096-a28ba465c781"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "customer_id                     0\n",
       "Name                            0\n",
       "age                             0\n",
       "gender                          0\n",
       "security_no                     0\n",
       "region_category                 0\n",
       "membership_category             0\n",
       "joining_date                    0\n",
       "joined_through_referral         0\n",
       "referral_id                     0\n",
       "preferred_offer_types           0\n",
       "medium_of_operation             0\n",
       "internet_option                 0\n",
       "last_visit_time                 0\n",
       "days_since_last_login           0\n",
       "avg_time_spent                  0\n",
       "avg_transaction_value           0\n",
       "avg_frequency_login_days        0\n",
       "points_in_wallet                0\n",
       "used_special_discount           0\n",
       "offer_application_preference    0\n",
       "past_complaint                  0\n",
       "complaint_status                0\n",
       "feedback                        0\n",
       "churn_risk_score                0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 57,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def handleMissingValues(df):\n",
    "    \n",
    "    df['joining_date']  = pd.to_datetime(df['joining_date'],format=\"%Y-%m-%d\")\n",
    "    \n",
    "    \n",
    "    # replacing Unknown words with most occured in df for gender column\n",
    "    df['gender'] = df['gender'].replace(['Unknown'], df[\"gender\"].mode()[0])\n",
    "    df['joined_through_referral'] = df['joined_through_referral'].replace(['?'], df[\"joined_through_referral\"].mode()[0])\n",
    "    df['avg_frequency_login_days'] = df['avg_frequency_login_days'].replace(['Error'], None)\n",
    "    \n",
    "    \n",
    "    df[\"region_category\"] = df[\"region_category\"].fillna(df[\"region_category\"].mode()[0])\n",
    "    df[\"preferred_offer_types\"] = df[\"preferred_offer_types\"].fillna(df[\"preferred_offer_types\"].mode()[0])\n",
    "    df[\"points_in_wallet\"] = df[\"points_in_wallet\"].fillna(df[\"points_in_wallet\"].median())\n",
    "    df[\"avg_frequency_login_days\"] = df[\"avg_frequency_login_days\"].fillna(df[\"avg_frequency_login_days\"].median())\n",
    "    \n",
    "    \n",
    "    df[\"avg_frequency_login_days\"] = pd.to_numeric(df[\"avg_frequency_login_days\"])\n",
    "    \n",
    "    return df\n",
    "\n",
    "df = handleMissingValues(df)\n",
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "least-objective",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "least-objective",
    "outputId": "9fdcfe14-67fb-439f-dc35-770dca3c4cf8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "F    18549\n",
      "M    18443\n",
      "Name: gender, dtype: int64\n",
      "--------------------------------------------------\n",
      "Town       19556\n",
      "City       12737\n",
      "Village     4699\n",
      "Name: region_category, dtype: int64\n",
      "--------------------------------------------------\n",
      "Basic Membership       7724\n",
      "No Membership          7692\n",
      "Gold Membership        6795\n",
      "Silver Membership      5988\n",
      "Premium Membership     4455\n",
      "Platinum Membership    4338\n",
      "Name: membership_category, dtype: int64\n",
      "--------------------------------------------------\n",
      "No     21277\n",
      "Yes    15715\n",
      "Name: joined_through_referral, dtype: int64\n",
      "--------------------------------------------------\n",
      "Gift Vouchers/Coupons       12637\n",
      "Credit/Debit Card Offers    12274\n",
      "Without Offers              12081\n",
      "Name: preferred_offer_types, dtype: int64\n",
      "--------------------------------------------------\n",
      "Desktop       13913\n",
      "Smartphone    13876\n",
      "?              5393\n",
      "Both           3810\n",
      "Name: medium_of_operation, dtype: int64\n",
      "--------------------------------------------------\n",
      "Wi-Fi          12413\n",
      "Mobile_Data    12343\n",
      "Fiber_Optic    12236\n",
      "Name: internet_option, dtype: int64\n",
      "--------------------------------------------------\n",
      "Yes    20342\n",
      "No     16650\n",
      "Name: used_special_discount, dtype: int64\n",
      "--------------------------------------------------\n",
      "Yes    20440\n",
      "No     16552\n",
      "Name: offer_application_preference, dtype: int64\n",
      "--------------------------------------------------\n",
      "No     18602\n",
      "Yes    18390\n",
      "Name: past_complaint, dtype: int64\n",
      "--------------------------------------------------\n",
      "Not Applicable              18602\n",
      "Unsolved                     4644\n",
      "Solved                       4619\n",
      "Solved in Follow-up          4577\n",
      "No Information Available     4550\n",
      "Name: complaint_status, dtype: int64\n",
      "--------------------------------------------------\n",
      "Poor Product Quality        6350\n",
      "No reason specified         6290\n",
      "Too many ads                6279\n",
      "Poor Website                6271\n",
      "Poor Customer Service       6252\n",
      "Reasonable Price            1417\n",
      "User Friendly Website       1391\n",
      "Products always in Stock    1382\n",
      "Quality Customer Care       1360\n",
      "Name: feedback, dtype: int64\n",
      "--------------------------------------------------\n",
      " 13.000000    1553\n",
      " 19.000000    1517\n",
      " 8.000000     1511\n",
      " 17.000000    1484\n",
      " 10.000000    1479\n",
      "              ... \n",
      "-4.202424        1\n",
      "-20.369214       1\n",
      "-9.016175        1\n",
      "-2.520089        1\n",
      "-0.520774        1\n",
      "Name: avg_frequency_login_days, Length: 1653, dtype: int64\n",
      "--------------------------------------------------\n",
      "2    10424\n",
      "3    10185\n",
      "4     9827\n",
      "0     3815\n",
      "1     2741\n",
      "Name: churn_risk_score, dtype: int64\n",
      "--------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "valueCounts(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "dated-republic",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "dated-republic",
    "outputId": "3b9807a1-5f77-4342-91ba-3e28cb4f29a2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 36992 entries, 0 to 36991\n",
      "Data columns (total 25 columns):\n",
      " #   Column                        Non-Null Count  Dtype         \n",
      "---  ------                        --------------  -----         \n",
      " 0   customer_id                   36992 non-null  object        \n",
      " 1   Name                          36992 non-null  object        \n",
      " 2   age                           36992 non-null  int64         \n",
      " 3   gender                        36992 non-null  object        \n",
      " 4   security_no                   36992 non-null  object        \n",
      " 5   region_category               36992 non-null  object        \n",
      " 6   membership_category           36992 non-null  object        \n",
      " 7   joining_date                  36992 non-null  datetime64[ns]\n",
      " 8   joined_through_referral       36992 non-null  object        \n",
      " 9   referral_id                   36992 non-null  object        \n",
      " 10  preferred_offer_types         36992 non-null  object        \n",
      " 11  medium_of_operation           36992 non-null  object        \n",
      " 12  internet_option               36992 non-null  object        \n",
      " 13  last_visit_time               36992 non-null  object        \n",
      " 14  days_since_last_login         36992 non-null  int64         \n",
      " 15  avg_time_spent                36992 non-null  float64       \n",
      " 16  avg_transaction_value         36992 non-null  float64       \n",
      " 17  avg_frequency_login_days      36992 non-null  float64       \n",
      " 18  points_in_wallet              36992 non-null  float64       \n",
      " 19  used_special_discount         36992 non-null  object        \n",
      " 20  offer_application_preference  36992 non-null  object        \n",
      " 21  past_complaint                36992 non-null  object        \n",
      " 22  complaint_status              36992 non-null  object        \n",
      " 23  feedback                      36992 non-null  object        \n",
      " 24  churn_risk_score              36992 non-null  int64         \n",
      "dtypes: datetime64[ns](1), float64(4), int64(3), object(17)\n",
      "memory usage: 7.1+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "elegant-landing",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 343
    },
    "id": "elegant-landing",
    "outputId": "f5b135db-08af-45a8-b365-06a9e4b806d7"
   },
   "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>customer_id</th>\n",
       "      <th>Name</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>security_no</th>\n",
       "      <th>region_category</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joining_date</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>referral_id</th>\n",
       "      <th>preferred_offer_types</th>\n",
       "      <th>medium_of_operation</th>\n",
       "      <th>internet_option</th>\n",
       "      <th>last_visit_time</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>complaint_status</th>\n",
       "      <th>feedback</th>\n",
       "      <th>churn_risk_score</th>\n",
       "      <th>todays_date</th>\n",
       "      <th>customer_days</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe4300490044003600300030003800</td>\n",
       "      <td>Pattie Morrisey</td>\n",
       "      <td>18</td>\n",
       "      <td>F</td>\n",
       "      <td>XW0DQ7H</td>\n",
       "      <td>Village</td>\n",
       "      <td>Platinum Membership</td>\n",
       "      <td>2017-08-17</td>\n",
       "      <td>No</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>?</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>16:08:02</td>\n",
       "      <td>17</td>\n",
       "      <td>300.63</td>\n",
       "      <td>53005.25</td>\n",
       "      <td>17.0</td>\n",
       "      <td>781.75</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Not Applicable</td>\n",
       "      <td>Products always in Stock</td>\n",
       "      <td>1</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1319.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440032003100300035003700</td>\n",
       "      <td>Traci Peery</td>\n",
       "      <td>32</td>\n",
       "      <td>F</td>\n",
       "      <td>5K0N3X1</td>\n",
       "      <td>City</td>\n",
       "      <td>Premium Membership</td>\n",
       "      <td>2017-08-28</td>\n",
       "      <td>No</td>\n",
       "      <td>CID21329</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>12:38:13</td>\n",
       "      <td>16</td>\n",
       "      <td>306.34</td>\n",
       "      <td>12838.38</td>\n",
       "      <td>10.0</td>\n",
       "      <td>697.62</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Quality Customer Care</td>\n",
       "      <td>0</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1308.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe4300490044003100390032003600</td>\n",
       "      <td>Merideth Mcmeen</td>\n",
       "      <td>44</td>\n",
       "      <td>F</td>\n",
       "      <td>1F2TCL3</td>\n",
       "      <td>Town</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2016-11-11</td>\n",
       "      <td>Yes</td>\n",
       "      <td>CID12313</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>22:53:21</td>\n",
       "      <td>14</td>\n",
       "      <td>516.16</td>\n",
       "      <td>21027.00</td>\n",
       "      <td>22.0</td>\n",
       "      <td>500.69</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved in Follow-up</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1598.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003000330031003600</td>\n",
       "      <td>Eufemia Cardwell</td>\n",
       "      <td>37</td>\n",
       "      <td>M</td>\n",
       "      <td>VJGJ33N</td>\n",
       "      <td>City</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2016-10-29</td>\n",
       "      <td>Yes</td>\n",
       "      <td>CID3793</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:57:50</td>\n",
       "      <td>11</td>\n",
       "      <td>53.27</td>\n",
       "      <td>25239.56</td>\n",
       "      <td>6.0</td>\n",
       "      <td>567.66</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Unsolved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1611.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440031003900350030003600</td>\n",
       "      <td>Meghan Kosak</td>\n",
       "      <td>31</td>\n",
       "      <td>F</td>\n",
       "      <td>SVZXCWB</td>\n",
       "      <td>City</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2017-09-12</td>\n",
       "      <td>No</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Credit/Debit Card Offers</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:46:44</td>\n",
       "      <td>20</td>\n",
       "      <td>113.13</td>\n",
       "      <td>24483.66</td>\n",
       "      <td>16.0</td>\n",
       "      <td>663.06</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1293.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id              Name  age gender  \\\n",
       "0      fffe4300490044003600300030003800   Pattie Morrisey   18      F   \n",
       "1  fffe43004900440032003100300035003700       Traci Peery   32      F   \n",
       "2      fffe4300490044003100390032003600   Merideth Mcmeen   44      F   \n",
