AmExpert_2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from datetime import datetime\n",
    "import os,re\n",
    "import json\n",
    "import statistics\n",
    "from collections import Counter\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "from sklearn.model_selection import StratifiedKFold\n",
    "import lightgbm as lgb\n",
    "from sklearn.metrics import roc_auc_score,accuracy_score\n",
    "import numpy as np\n",
    "from tqdm import tqdm\n",
    "from scipy import stats\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "train=pd.read_csv('train.csv')\n",
    "test=pd.read_csv('test_QyjYwdj.csv')\n",
    "campaign=pd.read_csv('campaign_data.csv')\n",
    "ci_mapping=pd.read_csv('coupon_item_mapping.csv')\n",
    "cust_demo=pd.read_csv('customer_demographics.csv')\n",
    "ct_data=pd.read_csv('customer_transaction_data.csv')\n",
    "item_data=pd.read_csv('item_data.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Merge train data with campaign data on campaign_id\n",
    "2. Merge 1 with customer demographic data on customer_id\n",
    "3. Merge coupon-item data with item data on item_id\n",
    "4. Extract aggregated features one for each coupon_id from 3\n",
    "5. Merge 2 and 4 on coupon_id\n",
    "6. Merge transaction data with item data and customer demographics data on item_id and customer_id respectively\n",
    "7. Extract aggregated features one for each customer_id from 6. You get a dataset with unique customer_ids.\n",
    "8. Merge 5 and 7. This is the final step"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>customer_id</th>\n",
       "      <th>item_id</th>\n",
       "      <th>quantity</th>\n",
       "      <th>selling_price</th>\n",
       "      <th>other_discount</th>\n",
       "      <th>coupon_discount</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2012-01-02</td>\n",
       "      <td>1501</td>\n",
       "      <td>26830</td>\n",
       "      <td>1</td>\n",
       "      <td>35.26</td>\n",
       "      <td>-10.69</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2012-01-02</td>\n",
       "      <td>1501</td>\n",
       "      <td>54253</td>\n",
       "      <td>1</td>\n",
       "      <td>53.43</td>\n",
       "      <td>-13.89</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2012-01-02</td>\n",
       "      <td>1501</td>\n",
       "      <td>31962</td>\n",
       "      <td>1</td>\n",
       "      <td>106.50</td>\n",
       "      <td>-14.25</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2012-01-02</td>\n",
       "      <td>1501</td>\n",
       "      <td>33647</td>\n",
       "      <td>1</td>\n",
       "      <td>67.32</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2012-01-02</td>\n",
       "      <td>1501</td>\n",
       "      <td>48199</td>\n",
       "      <td>1</td>\n",
       "      <td>71.24</td>\n",
       "      <td>-28.14</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date  customer_id  item_id  quantity  selling_price  other_discount  \\\n",
       "0  2012-01-02         1501    26830         1          35.26          -10.69   \n",
       "1  2012-01-02         1501    54253         1          53.43          -13.89   \n",
       "2  2012-01-02         1501    31962         1         106.50          -14.25   \n",
       "3  2012-01-02         1501    33647         1          67.32            0.00   \n",
       "4  2012-01-02         1501    48199         1          71.24          -28.14   \n",
       "\n",
       "   coupon_discount  \n",
       "0              0.0  \n",
       "1              0.0  \n",
       "2              0.0  \n",
       "3              0.0  \n",
       "4              0.0  "
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ct_data.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### As analysed in AmEx_1 only the features which are important are \n",
    "#### * quantity , selling_price , other_discount , coupon_discount,\tcoupon_campaign_days, campaign_type\n",
    "\n",
    "* So let's try to join the 3 tables which contains these features are train, campaign, cutomer_transaction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 153,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>campaign_id</th>\n",
       "      <th>coupon_id</th>\n",
       "      <th>customer_id</th>\n",
       "      <th>redemption_status</th>\n",
       "      <th>campaign_type</th>\n",
       "      <th>start_date</th>\n",
       "      <th>end_date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>13</td>\n",
       "      <td>27</td>\n",
       "      <td>1053</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>116</td>\n",
       "      <td>48</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>635</td>\n",
       "      <td>205</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>11/03/13</td>\n",
       "      <td>12/04/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7</td>\n",
       "      <td>13</td>\n",
       "      <td>644</td>\n",
       "      <td>1050</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9</td>\n",
       "      <td>8</td>\n",
       "      <td>1017</td>\n",
       "      <td>1489</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  campaign_id  coupon_id  customer_id  redemption_status campaign_type  \\\n",
       "0   1           13         27         1053                  0             X   \n",
       "1   2           13        116           48                  0             X   \n",
       "2   6            9        635          205                  0             Y   \n",
       "3   7           13        644         1050                  0             X   \n",
       "4   9            8       1017         1489                  0             X   \n",
       "\n",
       "  start_date  end_date  \n",
       "0   19/05/13  05/07/13  \n",
       "1   19/05/13  05/07/13  \n",
       "2   11/03/13  12/04/13  \n",
       "3   19/05/13  05/07/13  \n",
       "4   16/02/13  05/04/13  "
      ]
     },
     "execution_count": 153,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "newtrain=train.merge(campaign,on='campaign_id',how='left')\n",
    "newtrain.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>campaign_id</th>\n",
       "      <th>coupon_id</th>\n",
       "      <th>customer_id</th>\n",
       "      <th>campaign_type</th>\n",
       "      <th>start_date</th>\n",
       "      <th>end_date</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>22</td>\n",
       "      <td>869</td>\n",
       "      <td>967</td>\n",
       "      <td>X</td>\n",
       "      <td>16/09/13</td>\n",
       "      <td>18/10/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>20</td>\n",
       "      <td>389</td>\n",
       "      <td>1566</td>\n",
       "      <td>Y</td>\n",
       "      <td>07/09/13</td>\n",
       "      <td>16/11/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>981</td>\n",
       "      <td>510</td>\n",
       "      <td>X</td>\n",
       "      <td>16/09/13</td>\n",
       "      <td>18/10/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>25</td>\n",
       "      <td>1069</td>\n",
       "      <td>361</td>\n",
       "      <td>Y</td>\n",
       "      <td>21/10/13</td>\n",
       "      <td>22/11/13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10</td>\n",
       "      <td>17</td>\n",
       "      <td>498</td>\n",
       "      <td>811</td>\n",
       "      <td>Y</td>\n",
       "      <td>29/07/13</td>\n",
       "      <td>30/08/13</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  campaign_id  coupon_id  customer_id campaign_type start_date  end_date\n",
       "0   3           22        869          967             X   16/09/13  18/10/13\n",
       "1   4           20        389         1566             Y   07/09/13  16/11/13\n",
       "2   5           22        981          510             X   16/09/13  18/10/13\n",
       "3   8           25       1069          361             Y   21/10/13  22/11/13\n",
       "4  10           17        498          811             Y   29/07/13  30/08/13"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "newtest=test.merge(campaign,on='campaign_id',how='left')\n",
    "newtest.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "ct_data1=ct_data.merge(item_data,on=\"item_id\",how=\"left\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\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>item_id</th>\n",
       "      <th>quantity</th>\n",
       "      <th>selling_price</th>\n",
       "      <th>other_discount</th>\n",
       "      <th>coupon_discount</th>\n",
       "      <th>brand</th>\n",
       "      <th>brand_type</th>\n",
       "      <th>category</th>\n",
