Feature_Engg_Clean.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from datetime import datetime\n",
    "from datetime import date"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "odict_keys(['Transactions', 'NewCustomerList', 'CustomerDemographic', 'CustomerAddress'])\n"
     ]
    }
   ],
   "source": [
    "WBK = 'KPMG_Data.xlsx'\n",
    "Book = pd.read_excel(WBK, sheet_name=None)\n",
    "print(Book.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Note: The data and information in this document is reflective of a hypothetical situation and client. This document is to be used for KPMG Virtual Internship purposes only.</th>\n",
       "      <th>Unnamed: 1</th>\n",
       "      <th>Unnamed: 2</th>\n",
       "      <th>Unnamed: 3</th>\n",
       "      <th>Unnamed: 4</th>\n",
       "      <th>Unnamed: 5</th>\n",
       "      <th>Unnamed: 6</th>\n",
       "      <th>Unnamed: 7</th>\n",
       "      <th>Unnamed: 8</th>\n",
       "      <th>Unnamed: 9</th>\n",
       "      <th>Unnamed: 10</th>\n",
       "      <th>Unnamed: 11</th>\n",
       "      <th>Unnamed: 12</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>customer_id</td>\n",
       "      <td>first_name</td>\n",
       "      <td>last_name</td>\n",
       "      <td>gender</td>\n",
       "      <td>past_3_years_bike_related_purchases</td>\n",
       "      <td>DOB</td>\n",
       "      <td>job_title</td>\n",
       "      <td>job_industry_category</td>\n",
       "      <td>wealth_segment</td>\n",
       "      <td>deceased_indicator</td>\n",
       "      <td>default</td>\n",
       "      <td>owns_car</td>\n",
       "      <td>tenure</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Laraine</td>\n",
       "      <td>Medendorp</td>\n",
       "      <td>F</td>\n",
       "      <td>93</td>\n",
       "      <td>1953-10-12 00:00:00</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>\"'</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>Eli</td>\n",
       "      <td>Bockman</td>\n",
       "      <td>Male</td>\n",
       "      <td>81</td>\n",
       "      <td>1980-12-16 00:00:00</td>\n",
       "      <td>Administrative Officer</td>\n",
       "      <td>Financial Services</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>&lt;script&gt;alert('hi')&lt;/script&gt;</td>\n",
       "      <td>Yes</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Note: The data and information in this document is reflective of a hypothetical situation and client. This document is to be used for KPMG Virtual Internship purposes only.   \\\n",
       "0                                        customer_id                                                                                                                              \n",
       "1                                                  1                                                                                                                              \n",
       "2                                                  2                                                                                                                              \n",
       "\n",
       "   Unnamed: 1 Unnamed: 2 Unnamed: 3                           Unnamed: 4  \\\n",
       "0  first_name  last_name     gender  past_3_years_bike_related_purchases   \n",
       "1     Laraine  Medendorp          F                                   93   \n",
       "2         Eli    Bockman       Male                                   81   \n",
       "\n",
       "            Unnamed: 5              Unnamed: 6             Unnamed: 7  \\\n",
       "0                  DOB               job_title  job_industry_category   \n",
       "1  1953-10-12 00:00:00     Executive Secretary                 Health   \n",
       "2  1980-12-16 00:00:00  Administrative Officer     Financial Services   \n",
       "\n",
       "       Unnamed: 8          Unnamed: 9                   Unnamed: 10  \\\n",
       "0  wealth_segment  deceased_indicator                       default   \n",
       "1   Mass Customer                   N                            \"'   \n",
       "2   Mass Customer                   N  <script>alert('hi')</script>   \n",
       "\n",
       "  Unnamed: 11 Unnamed: 12  \n",
       "0    owns_car      tenure  \n",
       "1         Yes          11  \n",
       "2         Yes          16  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Demo_DF = pd.read_excel(WBK, sheet_name=\"CustomerDemographic\")\n",
    "Addr_DF= pd.read_excel(WBK, sheet_name=\"CustomerAddress\")\n",
    "Tranx_DF= pd.read_excel(WBK, sheet_name=\"Transactions\")\n",
