{
"cells": [
{
"cell_type": "markdown",
"id": "ab3c44f1-b880-42ed-98e9-e8b8394f13a5",
"metadata": {},
"source": [
"# Customer Lifetime Value"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bd735dde-76f2-45ef-b3b0-0f4d923ff30e",
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
"%matplotlib inline"
]
},
{
"cell_type": "markdown",
"id": "f9976dad-4321-472f-8b2b-eb7e24127f1c",
"metadata": {},
"source": [
"## Imports"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "efc9ea60-6f34-4540-804a-ee684cf66093",
"metadata": {},
"outputs": [],
"source": [
"from fastai.vision.all import *\n",
"from aiking.data.external import * #We need to import this after fastai modules\n",
"import pandas as pd\n",
"from sklearn.ensemble import RandomForestRegressor\n",
"from sklearn.model_selection import cross_val_score\n",
"from sklearn.feature_selection import mutual_info_regression"
]
},
{
"cell_type": "markdown",
"id": "074a41c2-c2c7-4da4-9e3a-ee1d6dd155d8",
"metadata": {},
"source": [
"## Getting Dataset"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3dd737ad-86ce-4652-b299-0232360a9849",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Path('/content/drive/MyDrive/PPV/S_Personal_Study/aiking/data/ibm-watson-marketing-customer-value-data')"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#kaggle datasets download -d pankajjsh06/ibm-watson-marketing-customer-value-data\n",
"path = untar_data(\"kaggle_datasets::pankajjsh06/ibm-watson-marketing-customer-value-data\"); path"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ec59a26e-9603-47f7-8694-e72410e18f6d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(#1) [Path('/content/drive/MyDrive/PPV/S_Personal_Study/aiking/data/ibm-watson-marketing-customer-value-data/WA_Fn-UseC_-Marketing-Customer-Value-Analysis.csv')]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"path.ls()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6842a931-5a78-4036-a58b-4bbd5172bc5b",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(path/\"WA_Fn-UseC_-Marketing-Customer-Value-Analysis.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fb41a39d-442a-4776-b487-78b0da188189",
"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</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" <th>3</th>\n",
" <th>4</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Customer</th>\n",
" <td>BU79786</td>\n",
" <td>QZ44356</td>\n",
" <td>AI49188</td>\n",
" <td>WW63253</td>\n",
" <td>HB64268</td>\n",
" </tr>\n",
" <tr>\n",
" <th>State</th>\n",
" <td>Washington</td>\n",
" <td>Arizona</td>\n",
" <td>Nevada</td>\n",
" <td>California</td>\n",
" <td>Washington</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Customer Lifetime Value</th>\n",
" <td>2763.519279</td>\n",
" <td>6979.535903</td>\n",
" <td>12887.43165</td>\n",
" <td>7645.861827</td>\n",
" <td>2813.692575</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Response</th>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Coverage</th>\n",
" <td>Basic</td>\n",
" <td>Extended</td>\n",
" <td>Premium</td>\n",
" <td>Basic</td>\n",
" <td>Basic</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Education</th>\n",
" <td>Bachelor</td>\n",
" <td>Bachelor</td>\n",
" <td>Bachelor</td>\n",
" <td>Bachelor</td>\n",
" <td>Bachelor</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Effective To Date</th>\n",
" <td>2/24/11</td>\n",
" <td>1/31/11</td>\n",
" <td>2/19/11</td>\n",
" <td>1/20/11</td>\n",
" <td>2/3/11</td>\n",
" </tr>\n",
" <tr>\n",
" <th>EmploymentStatus</th>\n",
" <td>Employed</td>\n",
" <td>Unemployed</td>\n",
" <td>Employed</td>\n",
" <td>Unemployed</td>\n",
" <td>Employed</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Gender</th>\n",
" <td>F</td>\n",
" <td>F</td>\n",
" <td>F</td>\n",
" <td>M</td>\n",
" <td>M</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Income</th>\n",