       "      <th>date</th>\n",
       "      <th>no_of_compaigns_participated</th>\n",
       "      <th>no_of_items_bought</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>8307</td>\n",
       "      <td>1227</td>\n",
       "      <td>98513.93</td>\n",
       "      <td>-17030.40</td>\n",
       "      <td>-2116.83</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>1048</td>\n",
       "      <td>56</td>\n",
       "      <td>463</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>53517</td>\n",
       "      <td>474</td>\n",
       "      <td>43100.03</td>\n",
       "      <td>-7051.95</td>\n",
       "      <td>-249.34</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>419</td>\n",
       "      <td>37</td>\n",
       "      <td>352</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>32573</td>\n",
       "      <td>8163</td>\n",
       "      <td>73050.27</td>\n",
       "      <td>-16013.53</td>\n",
       "      <td>-2179.54</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>705</td>\n",
       "      <td>41</td>\n",
       "      <td>406</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>47968</td>\n",
       "      <td>280</td>\n",
       "      <td>33973.22</td>\n",
       "      <td>-2927.19</td>\n",
       "      <td>-89.05</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>220</td>\n",
       "      <td>26</td>\n",
       "      <td>125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>35304</td>\n",
       "      <td>93353</td>\n",
       "      <td>103615.10</td>\n",
       "      <td>-10817.07</td>\n",
       "      <td>-90.83</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>792</td>\n",
       "      <td>163</td>\n",
       "      <td>490</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   customer_id  item_id  quantity  selling_price  other_discount  \\\n",
       "0            1     8307      1227       98513.93       -17030.40   \n",
       "1            2    53517       474       43100.03        -7051.95   \n",
       "2            3    32573      8163       73050.27       -16013.53   \n",
       "3            4    47968       280       33973.22        -2927.19   \n",
       "4            5    35304     93353      103615.10       -10817.07   \n",
       "\n",
       "   coupon_discount  brand   brand_type category  date  \\\n",
       "0         -2116.83     56  Established  Grocery  1048   \n",
       "1          -249.34     56  Established  Grocery   419   \n",
       "2         -2179.54     56  Established  Grocery   705   \n",
       "3           -89.05     56  Established  Grocery   220   \n",
       "4           -90.83     56  Established  Grocery   792   \n",
       "\n",
       "   no_of_compaigns_participated  no_of_items_bought  \n",
       "0                            56                 463  \n",
       "1                            37                 352  \n",
       "2                            41                 406  \n",
       "3                            26                 125  \n",
       "4                           163                 490  "
      ]
     },
     "execution_count": 132,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ct_data_grouped=ct_data1.groupby('customer_id')\n",
    "ct_data_groupby=ct_data_grouped.agg({'item_id': lambda x:Counter(x).most_common()[0][0],\n",
    "                                                    'quantity':'sum',\n",
    "                                                    'selling_price':'sum',\n",
    "                                                    'other_discount':'sum',\n",
    "                                                    'coupon_discount':'sum',\n",
    "                                                    'brand':lambda x:Counter(x).most_common()[0][0],\n",
    "                                                    'brand_type':lambda x:Counter(x).most_common()[0][0],\n",
    "                                                    'category':lambda x:Counter(x).most_common()[0][0],\n",
    "                                                     'date':'count'\n",
    "                                                    })\n",
    "ct_data_groupby['no_of_compaigns_participated']=ct_data_grouped['date'].apply(lambda x:len(x.unique()))\n",
    "ct_data_groupby['no_of_items_bought']=ct_data_grouped['item_id'].apply(lambda x:len(x.unique()))\n",
    "ct_data_groupby.reset_index(inplace=True)\n",
    "ct_data_groupby.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "customer_id has 0 null values\n",
      "age_range has 0 null values\n",
      "marital_status has 146 null values\n",
      "rented has 0 null values\n",
      "family_size has 0 null values\n",
      "no_of_children has 290 null values\n",
      "income_bracket has 0 null values\n",
      "age_range \n",
      "===========\n",
      "46-55    54\n",
      "26-35    37\n",
      "36-45    29\n",
      "70+      11\n",
      "18-25    10\n",
      "56-70     5\n",
      "Name: age_range, dtype: int64\n",
      "family_size \n",
      "===========\n",
      "2     97\n",
      "3     30\n",
      "4     13\n",
      "5+     6\n",
      "Name: family_size, dtype: int64\n",
      "customer_id has 0 null values\n",
      "age_range has 0 null values\n",
      "marital_status has 0 null values\n",
      "rented has 0 null values\n",
      "family_size has 0 null values\n",
      "no_of_children has 0 null values\n",
      "income_bracket has 0 null values\n"
     ]
    }
   ],
   "source": [
    "cust_demo.loc[(cust_demo['no_of_children'].isnull()) & (cust_demo['family_size'] == '1')][['no_of_children','family_size']]\n",
    "\n",
    "#there are 248 columns which can be filled as 0\n",
    "cust_demo.loc[(cust_demo['no_of_children'].isnull()) & (cust_demo['family_size'] == '1'),'no_of_children']='0'\n",
    "\n",
    "\n",
    "\n",
    "# follow the same process for marital_status as well.\n",
    "\n",
    "\n",
    "cust_demo.loc[(cust_demo['family_size'] == '1') & (cust_demo['marital_status'] == \"Married\")][['marital_status','family_size']]\n",
    "\n",
    "#So there are no customer is classified as married if the family size is single, so we can classify all the customers whose\n",
    "# family size is 1 to marital status as Single\n",
    "cust_demo.loc[(cust_demo['marital_status'].isnull()) & (cust_demo['family_size'] == '1'),'marital_status']='Single'\n",
    "cust_demo.loc[(cust_demo['marital_status'].isnull()) & (cust_demo['family_size'] == '1')][['marital_status','family_size']]\n",
    "\n",
    "#Now let's check how many null values in customer dataset\n",
    "for col in cust_demo.columns:\n",
    "    print(\"{} has {} null values\".format(col,cust_demo[col].isnull().sum()))\n",
    "\n",
    "# There are still few null values in no_of_children,marital_status let's try to fill these values\n",
    "# Let's see the other fields when the marital_status is null\n",
    "for col in ['age_range','family_size']:\n",
    "    print(col,\"\\n===========\")\n",
    "    print(cust_demo.loc[cust_demo['marital_status'].isnull()][col].value_counts())\n",
    "\n",
    "# So will take the mode of the combination of age_range&family_size  fields as they seem to be related\n",
    "\n",
    "newcust_df=cust_demo.groupby(['age_range','family_size']).agg({'marital_status':lambda x: x.mode()[0] if len(x.mode()) == 2 else x.mode()}).reset_index()\n",
    "\n",
    "\n",
    "for i,row in newcust_df.iterrows():\n",
    "    cust_demo.loc[(cust_demo['marital_status'].isnull())&(cust_demo['age_range'] == row['age_range'])&(cust_demo['family_size']==row['family_size']),'marital_status']=row['marital_status']\n",
    "    \n",
    "cust_demo.head()\n",
    "\n",
    "#If the person is married and family_size is 2 then the no_of_children should be 0\n",
    "# So write a condition to filter family_size=2 & marital_status=married\n",
    "cust_demo.loc[(cust_demo['marital_status']==\"Married\")&(cust_demo['family_size'] == '2'),'no_of_children']='0'\n",
    "cust_demo['no_of_children'].isnull().sum()\n",
    "\n",
    "#so there are still 26 records which have null values, let's see what are those\n",
    "\n",
    "cust_demo[cust_demo['no_of_children'].isnull()]\n",
    "\n",
    "\n",
    "#I am assuming that if the person's age range is greater than 26-35 \n",
    "#and the marrital_status is Single he would probably married and divorced, \n",
    "# so i am assigning the no_of_children as 1 since the family size is 2 for these\n",
    "cust_demo.loc[((cust_demo['age_range']).isin(['18-25','26-35'])) & (cust_demo['no_of_children'].isnull()),'no_of_children']='0'\n",
