propensity_prediciton_using_logistic_regression_model.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a765668f",
   "metadata": {
    "papermill": {
     "duration": 0.038298,
     "end_time": "2022-01-30T17:31:33.481698",
     "exception": false,
     "start_time": "2022-01-30T17:31:33.443400",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Customer propensity to purchase**\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8e0cd257",
   "metadata": {
    "papermill": {
     "duration": 0.037147,
     "end_time": "2022-01-30T17:31:33.556806",
     "exception": false,
     "start_time": "2022-01-30T17:31:33.519659",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# **Introduction**\n",
    "\n",
    "Aim is to build a Machine Learning model that predicts the customer's probability of purchase using historical data. Each website has a lot of visitors every day but not all of them make a purchase. Instead of spending money to target such visitors using digital marketing like social media platforms, it makes sense to optimize this activity by targeting real valuable prospects who are more likely to make a purchase.<br><br>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fd06bf17",
   "metadata": {
    "papermill": {
     "duration": 0.037742,
     "end_time": "2022-01-30T17:31:33.630960",
     "exception": false,
     "start_time": "2022-01-30T17:31:33.593218",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## About Dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fbc64662",
   "metadata": {
    "papermill": {
     "duration": 0.036742,
     "end_time": "2022-01-30T17:31:33.705517",
     "exception": false,
     "start_time": "2022-01-30T17:31:33.668775",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "For simplicity we just keep subset of dataset. Columns are as below:\n",
    "\n",
    "'UserID' – Unique Identifier for each customer\n",
    "\n",
    "'basket_add_detail' – A binary variable indicating if the customer added an item to the basket from the product detail page\n",
    "\n",
    "'promo_banner_click' – A binary variable indicating if the customer clicked on any promotional banners\n",
    "\n",
    "'sign_in' – Another binary variable, indicating if the customer signed into our website\n",
    "\n",
    "'returning_user' – Again, a binary variable indicating if the customer is a returning visitor to our website\n",
    "\n",
    "'saw_homepage' – A binary variable indicating if the customer saw the homepage of the website\n",
    "\n",
    "'ordered' – Our target variable. A binary variable indicating if the customer placed an order"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52e89517",
   "metadata": {
    "papermill": {
     "duration": 0.035112,
     "end_time": "2022-01-30T17:31:33.777184",
     "exception": false,
     "start_time": "2022-01-30T17:31:33.742072",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Import libraries we required"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "2553c9a8",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:11.556306Z",
     "start_time": "2022-03-02T12:27:11.551236Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:33.930710Z",
     "iopub.status.busy": "2022-01-30T17:31:33.930051Z",
     "iopub.status.idle": "2022-01-30T17:31:35.174835Z",
     "shell.execute_reply": "2022-01-30T17:31:35.173835Z",
     "shell.execute_reply.started": "2022-01-30T17:04:37.607934Z"
    },
    "papermill": {
     "duration": 1.290401,
     "end_time": "2022-01-30T17:31:35.175066",
     "exception": false,
     "start_time": "2022-01-30T17:31:33.884665",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8b773f17",
   "metadata": {
    "papermill": {
     "duration": 0.036403,
     "end_time": "2022-01-30T17:31:35.247215",
     "exception": false,
     "start_time": "2022-01-30T17:31:35.210812",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Import data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "a48ff25c",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:12.662112Z",
     "start_time": "2022-03-02T12:27:12.147583Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:35.422088Z",
     "iopub.status.busy": "2022-01-30T17:31:35.421134Z",
     "iopub.status.idle": "2022-01-30T17:31:37.294013Z",
     "shell.execute_reply": "2022-01-30T17:31:37.294564Z",
     "shell.execute_reply.started": "2022-01-30T17:04:37.635426Z"
    },
    "papermill": {
     "duration": 1.912805,
     "end_time": "2022-01-30T17:31:37.294755",
     "exception": false,
     "start_time": "2022-01-30T17:31:35.381950",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "data = pd.read_csv(\"training_sample.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "5094dda8",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:12.670945Z",
     "start_time": "2022-03-02T12:27:12.663409Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:37.371935Z",
     "iopub.status.busy": "2022-01-30T17:31:37.370902Z",
     "iopub.status.idle": "2022-01-30T17:31:37.402223Z",
     "shell.execute_reply": "2022-01-30T17:31:37.402748Z",
     "shell.execute_reply.started": "2022-01-30T17:04:38.875029Z"
    },
    "papermill": {
     "duration": 0.07199,
     "end_time": "2022-01-30T17:31:37.402950",
     "exception": false,
     "start_time": "2022-01-30T17:31:37.330960",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>UserID</th>\n",
       "      <th>basket_icon_click</th>\n",
       "      <th>basket_add_list</th>\n",
       "      <th>basket_add_detail</th>\n",
       "      <th>sort_by</th>\n",
       "      <th>image_picker</th>\n",
       "      <th>account_page_click</th>\n",
       "      <th>promo_banner_click</th>\n",
       "      <th>detail_wishlist_add</th>\n",
       "      <th>list_size_dropdown</th>\n",
       "      <th>...</th>\n",
       "      <th>saw_sizecharts</th>\n",
       "      <th>saw_delivery</th>\n",
       "      <th>saw_account_upgrade</th>\n",
       "      <th>saw_homepage</th>\n",
       "      <th>device_mobile</th>\n",
       "      <th>device_computer</th>\n",
       "      <th>device_tablet</th>\n",
       "      <th>returning_user</th>\n",
       "      <th>loc_uk</th>\n",