    "New_Cust_DF = pd.read_excel(WBK, sheet_name=\"NewCustomerList\")\n",
    "Demo_DF.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def col_name_format(*df):\n",
    "    DF_ls = []\n",
    "    for c in df:\n",
    "        new_col = c.iloc[0]\n",
    "        c = c[1:]\n",
    "        c.columns = new_col\n",
    "        DF_ls.append(c)\n",
    "    return DF_ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "Demo_DF, Addr_DF, Tranx_DF, New_Cust_DF = col_name_format(Demo_DF, Addr_DF, Tranx_DF, New_Cust_DF)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>customer_id</th>\n",
       "      <th>first_name</th>\n",
       "      <th>last_name</th>\n",
       "      <th>gender</th>\n",
       "      <th>past_3_years_bike_related_purchases</th>\n",
       "      <th>DOB</th>\n",
       "      <th>job_title</th>\n",
       "      <th>job_industry_category</th>\n",
       "      <th>wealth_segment</th>\n",
       "      <th>deceased_indicator</th>\n",
       "      <th>default</th>\n",
       "      <th>owns_car</th>\n",
       "      <th>tenure</th>\n",
       "      <th>address</th>\n",
       "      <th>postcode</th>\n",
       "      <th>state</th>\n",
       "      <th>country</th>\n",
       "      <th>property_valuation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Laraine</td>\n",
       "      <td>Medendorp</td>\n",
       "      <td>F</td>\n",
       "      <td>93</td>\n",
       "      <td>1953-10-12 00:00:00</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>\"'</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>060 Morning Avenue</td>\n",
       "      <td>2016</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>Australia</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>Eli</td>\n",
       "      <td>Bockman</td>\n",
       "      <td>Male</td>\n",
       "      <td>81</td>\n",
       "      <td>1980-12-16 00:00:00</td>\n",
       "      <td>Administrative Officer</td>\n",
       "      <td>Financial Services</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>&lt;script&gt;alert('hi')&lt;/script&gt;</td>\n",
       "      <td>Yes</td>\n",
       "      <td>16</td>\n",
       "      <td>6 Meadow Vale Court</td>\n",
       "      <td>2153</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>Australia</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>Arlin</td>\n",
       "      <td>Dearle</td>\n",
       "      <td>Male</td>\n",
       "      <td>61</td>\n",
       "      <td>1954-01-20 00:00:00</td>\n",
       "      <td>Recruiting Manager</td>\n",
       "      <td>Property</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>2018-02-01 00:00:00</td>\n",
       "      <td>Yes</td>\n",
       "      <td>15</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>Talbot</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Male</td>\n",
       "      <td>33</td>\n",
       "      <td>1961-10-03 00:00:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>IT</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>() { _; } &gt;_[$($())] { touch /tmp/blns.shellsh...</td>\n",
       "      <td>No</td>\n",
       "      <td>7</td>\n",
       "      <td>0 Holy Cross Court</td>\n",
       "      <td>4211</td>\n",
       "      <td>QLD</td>\n",
       "      <td>Australia</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>Sheila-kathryn</td>\n",
       "      <td>Calton</td>\n",
       "      <td>Female</td>\n",
       "      <td>56</td>\n",
       "      <td>1977-05-13 00:00:00</td>\n",
       "      <td>Senior Editor</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Affluent Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>NIL</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "      <td>17979 Del Mar Point</td>\n",
       "      <td>2448</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>Australia</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3995</td>\n",
       "      <td>3996</td>\n",
       "      <td>Rosalia</td>\n",
       "      <td>Halgarth</td>\n",
       "      <td>Female</td>\n",
       "      <td>8</td>\n",
       "      <td>1975-08-09 00:00:00</td>\n",
       "      <td>VP Product Management</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>-100</td>\n",
       "      <td>No</td>\n",
       "      <td>19</td>\n",
       "      <td>0 Transport Center</td>\n",
       "      <td>3977</td>\n",
       "      <td>VIC</td>\n",
       "      <td>Australia</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3996</td>\n",
       "      <td>3997</td>\n",
       "      <td>Blanch</td>\n",
       "      <td>Nisuis</td>\n",
       "      <td>Female</td>\n",
       "      <td>87</td>\n",
       "      <td>2001-07-13 00:00:00</td>\n",