    "cust_demo.loc[((cust_demo['age_range']).isin(['36-45','46-55','56-70','70+'])) & (cust_demo['no_of_children'].isnull()),'no_of_children']='1'\n",
    "\n",
    "for col in cust_demo.columns:\n",
    "    print('{} has {} null values'.format(col,cust_demo[col].isnull().sum()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 154,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>campaign_id</th>\n",
       "      <th>coupon_id</th>\n",
       "      <th>customer_id</th>\n",
       "      <th>redemption_status</th>\n",
       "      <th>campaign_type</th>\n",
       "      <th>start_date</th>\n",
       "      <th>end_date</th>\n",
       "      <th>age_range</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>rented</th>\n",
       "      <th>family_size</th>\n",
       "      <th>no_of_children</th>\n",
       "      <th>income_bracket</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>13</td>\n",
       "      <td>27</td>\n",
       "      <td>1053</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>116</td>\n",
       "      <td>48</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>635</td>\n",
       "      <td>205</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>11/03/13</td>\n",
       "      <td>12/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7</td>\n",
       "      <td>13</td>\n",
       "      <td>644</td>\n",
       "      <td>1050</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9</td>\n",
       "      <td>8</td>\n",
       "      <td>1017</td>\n",
       "      <td>1489</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>11</td>\n",
       "      <td>11</td>\n",
       "      <td>795</td>\n",
       "      <td>793</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>22/04/13</td>\n",
       "      <td>07/06/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>14</td>\n",
       "      <td>9</td>\n",
       "      <td>444</td>\n",
       "      <td>590</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>11/03/13</td>\n",
       "      <td>12/04/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>15</td>\n",
       "      <td>29</td>\n",
       "      <td>538</td>\n",
       "      <td>368</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>08/10/12</td>\n",
       "      <td>30/11/12</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>17</td>\n",
       "      <td>30</td>\n",
       "      <td>857</td>\n",
       "      <td>523</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/11/12</td>\n",
       "      <td>04/01/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>19</td>\n",
       "      <td>2</td>\n",
       "      <td>559</td>\n",
       "      <td>679</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>17/12/12</td>\n",
       "      <td>18/01/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Single</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>20</td>\n",
       "      <td>9</td>\n",
       "      <td>575</td>\n",
       "      <td>108</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>11/03/13</td>\n",
       "      <td>12/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>21</td>\n",
       "      <td>13</td>\n",
       "      <td>1028</td>\n",
       "      <td>89</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>22</td>\n",
       "      <td>9</td>\n",
       "      <td>705</td>\n",
       "      <td>712</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>11/03/13</td>\n",
       "      <td>12/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>23</td>\n",
       "      <td>13</td>\n",
       "      <td>517</td>\n",
       "      <td>1067</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>24</td>\n",
       "      <td>5</td>\n",
       "      <td>893</td>\n",
       "      <td>761</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>12/01/13</td>\n",
       "      <td>15/02/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>25</td>\n",
       "      <td>13</td>\n",
       "      <td>796</td>\n",
       "      <td>248</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>26</td>\n",
       "      <td>11</td>\n",
       "      <td>506</td>\n",
       "      <td>1464</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>22/04/13</td>\n",
       "      <td>07/06/13</td>\n",
       "      <td>18-25</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>27</td>\n",
       "      <td>5</td>\n",
       "      <td>689</td>\n",
       "      <td>186</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>12/01/13</td>\n",
       "      <td>15/02/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>28</td>\n",
       "      <td>13</td>\n",
       "      <td>268</td>\n",
       "      <td>1152</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>10.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>29</td>\n",
       "      <td>8</td>\n",
       "      <td>8</td>\n",
       "      <td>695</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>56-70</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>30</td>\n",
       "      <td>8</td>\n",
       "      <td>674</td>\n",
       "      <td>886</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>32</td>\n",
       "      <td>30</td>\n",
       "      <td>320</td>\n",
       "      <td>1255</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/11/12</td>\n",
       "      <td>04/01/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>33</td>\n",
       "      <td>12</td>\n",
       "      <td>109</td>\n",
       "      <td>553</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>22/04/13</td>\n",
       "      <td>24/05/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>11.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>34</td>\n",
       "      <td>8</td>\n",
       "      <td>278</td>\n",
       "      <td>1398</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>35</td>\n",
       "      <td>13</td>\n",
       "      <td>1031</td>\n",
       "      <td>1031</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>39</td>\n",
       "      <td>26</td>\n",
       "      <td>326</td>\n",
       "      <td>63</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>12/08/12</td>\n",
       "      <td>21/09/12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>42</td>\n",
       "      <td>30</td>\n",
       "      <td>363</td>\n",
       "      <td>88</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/11/12</td>\n",
       "      <td>04/01/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>43</td>\n",
       "      <td>8</td>\n",
       "      <td>911</td>\n",
       "      <td>197</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>18-25</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>45</td>\n",
       "      <td>8</td>\n",
       "      <td>383</td>\n",
       "      <td>1095</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>46</td>\n",
       "      <td>13</td>\n",
       "      <td>482</td>\n",
       "      <td>1096</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78339</th>\n",
       "      <td>128549</td>\n",
       "      <td>13</td>\n",
       "      <td>578</td>\n",
       "      <td>772</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78340</th>\n",
       "      <td>128550</td>\n",
       "      <td>26</td>\n",
       "      <td>947</td>\n",
       "      <td>758</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>12/08/12</td>\n",
       "      <td>21/09/12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78341</th>\n",
       "      <td>128551</td>\n",
       "      <td>13</td>\n",
       "      <td>865</td>\n",
       "      <td>1365</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78342</th>\n",
       "      <td>128555</td>\n",
       "      <td>26</td>\n",
       "      <td>1080</td>\n",
       "      <td>1450</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>12/08/12</td>\n",
       "      <td>21/09/12</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Single</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78343</th>\n",
       "      <td>128556</td>\n",
       "      <td>8</td>\n",
       "      <td>661</td>\n",
       "      <td>186</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78344</th>\n",
       "      <td>128557</td>\n",
       "      <td>8</td>\n",
       "      <td>920</td>\n",
       "      <td>939</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>70+</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78345</th>\n",
       "      <td>128558</td>\n",
       "      <td>10</td>\n",
       "      <td>996</td>\n",
       "      <td>1309</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>08/04/13</td>\n",
       "      <td>10/05/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78346</th>\n",