       "      <th>ordered</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a720-6b732349-a720-4862-bd21-644732</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a0c0-6b73247c-a0c0-4bd9-8baa-797356</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>86a8-6b735c67-86a8-407b-ba24-333055</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6a3d-6b736346-6a3d-4085-934b-396834</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>b74a-6b737717-b74a-45c3-8c6a-421140</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                UserID  basket_icon_click  basket_add_list  \\\n",
       "0  a720-6b732349-a720-4862-bd21-644732                  0                0   \n",
       "1  a0c0-6b73247c-a0c0-4bd9-8baa-797356                  0                0   \n",
       "2  86a8-6b735c67-86a8-407b-ba24-333055                  0                0   \n",
       "3  6a3d-6b736346-6a3d-4085-934b-396834                  0                0   \n",
       "4  b74a-6b737717-b74a-45c3-8c6a-421140                  0                1   \n",
       "\n",
       "   basket_add_detail  sort_by  image_picker  account_page_click  \\\n",
       "0                  0        0             0                   0   \n",
       "1                  0        0             0                   0   \n",
       "2                  0        0             0                   0   \n",
       "3                  0        0             0                   0   \n",
       "4                  0        1             0                   0   \n",
       "\n",
       "   promo_banner_click  detail_wishlist_add  list_size_dropdown  ...  \\\n",
       "0                   0                    0                   0  ...   \n",
       "1                   0                    0                   0  ...   \n",
       "2                   0                    0                   0  ...   \n",
       "3                   0                    0                   0  ...   \n",
       "4                   0                    0                   1  ...   \n",
       "\n",
       "   saw_sizecharts  saw_delivery  saw_account_upgrade  saw_homepage  \\\n",
       "0               0             0                    0             0   \n",
       "1               0             0                    0             0   \n",
       "2               0             0                    0             0   \n",
       "3               0             0                    0             0   \n",
       "4               0             0                    0             1   \n",
       "\n",
       "   device_mobile  device_computer  device_tablet  returning_user  loc_uk  \\\n",
       "0              1                0              0               0       1   \n",
       "1              1                0              0               0       1   \n",
       "2              1                0              0               1       1   \n",
       "3              1                0              0               1       1   \n",
       "4              0                0              1               0       1   \n",
       "\n",
       "   ordered  \n",
       "0        0  \n",
       "1        0  \n",
       "2        0  \n",
       "3        0  \n",
       "4        1  \n",
       "\n",
       "[5 rows x 25 columns]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "908529e7",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:12.833990Z",
     "start_time": "2022-03-02T12:27:12.672190Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:37.490600Z",
     "iopub.status.busy": "2022-01-30T17:31:37.489884Z",
     "iopub.status.idle": "2022-01-30T17:31:37.866176Z",
     "shell.execute_reply": "2022-01-30T17:31:37.866725Z",
     "shell.execute_reply.started": "2022-01-30T17:04:38.898399Z"
    },
    "papermill": {
     "duration": 0.425835,
     "end_time": "2022-01-30T17:31:37.866932",
     "exception": false,
     "start_time": "2022-01-30T17:31:37.441097",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>basket_icon_click</th>\n",
       "      <th>basket_add_list</th>\n",
       "      <th>basket_add_detail</th>\n",
       "      <th>sort_by</th>\n",
       "      <th>image_picker</th>\n",
       "      <th>account_page_click</th>\n",
       "      <th>promo_banner_click</th>\n",
       "      <th>detail_wishlist_add</th>\n",
       "      <th>list_size_dropdown</th>\n",
       "      <th>closed_minibasket_click</th>\n",
       "      <th>...</th>\n",
       "      <th>saw_sizecharts</th>\n",
       "      <th>saw_delivery</th>\n",
       "      <th>saw_account_upgrade</th>\n",
       "      <th>saw_homepage</th>\n",
       "      <th>device_mobile</th>\n",
       "      <th>device_computer</th>\n",
       "      <th>device_tablet</th>\n",
       "      <th>returning_user</th>\n",
       "      <th>loc_uk</th>\n",
       "      <th>ordered</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "      <td>455401.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.099150</td>\n",
       "      <td>0.074521</td>\n",
       "      <td>0.112916</td>\n",
       "      <td>0.036849</td>\n",
       "      <td>0.026735</td>\n",
       "      <td>0.003570</td>\n",
       "      <td>0.016208</td>\n",
       "      <td>0.003511</td>\n",
       "      <td>0.230362</td>\n",
       "      <td>0.017277</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000389</td>\n",
       "      <td>0.005542</td>\n",
       "      <td>0.001096</td>\n",
       "      <td>0.290024</td>\n",
       "      <td>0.680706</td>\n",
       "      <td>0.194220</td>\n",
       "      <td>0.128364</td>\n",
       "      <td>0.534915</td>\n",
       "      <td>0.933224</td>\n",
       "      <td>0.041926</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.298864</td>\n",
       "      <td>0.262617</td>\n",
       "      <td>0.316490</td>\n",
       "      <td>0.188391</td>\n",
       "      <td>0.161307</td>\n",
       "      <td>0.059647</td>\n",
       "      <td>0.126274</td>\n",
       "      <td>0.059151</td>\n",
       "      <td>0.421065</td>\n",
       "      <td>0.130302</td>\n",
       "      <td>...</td>\n",
       "      <td>0.019711</td>\n",
       "      <td>0.074241</td>\n",
       "      <td>0.033084</td>\n",
