EDA/Exploratory_Data_Analysis_BlackFriday_Sales.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "602ceece",
   "metadata": {},
   "source": [
    "# BlackFriday Sales\n",
    "- EDA and feature engineering\n",
    "- data cleaning and preparation for model training"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87b41880",
   "metadata": {},
   "source": [
    "### Problem statement\n",
    "- A retail company “ABC Private Limited” wants to understand the customer purchase behaviour (specifically, purchase amount) against various products of different categories. They have shared purchase summary of various customers for selected high volume products from last month.\n",
    "- The data set also contains customer demographics (age, gender, marital status, citytype, stayincurrentcity), product details (productid and product category) and Total purchaseamount from last month.\n",
    "- Now, they want to build a model to predict the purchase amount of customer against various products which will help them to create personalized offer for customers against different products.\n",
    "\n",
    "- link : https://www.kaggle.com/datasets/pranavuikey/black-friday-sales-eda"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e8a3b579",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6f7077ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "# import data\n",
    "df_train = pd.read_csv(\"/home/darshan/Desktop/Codes/IMP_Jupyter_Notebooks/data/Black Friday Dataset/train.csv\")\n",
    "df_test = pd.read_csv(\"/home/darshan/Desktop/Codes/IMP_Jupyter_Notebooks/data/Black Friday Dataset/test.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "c722c970",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>User_ID</th>\n",
       "      <th>Product_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>City_Category</th>\n",
       "      <th>Stay_In_Current_City_Years</th>\n",
       "      <th>Marital_Status</th>\n",
       "      <th>Product_Category_1</th>\n",
       "      <th>Product_Category_2</th>\n",
       "      <th>Product_Category_3</th>\n",
       "      <th>Purchase</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000001</td>\n",
       "      <td>P00069042</td>\n",
       "      <td>F</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8370</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1000001</td>\n",
       "      <td>P00248942</td>\n",
       "      <td>F</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>15200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1000001</td>\n",
       "      <td>P00087842</td>\n",
       "      <td>F</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1422</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1000001</td>\n",
       "      <td>P00085442</td>\n",
       "      <td>F</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>14.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1057</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1000002</td>\n",
       "      <td>P00285442</td>\n",
       "      <td>M</td>\n",
       "      <td>55+</td>\n",
       "      <td>16</td>\n",
       "      <td>C</td>\n",
       "      <td>4+</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7969</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   User_ID Product_ID Gender   Age  Occupation City_Category  \\\n",
       "0  1000001  P00069042      F  0-17          10             A   \n",
       "1  1000001  P00248942      F  0-17          10             A   \n",
       "2  1000001  P00087842      F  0-17          10             A   \n",
       "3  1000001  P00085442      F  0-17          10             A   \n",
       "4  1000002  P00285442      M   55+          16             C   \n",
       "\n",
       "  Stay_In_Current_City_Years  Marital_Status  Product_Category_1  \\\n",
       "0                          2               0                   3   \n",
       "1                          2               0                   1   \n",
       "2                          2               0                  12   \n",
       "3                          2               0                  12   \n",
       "4                         4+               0                   8   \n",
       "\n",
       "   Product_Category_2  Product_Category_3  Purchase  \n",
       "0                 NaN                 NaN      8370  \n",
       "1                 6.0                14.0     15200  \n",
       "2                 NaN                 NaN      1422  \n",
       "3                14.0                 NaN      1057  \n",
       "4                 NaN                 NaN      7969  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "fd1c1fc9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(550068, 12)\n",
      "(233599, 11)\n"
     ]
    }
   ],
   "source": [
    "print(df_train.shape)\n",
    "print(df_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a7ff7126",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(783667, 12)\n"
     ]
    }
   ],
   "source": [
    "# merge both train and test data for preprocessing\n",
    "# pd.merge(df_train,df_test) ---> it is used when both df has different features ukwim\n",
    "df = df_train.append(df_test)\n",
    "print(df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "364590b3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 783667 entries, 0 to 233598\n",
      "Data columns (total 12 columns):\n",
      " #   Column                      Non-Null Count   Dtype  \n",
      "---  ------                      --------------   -----  \n",
      " 0   User_ID                     783667 non-null  int64  \n",
      " 1   Product_ID                  783667 non-null  object \n",
      " 2   Gender                      783667 non-null  object \n",
      " 3   Age                         783667 non-null  object \n",
      " 4   Occupation                  783667 non-null  int64  \n",
      " 5   City_Category               783667 non-null  object \n",