       "      <td>Statistician II</td>\n",
       "      <td>Manufacturing</td>\n",
       "      <td>High Net Worth</td>\n",
       "      <td>N</td>\n",
       "      <td>â¦testâ§</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>4 Dovetail Crossing</td>\n",
       "      <td>2350</td>\n",
       "      <td>NSW</td>\n",
       "      <td>Australia</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3997</td>\n",
       "      <td>3998</td>\n",
       "      <td>Sarene</td>\n",
       "      <td>Woolley</td>\n",
       "      <td>U</td>\n",
       "      <td>60</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Assistant Manager</td>\n",
       "      <td>IT</td>\n",
       "      <td>High Net Worth</td>\n",
       "      <td>N</td>\n",
       "      <td>NaN</td>\n",
       "      <td>No</td>\n",
       "      <td>NaN</td>\n",
       "      <td>736 Roxbury Junction</td>\n",
       "      <td>2540</td>\n",
       "      <td>NSW</td>\n",
       "      <td>Australia</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3998</td>\n",
       "      <td>3999</td>\n",
       "      <td>Patrizius</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Male</td>\n",
       "      <td>11</td>\n",
       "      <td>1973-10-24 00:00:00</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Manufacturing</td>\n",
       "      <td>Affluent Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>Â¡â¢Â£Â¢âÂ§Â¶â¢ÂªÂºââ</td>\n",
       "      <td>Yes</td>\n",
       "      <td>10</td>\n",
       "      <td>1482 Hauk Trail</td>\n",
       "      <td>3064</td>\n",
       "      <td>VIC</td>\n",
       "      <td>Australia</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3999</td>\n",
       "      <td>4000</td>\n",
       "      <td>Kippy</td>\n",
       "      <td>Oldland</td>\n",
       "      <td>Male</td>\n",
       "      <td>76</td>\n",
       "      <td>1991-11-05 00:00:00</td>\n",
       "      <td>Software Engineer IV</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Affluent Customer</td>\n",
       "      <td>N</td>\n",
       "      <td>0/0</td>\n",
       "      <td>No</td>\n",
       "      <td>11</td>\n",
       "      <td>57042 Village Green Point</td>\n",
       "      <td>4511</td>\n",
       "      <td>QLD</td>\n",
       "      <td>Australia</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4000 rows × 18 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "0    customer_id      first_name  last_name  gender  \\\n",
       "0              1         Laraine  Medendorp       F   \n",
       "1              2             Eli    Bockman    Male   \n",
       "2              3           Arlin     Dearle    Male   \n",
       "3              4          Talbot        NaN    Male   \n",
       "4              5  Sheila-kathryn     Calton  Female   \n",
       "...          ...             ...        ...     ...   \n",
       "3995        3996         Rosalia   Halgarth  Female   \n",
       "3996        3997          Blanch     Nisuis  Female   \n",
       "3997        3998          Sarene    Woolley       U   \n",
       "3998        3999       Patrizius        NaN    Male   \n",
       "3999        4000           Kippy    Oldland    Male   \n",
       "\n",
       "0    past_3_years_bike_related_purchases                  DOB  \\\n",
       "0                                     93  1953-10-12 00:00:00   \n",
       "1                                     81  1980-12-16 00:00:00   \n",
       "2                                     61  1954-01-20 00:00:00   \n",
       "3                                     33  1961-10-03 00:00:00   \n",
       "4                                     56  1977-05-13 00:00:00   \n",
       "...                                  ...                  ...   \n",
       "3995                                   8  1975-08-09 00:00:00   \n",
       "3996                                  87  2001-07-13 00:00:00   \n",
       "3997                                  60                  NaN   \n",
       "3998                                  11  1973-10-24 00:00:00   \n",
       "3999                                  76  1991-11-05 00:00:00   \n",
       "\n",
       "0                  job_title job_industry_category     wealth_segment  \\\n",
       "0        Executive Secretary                Health      Mass Customer   \n",
       "1     Administrative Officer    Financial Services      Mass Customer   \n",
       "2         Recruiting Manager              Property      Mass Customer   \n",
       "3                        NaN                    IT      Mass Customer   \n",
       "4              Senior Editor                   NaN  Affluent Customer   \n",