       "      <td>0.453773</td>\n",
       "      <td>0.466204</td>\n",
       "      <td>0.395599</td>\n",
       "      <td>0.334495</td>\n",
       "      <td>0.498780</td>\n",
       "      <td>0.249634</td>\n",
       "      <td>0.200420</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 24 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       basket_icon_click  basket_add_list  basket_add_detail        sort_by  \\\n",
       "count      455401.000000    455401.000000      455401.000000  455401.000000   \n",
       "mean            0.099150         0.074521           0.112916       0.036849   \n",
       "std             0.298864         0.262617           0.316490       0.188391   \n",
       "min             0.000000         0.000000           0.000000       0.000000   \n",
       "25%             0.000000         0.000000           0.000000       0.000000   \n",
       "50%             0.000000         0.000000           0.000000       0.000000   \n",
       "75%             0.000000         0.000000           0.000000       0.000000   \n",
       "max             1.000000         1.000000           1.000000       1.000000   \n",
       "\n",
       "        image_picker  account_page_click  promo_banner_click  \\\n",
       "count  455401.000000       455401.000000       455401.000000   \n",
       "mean        0.026735            0.003570            0.016208   \n",
       "std         0.161307            0.059647            0.126274   \n",
       "min         0.000000            0.000000            0.000000   \n",
       "25%         0.000000            0.000000            0.000000   \n",
       "50%         0.000000            0.000000            0.000000   \n",
       "75%         0.000000            0.000000            0.000000   \n",
       "max         1.000000            1.000000            1.000000   \n",
       "\n",
       "       detail_wishlist_add  list_size_dropdown  closed_minibasket_click  ...  \\\n",
       "count        455401.000000       455401.000000            455401.000000  ...   \n",
       "mean              0.003511            0.230362                 0.017277  ...   \n",
       "std               0.059151            0.421065                 0.130302  ...   \n",
       "min               0.000000            0.000000                 0.000000  ...   \n",
       "25%               0.000000            0.000000                 0.000000  ...   \n",
       "50%               0.000000            0.000000                 0.000000  ...   \n",
       "75%               0.000000            0.000000                 0.000000  ...   \n",
       "max               1.000000            1.000000                 1.000000  ...   \n",
       "\n",
       "       saw_sizecharts   saw_delivery  saw_account_upgrade   saw_homepage  \\\n",
       "count   455401.000000  455401.000000        455401.000000  455401.000000   \n",
       "mean         0.000389       0.005542             0.001096       0.290024   \n",
       "std          0.019711       0.074241             0.033084       0.453773   \n",
       "min          0.000000       0.000000             0.000000       0.000000   \n",
       "25%          0.000000       0.000000             0.000000       0.000000   \n",
       "50%          0.000000       0.000000             0.000000       0.000000   \n",
       "75%          0.000000       0.000000             0.000000       1.000000   \n",
       "max          1.000000       1.000000             1.000000       1.000000   \n",
       "\n",
       "       device_mobile  device_computer  device_tablet  returning_user  \\\n",
       "count  455401.000000    455401.000000  455401.000000   455401.000000   \n",
       "mean        0.680706         0.194220       0.128364        0.534915   \n",
       "std         0.466204         0.395599       0.334495        0.498780   \n",
       "min         0.000000         0.000000       0.000000        0.000000   \n",
       "25%         0.000000         0.000000       0.000000        0.000000   \n",
       "50%         1.000000         0.000000       0.000000        1.000000   \n",
       "75%         1.000000         0.000000       0.000000        1.000000   \n",
       "max         1.000000         1.000000       1.000000        1.000000   \n",
       "\n",
       "              loc_uk        ordered  \n",
       "count  455401.000000  455401.000000  \n",
       "mean        0.933224       0.041926  \n",
       "std         0.249634       0.200420  \n",
       "min         0.000000       0.000000  \n",
       "25%         1.000000       0.000000  \n",
       "50%         1.000000       0.000000  \n",
       "75%         1.000000       0.000000  \n",
       "max         1.000000       1.000000  \n",
       "\n",
       "[8 rows x 24 columns]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "14aa8768",
   "metadata": {
    "papermill": {
     "duration": 0.038525,
     "end_time": "2022-01-30T17:31:38.047121",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.008596",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Data Preprocessing"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10579e5e",
   "metadata": {
    "papermill": {
     "duration": 0.038562,
     "end_time": "2022-01-30T17:31:38.125589",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.087027",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Checking the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "64f9efbd",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:13.408896Z",
     "start_time": "2022-03-02T12:27:13.340499Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:38.208807Z",
     "iopub.status.busy": "2022-01-30T17:31:38.207338Z",
     "iopub.status.idle": "2022-01-30T17:31:38.283610Z",
     "shell.execute_reply": "2022-01-30T17:31:38.282978Z",
     "shell.execute_reply.started": "2022-01-30T17:04:39.238249Z"
    },
    "papermill": {
     "duration": 0.118938,
     "end_time": "2022-01-30T17:31:38.283771",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.164833",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "UserID                     0\n",
       "basket_icon_click          0\n",
       "basket_add_list            0\n",