       "3  fffe43004900440036003000330031003600  Eufemia Cardwell   37      M   \n",
       "4  fffe43004900440031003900350030003600      Meghan Kosak   31      F   \n",
       "\n",
       "  security_no region_category  membership_category joining_date  \\\n",
       "0     XW0DQ7H         Village  Platinum Membership   2017-08-17   \n",
       "1     5K0N3X1            City   Premium Membership   2017-08-28   \n",
       "2     1F2TCL3            Town        No Membership   2016-11-11   \n",
       "3     VJGJ33N            City        No Membership   2016-10-29   \n",
       "4     SVZXCWB            City        No Membership   2017-09-12   \n",
       "\n",
       "  joined_through_referral referral_id     preferred_offer_types  \\\n",
       "0                      No    xxxxxxxx     Gift Vouchers/Coupons   \n",
       "1                      No    CID21329     Gift Vouchers/Coupons   \n",
       "2                     Yes    CID12313     Gift Vouchers/Coupons   \n",
       "3                     Yes     CID3793     Gift Vouchers/Coupons   \n",
       "4                      No    xxxxxxxx  Credit/Debit Card Offers   \n",
       "\n",
       "  medium_of_operation internet_option last_visit_time  days_since_last_login  \\\n",
       "0                   ?           Wi-Fi        16:08:02                     17   \n",
       "1             Desktop     Mobile_Data        12:38:13                     16   \n",
       "2             Desktop           Wi-Fi        22:53:21                     14   \n",
       "3             Desktop     Mobile_Data        15:57:50                     11   \n",
       "4          Smartphone     Mobile_Data        15:46:44                     20   \n",
       "\n",
       "   avg_time_spent  avg_transaction_value  avg_frequency_login_days  \\\n",
       "0          300.63               53005.25                      17.0   \n",
       "1          306.34               12838.38                      10.0   \n",
       "2          516.16               21027.00                      22.0   \n",
       "3           53.27               25239.56                       6.0   \n",
       "4          113.13               24483.66                      16.0   \n",
       "\n",
       "   points_in_wallet used_special_discount offer_application_preference  \\\n",
       "0            781.75                   Yes                          Yes   \n",
       "1            697.62                   Yes                           No   \n",
       "2            500.69                    No                          Yes   \n",
       "3            567.66                    No                          Yes   \n",
       "4            663.06                    No                          Yes   \n",
       "\n",
       "  past_complaint     complaint_status                  feedback  \\\n",
       "0             No       Not Applicable  Products always in Stock   \n",
       "1            Yes               Solved     Quality Customer Care   \n",
       "2            Yes  Solved in Follow-up              Poor Website   \n",
       "3            Yes             Unsolved              Poor Website   \n",
       "4            Yes               Solved              Poor Website   \n",
       "\n",
       "   churn_risk_score todays_date  customer_days  \n",
       "0                 1  2021-03-28         1319.0  \n",
       "1                 0  2021-03-28         1308.0  \n",
       "2                 4  2021-03-28         1598.0  \n",
       "3                 4  2021-03-28         1611.0  \n",
       "4                 4  2021-03-28         1293.0  "
      ]
     },
     "execution_count": 60,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def handleExtraFeatures(df):\n",
    "\n",
    "    from datetime import date\n",
    "    df['todays_date'] = date.today().strftime(\"%Y-%m-%d\")\n",
    "    df['todays_date']  = pd.to_datetime(df['todays_date'],format=\"%Y-%m-%d\")\n",
    "    \n",
    "\n",
    "    df['customer_days'] = df['todays_date'] - df['joining_date'] \n",
    "    df['customer_days'] = df['customer_days'] / np.timedelta64(1,'D')\n",
    "\n",
    "    return df\n",
    "df = handleExtraFeatures(df)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "frank-norman",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 343
    },
    "id": "frank-norman",
    "outputId": "a20338e4-df26-4c61-9e91-7c7ac0c1ed55"
   },
   "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>customer_id</th>\n",
       "      <th>Name</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>security_no</th>\n",
       "      <th>region_category</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joining_date</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>referral_id</th>\n",
       "      <th>preferred_offer_types</th>\n",
       "      <th>medium_of_operation</th>\n",
       "      <th>internet_option</th>\n",
       "      <th>last_visit_time</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>complaint_status</th>\n",
       "      <th>feedback</th>\n",
       "      <th>churn_risk_score</th>\n",
       "      <th>todays_date</th>\n",
       "      <th>customer_days</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe4300490044003600300030003800</td>\n",
       "      <td>Pattie Morrisey</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>XW0DQ7H</td>\n",
       "      <td>Village</td>\n",
       "      <td>Platinum Membership</td>\n",
       "      <td>2017-08-17</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>?</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>16:08:02</td>\n",
       "      <td>17</td>\n",
       "      <td>300.63</td>\n",
       "      <td>53005.25</td>\n",
       "      <td>17.0</td>\n",
       "      <td>781.75</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Not Applicable</td>\n",
       "      <td>Products always in Stock</td>\n",
       "      <td>1</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1319.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440032003100300035003700</td>\n",
       "      <td>Traci Peery</td>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>5K0N3X1</td>\n",
       "      <td>City</td>\n",
       "      <td>Premium Membership</td>\n",
       "      <td>2017-08-28</td>\n",
       "      <td>0</td>\n",
       "      <td>CID21329</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>12:38:13</td>\n",
       "      <td>16</td>\n",
       "      <td>306.34</td>\n",
       "      <td>12838.38</td>\n",
       "      <td>10.0</td>\n",
       "      <td>697.62</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Quality Customer Care</td>\n",
       "      <td>0</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1308.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe4300490044003100390032003600</td>\n",
       "      <td>Merideth Mcmeen</td>\n",
       "      <td>44</td>\n",
       "      <td>0</td>\n",
       "      <td>1F2TCL3</td>\n",
       "      <td>Town</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2016-11-11</td>\n",
       "      <td>1</td>\n",
       "      <td>CID12313</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>22:53:21</td>\n",
       "      <td>14</td>\n",
       "      <td>516.16</td>\n",
       "      <td>21027.00</td>\n",
       "      <td>22.0</td>\n",
       "      <td>500.69</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Solved in Follow-up</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1598.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003000330031003600</td>\n",
       "      <td>Eufemia Cardwell</td>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>VJGJ33N</td>\n",
       "      <td>City</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2016-10-29</td>\n",
       "      <td>1</td>\n",
       "      <td>CID3793</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:57:50</td>\n",
       "      <td>11</td>\n",
       "      <td>53.27</td>\n",
       "      <td>25239.56</td>\n",
       "      <td>6.0</td>\n",
       "      <td>567.66</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Unsolved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1611.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440031003900350030003600</td>\n",
       "      <td>Meghan Kosak</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>SVZXCWB</td>\n",
       "      <td>City</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2017-09-12</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Credit/Debit Card Offers</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:46:44</td>\n",
       "      <td>20</td>\n",
       "      <td>113.13</td>\n",
       "      <td>24483.66</td>\n",
       "      <td>16.0</td>\n",
       "      <td>663.06</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1293.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id              Name  age  gender  \\\n",
       "0      fffe4300490044003600300030003800   Pattie Morrisey   18       0   \n",
       "1  fffe43004900440032003100300035003700       Traci Peery   32       0   \n",
       "2      fffe4300490044003100390032003600   Merideth Mcmeen   44       0   \n",
       "3  fffe43004900440036003000330031003600  Eufemia Cardwell   37       1   \n",
       "4  fffe43004900440031003900350030003600      Meghan Kosak   31       0   \n",
       "\n",
       "  security_no region_category  membership_category joining_date  \\\n",
       "0     XW0DQ7H         Village  Platinum Membership   2017-08-17   \n",
       "1     5K0N3X1            City   Premium Membership   2017-08-28   \n",
       "2     1F2TCL3            Town        No Membership   2016-11-11   \n",
       "3     VJGJ33N            City        No Membership   2016-10-29   \n",
       "4     SVZXCWB            City        No Membership   2017-09-12   \n",
       "\n",
       "   joined_through_referral referral_id     preferred_offer_types  \\\n",
       "0                        0    xxxxxxxx     Gift Vouchers/Coupons   \n",
       "1                        0    CID21329     Gift Vouchers/Coupons   \n",
       "2                        1    CID12313     Gift Vouchers/Coupons   \n",
       "3                        1     CID3793     Gift Vouchers/Coupons   \n",
       "4                        0    xxxxxxxx  Credit/Debit Card Offers   \n",
       "\n",
       "  medium_of_operation internet_option last_visit_time  days_since_last_login  \\\n",
       "0                   ?           Wi-Fi        16:08:02                     17   \n",
       "1             Desktop     Mobile_Data        12:38:13                     16   \n",
       "2             Desktop           Wi-Fi        22:53:21                     14   \n",
       "3             Desktop     Mobile_Data        15:57:50                     11   \n",
       "4          Smartphone     Mobile_Data        15:46:44                     20   \n",
       "\n",
       "   avg_time_spent  avg_transaction_value  avg_frequency_login_days  \\\n",
       "0          300.63               53005.25                      17.0   \n",
       "1          306.34               12838.38                      10.0   \n",
       "2          516.16               21027.00                      22.0   \n",
       "3           53.27               25239.56                       6.0   \n",
       "4          113.13               24483.66                      16.0   \n",
       "\n",
       "   points_in_wallet  used_special_discount  offer_application_preference  \\\n",
       "0            781.75                      1                             1   \n",
       "1            697.62                      1                             0   \n",
       "2            500.69                      0                             1   \n",
       "3            567.66                      0                             1   \n",
       "4            663.06                      0                             1   \n",
       "\n",
       "   past_complaint     complaint_status                  feedback  \\\n",
       "0               0       Not Applicable  Products always in Stock   \n",
       "1               1               Solved     Quality Customer Care   \n",
       "2               1  Solved in Follow-up              Poor Website   \n",
       "3               1             Unsolved              Poor Website   \n",
       "4               1               Solved              Poor Website   \n",
       "\n",
       "   churn_risk_score todays_date  customer_days  \n",
       "0                 1  2021-03-28         1319.0  \n",
       "1                 0  2021-03-28         1308.0  \n",
       "2                 4  2021-03-28         1598.0  \n",
       "3                 4  2021-03-28         1611.0  \n",
       "4                 4  2021-03-28         1293.0  "
      ]
     },
     "execution_count": 61,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def labelEncoding(df, onlyTransform: False, label_object = {}):\n",
    "    categorical_columns = [\n",
    "        'gender',\n",
    "        'joined_through_referral',\n",
    "        'used_special_discount',\n",
    "        'offer_application_preference',\n",
    "        'past_complaint'\n",
    "    ]\n",
    "    for col in categorical_columns:\n",
    "        if col in df.columns:\n",
    "            labelencoder = None\n",
    "            if onlyTransform is False:\n",
    "                labelencoder = LabelEncoder()\n",
    "                labelencoder.fit(df[col])\n",
    "                label_object[col] = labelencoder\n",
    "            else:\n",
    "                labelencoder = label_object[col]\n",
    "\n",
    "            df[col] = labelencoder.transform(df[col])\n",
    "    return df, label_object\n",
    "\n",
    "df, label_object = labelEncoding(df, onlyTransform= False, label_object= {})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "shaped-fisher",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 343
    },
    "id": "shaped-fisher",