      " 6   Stay_In_Current_City_Years  783667 non-null  object \n",
      " 7   Marital_Status              783667 non-null  int64  \n",
      " 8   Product_Category_1          783667 non-null  int64  \n",
      " 9   Product_Category_2          537685 non-null  float64\n",
      " 10  Product_Category_3          237858 non-null  float64\n",
      " 11  Purchase                    550068 non-null  float64\n",
      "dtypes: float64(3), int64(4), object(5)\n",
      "memory usage: 77.7+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "4a665cac",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>User_ID</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>Marital_Status</th>\n",
       "      <th>Product_Category_1</th>\n",
       "      <th>Product_Category_2</th>\n",
       "      <th>Product_Category_3</th>\n",
       "      <th>Purchase</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>7.836670e+05</td>\n",
       "      <td>783667.000000</td>\n",
       "      <td>783667.000000</td>\n",
       "      <td>783667.000000</td>\n",
       "      <td>537685.000000</td>\n",
       "      <td>237858.000000</td>\n",
       "      <td>550068.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.003029e+06</td>\n",
       "      <td>8.079300</td>\n",
       "      <td>0.409777</td>\n",
       "      <td>5.366196</td>\n",
       "      <td>9.844506</td>\n",
       "      <td>12.668605</td>\n",
       "      <td>9263.968713</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.727267e+03</td>\n",
       "      <td>6.522206</td>\n",
       "      <td>0.491793</td>\n",
       "      <td>3.878160</td>\n",
       "      <td>5.089093</td>\n",
       "      <td>4.125510</td>\n",
       "      <td>5023.065394</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000001e+06</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>12.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.001519e+06</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>5823.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.003075e+06</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>9.000000</td>\n",
       "      <td>14.000000</td>\n",
       "      <td>8047.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.004478e+06</td>\n",
       "      <td>14.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>15.000000</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>12054.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.006040e+06</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>23961.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            User_ID     Occupation  Marital_Status  Product_Category_1  \\\n",
       "count  7.836670e+05  783667.000000   783667.000000       783667.000000   \n",
       "mean   1.003029e+06       8.079300        0.409777            5.366196   \n",
       "std    1.727267e+03       6.522206        0.491793            3.878160   \n",
       "min    1.000001e+06       0.000000        0.000000            1.000000   \n",
       "25%    1.001519e+06       2.000000        0.000000            1.000000   \n",
       "50%    1.003075e+06       7.000000        0.000000            5.000000   \n",
       "75%    1.004478e+06      14.000000        1.000000            8.000000   \n",
       "max    1.006040e+06      20.000000        1.000000           20.000000   \n",
       "\n",
       "       Product_Category_2  Product_Category_3       Purchase  \n",
       "count       537685.000000       237858.000000  550068.000000  \n",
       "mean             9.844506           12.668605    9263.968713  \n",
       "std              5.089093            4.125510    5023.065394  \n",
       "min              2.000000            3.000000      12.000000  \n",
       "25%              5.000000            9.000000    5823.000000  \n",
       "50%              9.000000           14.000000    8047.000000  \n",
       "75%             15.000000           16.000000   12054.000000  \n",
       "max             18.000000           18.000000   23961.000000  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8b3516dc",
   "metadata": {},
   "source": [
    "### remove unncessary features like user_id\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b314d577",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop([\"User_ID\"],axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "be0876a8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 783667 entries, 0 to 233598\n",
      "Data columns (total 11 columns):\n",
      " #   Column                      Non-Null Count   Dtype  \n",
      "---  ------                      --------------   -----  \n",
      " 0   Product_ID                  783667 non-null  object \n",
      " 1   Gender                      783667 non-null  object \n",
      " 2   Age                         783667 non-null  object \n",
      " 3   Occupation                  783667 non-null  int64  \n",
      " 4   City_Category               783667 non-null  object \n",
      " 5   Stay_In_Current_City_Years  783667 non-null  object \n",
      " 6   Marital_Status              783667 non-null  int64  \n",
      " 7   Product_Category_1          783667 non-null  int64  \n",
      " 8   Product_Category_2          537685 non-null  float64\n",
      " 9   Product_Category_3          237858 non-null  float64\n",
      " 10  Purchase                    550068 non-null  float64\n",
      "dtypes: float64(3), int64(3), object(5)\n",
      "memory usage: 71.7+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7571ed4b",
   "metadata": {},
   "source": [
    "### fix categorical features ---> gender Age City ...."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "8ab933f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>F</th>\n",