       "basket_add_detail          0\n",
       "sort_by                    0\n",
       "image_picker               0\n",
       "account_page_click         0\n",
       "promo_banner_click         0\n",
       "detail_wishlist_add        0\n",
       "list_size_dropdown         0\n",
       "closed_minibasket_click    0\n",
       "checked_delivery_detail    0\n",
       "checked_returns_detail     0\n",
       "sign_in                    0\n",
       "saw_checkout               0\n",
       "saw_sizecharts             0\n",
       "saw_delivery               0\n",
       "saw_account_upgrade        0\n",
       "saw_homepage               0\n",
       "device_mobile              0\n",
       "device_computer            0\n",
       "device_tablet              0\n",
       "returning_user             0\n",
       "loc_uk                     0\n",
       "ordered                    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "78f3f4f6",
   "metadata": {
    "papermill": {
     "duration": 0.038316,
     "end_time": "2022-01-30T17:31:38.360412",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.322096",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "from above, we can see there is no nan values in the data set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "eda56424",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:13.907350Z",
     "start_time": "2022-03-02T12:27:13.840433Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:38.445224Z",
     "iopub.status.busy": "2022-01-30T17:31:38.444461Z",
     "iopub.status.idle": "2022-01-30T17:31:38.526240Z",
     "shell.execute_reply": "2022-01-30T17:31:38.526990Z",
     "shell.execute_reply.started": "2022-01-30T17:04:39.319228Z"
    },
    "papermill": {
     "duration": 0.126961,
     "end_time": "2022-01-30T17:31:38.527279",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.400318",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 455401 entries, 0 to 455400\n",
      "Data columns (total 25 columns):\n",
      " #   Column                   Non-Null Count   Dtype \n",
      "---  ------                   --------------   ----- \n",
      " 0   UserID                   455401 non-null  object\n",
      " 1   basket_icon_click        455401 non-null  int64 \n",
      " 2   basket_add_list          455401 non-null  int64 \n",
      " 3   basket_add_detail        455401 non-null  int64 \n",
      " 4   sort_by                  455401 non-null  int64 \n",
      " 5   image_picker             455401 non-null  int64 \n",
      " 6   account_page_click       455401 non-null  int64 \n",
      " 7   promo_banner_click       455401 non-null  int64 \n",
      " 8   detail_wishlist_add      455401 non-null  int64 \n",
      " 9   list_size_dropdown       455401 non-null  int64 \n",
      " 10  closed_minibasket_click  455401 non-null  int64 \n",
      " 11  checked_delivery_detail  455401 non-null  int64 \n",
      " 12  checked_returns_detail   455401 non-null  int64 \n",
      " 13  sign_in                  455401 non-null  int64 \n",
      " 14  saw_checkout             455401 non-null  int64 \n",
      " 15  saw_sizecharts           455401 non-null  int64 \n",
      " 16  saw_delivery             455401 non-null  int64 \n",
      " 17  saw_account_upgrade      455401 non-null  int64 \n",
      " 18  saw_homepage             455401 non-null  int64 \n",
      " 19  device_mobile            455401 non-null  int64 \n",
      " 20  device_computer          455401 non-null  int64 \n",
      " 21  device_tablet            455401 non-null  int64 \n",
      " 22  returning_user           455401 non-null  int64 \n",
      " 23  loc_uk                   455401 non-null  int64 \n",
      " 24  ordered                  455401 non-null  int64 \n",
      "dtypes: int64(24), object(1)\n",
      "memory usage: 86.9+ MB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "a79fe699",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:14.102506Z",
     "start_time": "2022-03-02T12:27:14.073898Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ordered\n",
       "0    436308\n",
       "1     19093\n",
       "Name: ordered, dtype: int64"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.groupby('ordered').ordered.count()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "892c6a61",
   "metadata": {},
   "source": [
    "Above we can see that the dataset is highly imbalanced so the prediction will be biased. \n",
    "\n",
    "To solve this problem, we can use undersampling. Undersampling is a technique to balance uneven datasets by keeping all of the data in the minority class and decreasing the size of the majority class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "7d9d5ce1",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:14.440438Z",
     "start_time": "2022-03-02T12:27:14.342407Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ordered\n",
       "0    19093\n",
       "1    19093\n",
       "Name: ordered, dtype: int64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_balanced = data.groupby('ordered').apply(lambda x: x.sample(19093)).reset_index(drop=True)\n",
    "data = data_balanced.sample(frac = 1)\n",
    "data.groupby('ordered').ordered.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "6d4c39e2",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:14.599724Z",
     "start_time": "2022-03-02T12:27:14.593516Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:38.645780Z",
     "iopub.status.busy": "2022-01-30T17:31:38.644975Z",
     "iopub.status.idle": "2022-01-30T17:31:38.648684Z",
     "shell.execute_reply": "2022-01-30T17:31:38.648121Z",
     "shell.execute_reply.started": "2022-01-30T17:04:39.412436Z"
    },
    "papermill": {
     "duration": 0.08075,
     "end_time": "2022-01-30T17:31:38.648846",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.568096",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "X = data[['basket_add_detail', 'promo_banner_click', 'sign_in', 'saw_homepage', 'returning_user']]\n",
    "y = data['ordered']"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87ed108f",
   "metadata": {
    "papermill": {
     "duration": 0.040754,