       "      <td>128559</td>\n",
       "      <td>2</td>\n",
       "      <td>347</td>\n",
       "      <td>1086</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>17/12/12</td>\n",
       "      <td>18/01/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78347</th>\n",
       "      <td>128560</td>\n",
       "      <td>8</td>\n",
       "      <td>59</td>\n",
       "      <td>84</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78348</th>\n",
       "      <td>128562</td>\n",
       "      <td>7</td>\n",
       "      <td>986</td>\n",
       "      <td>1490</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>02/02/13</td>\n",
       "      <td>08/03/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78349</th>\n",
       "      <td>128563</td>\n",
       "      <td>13</td>\n",
       "      <td>142</td>\n",
       "      <td>1331</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78350</th>\n",
       "      <td>128565</td>\n",
       "      <td>30</td>\n",
       "      <td>857</td>\n",
       "      <td>979</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/11/12</td>\n",
       "      <td>04/01/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78351</th>\n",
       "      <td>128566</td>\n",
       "      <td>8</td>\n",
       "      <td>550</td>\n",
       "      <td>51</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>70+</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78352</th>\n",
       "      <td>128568</td>\n",
       "      <td>29</td>\n",
       "      <td>1081</td>\n",
       "      <td>19</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>08/10/12</td>\n",
       "      <td>30/11/12</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78353</th>\n",
       "      <td>128569</td>\n",
       "      <td>10</td>\n",
       "      <td>1043</td>\n",
       "      <td>686</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>08/04/13</td>\n",
       "      <td>10/05/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78354</th>\n",
       "      <td>128570</td>\n",
       "      <td>8</td>\n",
       "      <td>656</td>\n",
       "      <td>143</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>70+</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78355</th>\n",
       "      <td>128575</td>\n",
       "      <td>8</td>\n",
       "      <td>269</td>\n",
       "      <td>977</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78356</th>\n",
       "      <td>128576</td>\n",
       "      <td>12</td>\n",
       "      <td>705</td>\n",
       "      <td>621</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>22/04/13</td>\n",
       "      <td>24/05/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78357</th>\n",
       "      <td>128577</td>\n",
       "      <td>26</td>\n",
       "      <td>368</td>\n",
       "      <td>1508</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>12/08/12</td>\n",
       "      <td>21/09/12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78358</th>\n",
       "      <td>128579</td>\n",
       "      <td>9</td>\n",
       "      <td>535</td>\n",
       "      <td>1384</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>11/03/13</td>\n",
       "      <td>12/04/13</td>\n",
       "      <td>56-70</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78359</th>\n",
       "      <td>128580</td>\n",
       "      <td>5</td>\n",
       "      <td>934</td>\n",
       "      <td>1378</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>12/01/13</td>\n",
       "      <td>15/02/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>8.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78360</th>\n",
       "      <td>128581</td>\n",
       "      <td>26</td>\n",
       "      <td>475</td>\n",
       "      <td>207</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>12/08/12</td>\n",
       "      <td>21/09/12</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78361</th>\n",
       "      <td>128582</td>\n",
       "      <td>29</td>\n",
       "      <td>443</td>\n",
       "      <td>992</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>08/10/12</td>\n",
       "      <td>30/11/12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78362</th>\n",
       "      <td>128585</td>\n",
       "      <td>10</td>\n",
       "      <td>662</td>\n",
       "      <td>1563</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>08/04/13</td>\n",
       "      <td>10/05/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78363</th>\n",
       "      <td>128586</td>\n",
       "      <td>30</td>\n",
       "      <td>291</td>\n",
       "      <td>58</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/11/12</td>\n",
       "      <td>04/01/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78364</th>\n",
       "      <td>128587</td>\n",
       "      <td>8</td>\n",
       "      <td>71</td>\n",
       "      <td>1523</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>70+</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78365</th>\n",
       "      <td>128589</td>\n",
       "      <td>30</td>\n",
       "      <td>547</td>\n",
       "      <td>937</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/11/12</td>\n",
       "      <td>04/01/13</td>\n",
       "      <td>70+</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78366</th>\n",
       "      <td>128590</td>\n",
       "      <td>8</td>\n",
       "      <td>754</td>\n",
       "      <td>1004</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78367</th>\n",
       "      <td>128592</td>\n",
       "      <td>13</td>\n",
       "      <td>134</td>\n",
       "      <td>71</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5+</td>\n",
       "      <td>3+</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>78368</th>\n",
       "      <td>128595</td>\n",
       "      <td>13</td>\n",
       "      <td>681</td>\n",
       "      <td>623</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>78369 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           id  campaign_id  coupon_id  customer_id  redemption_status  \\\n",
       "0           1           13         27         1053                  0   \n",
       "1           2           13        116           48                  0   \n",
       "2           6            9        635          205                  0   \n",
       "3           7           13        644         1050                  0   \n",
       "4           9            8       1017         1489                  0   \n",
       "5          11           11        795          793                  0   \n",
       "6          14            9        444          590                  0   \n",
       "7          15           29        538          368                  0   \n",
       "8          17           30        857          523                  0   \n",
       "9          19            2        559          679                  0   \n",
       "10         20            9        575          108                  0   \n",
       "11         21           13       1028           89                  0   \n",
       "12         22            9        705          712                  0   \n",
       "13         23           13        517         1067                  0   \n",
       "14         24            5        893          761                  0   \n",
       "15         25           13        796          248                  0   \n",
       "16         26           11        506         1464                  0   \n",
       "17         27            5        689          186                  0   \n",
       "18         28           13        268         1152                  0   \n",
       "19         29            8          8          695                  0   \n",
       "20         30            8        674          886                  0   \n",
       "21         32           30        320         1255                  0   \n",
       "22         33           12        109          553                  0   \n",
       "23         34            8        278         1398                  0   \n",
       "24         35           13       1031         1031                  0   \n",
       "25         39           26        326           63                  0   \n",
       "26         42           30        363           88                  0   \n",
       "27         43            8        911          197                  0   \n",
       "28         45            8        383         1095                  0   \n",
       "29         46           13        482         1096                  0   \n",