    "outputId": "3db3bf99-070e-4699-bdb6-bb496a4001ce"
   },
   "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>customer_id</th>\n",
       "      <th>Name</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>security_no</th>\n",
       "      <th>region_category</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joining_date</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>referral_id</th>\n",
       "      <th>preferred_offer_types</th>\n",
       "      <th>medium_of_operation</th>\n",
       "      <th>internet_option</th>\n",
       "      <th>last_visit_time</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>complaint_status</th>\n",
       "      <th>feedback</th>\n",
       "      <th>churn_risk_score</th>\n",
       "      <th>todays_date</th>\n",
       "      <th>customer_days</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe4300490044003600300030003800</td>\n",
       "      <td>Pattie Morrisey</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>XW0DQ7H</td>\n",
       "      <td>Village</td>\n",
       "      <td>5</td>\n",
       "      <td>2017-08-17</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>?</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>16:08:02</td>\n",
       "      <td>17</td>\n",
       "      <td>300.63</td>\n",
       "      <td>53005.25</td>\n",
       "      <td>17.0</td>\n",
       "      <td>781.75</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Not Applicable</td>\n",
       "      <td>Products always in Stock</td>\n",
       "      <td>1</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1319.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440032003100300035003700</td>\n",
       "      <td>Traci Peery</td>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>5K0N3X1</td>\n",
       "      <td>City</td>\n",
       "      <td>4</td>\n",
       "      <td>2017-08-28</td>\n",
       "      <td>0</td>\n",
       "      <td>CID21329</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>12:38:13</td>\n",
       "      <td>16</td>\n",
       "      <td>306.34</td>\n",
       "      <td>12838.38</td>\n",
       "      <td>10.0</td>\n",
       "      <td>697.62</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Quality Customer Care</td>\n",
       "      <td>0</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1308.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe4300490044003100390032003600</td>\n",
       "      <td>Merideth Mcmeen</td>\n",
       "      <td>44</td>\n",
       "      <td>0</td>\n",
       "      <td>1F2TCL3</td>\n",
       "      <td>Town</td>\n",
       "      <td>0</td>\n",
       "      <td>2016-11-11</td>\n",
       "      <td>1</td>\n",
       "      <td>CID12313</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>22:53:21</td>\n",
       "      <td>14</td>\n",
       "      <td>516.16</td>\n",
       "      <td>21027.00</td>\n",
       "      <td>22.0</td>\n",
       "      <td>500.69</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Solved in Follow-up</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1598.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003000330031003600</td>\n",
       "      <td>Eufemia Cardwell</td>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>VJGJ33N</td>\n",
       "      <td>City</td>\n",
       "      <td>0</td>\n",
       "      <td>2016-10-29</td>\n",
       "      <td>1</td>\n",
       "      <td>CID3793</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:57:50</td>\n",
       "      <td>11</td>\n",
       "      <td>53.27</td>\n",
       "      <td>25239.56</td>\n",
       "      <td>6.0</td>\n",
       "      <td>567.66</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Unsolved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1611.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440031003900350030003600</td>\n",
       "      <td>Meghan Kosak</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>SVZXCWB</td>\n",
       "      <td>City</td>\n",
       "      <td>0</td>\n",
       "      <td>2017-09-12</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Credit/Debit Card Offers</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>15:46:44</td>\n",
       "      <td>20</td>\n",
       "      <td>113.13</td>\n",
       "      <td>24483.66</td>\n",
       "      <td>16.0</td>\n",
       "      <td>663.06</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Solved</td>\n",
       "      <td>Poor Website</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1293.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id              Name  age  gender  \\\n",
       "0      fffe4300490044003600300030003800   Pattie Morrisey   18       0   \n",
       "1  fffe43004900440032003100300035003700       Traci Peery   32       0   \n",
       "2      fffe4300490044003100390032003600   Merideth Mcmeen   44       0   \n",
       "3  fffe43004900440036003000330031003600  Eufemia Cardwell   37       1   \n",
       "4  fffe43004900440031003900350030003600      Meghan Kosak   31       0   \n",
       "\n",
       "  security_no region_category  membership_category joining_date  \\\n",
       "0     XW0DQ7H         Village                    5   2017-08-17   \n",
       "1     5K0N3X1            City                    4   2017-08-28   \n",
       "2     1F2TCL3            Town                    0   2016-11-11   \n",
       "3     VJGJ33N            City                    0   2016-10-29   \n",
       "4     SVZXCWB            City                    0   2017-09-12   \n",
       "\n",
       "   joined_through_referral referral_id     preferred_offer_types  \\\n",
       "0                        0    xxxxxxxx     Gift Vouchers/Coupons   \n",
       "1                        0    CID21329     Gift Vouchers/Coupons   \n",
       "2                        1    CID12313     Gift Vouchers/Coupons   \n",
       "3                        1     CID3793     Gift Vouchers/Coupons   \n",
       "4                        0    xxxxxxxx  Credit/Debit Card Offers   \n",
       "\n",
       "  medium_of_operation internet_option last_visit_time  days_since_last_login  \\\n",
       "0                   ?           Wi-Fi        16:08:02                     17   \n",
       "1             Desktop     Mobile_Data        12:38:13                     16   \n",
       "2             Desktop           Wi-Fi        22:53:21                     14   \n",
       "3             Desktop     Mobile_Data        15:57:50                     11   \n",
       "4          Smartphone     Mobile_Data        15:46:44                     20   \n",
       "\n",
       "   avg_time_spent  avg_transaction_value  avg_frequency_login_days  \\\n",
       "0          300.63               53005.25                      17.0   \n",
       "1          306.34               12838.38                      10.0   \n",
       "2          516.16               21027.00                      22.0   \n",
       "3           53.27               25239.56                       6.0   \n",
       "4          113.13               24483.66                      16.0   \n",
       "\n",
       "   points_in_wallet  used_special_discount  offer_application_preference  \\\n",
       "0            781.75                      1                             1   \n",
       "1            697.62                      1                             0   \n",
       "2            500.69                      0                             1   \n",
       "3            567.66                      0                             1   \n",
       "4            663.06                      0                             1   \n",
       "\n",
       "   past_complaint     complaint_status                  feedback  \\\n",
       "0               0       Not Applicable  Products always in Stock   \n",
       "1               1               Solved     Quality Customer Care   \n",
       "2               1  Solved in Follow-up              Poor Website   \n",
       "3               1             Unsolved              Poor Website   \n",
       "4               1               Solved              Poor Website   \n",
       "\n",
       "   churn_risk_score todays_date  customer_days  \n",
       "0                 1  2021-03-28         1319.0  \n",
       "1                 0  2021-03-28         1308.0  \n",
       "2                 4  2021-03-28         1598.0  \n",
       "3                 4  2021-03-28         1611.0  \n",
       "4                 4  2021-03-28         1293.0  "
      ]
     },
     "execution_count": 62,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def encodeMembership(df):\n",
    "    \n",
    "    cleanup_nums = {\n",
    "                    \"membership_category\":{\n",
    "                        \"No Membership\":0,\n",
    "                        \"Basic Membership\":1,\n",
    "                        \"Gold Membership\":2,\n",
    "                        \"Silver Membership\":3,\n",
    "                        \"Premium Membership\":4,\n",
    "                        \"Platinum Membership\":5\n",
    "                    }\n",
    "                   }\n",
    "    \n",
    "    df = df.replace(cleanup_nums)\n",
    "    \n",
    "    return df\n",
    "\n",
    "df = encodeMembership(df)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "functional-mauritius",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 309
    },
    "id": "functional-mauritius",
    "outputId": "488ef99f-d084-4967-a055-6b0466f57e05"
   },
   "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>customer_id</th>\n",
       "      <th>Name</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>security_no</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joining_date</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>referral_id</th>\n",
       "      <th>last_visit_time</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>churn_risk_score</th>\n",
       "      <th>todays_date</th>\n",
       "      <th>customer_days</th>\n",
       "      <th>region_category_0</th>\n",
       "      <th>region_category_1</th>\n",
       "      <th>region_category_2</th>\n",
       "      <th>preferred_offer_types_0</th>\n",
       "      <th>preferred_offer_types_1</th>\n",
       "      <th>preferred_offer_types_2</th>\n",
       "      <th>medium_of_operation_0</th>\n",
       "      <th>medium_of_operation_1</th>\n",
       "      <th>medium_of_operation_2</th>\n",
       "      <th>medium_of_operation_3</th>\n",
       "      <th>internet_option_0</th>\n",
       "      <th>internet_option_1</th>\n",
       "      <th>internet_option_2</th>\n",
       "      <th>complaint_status_0</th>\n",
       "      <th>complaint_status_1</th>\n",
       "      <th>complaint_status_2</th>\n",
       "      <th>complaint_status_3</th>\n",
       "      <th>complaint_status_4</th>\n",
       "      <th>feedback_0</th>\n",
       "      <th>feedback_1</th>\n",
       "      <th>feedback_2</th>\n",
       "      <th>feedback_3</th>\n",
       "      <th>feedback_4</th>\n",
       "      <th>feedback_5</th>\n",
       "      <th>feedback_6</th>\n",
       "      <th>feedback_7</th>\n",
       "      <th>feedback_8</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe4300490044003600300030003800</td>\n",
       "      <td>Pattie Morrisey</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>XW0DQ7H</td>\n",
       "      <td>5</td>\n",
       "      <td>2017-08-17</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>16:08:02</td>\n",
       "      <td>17</td>\n",
       "      <td>300.63</td>\n",
       "      <td>53005.25</td>\n",
       "      <td>17.0</td>\n",
       "      <td>781.75</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1319.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440032003100300035003700</td>\n",
       "      <td>Traci Peery</td>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>5K0N3X1</td>\n",
       "      <td>4</td>\n",
       "      <td>2017-08-28</td>\n",
       "      <td>0</td>\n",
       "      <td>CID21329</td>\n",
       "      <td>12:38:13</td>\n",
       "      <td>16</td>\n",
       "      <td>306.34</td>\n",
       "      <td>12838.38</td>\n",
       "      <td>10.0</td>\n",
       "      <td>697.62</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1308.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe4300490044003100390032003600</td>\n",
       "      <td>Merideth Mcmeen</td>\n",
       "      <td>44</td>\n",
       "      <td>0</td>\n",
       "      <td>1F2TCL3</td>\n",
       "      <td>0</td>\n",
       "      <td>2016-11-11</td>\n",
       "      <td>1</td>\n",
       "      <td>CID12313</td>\n",
       "      <td>22:53:21</td>\n",
       "      <td>14</td>\n",
       "      <td>516.16</td>\n",
       "      <td>21027.00</td>\n",
       "      <td>22.0</td>\n",
       "      <td>500.69</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1598.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003000330031003600</td>\n",
       "      <td>Eufemia Cardwell</td>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>VJGJ33N</td>\n",
       "      <td>0</td>\n",
       "      <td>2016-10-29</td>\n",
       "      <td>1</td>\n",
       "      <td>CID3793</td>\n",
       "      <td>15:57:50</td>\n",
       "      <td>11</td>\n",
       "      <td>53.27</td>\n",
       "      <td>25239.56</td>\n",
       "      <td>6.0</td>\n",
       "      <td>567.66</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1611.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440031003900350030003600</td>\n",
       "      <td>Meghan Kosak</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>SVZXCWB</td>\n",
       "      <td>0</td>\n",
       "      <td>2017-09-12</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>15:46:44</td>\n",
       "      <td>20</td>\n",
       "      <td>113.13</td>\n",
       "      <td>24483.66</td>\n",
       "      <td>16.0</td>\n",