     "end_time": "2022-01-30T17:31:38.729953",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.689199",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Feature selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "0efca053",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:18.815071Z",
     "start_time": "2022-03-02T12:27:18.660516Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:38.814539Z",
     "iopub.status.busy": "2022-01-30T17:31:38.813513Z",
     "iopub.status.idle": "2022-01-30T17:31:40.491716Z",
     "shell.execute_reply": "2022-01-30T17:31:40.492230Z",
     "shell.execute_reply.started": "2022-01-30T17:04:39.469434Z"
    },
    "papermill": {
     "duration": 1.722721,
     "end_time": "2022-01-30T17:31:40.492434",
     "exception": false,
     "start_time": "2022-01-30T17:31:38.769713",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x1080 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(20,15))\n",
    "sns.heatmap(X.corr(),linewidth=2)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "579bc135",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:18.939458Z",
     "start_time": "2022-03-02T12:27:18.936460Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:40.578568Z",
     "iopub.status.busy": "2022-01-30T17:31:40.577616Z",
     "iopub.status.idle": "2022-01-30T17:31:40.583709Z",
     "shell.execute_reply": "2022-01-30T17:31:40.584168Z",
     "shell.execute_reply.started": "2022-01-30T17:04:41.050526Z"
    },
    "papermill": {
     "duration": 0.050568,
     "end_time": "2022-01-30T17:31:40.584346",
     "exception": false,
     "start_time": "2022-01-30T17:31:40.533778",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "def correlation(dataset, threshold):\n",
    "    col_corr = set()  # Set of all the names of correlated columns\n",
    "    corr_matrix = dataset.corr()\n",
    "    for i in range(len(corr_matrix.columns)):\n",
    "        for j in range(i):\n",
    "            if abs(corr_matrix.iloc[i, j]) > threshold: # we are interested in absolute coeff value\n",
    "                colname = corr_matrix.columns[i]  # getting the name of column\n",
    "                col_corr.add(colname)\n",
    "    return col_corr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "9cf6ec76",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:19.341996Z",
     "start_time": "2022-03-02T12:27:19.323561Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:40.670039Z",
     "iopub.status.busy": "2022-01-30T17:31:40.669323Z",
     "iopub.status.idle": "2022-01-30T17:31:41.495242Z",
     "shell.execute_reply": "2022-01-30T17:31:41.494561Z",
     "shell.execute_reply.started": "2022-01-30T17:04:41.061872Z"
    },
    "papermill": {
     "duration": 0.870321,
     "end_time": "2022-01-30T17:31:41.495385",
     "exception": false,
     "start_time": "2022-01-30T17:31:40.625064",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corr_features = correlation(X, 0.7)\n",
    "len(set(corr_features))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "6855e0cb",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:19.699749Z",
     "start_time": "2022-03-02T12:27:19.692499Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:41.581427Z",
     "iopub.status.busy": "2022-01-30T17:31:41.580811Z",
     "iopub.status.idle": "2022-01-30T17:31:41.585716Z",
     "shell.execute_reply": "2022-01-30T17:31:41.586293Z",
     "shell.execute_reply.started": "2022-01-30T17:04:41.891401Z"
    },
    "papermill": {
     "duration": 0.049959,
     "end_time": "2022-01-30T17:31:41.586473",
     "exception": false,
     "start_time": "2022-01-30T17:31:41.536514",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "set()"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corr_features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "f44d4689",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:20.212983Z",
     "start_time": "2022-03-02T12:27:20.192423Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:41.672661Z",
     "iopub.status.busy": "2022-01-30T17:31:41.671979Z",
     "iopub.status.idle": "2022-01-30T17:31:41.804463Z",
     "shell.execute_reply": "2022-01-30T17:31:41.803813Z",
     "shell.execute_reply.started": "2022-01-30T17:04:41.901275Z"
    },
    "papermill": {
     "duration": 0.177013,
     "end_time": "2022-01-30T17:31:41.804647",
     "exception": false,
     "start_time": "2022-01-30T17:31:41.627634",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>basket_add_detail</th>\n",
       "      <th>promo_banner_click</th>\n",
       "      <th>sign_in</th>\n",
       "      <th>saw_homepage</th>\n",
       "      <th>returning_user</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4817</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20146</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>35621</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34816</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11855</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13461</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29476</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15028</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3305</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20944</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>38186 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       basket_add_detail  promo_banner_click  sign_in  saw_homepage  \\\n",
       "4817                   0                   0        0             0   \n",
       "20146                  0                   0        1             1   \n",
       "35621                  1                   0        1             1   \n",
       "34816                  0                   0        1             1   \n",
       "11855                  0                   0        0             0   \n",
       "...                  ...                 ...      ...           ...   \n",
       "13461                  0                   0        0             0   \n",
       "29476                  1                   0        1             1   \n",
       "15028                  1                   0        0             0   \n",