       "...                      ...                   ...                ...   \n",
       "3995   VP Product Management                Health      Mass Customer   \n",
       "3996         Statistician II         Manufacturing     High Net Worth   \n",
       "3997       Assistant Manager                    IT     High Net Worth   \n",
       "3998                     NaN         Manufacturing  Affluent Customer   \n",
       "3999    Software Engineer IV                   NaN  Affluent Customer   \n",
       "\n",
       "0    deceased_indicator                                            default  \\\n",
       "0                     N                                                 \"'   \n",
       "1                     N                       <script>alert('hi')</script>   \n",
       "2                     N                                2018-02-01 00:00:00   \n",
       "3                     N  () { _; } >_[$($())] { touch /tmp/blns.shellsh...   \n",
       "4                     N                                                NIL   \n",
       "...                 ...                                                ...   \n",
       "3995                  N                                               -100   \n",
       "3996                  N                                           â¦testâ§   \n",
       "3997                  N                                                NaN   \n",
       "3998                  N                             Â¡â¢Â£Â¢âÂ§Â¶â¢ÂªÂºââ    \n",
       "3999                  N                                                0/0   \n",
       "\n",
       "0    owns_car tenure                    address postcode            state  \\\n",
       "0         Yes     11         060 Morning Avenue     2016  New South Wales   \n",
       "1         Yes     16        6 Meadow Vale Court     2153  New South Wales   \n",
       "2         Yes     15                        NaN      NaN              NaN   \n",
       "3          No      7         0 Holy Cross Court     4211              QLD   \n",
       "4         Yes      8        17979 Del Mar Point     2448  New South Wales   \n",
       "...       ...    ...                        ...      ...              ...   \n",
       "3995       No     19         0 Transport Center     3977              VIC   \n",
       "3996      Yes      1        4 Dovetail Crossing     2350              NSW   \n",
       "3997       No    NaN       736 Roxbury Junction     2540              NSW   \n",
       "3998      Yes     10            1482 Hauk Trail     3064              VIC   \n",
       "3999       No     11  57042 Village Green Point     4511              QLD   \n",
       "\n",
       "0       country property_valuation  \n",
       "0     Australia                 10  \n",
       "1     Australia                 10  \n",
       "2           NaN                NaN  \n",
       "3     Australia                  9  \n",
       "4     Australia                  4  \n",
       "...         ...                ...  \n",
       "3995  Australia                  6  \n",
       "3996  Australia                  2  \n",
       "3997  Australia                  6  \n",
       "3998  Australia                  3  \n",
       "3999  Australia                  6  \n",
       "\n",
       "[4000 rows x 18 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Demo_DF = Demo_DF.merge(Addr_DF, how = \"left\", on=\"customer_id\")\n",
    "Demo_DF.where(Demo_DF.notnull(), np.nan)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "def nan_pcent(df):\n",
    "    points = df.shape[0]\n",
    "    for col in df.columns:\n",
    "        print(\"* {} has {}% nan values\\n\".format(col,((df[col].isna().sum())/points)*100))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Demo_DF shape: (4000, 18)\n",
      "\n",
      "* customer_id has 0.0% nan values\n",
      "\n",
      "* first_name has 0.0% nan values\n",
      "\n",
      "* last_name has 3.125% nan values\n",
      "\n",
      "* gender has 0.0% nan values\n",
      "\n",
      "* past_3_years_bike_related_purchases has 0.0% nan values\n",
      "\n",
      "* DOB has 2.175% nan values\n",
      "\n",
      "* job_title has 12.65% nan values\n",
      "\n",
      "* job_industry_category has 16.400000000000002% nan values\n",
      "\n",
      "* wealth_segment has 0.0% nan values\n",
      "\n",
      "* deceased_indicator has 0.0% nan values\n",
      "\n",
      "* default has 7.55% nan values\n",
      "\n",
      "* owns_car has 0.0% nan values\n",
      "\n",
      "* tenure has 2.175% nan values\n",
      "\n",
      "* address has 0.1% nan values\n",
      "\n",