       "      <td>663.06</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1293.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id              Name  age  gender  \\\n",
       "0      fffe4300490044003600300030003800   Pattie Morrisey   18       0   \n",
       "1  fffe43004900440032003100300035003700       Traci Peery   32       0   \n",
       "2      fffe4300490044003100390032003600   Merideth Mcmeen   44       0   \n",
       "3  fffe43004900440036003000330031003600  Eufemia Cardwell   37       1   \n",
       "4  fffe43004900440031003900350030003600      Meghan Kosak   31       0   \n",
       "\n",
       "  security_no  membership_category joining_date  joined_through_referral  \\\n",
       "0     XW0DQ7H                    5   2017-08-17                        0   \n",
       "1     5K0N3X1                    4   2017-08-28                        0   \n",
       "2     1F2TCL3                    0   2016-11-11                        1   \n",
       "3     VJGJ33N                    0   2016-10-29                        1   \n",
       "4     SVZXCWB                    0   2017-09-12                        0   \n",
       "\n",
       "  referral_id last_visit_time  days_since_last_login  avg_time_spent  \\\n",
       "0    xxxxxxxx        16:08:02                     17          300.63   \n",
       "1    CID21329        12:38:13                     16          306.34   \n",
       "2    CID12313        22:53:21                     14          516.16   \n",
       "3     CID3793        15:57:50                     11           53.27   \n",
       "4    xxxxxxxx        15:46:44                     20          113.13   \n",
       "\n",
       "   avg_transaction_value  avg_frequency_login_days  points_in_wallet  \\\n",
       "0               53005.25                      17.0            781.75   \n",
       "1               12838.38                      10.0            697.62   \n",
       "2               21027.00                      22.0            500.69   \n",
       "3               25239.56                       6.0            567.66   \n",
       "4               24483.66                      16.0            663.06   \n",
       "\n",
       "   used_special_discount  offer_application_preference  past_complaint  \\\n",
       "0                      1                             1               0   \n",
       "1                      1                             0               1   \n",
       "2                      0                             1               1   \n",
       "3                      0                             1               1   \n",
       "4                      0                             1               1   \n",
       "\n",
       "   churn_risk_score todays_date  customer_days  region_category_0  \\\n",
       "0                 1  2021-03-28         1319.0                0.0   \n",
       "1                 0  2021-03-28         1308.0                1.0   \n",
       "2                 4  2021-03-28         1598.0                0.0   \n",
       "3                 4  2021-03-28         1611.0                1.0   \n",
       "4                 4  2021-03-28         1293.0                1.0   \n",
       "\n",
       "   region_category_1  region_category_2  preferred_offer_types_0  \\\n",
       "0                0.0                1.0                      0.0   \n",
       "1                0.0                0.0                      0.0   \n",
       "2                1.0                0.0                      0.0   \n",
       "3                0.0                0.0                      0.0   \n",
       "4                0.0                0.0                      1.0   \n",
       "\n",
       "   preferred_offer_types_1  preferred_offer_types_2  medium_of_operation_0  \\\n",
       "0                      1.0                      0.0                    1.0   \n",
       "1                      1.0                      0.0                    0.0   \n",
       "2                      1.0                      0.0                    0.0   \n",
       "3                      1.0                      0.0                    0.0   \n",
       "4                      0.0                      0.0                    0.0   \n",
       "\n",
       "   medium_of_operation_1  medium_of_operation_2  medium_of_operation_3  \\\n",
       "0                    0.0                    0.0                    0.0   \n",
       "1                    0.0                    1.0                    0.0   \n",
       "2                    0.0                    1.0                    0.0   \n",
       "3                    0.0                    1.0                    0.0   \n",
       "4                    0.0                    0.0                    1.0   \n",
       "\n",
       "   internet_option_0  internet_option_1  internet_option_2  \\\n",
       "0                0.0                0.0                1.0   \n",
       "1                0.0                1.0                0.0   \n",
       "2                0.0                0.0                1.0   \n",
       "3                0.0                1.0                0.0   \n",
       "4                0.0                1.0                0.0   \n",
       "\n",
       "   complaint_status_0  complaint_status_1  complaint_status_2  \\\n",
       "0                 0.0                 1.0                 0.0   \n",
       "1                 0.0                 0.0                 1.0   \n",
       "2                 0.0                 0.0                 0.0   \n",
       "3                 0.0                 0.0                 0.0   \n",
       "4                 0.0                 0.0                 1.0   \n",
       "\n",
       "   complaint_status_3  complaint_status_4  feedback_0  feedback_1  feedback_2  \\\n",
       "0                 0.0                 0.0         0.0         0.0         0.0   \n",
       "1                 0.0                 0.0         0.0         0.0         0.0   \n",
       "2                 1.0                 0.0         0.0         0.0         0.0   \n",
       "3                 0.0                 1.0         0.0         0.0         0.0   \n",
       "4                 0.0                 0.0         0.0         0.0         0.0   \n",
       "\n",
       "   feedback_3  feedback_4  feedback_5  feedback_6  feedback_7  feedback_8  \n",
       "0         0.0         1.0         0.0         0.0         0.0         0.0  \n",
       "1         0.0         0.0         1.0         0.0         0.0         0.0  \n",
       "2         1.0         0.0         0.0         0.0         0.0         0.0  \n",
       "3         1.0         0.0         0.0         0.0         0.0         0.0  \n",
       "4         1.0         0.0         0.0         0.0         0.0         0.0  "
      ]
     },
     "execution_count": 63,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def oneHotEncoding(df, onlyTransform=False, one_hot_object = {}):\n",
    "    categorical_columns = [\n",
    "        'region_category',\n",
    "        'preferred_offer_types',\n",
    "        'medium_of_operation',\n",
    "        'internet_option',\n",
    "        'complaint_status',\n",
    "        'feedback'\n",
    "    ]\n",
    "    for col in categorical_columns:\n",
    "        \n",
    "        col_data  = df[col].values.reshape(-1,1)\n",
    "        \n",
    "        if onlyTransform is False:\n",
    "            onehot_encoder = OneHotEncoder()\n",
    "            onehot_encoder = onehot_encoder.fit(col_data)\n",
    "            one_hot_object[col] = onehot_encoder\n",
    "        \n",
    "        onehot_encoded = one_hot_object[col].transform(col_data).toarray()\n",
    "        columns_list = []\n",
    "        for i in range(onehot_encoded.shape[1]):\n",
    "            columns_list.append(col+\"_\"+str(int(i)))\n",
    "        dfOneHot = pd.DataFrame(onehot_encoded, columns = columns_list) \n",
    "        df = pd.concat([df, dfOneHot], axis=1)\n",
    "        \n",
    "\n",
    "    df = df.drop(categorical_columns,axis=1)\n",
    "    return df, one_hot_object\n",
    "\n",
    "\n",
    "df, one_hot_object = oneHotEncoding(df, onlyTransform=False, one_hot_object = {})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "yellow-glucose",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "id": "yellow-glucose",
    "outputId": "02795ce9-6816-4e51-a50b-baaa3847e38b"
   },
   "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>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>churn_risk_score</th>\n",
       "      <th>customer_days</th>\n",
       "      <th>region_category_0</th>\n",
       "      <th>region_category_1</th>\n",
       "      <th>region_category_2</th>\n",
       "      <th>preferred_offer_types_0</th>\n",
       "      <th>preferred_offer_types_1</th>\n",
       "      <th>preferred_offer_types_2</th>\n",
       "      <th>medium_of_operation_0</th>\n",
       "      <th>medium_of_operation_1</th>\n",
       "      <th>medium_of_operation_2</th>\n",
       "      <th>medium_of_operation_3</th>\n",
       "      <th>internet_option_0</th>\n",
       "      <th>internet_option_1</th>\n",
       "      <th>internet_option_2</th>\n",
       "      <th>complaint_status_0</th>\n",
       "      <th>complaint_status_1</th>\n",
       "      <th>complaint_status_2</th>\n",
       "      <th>complaint_status_3</th>\n",
       "      <th>complaint_status_4</th>\n",
       "      <th>feedback_0</th>\n",
       "      <th>feedback_1</th>\n",
       "      <th>feedback_2</th>\n",
       "      <th>feedback_3</th>\n",
       "      <th>feedback_4</th>\n",
       "      <th>feedback_5</th>\n",
       "      <th>feedback_6</th>\n",
       "      <th>feedback_7</th>\n",
       "      <th>feedback_8</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>17</td>\n",
       "      <td>300.63</td>\n",
       "      <td>53005.25</td>\n",
       "      <td>17.0</td>\n",
       "      <td>781.75</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1319.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>16</td>\n",
       "      <td>306.34</td>\n",
       "      <td>12838.38</td>\n",
       "      <td>10.0</td>\n",
       "      <td>697.62</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1308.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>44</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>14</td>\n",
       "      <td>516.16</td>\n",
       "      <td>21027.00</td>\n",
       "      <td>22.0</td>\n",
       "      <td>500.69</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1598.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>37</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>11</td>\n",
       "      <td>53.27</td>\n",
       "      <td>25239.56</td>\n",
       "      <td>6.0</td>\n",
       "      <td>567.66</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1611.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>113.13</td>\n",
       "      <td>24483.66</td>\n",
       "      <td>16.0</td>\n",
       "      <td>663.06</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1293.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  gender  membership_category  joined_through_referral  \\\n",
       "0   18       0                    5                        0   \n",
       "1   32       0                    4                        0   \n",
       "2   44       0                    0                        1   \n",
       "3   37       1                    0                        1   \n",
       "4   31       0                    0                        0   \n",
       "\n",
       "   days_since_last_login  avg_time_spent  avg_transaction_value  \\\n",
       "0                     17          300.63               53005.25   \n",
       "1                     16          306.34               12838.38   \n",
       "2                     14          516.16               21027.00   \n",
       "3                     11           53.27               25239.56   \n",
       "4                     20          113.13               24483.66   \n",
       "\n",
       "   avg_frequency_login_days  points_in_wallet  used_special_discount  \\\n",
       "0                      17.0            781.75                      1   \n",
       "1                      10.0            697.62                      1   \n",
       "2                      22.0            500.69                      0   \n",
       "3                       6.0            567.66                      0   \n",
       "4                      16.0            663.06                      0   \n",
       "\n",
       "   offer_application_preference  past_complaint  churn_risk_score  \\\n",
       "0                             1               0                 1   \n",
       "1                             0               1                 0   \n",
       "2                             1               1                 4   \n",
       "3                             1               1                 4   \n",
       "4                             1               1                 4   \n",
       "\n",
       "   customer_days  region_category_0  region_category_1  region_category_2  \\\n",
       "0         1319.0                0.0                0.0                1.0   \n",
       "1         1308.0                1.0                0.0                0.0   \n",
       "2         1598.0                0.0                1.0                0.0   \n",
       "3         1611.0                1.0                0.0                0.0   \n",
       "4         1293.0                1.0                0.0                0.0   \n",
       "\n",
       "   preferred_offer_types_0  preferred_offer_types_1  preferred_offer_types_2  \\\n",
       "0                      0.0                      1.0                      0.0   \n",
       "1                      0.0                      1.0                      0.0   \n",
       "2                      0.0                      1.0                      0.0   \n",