       "3305                   0                   0        0             1   \n",
       "20944                  1                   0        1             1   \n",
       "\n",
       "       returning_user  \n",
       "4817                1  \n",
       "20146               1  \n",
       "35621               1  \n",
       "34816               1  \n",
       "11855               0  \n",
       "...               ...  \n",
       "13461               1  \n",
       "29476               0  \n",
       "15028               1  \n",
       "3305                1  \n",
       "20944               1  \n",
       "\n",
       "[38186 rows x 5 columns]"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = X.drop(corr_features,axis=1)\n",
    "X"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10922aa6",
   "metadata": {
    "papermill": {
     "duration": 0.042145,
     "end_time": "2022-01-30T17:31:41.890786",
     "exception": false,
     "start_time": "2022-01-30T17:31:41.848641",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## Exploratory Data Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "863ae44b",
   "metadata": {
    "papermill": {
     "duration": 0.042115,
     "end_time": "2022-01-30T17:31:41.975829",
     "exception": false,
     "start_time": "2022-01-30T17:31:41.933714",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "How many users have purchased"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "4adccf9e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:22.378146Z",
     "start_time": "2022-03-02T12:27:22.279915Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:42.066895Z",
     "iopub.status.busy": "2022-01-30T17:31:42.066253Z",
     "iopub.status.idle": "2022-01-30T17:31:42.259511Z",
     "shell.execute_reply": "2022-01-30T17:31:42.260031Z",
     "shell.execute_reply.started": "2022-01-30T17:04:42.014081Z"
    },
    "papermill": {
     "duration": 0.241559,
     "end_time": "2022-01-30T17:31:42.260200",
     "exception": false,
     "start_time": "2022-01-30T17:31:42.018641",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# \n",
    "ax = sns.countplot(data=data,x=\"ordered\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "a2553fb7",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:22.896691Z",
     "start_time": "2022-03-02T12:27:22.890385Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:42.349920Z",
     "iopub.status.busy": "2022-01-30T17:31:42.349202Z",
     "iopub.status.idle": "2022-01-30T17:31:42.352668Z",
     "shell.execute_reply": "2022-01-30T17:31:42.353202Z",
     "shell.execute_reply.started": "2022-01-30T17:04:42.200112Z"
    },
    "papermill": {
     "duration": 0.050449,
     "end_time": "2022-01-30T17:31:42.353371",
     "exception": false,
     "start_time": "2022-01-30T17:31:42.302922",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "dataframe=data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8d20f72c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-30T14:32:45.057436Z",
     "iopub.status.busy": "2022-01-30T14:32:45.057207Z",
     "iopub.status.idle": "2022-01-30T14:32:45.066826Z",
     "shell.execute_reply": "2022-01-30T14:32:45.06608Z",
     "shell.execute_reply.started": "2022-01-30T14:32:45.057409Z"
    },
    "papermill": {
     "duration": 0.0433,
     "end_time": "2022-01-30T17:31:42.440057",
     "exception": false,
     "start_time": "2022-01-30T17:31:42.396757",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Model creation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "ff230ba9",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:23.758229Z",
     "start_time": "2022-03-02T12:27:23.741845Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:42.563207Z",
     "iopub.status.busy": "2022-01-30T17:31:42.561997Z",
     "iopub.status.idle": "2022-01-30T17:31:42.901185Z",
     "shell.execute_reply": "2022-01-30T17:31:42.900535Z",
     "shell.execute_reply.started": "2022-01-30T17:04:42.206388Z"
    },
    "papermill": {
     "duration": 0.415716,
     "end_time": "2022-01-30T17:31:42.901344",
     "exception": false,
     "start_time": "2022-01-30T17:31:42.485628",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.20,random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "26040d0e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:24.147779Z",
     "start_time": "2022-03-02T12:27:24.140406Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:43.000334Z",
     "iopub.status.busy": "2022-01-30T17:31:42.999637Z",
     "iopub.status.idle": "2022-01-30T17:31:43.006001Z",
     "shell.execute_reply": "2022-01-30T17:31:43.005415Z",
     "shell.execute_reply.started": "2022-01-30T17:04:42.414922Z"
    },
    "papermill": {
     "duration": 0.058124,
     "end_time": "2022-01-30T17:31:43.006145",
     "exception": false,
     "start_time": "2022-01-30T17:31:42.948021",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total no. of samples: Training and Testing dataset separately!\n",
      "X_train: (30548, 5)\n",
      "y_train: (30548,)\n",
      "X_test: (7638, 5)\n",
      "y_test: (7638,)\n"
     ]
    }
   ],
   "source": [
    "print('Total no. of samples: Training and Testing dataset separately!')\n",
    "print('X_train:', np.shape(X_train))\n",
    "print('y_train:', np.shape(y_train))\n",
    "print('X_test:', np.shape(X_test))\n",
    "print('y_test:', np.shape(y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "2ff53a9a",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:24.561684Z",
     "start_time": "2022-03-02T12:27:24.509725Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:43.103301Z",
     "iopub.status.busy": "2022-01-30T17:31:43.102637Z",
     "iopub.status.idle": "2022-01-30T17:31:46.561147Z",
     "shell.execute_reply": "2022-01-30T17:31:46.562114Z",
     "shell.execute_reply.started": "2022-01-30T17:04:42.424554Z"
    },
    "papermill": {
     "duration": 3.509446,
     "end_time": "2022-01-30T17:31:46.562434",
     "exception": false,
     "start_time": "2022-01-30T17:31:43.052988",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression()"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "classifier = LogisticRegression()\n",