       "      <th>M</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233594</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233595</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233596</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233597</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233598</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>783667 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        F  M\n",
       "0       1  0\n",
       "1       1  0\n",
       "2       1  0\n",
       "3       1  0\n",
       "4       0  1\n",
       "...    .. ..\n",
       "233594  1  0\n",
       "233595  1  0\n",
       "233596  1  0\n",
       "233597  1  0\n",
       "233598  1  0\n",
       "\n",
       "[783667 rows x 2 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df[\"Gender\"])\n",
    "# one way is create this kind of df, remove gender, merge this df...."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "be9e6d0e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# categorical features: Gender\n",
    "df[\"Gender\"]= df[\"Gender\"].map({'F':0,'M':1})\n",
    "# or\n",
    "# df[\"Gender\"]= pd.get_dummies(df[\"Gender\"],drop_first=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ca4b01c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Product_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>City_Category</th>\n",
       "      <th>Stay_In_Current_City_Years</th>\n",
       "      <th>Marital_Status</th>\n",
       "      <th>Product_Category_1</th>\n",
       "      <th>Product_Category_2</th>\n",
       "      <th>Product_Category_3</th>\n",
       "      <th>Purchase</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>P00069042</td>\n",
       "      <td>0</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8370.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>P00248942</td>\n",
       "      <td>0</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>15200.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>P00087842</td>\n",
       "      <td>0</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1422.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>P00085442</td>\n",
       "      <td>0</td>\n",
       "      <td>0-17</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>14.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1057.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>P00285442</td>\n",
       "      <td>1</td>\n",
       "      <td>55+</td>\n",
       "      <td>16</td>\n",
       "      <td>C</td>\n",
       "      <td>4+</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7969.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Product_ID  Gender   Age  Occupation City_Category  \\\n",
       "0  P00069042       0  0-17          10             A   \n",
       "1  P00248942       0  0-17          10             A   \n",
       "2  P00087842       0  0-17          10             A   \n",
       "3  P00085442       0  0-17          10             A   \n",
       "4  P00285442       1   55+          16             C   \n",
       "\n",
       "  Stay_In_Current_City_Years  Marital_Status  Product_Category_1  \\\n",
       "0                          2               0                   3   \n",
       "1                          2               0                   1   \n",
       "2                          2               0                  12   \n",
       "3                          2               0                  12   \n",
       "4                         4+               0                   8   \n",
       "\n",
       "   Product_Category_2  Product_Category_3  Purchase  \n",
       "0                 NaN                 NaN    8370.0  \n",
       "1                 6.0                14.0   15200.0  \n",
       "2                 NaN                 NaN    1422.0  \n",
       "3                14.0                 NaN    1057.0  \n",
       "4                 NaN                 NaN    7969.0  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5ebc2386",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['0-17', '55+', '26-35', '46-50', '51-55', '36-45', '18-25'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# categorical features: Age\n",
    "df[\"Age\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "4d80d2e8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0-17</th>\n",
       "      <th>18-25</th>\n",
       "      <th>26-35</th>\n",
       "      <th>36-45</th>\n",
       "      <th>46-50</th>\n",
       "      <th>51-55</th>\n",
       "      <th>55+</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\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>...</th>\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>233594</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233595</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233596</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233597</th>\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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>233598</th>\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",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>783667 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        0-17  18-25  26-35  36-45  46-50  51-55  55+\n",
       "0          1      0      0      0      0      0    0\n",
       "1          1      0      0      0      0      0    0\n",
       "2          1      0      0      0      0      0    0\n",
       "3          1      0      0      0      0      0    0\n",
       "4          0      0      0      0      0      0    1\n",
       "...      ...    ...    ...    ...    ...    ...  ...\n",
       "233594     0      0      1      0      0      0    0\n",
       "233595     0      0      1      0      0      0    0\n",
       "233596     0      0      1      0      0      0    0\n",
       "233597     0      0      0      0      1      0    0\n",
       "233598     0      0      0      0      1      0    0\n",
       "\n",