      "* postcode has 0.1% nan values\n",
      "\n",
      "* state has 0.1% nan values\n",
      "\n",
      "* country has 0.1% nan values\n",
      "\n",
      "* property_valuation has 0.1% nan values\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"Demo_DF shape: {}\".format(Demo_DF.shape))\n",
    "print()\n",
    "nan_pcent(Demo_DF)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "Demo_DF.drop(columns=[\"first_name\", \"last_name\", \"default\", \"deceased_indicator\", \"address\", \"country\"], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "Demo_DF[\"gender\"] = Demo_DF[\"gender\"].apply(lambda x: \"Female\" if x==\"F\" else \"Female\" if x==\"Femal\" else \"Male\" if x==\"M\" else \"NA\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['NA', 'Male', 'Female']\n"
     ]
    }
   ],
   "source": [
    "print(list(set(Demo_DF[\"gender\"])))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'NA', 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 174, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 73, 74, 77, 82, 86, 46}\n"
     ]
    }
   ],
   "source": [
    "def age_calculation(dob):\n",
    "    dob = pd.to_datetime(dob)\n",
    "    today = date.today()\n",
    "    return (today.year - 3) - dob.year\n",
    "\n",
    "Demo_DF['Age'] = Demo_DF['DOB'].apply(age_calculation)\n",
    "Demo_DF['Age'] = Demo_DF['Age'].replace(np.nan, \"NA\")\n",
    "Demo_DF['Age'] = Demo_DF['Age'].apply(lambda x: int(x) if isinstance(x, float) else \"NA\")\n",
    "print(set(Demo_DF[\"Age\"].to_list()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "Demo_DF.drop(columns=\"DOB\",inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Tranx_DF shape: (20000, 13)\n",
      "\n",
      "* transaction_id has 0.0% nan values\n",
      "\n",
      "* product_id has 0.0% nan values\n",
      "\n",
      "* customer_id has 0.0% nan values\n",
      "\n",
      "* transaction_date has 0.0% nan values\n",
      "\n",
      "* online_order has 1.7999999999999998% nan values\n",
      "\n",
      "* order_status has 0.0% nan values\n",
      "\n",
      "* brand has 0.985% nan values\n",
      "\n",
      "* product_line has 0.985% nan values\n",
      "\n",
      "* product_class has 0.985% nan values\n",
      "\n",
      "* product_size has 0.985% nan values\n",
      "\n",
      "* list_price has 0.0% nan values\n",
      "\n",
      "* standard_cost has 0.985% nan values\n",
      "\n",
      "* product_first_sold_date has 0.985% nan values\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"Tranx_DF shape: {}\".format(Tranx_DF.shape))\n",
    "print()\n",
    "nan_pcent(Tranx_DF)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "Tranx_DF.drop(columns=[\"transaction_date\", \"online_order\", \"order_status\", \"product_id\", \"transaction_id\", \"list_price\", \"standard_cost\", \"product_first_sold_date\"], inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>customer_id</th>\n",
       "      <th>brand</th>\n",
       "      <th>product_line</th>\n",
       "      <th>product_class</th>\n",
       "      <th>product_size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2950</td>\n",
       "      <td>Solex</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>3120</td>\n",
       "      <td>Trek Bicycles</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>large</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>402</td>\n",
       "      <td>OHM Cycles</td>\n",
       "      <td>Standard</td>\n",
       "      <td>low</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>3135</td>\n",
       "      <td>Norco Bicycles</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>787</td>\n",
       "      <td>Giant Bicycles</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>large</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "0 customer_id           brand product_line product_class product_size\n",
       "1        2950           Solex     Standard        medium       medium\n",
       "2        3120   Trek Bicycles     Standard        medium        large\n",
       "3         402      OHM Cycles     Standard           low       medium\n",
       "4        3135  Norco Bicycles     Standard        medium       medium\n",
       "5         787  Giant Bicycles     Standard        medium        large"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Tranx_DF.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Col 'brand' items: {nan, 'Trek Bicycles', 'OHM Cycles', 'Norco Bicycles', 'Giant Bicycles', 'WeareA2B', 'Solex'}\n",
      "\n",
      "Col 'product_line' items: {nan, 'Touring', 'Road', 'Mountain', 'Standard'}\n",
      "\n",