       "...       ...          ...        ...          ...                ...   \n",
       "78339  128549           13        578          772                  0   \n",
       "78340  128550           26        947          758                  0   \n",
       "78341  128551           13        865         1365                  0   \n",
       "78342  128555           26       1080         1450                  0   \n",
       "78343  128556            8        661          186                  0   \n",
       "78344  128557            8        920          939                  0   \n",
       "78345  128558           10        996         1309                  0   \n",
       "78346  128559            2        347         1086                  0   \n",
       "78347  128560            8         59           84                  0   \n",
       "78348  128562            7        986         1490                  0   \n",
       "78349  128563           13        142         1331                  0   \n",
       "78350  128565           30        857          979                  0   \n",
       "78351  128566            8        550           51                  0   \n",
       "78352  128568           29       1081           19                  0   \n",
       "78353  128569           10       1043          686                  0   \n",
       "78354  128570            8        656          143                  0   \n",
       "78355  128575            8        269          977                  0   \n",
       "78356  128576           12        705          621                  0   \n",
       "78357  128577           26        368         1508                  0   \n",
       "78358  128579            9        535         1384                  0   \n",
       "78359  128580            5        934         1378                  0   \n",
       "78360  128581           26        475          207                  0   \n",
       "78361  128582           29        443          992                  0   \n",
       "78362  128585           10        662         1563                  0   \n",
       "78363  128586           30        291           58                  0   \n",
       "78364  128587            8         71         1523                  0   \n",
       "78365  128589           30        547          937                  0   \n",
       "78366  128590            8        754         1004                  0   \n",
       "78367  128592           13        134           71                  0   \n",
       "78368  128595           13        681          623                  0   \n",
       "\n",
       "      campaign_type start_date  end_date age_range marital_status  rented  \\\n",
       "0                 X   19/05/13  05/07/13     46-55         Single     0.0   \n",
       "1                 X   19/05/13  05/07/13     36-45        Married     0.0   \n",
       "2                 Y   11/03/13  12/04/13     46-55        Married     0.0   \n",
       "3                 X   19/05/13  05/07/13       NaN            NaN     NaN   \n",
       "4                 X   16/02/13  05/04/13     46-55        Married     0.0   \n",
       "5                 Y   22/04/13  07/06/13     46-55        Married     0.0   \n",
       "6                 Y   11/03/13  12/04/13     36-45        Married     0.0   \n",
       "7                 Y   08/10/12  30/11/12     36-45         Single     0.0   \n",
       "8                 X   19/11/12  04/01/13       NaN            NaN     NaN   \n",
       "9                 Y   17/12/12  18/01/13     36-45         Single     1.0   \n",
       "10                Y   11/03/13  12/04/13     46-55         Single     0.0   \n",
       "11                X   19/05/13  05/07/13     46-55         Single     0.0   \n",
       "12                Y   11/03/13  12/04/13     46-55        Married     0.0   \n",
       "13                X   19/05/13  05/07/13     46-55         Single     0.0   \n",
       "14                Y   12/01/13  15/02/13       NaN            NaN     NaN   \n",
       "15                X   19/05/13  05/07/13     36-45         Single     0.0   \n",
       "16                Y   22/04/13  07/06/13     18-25         Single     0.0   \n",
       "17                Y   12/01/13  15/02/13     26-35        Married     0.0   \n",
       "18                X   19/05/13  05/07/13     46-55        Married     0.0   \n",
       "19                X   16/02/13  05/04/13     56-70        Married     0.0   \n",
       "20                X   16/02/13  05/04/13     46-55        Married     0.0   \n",
       "21                X   19/11/12  04/01/13       NaN            NaN     NaN   \n",
       "22                Y   22/04/13  24/05/13     36-45        Married     0.0   \n",
       "23                X   16/02/13  05/04/13     36-45         Single     0.0   \n",
       "24                X   19/05/13  05/07/13     36-45         Single     0.0   \n",
       "25                X   12/08/12  21/09/12       NaN            NaN     NaN   \n",
       "26                X   19/11/12  04/01/13       NaN            NaN     NaN   \n",
       "27                X   16/02/13  05/04/13     18-25         Single     0.0   \n",
       "28                X   16/02/13  05/04/13       NaN            NaN     NaN   \n",
       "29                X   19/05/13  05/07/13       NaN            NaN     NaN   \n",
       "...             ...        ...       ...       ...            ...     ...   \n",
       "78339             X   19/05/13  05/07/13       NaN            NaN     NaN   \n",
       "78340             X   12/08/12  21/09/12       NaN            NaN     NaN   \n",
       "78341             X   19/05/13  05/07/13       NaN            NaN     NaN   \n",
       "78342             X   12/08/12  21/09/12     36-45         Single     1.0   \n",
       "78343             X   16/02/13  05/04/13     26-35        Married     0.0   \n",
       "78344             X   16/02/13  05/04/13       70+         Single     0.0   \n",
       "78345             Y   08/04/13  10/05/13     26-35        Married     0.0   \n",
       "78346             Y   17/12/12  18/01/13       NaN            NaN     NaN   \n",
       "78347             X   16/02/13  05/04/13     46-55         Single     0.0   \n",
       "78348             Y   02/02/13  08/03/13     26-35         Single     0.0   \n",
       "78349             X   19/05/13  05/07/13       NaN            NaN     NaN   \n",
       "78350             X   19/11/12  04/01/13       NaN            NaN     NaN   \n",
       "78351             X   16/02/13  05/04/13       70+        Married     0.0   \n",
       "78352             Y   08/10/12  30/11/12     46-55         Single     0.0   \n",
       "78353             Y   08/04/13  10/05/13     26-35        Married     0.0   \n",
       "78354             X   16/02/13  05/04/13       70+         Single     0.0   \n",
       "78355             X   16/02/13  05/04/13     46-55        Married     0.0   \n",
       "78356             Y   22/04/13  24/05/13       NaN            NaN     NaN   \n",
       "78357             X   12/08/12  21/09/12       NaN            NaN     NaN   \n",
       "78358             Y   11/03/13  12/04/13     56-70         Single     0.0   \n",
       "78359             Y   12/01/13  15/02/13     26-35        Married     0.0   \n",
       "78360             X   12/08/12  21/09/12     46-55         Single     0.0   \n",
       "78361             Y   08/10/12  30/11/12       NaN            NaN     NaN   \n",
       "78362             Y   08/04/13  10/05/13       NaN            NaN     NaN   \n",
       "78363             X   19/11/12  04/01/13     26-35         Single     0.0   \n",
       "78364             X   16/02/13  05/04/13       70+        Married     0.0   \n",
       "78365             X   19/11/12  04/01/13       70+        Married     0.0   \n",
       "78366             X   16/02/13  05/04/13       NaN            NaN     NaN   \n",
       "78367             X   19/05/13  05/07/13     36-45        Married     0.0   \n",
       "78368             X   19/05/13  05/07/13       NaN            NaN     NaN   \n",
       "\n",
       "      family_size no_of_children  income_bracket  \n",
       "0               1              0             5.0  \n",
       "1               2              0             3.0  \n",
       "2               2              0             7.0  \n",
       "3             NaN            NaN             NaN  \n",
       "4               2              0             3.0  \n",
       "5               2              0             5.0  \n",
       "6               2              0             1.0  \n",
       "7               1              0             5.0  \n",