       "3                      0.0                      1.0                      0.0   \n",
       "4                      1.0                      0.0                      0.0   \n",
       "\n",
       "   medium_of_operation_0  medium_of_operation_1  medium_of_operation_2  \\\n",
       "0                    1.0                    0.0                    0.0   \n",
       "1                    0.0                    0.0                    1.0   \n",
       "2                    0.0                    0.0                    1.0   \n",
       "3                    0.0                    0.0                    1.0   \n",
       "4                    0.0                    0.0                    0.0   \n",
       "\n",
       "   medium_of_operation_3  internet_option_0  internet_option_1  \\\n",
       "0                    0.0                0.0                0.0   \n",
       "1                    0.0                0.0                1.0   \n",
       "2                    0.0                0.0                0.0   \n",
       "3                    0.0                0.0                1.0   \n",
       "4                    1.0                0.0                1.0   \n",
       "\n",
       "   internet_option_2  complaint_status_0  complaint_status_1  \\\n",
       "0                1.0                 0.0                 1.0   \n",
       "1                0.0                 0.0                 0.0   \n",
       "2                1.0                 0.0                 0.0   \n",
       "3                0.0                 0.0                 0.0   \n",
       "4                0.0                 0.0                 0.0   \n",
       "\n",
       "   complaint_status_2  complaint_status_3  complaint_status_4  feedback_0  \\\n",
       "0                 0.0                 0.0                 0.0         0.0   \n",
       "1                 1.0                 0.0                 0.0         0.0   \n",
       "2                 0.0                 1.0                 0.0         0.0   \n",
       "3                 0.0                 0.0                 1.0         0.0   \n",
       "4                 1.0                 0.0                 0.0         0.0   \n",
       "\n",
       "   feedback_1  feedback_2  feedback_3  feedback_4  feedback_5  feedback_6  \\\n",
       "0         0.0         0.0         0.0         1.0         0.0         0.0   \n",
       "1         0.0         0.0         0.0         0.0         1.0         0.0   \n",
       "2         0.0         0.0         1.0         0.0         0.0         0.0   \n",
       "3         0.0         0.0         1.0         0.0         0.0         0.0   \n",
       "4         0.0         0.0         1.0         0.0         0.0         0.0   \n",
       "\n",
       "   feedback_7  feedback_8  \n",
       "0         0.0         0.0  \n",
       "1         0.0         0.0  \n",
       "2         0.0         0.0  \n",
       "3         0.0         0.0  \n",
       "4         0.0         0.0  "
      ]
     },
     "execution_count": 64,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def removeRedundantColumns(df):\n",
    "    \n",
    "    redundant_columns = ['customer_id','Name','security_no','joining_date','referral_id','last_visit_time','todays_date']\n",
    "\n",
    "    df = df.drop(redundant_columns,axis=1)\n",
    "    \n",
    "    return df\n",
    "\n",
    "df = removeRedundantColumns(df)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "working-wireless",
   "metadata": {
    "id": "working-wireless"
   },
   "outputs": [],
   "source": [
    "df = df.sample(frac=1).reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "controlling-coach",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "controlling-coach",
    "outputId": "2a58faaf-df83-4f54-e548-767cf8f502f3"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(36992, 40)\n",
      "(36992, 1)\n"
     ]
    }
   ],
   "source": [
    "from keras.utils import np_utils\n",
    "y = pd.DataFrame(df[\"churn_risk_score\"])\n",
    "df = df.drop(\"churn_risk_score\", axis=1)\n",
    "\n",
    "X = pd.DataFrame(df)\n",
    "print(X.shape)\n",
    "print(y.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "blessed-lewis",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "blessed-lewis",
    "outputId": "82eef8ff-a8c6-4f37-8efd-34946587a71f"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(44675, 40) (44675,)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
      "  y = column_or_1d(y, warn=True)\n",
      "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
      "  warnings.warn(msg, category=FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "from imblearn.over_sampling import SMOTE\n",
    "smote = SMOTE('minority')\n",
    "X_sm,y_sm = smote.fit_resample(X=X,y=y)\n",
    "print(X_sm.shape,y_sm.shape)\n",
    "\n",
    "X = X_sm\n",
    "y = y_sm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "id": "liked-parallel",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "liked-parallel",
    "outputId": "77acc819-6a11-45cd-e382-fbc41bc638dc"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(44675, 40)\n",
      "(44675,)\n",
      "(8935, 40)\n",
      "(8935,)\n"
     ]
    }
   ],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.2, stratify=y,shuffle=True)\n",
    "\n",
    "X_train = X\n",
    "y_train = y\n",
    "\n",
    "print(X_train.shape)\n",
    "print(y_train.shape)\n",
    "print(X_test.shape)\n",
    "print(y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "sound-statistics",
   "metadata": {
    "id": "sound-statistics"
   },
   "outputs": [],
   "source": [
    "\n",
    "from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler\n",
    "\n",
    "scalerX = StandardScaler()\n",
    "# scalerX = RobustScaler()\n",
    "# scalerX = MinMaxScaler()\n",
    "scalerX = scalerX.fit(X_train)\n",
    "X_train = scalerX.transform(X_train)\n",
    "X_train = pd.DataFrame(X_train)\n",
    "\n",
    "X_test = scalerX.transform(X_test)\n",
    "X_test = pd.DataFrame(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "black-agent",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "black-agent",
    "outputId": "4138f7c7-52a5-4bc9-f5dc-820b678790cc"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "XGBClassifier(base_score=0.5, booster='gbtree', clf__learning_rate=0.01,\n",
       "              clf__max_depth=3, clf__n_estimators=250, colsample_bylevel=1,\n",
       "              colsample_bynode=1, colsample_bytree=1, gamma=0,\n",
       "              learning_rate=0.1, max_delta_step=0, max_depth=3,\n",
       "              min_child_weight=1, missing=None, n_estimators=1000, n_jobs=1,\n",
       "              nthread=None, objective='multi:softprob', random_state=0,\n",
       "              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n",
       "              silent=None, subsample=1, verbosity=1)"
      ]
     },
     "execution_count": 70,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from xgboost import XGBClassifier\n",
    "model = XGBClassifier(base_score=0.5, booster='gbtree', clf__learning_rate=0.01,\n",
    "              clf__max_depth=3, clf__n_estimators=250, colsample_bylevel=1,\n",
    "              colsample_bynode=1, colsample_bytree=1, gamma=0,\n",
    "              learning_rate=0.1, max_delta_step=0, max_depth=3,\n",
    "              min_child_weight=1, missing=None, n_estimators=1000, n_jobs=1,\n",
    "              nthread=None, objective='multi:softprob', random_state=0,\n",
    "              reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,\n",
    "              silent=None, subsample=1, verbosity=1)\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "eleven-pilot",
   "metadata": {
    "id": "eleven-pilot"
   },
   "outputs": [],
   "source": [
    "# from xgboost import XGBClassifier\n",
    "# from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "# xgb = XGBClassifier()\n",
    "\n",
    "# search_space = [\n",
    "#   {\n",
    "#     'clf__n_estimators': [250, 500,1000],\n",
    "#     'clf__learning_rate': [0.01,0.3, 0.5],\n",
    "#     'clf__max_depth': range(3, 8),\n",
    "#   }\n",
    "# ]\n",
    "\n",
    "# grid = GridSearchCV(\n",
    "#     estimator=xgb,\n",
    "#     param_grid=search_space,\n",
    "#     verbose=4,\n",
    "#     n_jobs=-1\n",
    "# )\n",
    "\n",
    "# model = grid.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "lGPEszb5Pxye",
   "metadata": {
    "id": "lGPEszb5Pxye"
   },
   "outputs": [],
   "source": [
    "# grid.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "advisory-simulation",
   "metadata": {
    "id": "advisory-simulation"
   },
   "outputs": [],
   "source": [
    "prediction = model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "bulgarian-debate",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "bulgarian-debate",
    "outputId": "ace21d53-8bee-47a4-b117-552ffb3869c1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2 1 3 ... 3 4 1]\n",
      "[2 1 3 ... 3 4 1]\n"
     ]
    }
   ],
   "source": [
    "y_label = y_test\n",
    "predict_label = prediction\n",
    "\n",
    "print(y_label)\n",
    "print(predict_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "original-flexibility",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "original-flexibility",
    "outputId": "cd8c8b4b-af45-4ba8-f96a-2086e1670266"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sk_accuracy_score : 88.37157246782317\n",
      "sk_f1_score : 86.64826466352518\n",
      "sk_precision_score : 88.53620756606941\n",
      "sk_recall_score : 85.79792457954755\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score as sk_accuracy_score\n",
    "from sklearn.metrics import f1_score as sk_f1_score\n",
    "from sklearn.metrics import precision_score as sk_precision_score\n",
    "from sklearn.metrics import recall_score as sk_recall_score\n",
    "from sklearn.metrics import confusion_matrix as sk_confusion_matrix\n",
    "\n",
    "print(\"sk_accuracy_score :\",100*sk_accuracy_score(y_label, predict_label))\n",
    "print(\"sk_f1_score :\",100*sk_f1_score(y_label, predict_label,average=\"macro\"))\n",
    "print(\"sk_precision_score :\", 100*sk_precision_score(y_label, predict_label,average=\"macro\"))\n",
    "print(\"sk_recall_score :\" ,100*sk_recall_score(y_label, predict_label,average=\"macro\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "abstract-china",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 343
    },
    "id": "abstract-china",
    "outputId": "a926349c-e659-4797-e482-38351a7792c5"
   },
   "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>customer_id</th>\n",
       "      <th>Name</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>security_no</th>\n",
       "      <th>region_category</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joining_date</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>referral_id</th>\n",
       "      <th>preferred_offer_types</th>\n",
       "      <th>medium_of_operation</th>\n",
       "      <th>internet_option</th>\n",
       "      <th>last_visit_time</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>complaint_status</th>\n",
       "      <th>feedback</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe43004900440031003700300030003400</td>\n",
       "      <td>Alethia Meints</td>\n",
       "      <td>50</td>\n",
       "      <td>F</td>\n",
       "      <td>OQJ1XAY</td>\n",
       "      <td>Village</td>\n",
       "      <td>Premium Membership</td>\n",
       "      <td>2015-11-02</td>\n",
       "      <td>No</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Without Offers</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>Wi-Fi</td>\n",
       "      <td>07:19:30</td>\n",
       "      <td>12</td>\n",
       "      <td>386.26</td>\n",
       "      <td>40721.44</td>\n",
       "      <td>7.0</td>\n",
       "      <td>733.830000</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Not Applicable</td>\n",
       "      <td>Poor Product Quality</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440031003900370037003300</td>\n",
       "      <td>Ming Lopez</td>\n",
       "      <td>41</td>\n",
       "      <td>M</td>\n",
       "      <td>OUQRPKO</td>\n",
       "      <td>Village</td>\n",
       "      <td>Gold Membership</td>\n",
       "      <td>2016-03-01</td>\n",
       "      <td>No</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Without Offers</td>\n",
       "      <td>Desktop</td>\n",
       "      <td>Fiber_Optic</td>\n",
       "      <td>22:21:16</td>\n",
       "      <td>11</td>\n",
       "      <td>37.80</td>\n",
       "      <td>9644.40</td>\n",
       "      <td>9.0</td>\n",
       "      <td>726.000000</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Not Applicable</td>\n",
       "      <td>Poor Website</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe43004900440034003800360037003000</td>\n",
       "      <td>Carina Flannigan</td>\n",
       "      <td>31</td>\n",
       "      <td>F</td>\n",
       "      <td>02J2RE7</td>\n",
       "      <td>Town</td>\n",
       "      <td>Silver Membership</td>\n",
       "      <td>2017-03-03</td>\n",
       "      <td>No</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>Gift Vouchers/Coupons</td>\n",
       "      <td>Both</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>16:40:39</td>\n",
       "      <td>18</td>\n",
       "      <td>215.36</td>\n",
       "      <td>3693.25</td>\n",
       "      <td>21.0</td>\n",
       "      <td>713.780000</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved in Follow-up</td>\n",
       "      <td>No reason specified</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003200370033003400</td>\n",
       "      <td>Kyung Wanner</td>\n",
       "      <td>64</td>\n",
       "      <td>M</td>\n",
       "      <td>5YEQIF1</td>\n",
       "      <td>Town</td>\n",
       "      <td>Silver Membership</td>\n",