      "Col 'product_class' items: {'high', nan, 'low', 'medium'}\n",
      "\n",
      "Col 'product_size' items: {nan, 'large', 'medium', 'small'}\n",
      "\n"
     ]
    }
   ],
   "source": [
    "def prod_class(*trnx_df):\n",
    "    df = Tranx_DF\n",
    "    for column in trnx_df:\n",
    "        print(\"Col \\'{}\\' items: {}\".format(column, set(df[column].to_list())))\n",
    "        print()\n",
    "                 \n",
    "prod_class(\"brand\", \"product_line\", \"product_class\", \"product_size\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "Demo_DF_old = Demo_DF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'NA', 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79}\n"
     ]
    }
   ],
   "source": [
    "New_Cust_DF['Age'] = New_Cust_DF['DOB'].apply(age_calculation)\n",
    "New_Cust_DF['Age'] = New_Cust_DF['Age'].replace(np.nan, \"NA\")\n",
    "New_Cust_DF['Age'] = New_Cust_DF['Age'].apply(lambda x: int(x) if isinstance(x, float) else \"NA\")\n",
    "print(set(New_Cust_DF[\"Age\"].to_list()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['first_name', 'last_name', 'gender', 'past_3_years_bike_related_purchases', 'DOB', 'job_title', 'job_industry_category', 'wealth_segment', 'deceased_indicator', 'owns_car', 'tenure', 'address', 'postcode', 'state', 'country', 'property_valuation', nan, nan, nan, nan, nan, 'Rank', 'Value', 'Age']\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print([col for col in New_Cust_DF.columns.to_list()])\n",
    "print()\n",
    "New_Cust_DF = New_Cust_DF.loc[:, New_Cust_DF.columns.notnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "New_Cust_DF[\"customer_id\"] = [Demo_DF.shape[0]+1+i for i in range(len(New_Cust_DF))]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "New_Cust_DF = New_Cust_DF[[col for col in Demo_DF.columns.to_list()]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "New_Cust_DF = Demo_DF.append(New_Cust_DF, ignore_index = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>customer_id</th>\n",
       "      <th>gender</th>\n",
       "      <th>past_3_years_bike_related_purchases</th>\n",
       "      <th>job_title</th>\n",
       "      <th>job_industry_category</th>\n",
       "      <th>wealth_segment</th>\n",
       "      <th>owns_car</th>\n",
       "      <th>tenure</th>\n",
       "      <th>postcode</th>\n",
       "      <th>state</th>\n",
       "      <th>property_valuation</th>\n",
       "      <th>Age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Female</td>\n",
       "      <td>93</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>2016</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>10</td>\n",
       "      <td>64</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NA</td>\n",
       "      <td>81</td>\n",
       "      <td>Administrative Officer</td>\n",
       "      <td>Financial Services</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>16</td>\n",
       "      <td>2153</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>10</td>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>NA</td>\n",
       "      <td>61</td>\n",
       "      <td>Recruiting Manager</td>\n",
       "      <td>Property</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>15</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>NA</td>\n",
       "      <td>33</td>\n",
       "      <td>NaN</td>\n",
       "      <td>IT</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>No</td>\n",
       "      <td>7</td>\n",
       "      <td>4211</td>\n",
       "      <td>QLD</td>\n",
       "      <td>9</td>\n",
       "      <td>56</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>NA</td>\n",
       "      <td>56</td>\n",
       "      <td>Senior Editor</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Affluent Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "      <td>2448</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>4</td>\n",
       "      <td>40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4995</td>\n",
       "      <td>4996</td>\n",
       "      <td>Male</td>\n",
       "      <td>60</td>\n",
       "      <td>Paralegal</td>\n",
       "      <td>Financial Services</td>\n",
       "      <td>Affluent Customer</td>\n",
       "      <td>No</td>\n",
       "      <td>9</td>\n",
       "      <td>2200</td>\n",
       "      <td>NSW</td>\n",
       "      <td>7</td>\n",
       "      <td>58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4996</td>\n",
       "      <td>4997</td>\n",
       "      <td>Male</td>\n",
       "      <td>22</td>\n",
       "      <td>Senior Sales Associate</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>No</td>\n",