       "8             NaN            NaN             NaN  \n",
       "9               2              1             4.0  \n",
       "10              1              0             5.0  \n",
       "11              1              0             3.0  \n",
       "12              3              1             5.0  \n",
       "13              1              0             5.0  \n",
       "14            NaN            NaN             NaN  \n",
       "15              1              0             3.0  \n",
       "16              1              0             1.0  \n",
       "17              2              0             4.0  \n",
       "18              3              1            10.0  \n",
       "19              2              0             6.0  \n",
       "20              3              1             5.0  \n",
       "21            NaN            NaN             NaN  \n",
       "22              3              1            11.0  \n",
       "23              1              0             2.0  \n",
       "24              1              0             2.0  \n",
       "25            NaN            NaN             NaN  \n",
       "26            NaN            NaN             NaN  \n",
       "27              4              2             4.0  \n",
       "28            NaN            NaN             NaN  \n",
       "29            NaN            NaN             NaN  \n",
       "...           ...            ...             ...  \n",
       "78339         NaN            NaN             NaN  \n",
       "78340         NaN            NaN             NaN  \n",
       "78341         NaN            NaN             NaN  \n",
       "78342           1              0             4.0  \n",
       "78343           2              0             4.0  \n",
       "78344           1              0             3.0  \n",
       "78345           3              1             7.0  \n",
       "78346         NaN            NaN             NaN  \n",
       "78347           1              0             8.0  \n",
       "78348           1              0             5.0  \n",
       "78349         NaN            NaN             NaN  \n",
       "78350         NaN            NaN             NaN  \n",
       "78351           2              0             2.0  \n",
       "78352           1              0             3.0  \n",
       "78353           2              0             4.0  \n",
       "78354           1              0             2.0  \n",
       "78355           2              0             4.0  \n",
       "78356         NaN            NaN             NaN  \n",
       "78357         NaN            NaN             NaN  \n",
       "78358           1              0             3.0  \n",
       "78359           4              2             8.0  \n",
       "78360           1              0             5.0  \n",
       "78361         NaN            NaN             NaN  \n",
       "78362         NaN            NaN             NaN  \n",
       "78363           1              0             4.0  \n",
       "78364           2              0             1.0  \n",
       "78365           2              0             2.0  \n",
       "78366         NaN            NaN             NaN  \n",
       "78367          5+             3+             4.0  \n",
       "78368         NaN            NaN             NaN  \n",
       "\n",
       "[78369 rows x 14 columns]"
      ]
     },
     "execution_count": 154,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "newtrain=newtrain.merge(cust_demo,on='customer_id',how='left')\n",
    "newtrain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "metadata": {},
   "outputs": [],
   "source": [
    "newtrain['marital_status'].fillna(newtrain['marital_status'].mode()[0],inplace=True)\n",
    "newtrain['age_range'].fillna(newtrain['age_range'].mode()[0],inplace=True)\n",
    "newtrain['rented'].fillna(newtrain['rented'].mode()[0],inplace=True)\n",
    "newtrain['family_size'].fillna(newtrain['family_size'].mode()[0],inplace=True)\n",
    "newtrain['no_of_children'].fillna(newtrain['no_of_children'].mode()[0],inplace=True)\n",
    "newtrain['income_bracket'].fillna(newtrain['income_bracket'].mode()[0],inplace=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "metadata": {},
   "outputs": [],
   "source": [
    "newtest=newtest.merge(cust_demo,on='customer_id',how='left')\n",
    "newtrain\n",
    "\n",
    "newtest['marital_status'].fillna(newtest['marital_status'].mode()[0],inplace=True)\n",
    "newtest['age_range'].fillna(newtest['age_range'].mode()[0],inplace=True)\n",
    "newtest['rented'].fillna(newtest['rented'].mode()[0],inplace=True)\n",
    "newtest['family_size'].fillna(newtest['family_size'].mode()[0],inplace=True)\n",
    "newtest['no_of_children'].fillna(newtest['no_of_children'].mode()[0],inplace=True)\n",
    "newtest['income_bracket'].fillna(newtest['income_bracket'].mode()[0],inplace=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>campaign_id</th>\n",
       "      <th>coupon_id</th>\n",
       "      <th>customer_id</th>\n",
       "      <th>redemption_status</th>\n",
       "      <th>campaign_type</th>\n",
       "      <th>start_date</th>\n",
       "      <th>end_date</th>\n",
       "      <th>age_range</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>...</th>\n",
       "      <th>quantity</th>\n",
       "      <th>selling_price</th>\n",
       "      <th>other_discount</th>\n",
       "      <th>coupon_discount</th>\n",
       "      <th>brand</th>\n",
       "      <th>brand_type</th>\n",
       "      <th>category</th>\n",
       "      <th>date</th>\n",
       "      <th>no_of_compaigns_participated</th>\n",
       "      <th>no_of_items_bought</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>13</td>\n",
       "      <td>27</td>\n",
       "      <td>1053</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Single</td>\n",
       "      <td>...</td>\n",
       "      <td>105551</td>\n",
       "      <td>57120.75</td>\n",
       "      <td>-10282.37</td>\n",
       "      <td>-89.05</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>310</td>\n",
       "      <td>80</td>\n",
       "      <td>208</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>13</td>\n",
       "      <td>116</td>\n",
       "      <td>48</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Married</td>\n",
       "      <td>...</td>\n",
       "      <td>12143</td>\n",
       "      <td>90185.10</td>\n",
       "      <td>-10664.18</td>\n",
       "      <td>-1237.79</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>385</td>\n",
       "      <td>64</td>\n",
       "      <td>244</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>635</td>\n",
       "      <td>205</td>\n",
       "      <td>0</td>\n",
       "      <td>Y</td>\n",
       "      <td>11/03/13</td>\n",
       "      <td>12/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>...</td>\n",
       "      <td>1351</td>\n",
       "      <td>117461.66</td>\n",
       "      <td>-17261.79</td>\n",
       "      <td>-2145.72</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>970</td>\n",
       "      <td>83</td>\n",
       "      <td>533</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7</td>\n",
       "      <td>13</td>\n",
       "      <td>644</td>\n",
       "      <td>1050</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>19/05/13</td>\n",
       "      <td>05/07/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>...</td>\n",
       "      <td>306</td>\n",
       "      <td>23291.42</td>\n",
       "      <td>-3947.37</td>\n",
       "      <td>-178.10</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>237</td>\n",
       "      <td>64</td>\n",
       "      <td>216</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>9</td>\n",
       "      <td>8</td>\n",
       "      <td>1017</td>\n",
       "      <td>1489</td>\n",
       "      <td>0</td>\n",
       "      <td>X</td>\n",
       "      <td>16/02/13</td>\n",
       "      <td>05/04/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>...</td>\n",
       "      <td>139063</td>\n",
       "      <td>67797.49</td>\n",
       "      <td>-11534.90</td>\n",
       "      <td>-265.01</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>562</td>\n",
       "      <td>97</td>\n",
       "      <td>327</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  campaign_id  coupon_id  customer_id  redemption_status campaign_type  \\\n",
       "0   1           13         27         1053                  0             X   \n",
       "1   2           13        116           48                  0             X   \n",