    "classifier.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "12d7a825",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:39.461606Z",
     "start_time": "2022-03-02T12:27:39.446933Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:46.709442Z",
     "iopub.status.busy": "2022-01-30T17:31:46.708227Z",
     "iopub.status.idle": "2022-01-30T17:31:46.917255Z",
     "shell.execute_reply": "2022-01-30T17:31:46.916297Z",
     "shell.execute_reply.started": "2022-01-30T17:17:34.549035Z"
    },
    "papermill": {
     "duration": 0.271712,
     "end_time": "2022-01-30T17:31:46.917491",
     "exception": false,
     "start_time": "2022-01-30T17:31:46.645779",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0 0]\n",
      " [0 0]\n",
      " [1 1]\n",
      " ...\n",
      " [0 0]\n",
      " [0 0]\n",
      " [0 0]]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda3/lib/python3.8/site-packages/sklearn/base.py:445: UserWarning: X does not have valid feature names, but LogisticRegression was fitted with feature names\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "sc = StandardScaler()\n",
    "X_train = sc.fit_transform(X_train)\n",
    "X_test = sc.transform(X_test)\n",
    "y_pred = classifier.predict(X_test)\n",
    "print(np.concatenate((y_pred.reshape(len(y_pred),1), y_test.values.reshape(len(y_test),1)),1))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "198fd317",
   "metadata": {
    "papermill": {
     "duration": 0.044502,
     "end_time": "2022-01-30T17:31:47.145693",
     "exception": false,
     "start_time": "2022-01-30T17:31:47.101191",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Metric Evaluation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "91556c78",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:41.174797Z",
     "start_time": "2022-03-02T12:27:41.063602Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:47.242270Z",
     "iopub.status.busy": "2022-01-30T17:31:47.241561Z",
     "iopub.status.idle": "2022-01-30T17:31:47.526856Z",
     "shell.execute_reply": "2022-01-30T17:31:47.527932Z",
     "shell.execute_reply.started": "2022-01-30T17:27:24.903537Z"
    },
    "papermill": {
     "duration": 0.337294,
     "end_time": "2022-01-30T17:31:47.528285",
     "exception": false,
     "start_time": "2022-01-30T17:31:47.190991",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[3621  161]\n",
      " [ 222 3634]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix, accuracy_score, roc_auc_score\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)\n",
    "from mlxtend.plotting import plot_confusion_matrix\n",
    "fig, ax = plot_confusion_matrix(conf_mat=cm, figsize=(6, 6), cmap=plt.cm.Greens)\n",
    "plt.xlabel('Predictions', fontsize=18)\n",
    "plt.ylabel('Actuals', fontsize=18)\n",
    "plt.title('Confusion Matrix', fontsize=18)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "5fdcd0a8",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:44.724859Z",
     "start_time": "2022-03-02T12:27:44.708647Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:47.648813Z",
     "iopub.status.busy": "2022-01-30T17:31:47.647965Z",
     "iopub.status.idle": "2022-01-30T17:31:47.674297Z",
     "shell.execute_reply": "2022-01-30T17:31:47.674841Z",
     "shell.execute_reply.started": "2022-01-30T17:25:00.660905Z"
    },
    "papermill": {
     "duration": 0.076526,
     "end_time": "2022-01-30T17:31:47.675043",
     "exception": false,
     "start_time": "2022-01-30T17:31:47.598517",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy :  0.9498559832416863 \n",
      "ROC Score :  0.9499286585727106\n"
     ]
    }
   ],
   "source": [
    "logreg=accuracy_score(y_test,y_pred)\n",
    "rocreg=roc_auc_score(y_test, y_pred)\n",
    "print('Accuracy : ',logreg,'\\nROC Score : ',rocreg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "1bdfad5b",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:27:46.284402Z",
     "start_time": "2022-03-02T12:27:46.257421Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:47.772432Z",
     "iopub.status.busy": "2022-01-30T17:31:47.771785Z",
     "iopub.status.idle": "2022-01-30T17:31:47.894042Z",
     "shell.execute_reply": "2022-01-30T17:31:47.893376Z",
     "shell.execute_reply.started": "2022-01-30T17:17:54.556981Z"
    },
    "papermill": {
     "duration": 0.172101,
     "end_time": "2022-01-30T17:31:47.894207",
     "exception": false,
     "start_time": "2022-01-30T17:31:47.722106",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.94      0.96      0.95      3782\n",
      "           1       0.96      0.94      0.95      3856\n",
      "\n",
      "    accuracy                           0.95      7638\n",
      "   macro avg       0.95      0.95      0.95      7638\n",
      "weighted avg       0.95      0.95      0.95      7638\n",
      "\n"
     ]
    }
   ],
   "source": [
    "import sklearn.metrics as metrics\n",
    "print(metrics.classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd9d3c8b",
   "metadata": {
    "papermill": {
     "duration": 0.048232,
     "end_time": "2022-01-30T17:31:47.990581",
     "exception": false,
     "start_time": "2022-01-30T17:31:47.942349",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "### Hyper tuning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "06c5ca60",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:28:07.107610Z",
     "start_time": "2022-03-02T12:28:03.606308Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:31:48.089930Z",
     "iopub.status.busy": "2022-01-30T17:31:48.089219Z",
     "iopub.status.idle": "2022-01-30T17:32:32.686754Z",
     "shell.execute_reply": "2022-01-30T17:32:32.687640Z",
     "shell.execute_reply.started": "2022-01-30T17:17:58.775520Z"
    },
    "papermill": {
     "duration": 44.64942,
     "end_time": "2022-01-30T17:32:32.687944",
     "exception": false,
     "start_time": "2022-01-30T17:31:48.038524",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best Accuracy of LR: 97.23 %\n",
      "Best Parameter of LR: {'C': 0.001, 'penalty': 'l2'}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/anaconda3/lib/python3.8/site-packages/sklearn/model_selection/_validation.py:372: FitFailedWarning: \n",