       "[783667 rows x 7 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.get_dummies(df[\"Age\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "4e2919b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"Age\"]= df[\"Age\"].map({'0-17':1, '18-25':2 , '26-35':3, '36-45':4, '46-50':5, '51-55':6,'55+':7})\n",
    "# or\n",
    "# ## Import label encoder \n",
    "# from sklearn import preprocessing \n",
    "\n",
    "# # label_encoder object knows how to understand word labels. \n",
    "# label_encoder = preprocessing.LabelEncoder() \n",
    "# df['Age']= label_encoder.fit_transform(df['Age']) \n",
    "# df['Age'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "7597eafe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Product_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>City_Category</th>\n",
       "      <th>Stay_In_Current_City_Years</th>\n",
       "      <th>Marital_Status</th>\n",
       "      <th>Product_Category_1</th>\n",
       "      <th>Product_Category_2</th>\n",
       "      <th>Product_Category_3</th>\n",
       "      <th>Purchase</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>P00069042</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8370.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>P00248942</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>15200.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>P00087842</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1422.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>P00085442</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>A</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>14.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1057.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>P00285442</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>16</td>\n",
       "      <td>C</td>\n",
       "      <td>4+</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7969.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Product_ID  Gender  Age  Occupation City_Category  \\\n",
       "0  P00069042       0    1          10             A   \n",
       "1  P00248942       0    1          10             A   \n",
       "2  P00087842       0    1          10             A   \n",
       "3  P00085442       0    1          10             A   \n",
       "4  P00285442       1    7          16             C   \n",
       "\n",
       "  Stay_In_Current_City_Years  Marital_Status  Product_Category_1  \\\n",
       "0                          2               0                   3   \n",
       "1                          2               0                   1   \n",
       "2                          2               0                  12   \n",
       "3                          2               0                  12   \n",
       "4                         4+               0                   8   \n",
       "\n",
       "   Product_Category_2  Product_Category_3  Purchase  \n",
       "0                 NaN                 NaN    8370.0  \n",
       "1                 6.0                14.0   15200.0  \n",
       "2                 NaN                 NaN    1422.0  \n",
       "3                14.0                 NaN    1057.0  \n",
       "4                 NaN                 NaN    7969.0  "
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "977c53ac",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        B  C\n",
      "0       0  0\n",
      "1       0  0\n",
      "2       0  0\n",
      "3       0  0\n",
      "4       0  1\n",
      "...    .. ..\n",
      "233594  1  0\n",
      "233595  1  0\n",
      "233596  1  0\n",
      "233597  0  1\n",
      "233598  1  0\n",
      "\n",
      "[783667 rows x 2 columns]\n"
     ]
    }
   ],
   "source": [
    "df_city= pd.get_dummies(df[\"City_Category\"],drop_first=True)\n",
    "print(df_city)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "b1059cbe",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.concat([df,df_city],axis=1)\n",
    "df.drop([\"City_Category\"],axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "53c9842e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Product_ID</th>\n",
       "      <th>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>Stay_In_Current_City_Years</th>\n",
       "      <th>Marital_Status</th>\n",
       "      <th>Product_Category_1</th>\n",
       "      <th>Product_Category_2</th>\n",
       "      <th>Product_Category_3</th>\n",
       "      <th>Purchase</th>\n",
       "      <th>B</th>\n",
       "      <th>C</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>P00069042</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8370.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>P00248942</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>6.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>15200.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>P00087842</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1422.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>P00085442</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>14.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1057.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>P00285442</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>16</td>\n",
       "      <td>4+</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7969.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Product_ID  Gender  Age  Occupation Stay_In_Current_City_Years  \\\n",
       "0  P00069042       0    1          10                          2   \n",
       "1  P00248942       0    1          10                          2   \n",
       "2  P00087842       0    1          10                          2   \n",
       "3  P00085442       0    1          10                          2   \n",
       "4  P00285442       1    7          16                         4+   \n",
       "\n",
       "   Marital_Status  Product_Category_1  Product_Category_2  Product_Category_3  \\\n",
       "0               0                   3                 NaN                 NaN   \n",