" <td>56274</td>\n",
" <td>0</td>\n",
" <td>48767</td>\n",
" <td>0</td>\n",
" <td>43836</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Location Code</th>\n",
" <td>Suburban</td>\n",
" <td>Suburban</td>\n",
" <td>Suburban</td>\n",
" <td>Suburban</td>\n",
" <td>Rural</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Marital Status</th>\n",
" <td>Married</td>\n",
" <td>Single</td>\n",
" <td>Married</td>\n",
" <td>Married</td>\n",
" <td>Single</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Monthly Premium Auto</th>\n",
" <td>69</td>\n",
" <td>94</td>\n",
" <td>108</td>\n",
" <td>106</td>\n",
" <td>73</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Months Since Last Claim</th>\n",
" <td>32</td>\n",
" <td>13</td>\n",
" <td>18</td>\n",
" <td>18</td>\n",
" <td>12</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Months Since Policy Inception</th>\n",
" <td>5</td>\n",
" <td>42</td>\n",
" <td>38</td>\n",
" <td>65</td>\n",
" <td>44</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Number of Open Complaints</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Number of Policies</th>\n",
" <td>1</td>\n",
" <td>8</td>\n",
" <td>2</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Policy Type</th>\n",
" <td>Corporate Auto</td>\n",
" <td>Personal Auto</td>\n",
" <td>Personal Auto</td>\n",
" <td>Corporate Auto</td>\n",
" <td>Personal Auto</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Policy</th>\n",
" <td>Corporate L3</td>\n",
" <td>Personal L3</td>\n",
" <td>Personal L3</td>\n",
" <td>Corporate L2</td>\n",
" <td>Personal L1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Renew Offer Type</th>\n",
" <td>Offer1</td>\n",
" <td>Offer3</td>\n",
" <td>Offer1</td>\n",
" <td>Offer1</td>\n",
" <td>Offer1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Sales Channel</th>\n",
" <td>Agent</td>\n",
" <td>Agent</td>\n",
" <td>Agent</td>\n",
" <td>Call Center</td>\n",
" <td>Agent</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Total Claim Amount</th>\n",
" <td>384.811147</td>\n",
" <td>1131.464935</td>\n",
" <td>566.472247</td>\n",
" <td>529.881344</td>\n",
" <td>138.130879</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Vehicle Class</th>\n",
" <td>Two-Door Car</td>\n",
" <td>Four-Door Car</td>\n",
" <td>Two-Door Car</td>\n",
" <td>SUV</td>\n",
" <td>Four-Door Car</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Vehicle Size</th>\n",
" <td>Medsize</td>\n",
" <td>Medsize</td>\n",
" <td>Medsize</td>\n",
" <td>Medsize</td>\n",
" <td>Medsize</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0 ... 4\n",
"Customer BU79786 ... HB64268\n",
"State Washington ... Washington\n",
"Customer Lifetime Value 2763.519279 ... 2813.692575\n",
"Response No ... No\n",
"Coverage Basic ... Basic\n",
"Education Bachelor ... Bachelor\n",
"Effective To Date 2/24/11 ... 2/3/11\n",
"EmploymentStatus Employed ... Employed\n",
"Gender F ... M\n",
"Income 56274 ... 43836\n",
"Location Code Suburban ... Rural\n",
"Marital Status Married ... Single\n",
"Monthly Premium Auto 69 ... 73\n",
"Months Since Last Claim 32 ... 12\n",
"Months Since Policy Inception 5 ... 44\n",
"Number of Open Complaints 0 ... 0\n",
"Number of Policies 1 ... 1\n",
"Policy Type Corporate Auto ... Personal Auto\n",
"Policy Corporate L3 ... Personal L1\n",
"Renew Offer Type Offer1 ... Offer1\n",
"Sales Channel Agent ... Agent\n",
"Total Claim Amount 384.811147 ... 138.130879\n",
"Vehicle Class Two-Door Car ... Four-Door Car\n",
"Vehicle Size Medsize ... Medsize\n",
"\n",
"[24 rows x 5 columns]"
]
},
"execution_count": null,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head().T"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8926c0db-45cf-45dd-b3c9-d7a74fa4709a",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}