       "      <td>2017-08-18</td>\n",
       "      <td>Yes</td>\n",
       "      <td>CID8941</td>\n",
       "      <td>Credit/Debit Card Offers</td>\n",
       "      <td>?</td>\n",
       "      <td>Fiber_Optic</td>\n",
       "      <td>14:56:17</td>\n",
       "      <td>-999</td>\n",
       "      <td>44.57</td>\n",
       "      <td>36809.56</td>\n",
       "      <td>11.0</td>\n",
       "      <td>744.970000</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>No Information Available</td>\n",
       "      <td>Too many ads</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440035003000370031003900</td>\n",
       "      <td>Enola Gatto</td>\n",
       "      <td>16</td>\n",
       "      <td>F</td>\n",
       "      <td>100RYB5</td>\n",
       "      <td>Town</td>\n",
       "      <td>No Membership</td>\n",
       "      <td>2015-05-05</td>\n",
       "      <td>Yes</td>\n",
       "      <td>CID5690</td>\n",
       "      <td>Without Offers</td>\n",
       "      <td>Smartphone</td>\n",
       "      <td>Mobile_Data</td>\n",
       "      <td>02:57:53</td>\n",
       "      <td>6</td>\n",
       "      <td>349.88</td>\n",
       "      <td>40675.86</td>\n",
       "      <td>8.0</td>\n",
       "      <td>299.048351</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Yes</td>\n",
       "      <td>Solved in Follow-up</td>\n",
       "      <td>Poor Website</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id              Name  age gender  \\\n",
       "0  fffe43004900440031003700300030003400    Alethia Meints   50      F   \n",
       "1  fffe43004900440031003900370037003300        Ming Lopez   41      M   \n",
       "2  fffe43004900440034003800360037003000  Carina Flannigan   31      F   \n",
       "3  fffe43004900440036003200370033003400      Kyung Wanner   64      M   \n",
       "4  fffe43004900440035003000370031003900       Enola Gatto   16      F   \n",
       "\n",
       "  security_no region_category membership_category joining_date  \\\n",
       "0     OQJ1XAY         Village  Premium Membership   2015-11-02   \n",
       "1     OUQRPKO         Village     Gold Membership   2016-03-01   \n",
       "2     02J2RE7            Town   Silver Membership   2017-03-03   \n",
       "3     5YEQIF1            Town   Silver Membership   2017-08-18   \n",
       "4     100RYB5            Town       No Membership   2015-05-05   \n",
       "\n",
       "  joined_through_referral referral_id     preferred_offer_types  \\\n",
       "0                      No    xxxxxxxx            Without Offers   \n",
       "1                      No    xxxxxxxx            Without Offers   \n",
       "2                      No    xxxxxxxx     Gift Vouchers/Coupons   \n",
       "3                     Yes     CID8941  Credit/Debit Card Offers   \n",
       "4                     Yes     CID5690            Without Offers   \n",
       "\n",
       "  medium_of_operation internet_option last_visit_time  days_since_last_login  \\\n",
       "0          Smartphone           Wi-Fi        07:19:30                     12   \n",
       "1             Desktop     Fiber_Optic        22:21:16                     11   \n",
       "2                Both     Mobile_Data        16:40:39                     18   \n",
       "3                   ?     Fiber_Optic        14:56:17                   -999   \n",
       "4          Smartphone     Mobile_Data        02:57:53                      6   \n",
       "\n",
       "   avg_time_spent  avg_transaction_value avg_frequency_login_days  \\\n",
       "0          386.26               40721.44                      7.0   \n",
       "1           37.80                9644.40                      9.0   \n",
       "2          215.36                3693.25                     21.0   \n",
       "3           44.57               36809.56                     11.0   \n",
       "4          349.88               40675.86                      8.0   \n",
       "\n",
       "   points_in_wallet used_special_discount offer_application_preference  \\\n",
       "0        733.830000                   Yes                           No   \n",
       "1        726.000000                   Yes                           No   \n",
       "2        713.780000                   Yes                           No   \n",
       "3        744.970000                   Yes                           No   \n",
       "4        299.048351                    No                          Yes   \n",
       "\n",
       "  past_complaint          complaint_status              feedback  \n",
       "0             No            Not Applicable  Poor Product Quality  \n",
       "1             No            Not Applicable          Poor Website  \n",
       "2            Yes       Solved in Follow-up   No reason specified  \n",
       "3            Yes  No Information Available          Too many ads  \n",
       "4            Yes       Solved in Follow-up          Poor Website  "
      ]
     },
     "execution_count": 76,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test = pd.read_csv(\"./drive/MyDrive/dataset/test.csv\")\n",
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "id": "underlying-output",
   "metadata": {
    "id": "underlying-output"
   },
   "outputs": [],
   "source": [
    "df_test =  handleMissingValues(df_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "id": "handled-martial",
   "metadata": {
    "id": "handled-martial"
   },
   "outputs": [],
   "source": [
    "df_test = handleExtraFeatures(df_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "id": "raised-stack",
   "metadata": {
    "id": "raised-stack"
   },
   "outputs": [],
   "source": [
    "df_test, label_object = labelEncoding(df_test, onlyTransform= True, label_object= label_object)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "enhanced-dubai",
   "metadata": {
    "id": "enhanced-dubai"
   },
   "outputs": [],
   "source": [
    "df_test = encodeMembership(df_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "id": "functional-silicon",
   "metadata": {
    "id": "functional-silicon"
   },
   "outputs": [],
   "source": [
    "df_test, one_hot_object = oneHotEncoding(df_test, onlyTransform=True, one_hot_object = one_hot_object)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "id": "acoustic-identifier",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 309
    },
    "id": "acoustic-identifier",
    "outputId": "0b634448-4554-4701-979a-2154fc12e268"
   },
   "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>customer_id</th>\n",
       "      <th>Name</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>security_no</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joining_date</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>referral_id</th>\n",
       "      <th>last_visit_time</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>todays_date</th>\n",
       "      <th>customer_days</th>\n",
       "      <th>region_category_0</th>\n",
       "      <th>region_category_1</th>\n",
       "      <th>region_category_2</th>\n",
       "      <th>preferred_offer_types_0</th>\n",
       "      <th>preferred_offer_types_1</th>\n",
       "      <th>preferred_offer_types_2</th>\n",
       "      <th>medium_of_operation_0</th>\n",
       "      <th>medium_of_operation_1</th>\n",
       "      <th>medium_of_operation_2</th>\n",
       "      <th>medium_of_operation_3</th>\n",
       "      <th>internet_option_0</th>\n",
       "      <th>internet_option_1</th>\n",
       "      <th>internet_option_2</th>\n",
       "      <th>complaint_status_0</th>\n",
       "      <th>complaint_status_1</th>\n",
       "      <th>complaint_status_2</th>\n",
       "      <th>complaint_status_3</th>\n",
       "      <th>complaint_status_4</th>\n",
       "      <th>feedback_0</th>\n",
       "      <th>feedback_1</th>\n",
       "      <th>feedback_2</th>\n",
       "      <th>feedback_3</th>\n",
       "      <th>feedback_4</th>\n",
       "      <th>feedback_5</th>\n",
       "      <th>feedback_6</th>\n",
       "      <th>feedback_7</th>\n",
       "      <th>feedback_8</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe43004900440031003700300030003400</td>\n",
       "      <td>Alethia Meints</td>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "      <td>OQJ1XAY</td>\n",
       "      <td>4</td>\n",
       "      <td>2015-11-02</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>07:19:30</td>\n",
       "      <td>12</td>\n",
       "      <td>386.26</td>\n",
       "      <td>40721.44</td>\n",
       "      <td>7.0</td>\n",
       "      <td>733.830000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1973.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440031003900370037003300</td>\n",
       "      <td>Ming Lopez</td>\n",
       "      <td>41</td>\n",
       "      <td>1</td>\n",
       "      <td>OUQRPKO</td>\n",
       "      <td>2</td>\n",
       "      <td>2016-03-01</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>22:21:16</td>\n",
       "      <td>11</td>\n",
       "      <td>37.80</td>\n",
       "      <td>9644.40</td>\n",
       "      <td>9.0</td>\n",
       "      <td>726.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1853.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe43004900440034003800360037003000</td>\n",
       "      <td>Carina Flannigan</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>02J2RE7</td>\n",
       "      <td>3</td>\n",
       "      <td>2017-03-03</td>\n",
       "      <td>0</td>\n",
       "      <td>xxxxxxxx</td>\n",
       "      <td>16:40:39</td>\n",
       "      <td>18</td>\n",
       "      <td>215.36</td>\n",
       "      <td>3693.25</td>\n",
       "      <td>21.0</td>\n",
       "      <td>713.780000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1486.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003200370033003400</td>\n",
       "      <td>Kyung Wanner</td>\n",
       "      <td>64</td>\n",
       "      <td>1</td>\n",
       "      <td>5YEQIF1</td>\n",
       "      <td>3</td>\n",
       "      <td>2017-08-18</td>\n",
       "      <td>1</td>\n",
       "      <td>CID8941</td>\n",
       "      <td>14:56:17</td>\n",
       "      <td>-999</td>\n",
       "      <td>44.57</td>\n",
       "      <td>36809.56</td>\n",
       "      <td>11.0</td>\n",
       "      <td>744.970000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>1318.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440035003000370031003900</td>\n",
       "      <td>Enola Gatto</td>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "      <td>100RYB5</td>\n",
       "      <td>0</td>\n",
       "      <td>2015-05-05</td>\n",
       "      <td>1</td>\n",
       "      <td>CID5690</td>\n",
       "      <td>02:57:53</td>\n",
       "      <td>6</td>\n",
       "      <td>349.88</td>\n",
       "      <td>40675.86</td>\n",
       "      <td>8.0</td>\n",
       "      <td>299.048351</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2021-03-28</td>\n",
       "      <td>2154.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id              Name  age  gender  \\\n",
       "0  fffe43004900440031003700300030003400    Alethia Meints   50       0   \n",
       "1  fffe43004900440031003900370037003300        Ming Lopez   41       1   \n",
       "2  fffe43004900440034003800360037003000  Carina Flannigan   31       0   \n",
       "3  fffe43004900440036003200370033003400      Kyung Wanner   64       1   \n",
       "4  fffe43004900440035003000370031003900       Enola Gatto   16       0   \n",
       "\n",
       "  security_no  membership_category joining_date  joined_through_referral  \\\n",
       "0     OQJ1XAY                    4   2015-11-02                        0   \n",
       "1     OUQRPKO                    2   2016-03-01                        0   \n",
       "2     02J2RE7                    3   2017-03-03                        0   \n",
       "3     5YEQIF1                    3   2017-08-18                        1   \n",
       "4     100RYB5                    0   2015-05-05                        1   \n",
       "\n",
       "  referral_id last_visit_time  days_since_last_login  avg_time_spent  \\\n",
       "0    xxxxxxxx        07:19:30                     12          386.26   \n",
       "1    xxxxxxxx        22:21:16                     11           37.80   \n",
       "2    xxxxxxxx        16:40:39                     18          215.36   \n",
       "3     CID8941        14:56:17                   -999           44.57   \n",
       "4     CID5690        02:57:53                      6          349.88   \n",
       "\n",
       "   avg_transaction_value  avg_frequency_login_days  points_in_wallet  \\\n",
       "0               40721.44                       7.0        733.830000   \n",
       "1                9644.40                       9.0        726.000000   \n",
       "2                3693.25                      21.0        713.780000   \n",
       "3               36809.56                      11.0        744.970000   \n",
       "4               40675.86                       8.0        299.048351   \n",
       "\n",
       "   used_special_discount  offer_application_preference  past_complaint  \\\n",
       "0                      1                             0               0   \n",
       "1                      1                             0               0   \n",
       "2                      1                             0               1   \n",
       "3                      1                             0               1   \n",
       "4                      0                             1               1   \n",
       "\n",
       "  todays_date  customer_days  region_category_0  region_category_1  \\\n",
       "0  2021-03-28         1973.0                0.0                0.0   \n",
       "1  2021-03-28         1853.0                0.0                0.0   \n",
       "2  2021-03-28         1486.0                0.0                1.0   \n",