       "      <td>6</td>\n",
       "      <td>2196</td>\n",
       "      <td>NSW</td>\n",
       "      <td>10</td>\n",
       "      <td>16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4997</td>\n",
       "      <td>4998</td>\n",
       "      <td>Female</td>\n",
       "      <td>17</td>\n",
       "      <td>Budget/Accounting Analyst IV</td>\n",
       "      <td>Financial Services</td>\n",
       "      <td>Affluent Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>15</td>\n",
       "      <td>4702</td>\n",
       "      <td>QLD</td>\n",
       "      <td>2</td>\n",
       "      <td>63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4998</td>\n",
       "      <td>4999</td>\n",
       "      <td>Male</td>\n",
       "      <td>30</td>\n",
       "      <td>Financial Advisor</td>\n",
       "      <td>Financial Services</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>19</td>\n",
       "      <td>4215</td>\n",
       "      <td>QLD</td>\n",
       "      <td>2</td>\n",
       "      <td>65</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4999</td>\n",
       "      <td>5000</td>\n",
       "      <td>Male</td>\n",
       "      <td>56</td>\n",
       "      <td>Staff Accountant IV</td>\n",
       "      <td>Property</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>14</td>\n",
       "      <td>2010</td>\n",
       "      <td>NSW</td>\n",
       "      <td>9</td>\n",
       "      <td>62</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5000 rows × 12 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "0    customer_id  gender past_3_years_bike_related_purchases  \\\n",
       "0              1  Female                                  93   \n",
       "1              2      NA                                  81   \n",
       "2              3      NA                                  61   \n",
       "3              4      NA                                  33   \n",
       "4              5      NA                                  56   \n",
       "...          ...     ...                                 ...   \n",
       "4995        4996    Male                                  60   \n",
       "4996        4997    Male                                  22   \n",
       "4997        4998  Female                                  17   \n",
       "4998        4999    Male                                  30   \n",
       "4999        5000    Male                                  56   \n",
       "\n",
       "0                        job_title job_industry_category     wealth_segment  \\\n",
       "0              Executive Secretary                Health      Mass Customer   \n",
       "1           Administrative Officer    Financial Services      Mass Customer   \n",
       "2               Recruiting Manager              Property      Mass Customer   \n",
       "3                              NaN                    IT      Mass Customer   \n",
       "4                    Senior Editor                   NaN  Affluent Customer   \n",
       "...                            ...                   ...                ...   \n",
       "4995                     Paralegal    Financial Services  Affluent Customer   \n",
       "4996        Senior Sales Associate                Health      Mass Customer   \n",
       "4997  Budget/Accounting Analyst IV    Financial Services  Affluent Customer   \n",
       "4998             Financial Advisor    Financial Services      Mass Customer   \n",
       "4999           Staff Accountant IV              Property      Mass Customer   \n",
       "\n",
       "0    owns_car tenure postcode            state property_valuation Age  \n",
       "0         Yes     11     2016  New South Wales                 10  64  \n",
       "1         Yes     16     2153  New South Wales                 10  37  \n",
       "2         Yes     15      NaN              NaN                NaN  63  \n",
       "3          No      7     4211              QLD                  9  56  \n",
       "4         Yes      8     2448  New South Wales                  4  40  \n",
       "...       ...    ...      ...              ...                ...  ..  \n",
       "4995       No      9     2200              NSW                  7  58  \n",
       "4996       No      6     2196              NSW                 10  16  \n",
       "4997      Yes     15     4702              QLD                  2  63  \n",
       "4998      Yes     19     4215              QLD                  2  65  \n",
       "4999      Yes     14     2010              NSW                  9  62  \n",
       "\n",