       "2   6            9        635          205                  0             Y   \n",
       "3   7           13        644         1050                  0             X   \n",
       "4   9            8       1017         1489                  0             X   \n",
       "\n",
       "  start_date  end_date age_range marital_status         ...          quantity  \\\n",
       "0   19/05/13  05/07/13     46-55         Single         ...            105551   \n",
       "1   19/05/13  05/07/13     36-45        Married         ...             12143   \n",
       "2   11/03/13  12/04/13     46-55        Married         ...              1351   \n",
       "3   19/05/13  05/07/13     46-55        Married         ...               306   \n",
       "4   16/02/13  05/04/13     46-55        Married         ...            139063   \n",
       "\n",
       "  selling_price other_discount  coupon_discount  brand   brand_type  category  \\\n",
       "0      57120.75      -10282.37           -89.05     56  Established   Grocery   \n",
       "1      90185.10      -10664.18         -1237.79     56  Established   Grocery   \n",
       "2     117461.66      -17261.79         -2145.72     56  Established   Grocery   \n",
       "3      23291.42       -3947.37          -178.10     56  Established   Grocery   \n",
       "4      67797.49      -11534.90          -265.01     56  Established   Grocery   \n",
       "\n",
       "   date  no_of_compaigns_participated  no_of_items_bought  \n",
       "0   310                            80                 208  \n",
       "1   385                            64                 244  \n",
       "2   970                            83                 533  \n",
       "3   237                            64                 216  \n",
       "4   562                            97                 327  \n",
       "\n",
       "[5 rows x 25 columns]"
      ]
     },
     "execution_count": 163,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "newtrain2=newtrain.merge(ct_data_groupby,on='customer_id',how=\"left\")\n",
    "newtrain2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>campaign_id</th>\n",
       "      <th>coupon_id</th>\n",
       "      <th>customer_id</th>\n",
       "      <th>campaign_type</th>\n",
       "      <th>start_date</th>\n",
       "      <th>end_date</th>\n",
       "      <th>age_range</th>\n",
       "      <th>marital_status</th>\n",
       "      <th>rented</th>\n",
       "      <th>...</th>\n",
       "      <th>quantity</th>\n",
       "      <th>selling_price</th>\n",
       "      <th>other_discount</th>\n",
       "      <th>coupon_discount</th>\n",
       "      <th>brand</th>\n",
       "      <th>brand_type</th>\n",
       "      <th>category</th>\n",
       "      <th>date</th>\n",
       "      <th>no_of_compaigns_participated</th>\n",
       "      <th>no_of_items_bought</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>22</td>\n",
       "      <td>869</td>\n",
       "      <td>967</td>\n",
       "      <td>X</td>\n",
       "      <td>16/09/13</td>\n",
       "      <td>18/10/13</td>\n",
       "      <td>36-45</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>16644</td>\n",
       "      <td>156733.77</td>\n",
       "      <td>-16292.99</td>\n",
       "      <td>-2111.86</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>1362</td>\n",
       "      <td>67</td>\n",
       "      <td>658</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>20</td>\n",
       "      <td>389</td>\n",
       "      <td>1566</td>\n",
       "      <td>Y</td>\n",
       "      <td>07/09/13</td>\n",
       "      <td>16/11/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>282396</td>\n",
       "      <td>297070.87</td>\n",
       "      <td>-32760.94</td>\n",
       "      <td>-1489.97</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>2661</td>\n",
       "      <td>89</td>\n",
       "      <td>1214</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>981</td>\n",
       "      <td>510</td>\n",
       "      <td>X</td>\n",
       "      <td>16/09/13</td>\n",
       "      <td>18/10/13</td>\n",
       "      <td>26-35</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>181500</td>\n",
       "      <td>161811.27</td>\n",
       "      <td>-39450.39</td>\n",
       "      <td>-2384.75</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>1642</td>\n",
       "      <td>141</td>\n",
       "      <td>1019</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>25</td>\n",
       "      <td>1069</td>\n",
       "      <td>361</td>\n",
       "      <td>Y</td>\n",
       "      <td>21/10/13</td>\n",
       "      <td>22/11/13</td>\n",
       "      <td>18-25</td>\n",
       "      <td>Single</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>22196</td>\n",
       "      <td>49149.16</td>\n",
       "      <td>-7705.95</td>\n",
       "      <td>0.00</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>573</td>\n",
       "      <td>140</td>\n",
       "      <td>323</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10</td>\n",
       "      <td>17</td>\n",
       "      <td>498</td>\n",
       "      <td>811</td>\n",
       "      <td>Y</td>\n",
       "      <td>29/07/13</td>\n",
       "      <td>30/08/13</td>\n",
       "      <td>46-55</td>\n",
       "      <td>Married</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1729</td>\n",
       "      <td>117044.09</td>\n",
       "      <td>-19214.01</td>\n",
       "      <td>-89.04</td>\n",
       "      <td>56</td>\n",
       "      <td>Established</td>\n",
       "      <td>Grocery</td>\n",
       "      <td>1319</td>\n",
       "      <td>123</td>\n",
       "      <td>720</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  campaign_id  coupon_id  customer_id campaign_type start_date  end_date  \\\n",
       "0   3           22        869          967             X   16/09/13  18/10/13   \n",
       "1   4           20        389         1566             Y   07/09/13  16/11/13   \n",
       "2   5           22        981          510             X   16/09/13  18/10/13   \n",
       "3   8           25       1069          361             Y   21/10/13  22/11/13   \n",
       "4  10           17        498          811             Y   29/07/13  30/08/13   \n",
       "\n",
       "  age_range marital_status  rented        ...         quantity selling_price  \\\n",
       "0     36-45         Single     0.0        ...            16644     156733.77   \n",
       "1     26-35        Married     0.0        ...           282396     297070.87   \n",
       "2     26-35        Married     0.0        ...           181500     161811.27   \n",
       "3     18-25         Single     0.0        ...            22196      49149.16   \n",
       "4     46-55        Married     0.0        ...             1729     117044.09   \n",
       "\n",
       "   other_discount  coupon_discount  brand   brand_type  category  date  \\\n",
       "0       -16292.99         -2111.86     56  Established   Grocery  1362   \n",
       "1       -32760.94         -1489.97     56  Established   Grocery  2661   \n",
       "2       -39450.39         -2384.75     56  Established   Grocery  1642   \n",
       "3        -7705.95             0.00     56  Established   Grocery   573   \n",
       "4       -19214.01           -89.04     56  Established   Grocery  1319   \n",
       "\n",
       "   no_of_compaigns_participated no_of_items_bought  \n",
       "0                            67                658  \n",
       "1                            89               1214  \n",
       "2                           141               1019  \n",
       "3                           140                323  \n",
       "4                           123                720  \n",
       "\n",
       "[5 rows x 24 columns]"
      ]
     },
     "execution_count": 165,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "newtest2=newtest.merge(ct_data_groupby,on='customer_id',how=\"left\")\n",
    "newtest2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [],
   "source": [
    "newtrain2['coupon_campaign_days']=pd.to_datetime(newtrain2['end_date'],dayfirst=True)-pd.to_datetime(newtrain2['start_date'],dayfirst=True)\n",
    "\n",
    "newtrain2['coupon_campaign_days']=newtrain2['coupon_campaign_days'].apply(lambda x: x.days)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "metadata": {},
   "outputs": [],
   "source": [
    "newtest2['coupon_campaign_days']=pd.to_datetime(newtest2['end_date'],dayfirst=True)-pd.to_datetime(newtest2['start_date'],dayfirst=True)\n",
    "\n",
    "newtest2['coupon_campaign_days']=newtest2['coupon_campaign_days'].apply(lambda x: x.days)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "metadata": {},