       "1               0                   1                 6.0                14.0   \n",
       "2               0                  12                 NaN                 NaN   \n",
       "3               0                  12                14.0                 NaN   \n",
       "4               0                   8                 NaN                 NaN   \n",
       "\n",
       "   Purchase  B  C  \n",
       "0    8370.0  0  0  \n",
       "1   15200.0  0  0  \n",
       "2    1422.0  0  0  \n",
       "3    1057.0  0  0  \n",
       "4    7969.0  0  1  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6fba198f",
   "metadata": {},
   "source": [
    "### check missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "443ac2e3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Product_ID                         0\n",
       "Gender                             0\n",
       "Age                                0\n",
       "Occupation                         0\n",
       "Stay_In_Current_City_Years         0\n",
       "Marital_Status                     0\n",
       "Product_Category_1                 0\n",
       "Product_Category_2            245982\n",
       "Product_Category_3            545809\n",
       "Purchase                      233599\n",
       "B                                  0\n",
       "C                                  0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "8b0cb92f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([nan, 14., 17.,  5.,  4., 16., 15.,  8.,  9., 13.,  6., 12.,  3.,\n",
       "       18., 11., 10.])"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# solution : look for replacing missing values\n",
    "# this is discrite feature not a series or continuos feature\n",
    "# we can replace nan with mode value\n",
    "df[\"Product_Category_3\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "402406a4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([nan,  6., 14.,  2.,  8., 15., 16., 11.,  5.,  3.,  4., 12.,  9.,\n",
       "       10., 17., 13.,  7., 18.])"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Product_Category_2\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "fdc155ec",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    16.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Product_Category_3\"].mode()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "08eb80f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"Product_Category_3\"]=df[\"Product_Category_3\"].fillna(df[\"Product_Category_3\"].mode()[0])\n",
    "df[\"Product_Category_2\"]=df[\"Product_Category_2\"].fillna(df[\"Product_Category_2\"].mode()[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "31b096f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Product_ID                         0\n",
       "Gender                             0\n",
       "Age                                0\n",
       "Occupation                         0\n",
       "Stay_In_Current_City_Years         0\n",
       "Marital_Status                     0\n",
       "Product_Category_1                 0\n",
       "Product_Category_2                 0\n",
       "Product_Category_3                 0\n",
       "Purchase                      233599\n",
       "B                                  0\n",
       "C                                  0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "e7cb28ce",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 783667 entries, 0 to 233598\n",
      "Data columns (total 12 columns):\n",
      " #   Column                      Non-Null Count   Dtype  \n",
      "---  ------                      --------------   -----  \n",
      " 0   Product_ID                  783667 non-null  object \n",
      " 1   Gender                      783667 non-null  int64  \n",
      " 2   Age                         783667 non-null  int64  \n",
      " 3   Occupation                  783667 non-null  int64  \n",
      " 4   Stay_In_Current_City_Years  783667 non-null  object \n",
      " 5   Marital_Status              783667 non-null  int64  \n",
      " 6   Product_Category_1          783667 non-null  int64  \n",
      " 7   Product_Category_2          783667 non-null  float64\n",
      " 8   Product_Category_3          783667 non-null  float64\n",
      " 9   Purchase                    550068 non-null  float64\n",
      " 10  B                           783667 non-null  uint8  \n",
      " 11  C                           783667 non-null  uint8  \n",
      "dtypes: float64(3), int64(5), object(2), uint8(2)\n",
      "memory usage: 67.3+ MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "9fc3e665",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['2', '4+', '3', '1', '0'], dtype=object)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Stay_In_Current_City_Years\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "b83ae2bb",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_148558/3223755903.py:1: FutureWarning: The default value of regex will change from True to False in a future version. In addition, single character regular expressions will *not* be treated as literal strings when regex=True.\n",
      "  df[\"Stay_In_Current_City_Years\"] = df[\"Stay_In_Current_City_Years\"].str.replace('+','')\n"
     ]
    }
   ],
   "source": [
    "df[\"Stay_In_Current_City_Years\"] = df[\"Stay_In_Current_City_Years\"].str.replace('+','')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "5eb820cb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['2', '4', '3', '1', '0'], dtype=object)"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"Stay_In_Current_City_Years\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "2b96a67a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# change data type to int or float from other data type\n",