       "[5000 rows x 12 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "New_Cust_DF"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "Demo_DF_old = Demo_DF_old.merge(Tranx_DF, how=\"inner\", on=\"customer_id\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>customer_id</th>\n",
       "      <th>gender</th>\n",
       "      <th>past_3_years_bike_related_purchases</th>\n",
       "      <th>job_title</th>\n",
       "      <th>job_industry_category</th>\n",
       "      <th>wealth_segment</th>\n",
       "      <th>owns_car</th>\n",
       "      <th>tenure</th>\n",
       "      <th>postcode</th>\n",
       "      <th>state</th>\n",
       "      <th>property_valuation</th>\n",
       "      <th>Age</th>\n",
       "      <th>brand</th>\n",
       "      <th>product_line</th>\n",
       "      <th>product_class</th>\n",
       "      <th>product_size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>Female</td>\n",
       "      <td>93</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>2016</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>10</td>\n",
       "      <td>64</td>\n",
       "      <td>OHM Cycles</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Female</td>\n",
       "      <td>93</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>2016</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>10</td>\n",
       "      <td>64</td>\n",
       "      <td>Solex</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>Female</td>\n",
       "      <td>93</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>2016</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>10</td>\n",
       "      <td>64</td>\n",
       "      <td>Trek Bicycles</td>\n",
       "      <td>Road</td>\n",
       "      <td>low</td>\n",
       "      <td>small</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>Female</td>\n",
       "      <td>93</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>2016</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>10</td>\n",
       "      <td>64</td>\n",
       "      <td>Norco Bicycles</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>Female</td>\n",
       "      <td>93</td>\n",
       "      <td>Executive Secretary</td>\n",
       "      <td>Health</td>\n",
       "      <td>Mass Customer</td>\n",
       "      <td>Yes</td>\n",
       "      <td>11</td>\n",
       "      <td>2016</td>\n",
       "      <td>New South Wales</td>\n",
       "      <td>10</td>\n",
       "      <td>64</td>\n",
       "      <td>Solex</td>\n",
       "      <td>Standard</td>\n",
       "      <td>medium</td>\n",
       "      <td>medium</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "0 customer_id  gender past_3_years_bike_related_purchases  \\\n",
       "0           1  Female                                  93   \n",
       "1           1  Female                                  93   \n",
       "2           1  Female                                  93   \n",
       "3           1  Female                                  93   \n",
       "4           1  Female                                  93   \n",
       "\n",
       "0            job_title job_industry_category wealth_segment owns_car tenure  \\\n",
       "0  Executive Secretary                Health  Mass Customer      Yes     11   \n",
       "1  Executive Secretary                Health  Mass Customer      Yes     11   \n",
       "2  Executive Secretary                Health  Mass Customer      Yes     11   \n",
       "3  Executive Secretary                Health  Mass Customer      Yes     11   \n",
       "4  Executive Secretary                Health  Mass Customer      Yes     11   \n",
       "\n",
       "0 postcode            state property_valuation Age           brand  \\\n",
       "0     2016  New South Wales                 10  64      OHM Cycles   \n",
       "1     2016  New South Wales                 10  64           Solex   \n",
       "2     2016  New South Wales                 10  64   Trek Bicycles   \n",
       "3     2016  New South Wales                 10  64  Norco Bicycles   \n",
       "4     2016  New South Wales                 10  64           Solex   \n",
       "\n",
       "0 product_line product_class product_size  \n",
       "0     Standard        medium       medium  \n",
       "1     Standard        medium       medium  \n",
       "2         Road           low        small  \n",
       "3     Standard        medium       medium  \n",
       "4     Standard        medium       medium  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Demo_DF_old.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*By:*  `Adipta Biwas`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}