       "3  2021-03-28         1318.0                0.0                1.0   \n",
       "4  2021-03-28         2154.0                0.0                1.0   \n",
       "\n",
       "   region_category_2  preferred_offer_types_0  preferred_offer_types_1  \\\n",
       "0                1.0                      0.0                      0.0   \n",
       "1                1.0                      0.0                      0.0   \n",
       "2                0.0                      0.0                      1.0   \n",
       "3                0.0                      1.0                      0.0   \n",
       "4                0.0                      0.0                      0.0   \n",
       "\n",
       "   preferred_offer_types_2  medium_of_operation_0  medium_of_operation_1  \\\n",
       "0                      1.0                    0.0                    0.0   \n",
       "1                      1.0                    0.0                    0.0   \n",
       "2                      0.0                    0.0                    1.0   \n",
       "3                      0.0                    1.0                    0.0   \n",
       "4                      1.0                    0.0                    0.0   \n",
       "\n",
       "   medium_of_operation_2  medium_of_operation_3  internet_option_0  \\\n",
       "0                    0.0                    1.0                0.0   \n",
       "1                    1.0                    0.0                1.0   \n",
       "2                    0.0                    0.0                0.0   \n",
       "3                    0.0                    0.0                1.0   \n",
       "4                    0.0                    1.0                0.0   \n",
       "\n",
       "   internet_option_1  internet_option_2  complaint_status_0  \\\n",
       "0                0.0                1.0                 0.0   \n",
       "1                0.0                0.0                 0.0   \n",
       "2                1.0                0.0                 0.0   \n",
       "3                0.0                0.0                 1.0   \n",
       "4                1.0                0.0                 0.0   \n",
       "\n",
       "   complaint_status_1  complaint_status_2  complaint_status_3  \\\n",
       "0                 1.0                 0.0                 0.0   \n",
       "1                 1.0                 0.0                 0.0   \n",
       "2                 0.0                 0.0                 1.0   \n",
       "3                 0.0                 0.0                 0.0   \n",
       "4                 0.0                 0.0                 1.0   \n",
       "\n",
       "   complaint_status_4  feedback_0  feedback_1  feedback_2  feedback_3  \\\n",
       "0                 0.0         0.0         0.0         1.0         0.0   \n",
       "1                 0.0         0.0         0.0         0.0         1.0   \n",
       "2                 0.0         1.0         0.0         0.0         0.0   \n",
       "3                 0.0         0.0         0.0         0.0         0.0   \n",
       "4                 0.0         0.0         0.0         0.0         1.0   \n",
       "\n",
       "   feedback_4  feedback_5  feedback_6  feedback_7  feedback_8  \n",
       "0         0.0         0.0         0.0         0.0         0.0  \n",
       "1         0.0         0.0         0.0         0.0         0.0  \n",
       "2         0.0         0.0         0.0         0.0         0.0  \n",
       "3         0.0         0.0         0.0         1.0         0.0  \n",
       "4         0.0         0.0         0.0         0.0         0.0  "
      ]
     },
     "execution_count": 82,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "id": "effective-variable",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "id": "effective-variable",
    "outputId": "32b7b38a-f69c-4af6-e16b-6ef07ddac941"
   },
   "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>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>membership_category</th>\n",
       "      <th>joined_through_referral</th>\n",
       "      <th>days_since_last_login</th>\n",
       "      <th>avg_time_spent</th>\n",
       "      <th>avg_transaction_value</th>\n",
       "      <th>avg_frequency_login_days</th>\n",
       "      <th>points_in_wallet</th>\n",
       "      <th>used_special_discount</th>\n",
       "      <th>offer_application_preference</th>\n",
       "      <th>past_complaint</th>\n",
       "      <th>customer_days</th>\n",
       "      <th>region_category_0</th>\n",
       "      <th>region_category_1</th>\n",
       "      <th>region_category_2</th>\n",
       "      <th>preferred_offer_types_0</th>\n",
       "      <th>preferred_offer_types_1</th>\n",
       "      <th>preferred_offer_types_2</th>\n",
       "      <th>medium_of_operation_0</th>\n",
       "      <th>medium_of_operation_1</th>\n",
       "      <th>medium_of_operation_2</th>\n",
       "      <th>medium_of_operation_3</th>\n",
       "      <th>internet_option_0</th>\n",
       "      <th>internet_option_1</th>\n",
       "      <th>internet_option_2</th>\n",
       "      <th>complaint_status_0</th>\n",
       "      <th>complaint_status_1</th>\n",
       "      <th>complaint_status_2</th>\n",
       "      <th>complaint_status_3</th>\n",
       "      <th>complaint_status_4</th>\n",
       "      <th>feedback_0</th>\n",
       "      <th>feedback_1</th>\n",
       "      <th>feedback_2</th>\n",
       "      <th>feedback_3</th>\n",
       "      <th>feedback_4</th>\n",
       "      <th>feedback_5</th>\n",
       "      <th>feedback_6</th>\n",
       "      <th>feedback_7</th>\n",
       "      <th>feedback_8</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>50</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>386.26</td>\n",
       "      <td>40721.44</td>\n",
       "      <td>7.0</td>\n",
       "      <td>733.830000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1973.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>41</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>37.80</td>\n",
       "      <td>9644.40</td>\n",
       "      <td>9.0</td>\n",
       "      <td>726.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1853.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>215.36</td>\n",
       "      <td>3693.25</td>\n",
       "      <td>21.0</td>\n",
       "      <td>713.780000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1486.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>64</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>-999</td>\n",
       "      <td>44.57</td>\n",
       "      <td>36809.56</td>\n",
       "      <td>11.0</td>\n",
       "      <td>744.970000</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1318.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>349.88</td>\n",
       "      <td>40675.86</td>\n",
       "      <td>8.0</td>\n",
       "      <td>299.048351</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2154.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age  gender  membership_category  joined_through_referral  \\\n",
       "0   50       0                    4                        0   \n",
       "1   41       1                    2                        0   \n",
       "2   31       0                    3                        0   \n",
       "3   64       1                    3                        1   \n",
       "4   16       0                    0                        1   \n",
       "\n",
       "   days_since_last_login  avg_time_spent  avg_transaction_value  \\\n",
       "0                     12          386.26               40721.44   \n",
       "1                     11           37.80                9644.40   \n",
       "2                     18          215.36                3693.25   \n",
       "3                   -999           44.57               36809.56   \n",
       "4                      6          349.88               40675.86   \n",
       "\n",
       "   avg_frequency_login_days  points_in_wallet  used_special_discount  \\\n",
       "0                       7.0        733.830000                      1   \n",
       "1                       9.0        726.000000                      1   \n",
       "2                      21.0        713.780000                      1   \n",
       "3                      11.0        744.970000                      1   \n",
       "4                       8.0        299.048351                      0   \n",
       "\n",
       "   offer_application_preference  past_complaint  customer_days  \\\n",
       "0                             0               0         1973.0   \n",
       "1                             0               0         1853.0   \n",
       "2                             0               1         1486.0   \n",
       "3                             0               1         1318.0   \n",
       "4                             1               1         2154.0   \n",
       "\n",
       "   region_category_0  region_category_1  region_category_2  \\\n",
       "0                0.0                0.0                1.0   \n",
       "1                0.0                0.0                1.0   \n",
       "2                0.0                1.0                0.0   \n",
       "3                0.0                1.0                0.0   \n",
       "4                0.0                1.0                0.0   \n",
       "\n",
       "   preferred_offer_types_0  preferred_offer_types_1  preferred_offer_types_2  \\\n",
       "0                      0.0                      0.0                      1.0   \n",
       "1                      0.0                      0.0                      1.0   \n",
       "2                      0.0                      1.0                      0.0   \n",
       "3                      1.0                      0.0                      0.0   \n",
       "4                      0.0                      0.0                      1.0   \n",
       "\n",
       "   medium_of_operation_0  medium_of_operation_1  medium_of_operation_2  \\\n",
       "0                    0.0                    0.0                    0.0   \n",
       "1                    0.0                    0.0                    1.0   \n",
       "2                    0.0                    1.0                    0.0   \n",
       "3                    1.0                    0.0                    0.0   \n",
       "4                    0.0                    0.0                    0.0   \n",
       "\n",
       "   medium_of_operation_3  internet_option_0  internet_option_1  \\\n",
       "0                    1.0                0.0                0.0   \n",
       "1                    0.0                1.0                0.0   \n",
       "2                    0.0                0.0                1.0   \n",
       "3                    0.0                1.0                0.0   \n",
       "4                    1.0                0.0                1.0   \n",
       "\n",
       "   internet_option_2  complaint_status_0  complaint_status_1  \\\n",
       "0                1.0                 0.0                 1.0   \n",
       "1                0.0                 0.0                 1.0   \n",
       "2                0.0                 0.0                 0.0   \n",
       "3                0.0                 1.0                 0.0   \n",
       "4                0.0                 0.0                 0.0   \n",
       "\n",
       "   complaint_status_2  complaint_status_3  complaint_status_4  feedback_0  \\\n",
       "0                 0.0                 0.0                 0.0         0.0   \n",
       "1                 0.0                 0.0                 0.0         0.0   \n",
       "2                 0.0                 1.0                 0.0         1.0   \n",
       "3                 0.0                 0.0                 0.0         0.0   \n",
       "4                 0.0                 1.0                 0.0         0.0   \n",
       "\n",
       "   feedback_1  feedback_2  feedback_3  feedback_4  feedback_5  feedback_6  \\\n",
       "0         0.0         1.0         0.0         0.0         0.0         0.0   \n",
       "1         0.0         0.0         1.0         0.0         0.0         0.0   \n",
       "2         0.0         0.0         0.0         0.0         0.0         0.0   \n",
       "3         0.0         0.0         0.0         0.0         0.0         0.0   \n",
       "4         0.0         0.0         1.0         0.0         0.0         0.0   \n",
       "\n",
       "   feedback_7  feedback_8  \n",
       "0         0.0         0.0  \n",
       "1         0.0         0.0  \n",
       "2         0.0         0.0  \n",
       "3         1.0         0.0  \n",
       "4         0.0         0.0  "
      ]
     },
     "execution_count": 83,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "customer_ids = df_test[\"customer_id\"]\n",
    "customer_ids_df = pd.DataFrame(data = customer_ids,columns=[\"customer_id\"])\n",
    "df_test = removeRedundantColumns(df_test)\n",
    "df_test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "id": "banned-despite",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "id": "banned-despite",
    "outputId": "0f8a6135-d6d2-49f2-b3aa-f4451b992d0b"
   },
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "      <th>16</th>\n",
       "      <th>17</th>\n",
       "      <th>18</th>\n",
       "      <th>19</th>\n",
       "      <th>20</th>\n",
       "      <th>21</th>\n",
       "      <th>22</th>\n",
       "      <th>23</th>\n",
       "      <th>24</th>\n",
       "      <th>25</th>\n",
       "      <th>26</th>\n",
       "      <th>27</th>\n",
       "      <th>28</th>\n",
       "      <th>29</th>\n",
       "      <th>30</th>\n",
       "      <th>31</th>\n",
       "      <th>32</th>\n",
       "      <th>33</th>\n",
       "      <th>34</th>\n",