    "df[\"Stay_In_Current_City_Years\"]= df[\"Stay_In_Current_City_Years\"].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "162da952",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop([\"Product_ID\"],axis=1,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "89d125c0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 783667 entries, 0 to 233598\n",
      "Data columns (total 11 columns):\n",
      " #   Column                      Non-Null Count   Dtype  \n",
      "---  ------                      --------------   -----  \n",
      " 0   Gender                      783667 non-null  int64  \n",
      " 1   Age                         783667 non-null  int64  \n",
      " 2   Occupation                  783667 non-null  int64  \n",
      " 3   Stay_In_Current_City_Years  783667 non-null  int64  \n",
      " 4   Marital_Status              783667 non-null  int64  \n",
      " 5   Product_Category_1          783667 non-null  int64  \n",
      " 6   Product_Category_2          783667 non-null  float64\n",
      " 7   Product_Category_3          783667 non-null  float64\n",
      " 8   Purchase                    550068 non-null  float64\n",
      " 9   B                           783667 non-null  uint8  \n",
      " 10  C                           783667 non-null  uint8  \n",
      "dtypes: float64(3), int64(6), uint8(2)\n",
      "memory usage: 61.3 MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "546e6f58",
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"B\"]=df[\"B\"].astype(int)\n",
    "df[\"C\"]=df[\"C\"].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "6ed43b23",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 783667 entries, 0 to 233598\n",
      "Data columns (total 11 columns):\n",
      " #   Column                      Non-Null Count   Dtype  \n",
      "---  ------                      --------------   -----  \n",
      " 0   Gender                      783667 non-null  int64  \n",
      " 1   Age                         783667 non-null  int64  \n",
      " 2   Occupation                  783667 non-null  int64  \n",
      " 3   Stay_In_Current_City_Years  783667 non-null  int64  \n",
      " 4   Marital_Status              783667 non-null  int64  \n",
      " 5   Product_Category_1          783667 non-null  int64  \n",
      " 6   Product_Category_2          783667 non-null  float64\n",
      " 7   Product_Category_3          783667 non-null  float64\n",
      " 8   Purchase                    550068 non-null  float64\n",
      " 9   B                           783667 non-null  int64  \n",
      " 10  C                           783667 non-null  int64  \n",
      "dtypes: float64(3), int64(8)\n",
      "memory usage: 71.7 MB\n"
     ]
    }
   ],
   "source": [
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9bfcea56",
   "metadata": {},
   "source": [
    "### visualization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "2d03d136",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Age', ylabel='Purchase'>"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(x='Age',y='Purchase',hue='Gender',data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "764846a9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Occupation', ylabel='Purchase'>"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(x='Occupation',y='Purchase',hue='Gender',data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "768be411",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Product_Category_1', ylabel='Purchase'>"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(x='Product_Category_1',y='Purchase',hue='Gender',data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "de4a0884",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Product_Category_2', ylabel='Purchase'>"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(x='Product_Category_2',y='Purchase',hue='Gender',data=df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "51a36587",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Product_Category_3', ylabel='Purchase'>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.barplot(x='Product_Category_3',y='Purchase',hue='Gender',data=df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "58fed791",
   "metadata": {},
   "source": [
    "### feature scaling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "72b6223c",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_test = df[df[\"Purchase\"].isnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "de67c934",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = df[~df[\"Purchase\"].isnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "adf79494",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(233599, 11)\n",
      "(550068, 11)\n"
     ]
    }
   ],
   "source": [
    "print(df_test.shape)\n",
    "print(df_train.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "5c525bdb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0          8370.0\n",
      "1         15200.0\n",
      "2          1422.0\n",
      "3          1057.0\n",
      "4          7969.0\n",
      "           ...   \n",
      "550063      368.0\n",
      "550064      371.0\n",
      "550065      137.0\n",
      "550066      365.0\n",
      "550067      490.0\n",
      "Name: Purchase, Length: 550068, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "X = df_train.drop([\"Purchase\"],axis=1)\n",
    "y = df_train[\"Purchase\"]\n",
    "\n",
    "# print(X.shape)\n",
    "print(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "04c2b4df",
   "metadata": {},
   "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=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "2e2c27bf",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "sc = StandardScaler()\n",
    "X_train = sc.fit_transform(X_train)\n",
    "X_test = sc.fit_transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "539af401",
   "metadata": {},
   "outputs": [],
   "source": [
    "# train your models....."
   ]
  }
 ],
 "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}