      "70 fits failed out of a total of 140.\n",
      "The score on these train-test partitions for these parameters will be set to nan.\n",
      "If these failures are not expected, you can try to debug them by setting error_score='raise'.\n",
      "\n",
      "Below are more details about the failures:\n",
      "--------------------------------------------------------------------------------\n",
      "70 fits failed with the following error:\n",
      "Traceback (most recent call last):\n",
      "  File \"/opt/anaconda3/lib/python3.8/site-packages/sklearn/model_selection/_validation.py\", line 681, in _fit_and_score\n",
      "    estimator.fit(X_train, y_train, **fit_params)\n",
      "  File \"/opt/anaconda3/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py\", line 1461, in fit\n",
      "    solver = _check_solver(self.solver, self.penalty, self.dual)\n",
      "  File \"/opt/anaconda3/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py\", line 447, in _check_solver\n",
      "    raise ValueError(\n",
      "ValueError: Solver lbfgs supports only 'l2' or 'none' penalties, got l1 penalty.\n",
      "\n",
      "  warnings.warn(some_fits_failed_message, FitFailedWarning)\n",
      "/opt/anaconda3/lib/python3.8/site-packages/sklearn/model_selection/_search.py:969: UserWarning: One or more of the test scores are non-finite: [       nan 0.97233849        nan 0.97233849        nan 0.97233849\n",
      "        nan 0.97233849        nan 0.97233849        nan 0.97233849\n",
      "        nan 0.97233849]\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "parameters_lr = [{'penalty':['l1','l2'],'C': [0.001, 0.01, 0.1, 1, 10, 100, 1000]}]\n",
    "grid_search_lr = GridSearchCV(estimator = classifier,\n",
    "                           param_grid = parameters_lr,\n",
    "                           scoring = 'accuracy',\n",
    "                           cv = 10,\n",
    "                           n_jobs = -1)\n",
    "grid_search_lr.fit(X_train, y_train)\n",
    "best_accuracy_lr = grid_search_lr.best_score_\n",
    "best_paramaeter_lr = grid_search_lr.best_params_  \n",
    "print(\"Best Accuracy of LR: {:.2f} %\".format(best_accuracy_lr.mean()*100))\n",
    "print(\"Best Parameter of LR:\", best_paramaeter_lr)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b988f0c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-30T14:33:33.788943Z",
     "iopub.status.busy": "2022-01-30T14:33:33.784381Z",
     "iopub.status.idle": "2022-01-30T14:33:33.805139Z",
     "shell.execute_reply": "2022-01-30T14:33:33.801499Z",
     "shell.execute_reply.started": "2022-01-30T14:33:33.788853Z"
    },
    "papermill": {
     "duration": 0.046706,
     "end_time": "2022-01-30T17:32:32.792298",
     "exception": false,
     "start_time": "2022-01-30T17:32:32.745592",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "By using above parameter we get 97% accuracy"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "636e4e56",
   "metadata": {
    "papermill": {
     "duration": 0.046356,
     "end_time": "2022-01-30T17:32:32.885052",
     "exception": false,
     "start_time": "2022-01-30T17:32:32.838696",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "##  Testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "da224e01",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:28:17.217165Z",
     "start_time": "2022-03-02T12:28:17.180400Z"
    },
    "execution": {
     "iopub.execute_input": "2022-01-30T17:32:32.984640Z",
     "iopub.status.busy": "2022-01-30T17:32:32.983973Z",
     "iopub.status.idle": "2022-01-30T17:32:34.397386Z",
     "shell.execute_reply": "2022-01-30T17:32:34.398286Z",
     "shell.execute_reply.started": "2022-01-30T17:18:43.483236Z"
    },
    "papermill": {
     "duration": 1.467431,
     "end_time": "2022-01-30T17:32:34.398583",
     "exception": false,
     "start_time": "2022-01-30T17:32:32.931152",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=0.001)"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifierhyp = LogisticRegression(C=0.001,penalty='l2')\n",
    "classifierhyp.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "3d57f5bd",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:28:17.720465Z",
     "start_time": "2022-03-02T12:28:17.707924Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9719821942916994"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred=classifierhyp.predict(X_test)\n",
    "\n",
    "#evaluate the model fit\n",
    "from sklearn import metrics\n",
    "metrics.accuracy_score(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "fb77aa49",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:28:18.435499Z",
     "start_time": "2022-03-02T12:28:18.330726Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[3589  193]\n",
      " [  21 3835]]\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix, accuracy_score, roc_auc_score\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "print(cm)\n",
    "from mlxtend.plotting import plot_confusion_matrix\n",
    "fig, ax = plot_confusion_matrix(conf_mat=cm, figsize=(6, 6), cmap=plt.cm.Greens)\n",
    "plt.xlabel('Predictions', fontsize=18)\n",
    "plt.ylabel('Actuals', fontsize=18)\n",
    "plt.title('Confusion Matrix', fontsize=18)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "08260fde",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:28:21.798942Z",
     "start_time": "2022-03-02T12:28:21.790398Z"
    }
   },
   "outputs": [],
   "source": [
    "#save the pickle file to be loaded in the streamlit app\n",
    "import pickle\n",
    "with open(\"propensity_model.pkl\", 'wb') as pfile:\n",
    "    pickle.dump(classifierhyp, pfile)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "a32734a1",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-03-02T12:28:22.549015Z",
     "start_time": "2022-03-02T12:28:22.540439Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7638, 5)"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 77.020716,
   "end_time": "2022-01-30T17:32:38.580320",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2022-01-30T17:31:21.559604",
   "version": "2.3.3"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}