   "outputs": [],
   "source": [
    "newtrain3=newtrain2.drop(['id', 'campaign_id', 'coupon_id', 'customer_id','start_date','end_date','item_id'],axis=1)\n",
    "newtest3=newtest2.drop(['id', 'campaign_id', 'coupon_id', 'customer_id','start_date','end_date','item_id'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 174,
   "metadata": {},
   "outputs": [],
   "source": [
    "get_dum_cols=['campaign_type','brand','brand_type','category','age_range','income_bracket','no_of_children','family_size','marital_status']\n",
    "newtrain3=pd.get_dummies(newtrain3,columns=get_dum_cols,drop_first=True)\n",
    "newtest3=pd.get_dummies(newtest3,columns=get_dum_cols,drop_first=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 175,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['redemption_status', 'rented', 'quantity', 'selling_price',\n",
       "       'other_discount', 'coupon_discount', 'date',\n",
       "       'no_of_compaigns_participated', 'no_of_items_bought',\n",
       "       'coupon_campaign_days', 'campaign_type_Y', 'brand_63', 'brand_89',\n",
       "       'brand_133', 'brand_158', 'brand_278', 'brand_303', 'brand_369',\n",
       "       'brand_482', 'brand_487', 'brand_524', 'brand_659', 'brand_681',\n",
       "       'brand_779', 'brand_838', 'brand_892', 'brand_923', 'brand_946',\n",
       "       'brand_967', 'brand_1075', 'brand_1088', 'brand_1101', 'brand_1124',\n",
       "       'brand_1337', 'brand_1447', 'brand_1562', 'brand_1564', 'brand_1996',\n",
       "       'brand_2025', 'brand_2084', 'brand_2370', 'brand_2379', 'brand_4991',\n",
       "       'brand_type_Local', 'category_Grocery', 'category_Packaged Meat',\n",
       "       'category_Pharmaceutical', 'age_range_26-35', 'age_range_36-45',\n",
       "       'age_range_46-55', 'age_range_56-70', 'age_range_70+',\n",
       "       'income_bracket_2.0', 'income_bracket_3.0', 'income_bracket_4.0',\n",
       "       'income_bracket_5.0', 'income_bracket_6.0', 'income_bracket_7.0',\n",
       "       'income_bracket_8.0', 'income_bracket_9.0', 'income_bracket_10.0',\n",
       "       'income_bracket_11.0', 'income_bracket_12.0', 'no_of_children_1',\n",
       "       'no_of_children_2', 'no_of_children_3+', 'family_size_2',\n",
       "       'family_size_3', 'family_size_4', 'family_size_5+',\n",
       "       'marital_status_Single'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 175,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "newtrain3.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 177,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[100]\tcv_agg's auc: 0.878759 + 0.0242008\n",
      "[200]\tcv_agg's auc: 0.884601 + 0.0230839\n",
      "[300]\tcv_agg's auc: 0.887062 + 0.0224103\n",
      "[400]\tcv_agg's auc: 0.889042 + 0.0214832\n",
      "[500]\tcv_agg's auc: 0.889923 + 0.0212531\n"
     ]
    }
   ],
   "source": [
    "X=newtrain3.drop('redemption_status',axis=1)\n",
    "y=newtrain3['redemption_status']\n",
    "param_lgb = { 'boosting_type': 'gbdt', 'objective': 'binary', 'metric':'auc',\n",
    "             'bagging_freq':1, 'subsample':1, 'feature_fraction': 0.7,\n",
    "              'num_leaves': 8, 'learning_rate': 0.05, 'lambda_l1':5,'max_bin':255}\n",
    "# form LightGBM datasets\n",
    "dtrain_lgb = lgb.Dataset(X, label=y)\n",
    "# LightGBM, cross-validation\n",
    "cv_result_lgb = lgb.cv(param_lgb, \n",
    "                       dtrain_lgb, \n",
    "                       num_boost_round=1000, \n",
    "                       nfold=20, \n",
    "                       stratified=True, \n",
    "                       early_stopping_rounds=15, \n",
    "                       verbose_eval=100, \n",
    "                       show_stdv=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([438, 333, 391, 563, 455, 486, 415, 328,  43,  13,   0,   0,   0,\n",
       "         0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   3,\n",
       "         0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
       "         0,   0,   0,   0,   1,   3,   0,   0,   0,   0])"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "model_lgb = lgb.train(param_lgb, dtrain_lgb, num_boost_round=len(cv_result_lgb['auc-mean']))\n",
    "y_pred=model_lgb.predict(newtest3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 179,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([  0, 435, 338, 437, 573, 443, 475, 419, 319,  56,   0,   0,   0,\n",
       "         0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   1,   0,\n",
       "         0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
       "         0,   0,   0,   1,   0,   0,   0,  11,   1,  13,   0,   3,   1,\n",
       "         0,   7,  13,   1,   0,   0,   0,   2,   0,   0,   4,   0,  11,\n",
       "        11,   2,   0,   0,  35])"
      ]
     },
     "execution_count": 179,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model_lgb.feature_importance()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 182,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['rented', 'quantity', 'selling_price', 'other_discount',\n",
       "       'coupon_discount', 'date', 'no_of_compaigns_participated',\n",
       "       'no_of_items_bought', 'coupon_campaign_days', 'campaign_type_Y',\n",
       "       'brand_63', 'brand_89', 'brand_133', 'brand_158', 'brand_278',\n",
       "       'brand_303', 'brand_369', 'brand_482', 'brand_487', 'brand_524',\n",
       "       'brand_659', 'brand_681', 'brand_779', 'brand_838', 'brand_892',\n",
       "       'brand_923', 'brand_946', 'brand_967', 'brand_1075', 'brand_1088',\n",
       "       'brand_1101', 'brand_1124', 'brand_1337', 'brand_1447', 'brand_1562',\n",
       "       'brand_1564', 'brand_1996', 'brand_2025', 'brand_2084', 'brand_2370',\n",
       "       'brand_2379', 'brand_4991', 'brand_type_Local', 'category_Grocery',\n",
       "       'category_Packaged Meat', 'category_Pharmaceutical', 'age_range_26-35',\n",
       "       'age_range_36-45', 'age_range_46-55', 'age_range_56-70',\n",
       "       'age_range_70+', 'income_bracket_2.0', 'income_bracket_3.0',\n",
       "       'income_bracket_4.0', 'income_bracket_5.0', 'income_bracket_6.0',\n",
       "       'income_bracket_7.0', 'income_bracket_8.0', 'income_bracket_9.0',\n",
       "       'income_bracket_10.0', 'income_bracket_11.0', 'income_bracket_12.0',\n",
       "       'no_of_children_1', 'no_of_children_2', 'no_of_children_3+',\n",
       "       'family_size_2', 'family_size_3', 'family_size_4', 'family_size_5+',\n",
       "       'marital_status_Single'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 182,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>redemption_status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>0.036027</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>0.008227</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>0.050259</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>0.000193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10</td>\n",
       "      <td>0.000203</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  redemption_status\n",
       "0   3           0.036027\n",
       "1   4           0.008227\n",
       "2   5           0.050259\n",
       "3   8           0.000193\n",
       "4  10           0.000203"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sample_submission=pd.read_csv('sample_submission2.csv')\n",
    "sample_submission.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 180,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>redemption_status</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>0.027868</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>0.007321</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>0.051074</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>0.000233</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>10</td>\n",
       "      <td>0.000225</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   id  redemption_status\n",
       "0   3           0.027868\n",
       "1   4           0.007321\n",
       "2   5           0.051074\n",
       "3   8           0.000233\n",
       "4  10           0.000225"
      ]
     },
     "execution_count": 180,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sample_submission['redemption_status']=y_pred\n",
    "sample_submission.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 181,
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_submission.to_csv('sample_submission5.csv',index=False)"
   ]
  }
 ],
 "metadata": {
  "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}