       "      <th>35</th>\n",
       "      <th>36</th>\n",
       "      <th>37</th>\n",
       "      <th>38</th>\n",
       "      <th>39</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.842922</td>\n",
       "      <td>-1.02554</td>\n",
       "      <td>0.998865</td>\n",
       "      <td>-0.857913</td>\n",
       "      <td>0.232736</td>\n",
       "      <td>0.359131</td>\n",
       "      <td>0.337132</td>\n",
       "      <td>-0.893625</td>\n",
       "      <td>0.208865</td>\n",
       "      <td>0.926124</td>\n",
       "      <td>-1.161612</td>\n",
       "      <td>-1.019110</td>\n",
       "      <td>0.781095</td>\n",
       "      <td>-0.736459</td>\n",
       "      <td>-1.087578</td>\n",
       "      <td>2.628549</td>\n",
       "      <td>-0.733424</td>\n",
       "      <td>-0.764810</td>\n",
       "      <td>1.529731</td>\n",
       "      <td>-0.420083</td>\n",
       "      <td>-0.351416</td>\n",
       "      <td>-0.814267</td>\n",
       "      <td>1.347724</td>\n",
       "      <td>-0.724902</td>\n",
       "      <td>-0.728073</td>\n",
       "      <td>1.448432</td>\n",
       "      <td>-0.383722</td>\n",
       "      <td>1.019110</td>\n",
       "      <td>-0.387892</td>\n",
       "      <td>-0.383543</td>\n",
       "      <td>-0.389893</td>\n",
       "      <td>-0.404804</td>\n",
       "      <td>-0.40338</td>\n",
       "      <td>2.456712</td>\n",
       "      <td>-0.404092</td>\n",
       "      <td>-0.305021</td>\n",
       "      <td>-0.310525</td>\n",
       "      <td>-0.307478</td>\n",
       "      <td>-0.404392</td>\n",
       "      <td>-0.308103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.259310</td>\n",
       "      <td>1.03543</td>\n",
       "      <td>-0.225583</td>\n",
       "      <td>-0.857913</td>\n",
       "      <td>0.228232</td>\n",
       "      <td>-0.542380</td>\n",
       "      <td>-1.022910</td>\n",
       "      <td>-0.672039</td>\n",
       "      <td>0.164449</td>\n",
       "      <td>0.926124</td>\n",
       "      <td>-1.161612</td>\n",
       "      <td>-1.019110</td>\n",
       "      <td>0.399197</td>\n",
       "      <td>-0.736459</td>\n",
       "      <td>-1.087578</td>\n",
       "      <td>2.628549</td>\n",
       "      <td>-0.733424</td>\n",
       "      <td>-0.764810</td>\n",
       "      <td>1.529731</td>\n",
       "      <td>-0.420083</td>\n",
       "      <td>-0.351416</td>\n",
       "      <td>1.304013</td>\n",
       "      <td>-0.785056</td>\n",
       "      <td>1.464279</td>\n",
       "      <td>-0.728073</td>\n",
       "      <td>-0.732327</td>\n",
       "      <td>-0.383722</td>\n",
       "      <td>1.019110</td>\n",
       "      <td>-0.387892</td>\n",
       "      <td>-0.383543</td>\n",
       "      <td>-0.389893</td>\n",
       "      <td>-0.404804</td>\n",
       "      <td>-0.40338</td>\n",
       "      <td>-0.407048</td>\n",
       "      <td>2.474684</td>\n",
       "      <td>-0.305021</td>\n",
       "      <td>-0.310525</td>\n",
       "      <td>-0.307478</td>\n",
       "      <td>-0.404392</td>\n",
       "      <td>-0.308103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.389147</td>\n",
       "      <td>-1.02554</td>\n",
       "      <td>0.386641</td>\n",
       "      <td>-0.857913</td>\n",
       "      <td>0.259762</td>\n",
       "      <td>-0.083009</td>\n",
       "      <td>-1.283353</td>\n",
       "      <td>0.657480</td>\n",
       "      <td>0.095130</td>\n",
       "      <td>0.926124</td>\n",
       "      <td>-1.161612</td>\n",
       "      <td>1.043111</td>\n",
       "      <td>-0.768772</td>\n",
       "      <td>-0.736459</td>\n",
       "      <td>0.975309</td>\n",
       "      <td>-0.407758</td>\n",
       "      <td>-0.733424</td>\n",
       "      <td>1.391793</td>\n",
       "      <td>-0.686078</td>\n",
       "      <td>-0.420083</td>\n",
       "      <td>3.016169</td>\n",
       "      <td>-0.814267</td>\n",
       "      <td>-0.785056</td>\n",
       "      <td>-0.724902</td>\n",
       "      <td>1.457954</td>\n",
       "      <td>-0.732327</td>\n",
       "      <td>-0.383722</td>\n",
       "      <td>-1.043111</td>\n",
       "      <td>-0.387892</td>\n",
       "      <td>2.751855</td>\n",
       "      <td>-0.389893</td>\n",
       "      <td>2.470333</td>\n",
       "      <td>-0.40338</td>\n",
       "      <td>-0.407048</td>\n",
       "      <td>-0.404092</td>\n",
       "      <td>-0.305021</td>\n",
       "      <td>-0.310525</td>\n",
       "      <td>-0.307478</td>\n",
       "      <td>-0.404392</td>\n",
       "      <td>-0.308103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.750762</td>\n",
       "      <td>1.03543</td>\n",
       "      <td>0.386641</td>\n",
       "      <td>1.228870</td>\n",
       "      <td>-4.321117</td>\n",
       "      <td>-0.524865</td>\n",
       "      <td>0.165935</td>\n",
       "      <td>-0.450452</td>\n",
       "      <td>0.272058</td>\n",
       "      <td>0.926124</td>\n",
       "      <td>-1.161612</td>\n",
       "      <td>1.043111</td>\n",
       "      <td>-1.303428</td>\n",
       "      <td>-0.736459</td>\n",
       "      <td>0.975309</td>\n",
       "      <td>-0.407758</td>\n",
       "      <td>1.451110</td>\n",
       "      <td>-0.764810</td>\n",
       "      <td>-0.686078</td>\n",
       "      <td>2.514342</td>\n",
       "      <td>-0.351416</td>\n",
       "      <td>-0.814267</td>\n",
       "      <td>-0.785056</td>\n",
       "      <td>1.464279</td>\n",
       "      <td>-0.728073</td>\n",
       "      <td>-0.732327</td>\n",
       "      <td>2.752049</td>\n",
       "      <td>-1.043111</td>\n",
       "      <td>-0.387892</td>\n",
       "      <td>-0.383543</td>\n",
       "      <td>-0.389893</td>\n",
       "      <td>-0.404804</td>\n",
       "      <td>-0.40338</td>\n",
       "      <td>-0.407048</td>\n",
       "      <td>-0.404092</td>\n",
       "      <td>-0.305021</td>\n",
       "      <td>-0.310525</td>\n",
       "      <td>-0.307478</td>\n",
       "      <td>2.472850</td>\n",
       "      <td>-0.308103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-1.361833</td>\n",
       "      <td>-1.02554</td>\n",
       "      <td>-1.450032</td>\n",
       "      <td>1.228870</td>\n",
       "      <td>0.205710</td>\n",
       "      <td>0.265011</td>\n",
       "      <td>0.335138</td>\n",
       "      <td>-0.782832</td>\n",
       "      <td>-2.257467</td>\n",
       "      <td>-1.143462</td>\n",
       "      <td>0.911895</td>\n",
       "      <td>1.043111</td>\n",
       "      <td>1.357123</td>\n",
       "      <td>-0.736459</td>\n",
       "      <td>0.975309</td>\n",
       "      <td>-0.407758</td>\n",
       "      <td>-0.733424</td>\n",
       "      <td>-0.764810</td>\n",
       "      <td>1.529731</td>\n",
       "      <td>-0.420083</td>\n",
       "      <td>-0.351416</td>\n",
       "      <td>-0.814267</td>\n",
       "      <td>1.347724</td>\n",
       "      <td>-0.724902</td>\n",
       "      <td>1.457954</td>\n",
       "      <td>-0.732327</td>\n",
       "      <td>-0.383722</td>\n",
       "      <td>-1.043111</td>\n",
       "      <td>-0.387892</td>\n",
       "      <td>2.751855</td>\n",
       "      <td>-0.389893</td>\n",
       "      <td>-0.404804</td>\n",
       "      <td>-0.40338</td>\n",
       "      <td>-0.407048</td>\n",
       "      <td>2.474684</td>\n",
       "      <td>-0.305021</td>\n",
       "      <td>-0.310525</td>\n",
       "      <td>-0.307478</td>\n",
       "      <td>-0.404392</td>\n",
       "      <td>-0.308103</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         0        1         2         3         4         5         6   \\\n",
       "0  0.842922 -1.02554  0.998865 -0.857913  0.232736  0.359131  0.337132   \n",
       "1  0.259310  1.03543 -0.225583 -0.857913  0.228232 -0.542380 -1.022910   \n",
       "2 -0.389147 -1.02554  0.386641 -0.857913  0.259762 -0.083009 -1.283353   \n",
       "3  1.750762  1.03543  0.386641  1.228870 -4.321117 -0.524865  0.165935   \n",
       "4 -1.361833 -1.02554 -1.450032  1.228870  0.205710  0.265011  0.335138   \n",
       "\n",
       "         7         8         9         10        11        12        13  \\\n",
       "0 -0.893625  0.208865  0.926124 -1.161612 -1.019110  0.781095 -0.736459   \n",
       "1 -0.672039  0.164449  0.926124 -1.161612 -1.019110  0.399197 -0.736459   \n",
       "2  0.657480  0.095130  0.926124 -1.161612  1.043111 -0.768772 -0.736459   \n",
       "3 -0.450452  0.272058  0.926124 -1.161612  1.043111 -1.303428 -0.736459   \n",
       "4 -0.782832 -2.257467 -1.143462  0.911895  1.043111  1.357123 -0.736459   \n",
       "\n",
       "         14        15        16        17        18        19        20  \\\n",
       "0 -1.087578  2.628549 -0.733424 -0.764810  1.529731 -0.420083 -0.351416   \n",
       "1 -1.087578  2.628549 -0.733424 -0.764810  1.529731 -0.420083 -0.351416   \n",
       "2  0.975309 -0.407758 -0.733424  1.391793 -0.686078 -0.420083  3.016169   \n",
       "3  0.975309 -0.407758  1.451110 -0.764810 -0.686078  2.514342 -0.351416   \n",
       "4  0.975309 -0.407758 -0.733424 -0.764810  1.529731 -0.420083 -0.351416   \n",
       "\n",
       "         21        22        23        24        25        26        27  \\\n",
       "0 -0.814267  1.347724 -0.724902 -0.728073  1.448432 -0.383722  1.019110   \n",
       "1  1.304013 -0.785056  1.464279 -0.728073 -0.732327 -0.383722  1.019110   \n",
       "2 -0.814267 -0.785056 -0.724902  1.457954 -0.732327 -0.383722 -1.043111   \n",
       "3 -0.814267 -0.785056  1.464279 -0.728073 -0.732327  2.752049 -1.043111   \n",
       "4 -0.814267  1.347724 -0.724902  1.457954 -0.732327 -0.383722 -1.043111   \n",
       "\n",
       "         28        29        30        31       32        33        34  \\\n",
       "0 -0.387892 -0.383543 -0.389893 -0.404804 -0.40338  2.456712 -0.404092   \n",
       "1 -0.387892 -0.383543 -0.389893 -0.404804 -0.40338 -0.407048  2.474684   \n",
       "2 -0.387892  2.751855 -0.389893  2.470333 -0.40338 -0.407048 -0.404092   \n",
       "3 -0.387892 -0.383543 -0.389893 -0.404804 -0.40338 -0.407048 -0.404092   \n",
       "4 -0.387892  2.751855 -0.389893 -0.404804 -0.40338 -0.407048  2.474684   \n",
       "\n",
       "         35        36        37        38        39  \n",
       "0 -0.305021 -0.310525 -0.307478 -0.404392 -0.308103  \n",
       "1 -0.305021 -0.310525 -0.307478 -0.404392 -0.308103  \n",
       "2 -0.305021 -0.310525 -0.307478 -0.404392 -0.308103  \n",
       "3 -0.305021 -0.310525 -0.307478  2.472850 -0.308103  \n",
       "4 -0.305021 -0.310525 -0.307478 -0.404392 -0.308103  "
      ]
     },
     "execution_count": 84,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x_test_submit = scalerX.transform(df_test)\n",
    "x_test_submit = pd.DataFrame(x_test_submit)\n",
    "x_test_submit.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "id": "divine-fleet",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "divine-fleet",
    "outputId": "26591af8-c1cb-4efa-85c3-21d83855be77"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2 2 2 ... 4 3 2]\n"
     ]
    }
   ],
   "source": [
    "prediction_submit = model.predict(x_test_submit)\n",
    "predict_label = prediction_submit\n",
    "\n",
    "print(predict_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "id": "handy-devon",
   "metadata": {
    "id": "handy-devon"
   },
   "outputs": [],
   "source": [
    "df_to_submit = pd.concat([customer_ids_df,pd.DataFrame(data = predict_label,columns=[\"churn_risk_score\"])], axis=1)\n",
    "df_to_submit['churn_risk_score'] = df_to_submit['churn_risk_score'].apply(lambda x:x+1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "id": "raised-clerk",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "id": "raised-clerk",
    "outputId": "d4a329c6-4145-4bfd-ce49-9f58a3c3e237"
   },
   "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>customer_id</th>\n",
       "      <th>churn_risk_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>fffe43004900440031003700300030003400</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>fffe43004900440031003900370037003300</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>fffe43004900440034003800360037003000</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>fffe43004900440036003200370033003400</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fffe43004900440035003000370031003900</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                            customer_id  churn_risk_score\n",
       "0  fffe43004900440031003700300030003400                 3\n",
       "1  fffe43004900440031003900370037003300                 3\n",
       "2  fffe43004900440034003800360037003000                 3\n",
       "3  fffe43004900440036003200370033003400                 3\n",
       "4  fffe43004900440035003000370031003900                 4"
      ]
     },
     "execution_count": 87,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_to_submit.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "concerned-mining",
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "concerned-mining",
    "outputId": "59240ceb-b9ce-4d7a-9ddd-e7859a0ee805"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5    5986\n",
      "3    5548\n",
      "4    5362\n",
      "1    1544\n",
      "2    1479\n",
      "Name: churn_risk_score, dtype: int64\n",
      "--------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "print(df_to_submit[\"churn_risk_score\"].value_counts())\n",
    "print(\"-\"*50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "id": "determined-still",
   "metadata": {
    "id": "determined-still"
   },
   "outputs": [],
   "source": [
    "df_to_submit.to_csv(path_or_buf=\"./drive/MyDrive/dataset/df_to_submit\"+\".csv\",float_format='%.0f',index=False)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "churn_rate_over_sampling_xgb.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}