diff --git a/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb b/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb
new file mode 100644
index 0000000..64f5032
--- /dev/null
+++ b/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb
@@ -0,0 +1,2250 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "f428a16d",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Importing libraries\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "from sklearn.preprocessing import MinMaxScaler\n",
+ "from sklearn.model_selection import train_test_split"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "190485ab",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Customer | \n",
+ " State | \n",
+ " Customer Lifetime Value | \n",
+ " Response | \n",
+ " Coverage | \n",
+ " Education | \n",
+ " Effective To Date | \n",
+ " EmploymentStatus | \n",
+ " Gender | \n",
+ " Income | \n",
+ " ... | \n",
+ " Months Since Policy Inception | \n",
+ " Number of Open Complaints | \n",
+ " Number of Policies | \n",
+ " Policy Type | \n",
+ " Policy | \n",
+ " Renew Offer Type | \n",
+ " Sales Channel | \n",
+ " Total Claim Amount | \n",
+ " Vehicle Class | \n",
+ " Vehicle Size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 384.811147 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " 1131.464935 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 566.472247 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " 529.881344 | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 138.130879 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " 198.234764 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 379.200000 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 790.784983 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " 691.200000 | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " 369.600000 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 24 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Customer State Customer Lifetime Value Response Coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " Education Effective To Date EmploymentStatus Gender Income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " Months Since Policy Inception Number of Open Complaints \\\n",
+ "0 5 0 \n",
+ "1 42 0 \n",
+ "2 38 0 \n",
+ "3 65 0 \n",
+ "4 44 0 \n",
+ "... ... ... \n",
+ "9129 89 0 \n",
+ "9130 28 0 \n",
+ "9131 37 3 \n",
+ "9132 3 0 \n",
+ "9133 90 0 \n",
+ "\n",
+ " Number of Policies Policy Type Policy Renew Offer Type \\\n",
+ "0 1 Corporate Auto Corporate L3 Offer1 \n",
+ "1 8 Personal Auto Personal L3 Offer3 \n",
+ "2 2 Personal Auto Personal L3 Offer1 \n",
+ "3 7 Corporate Auto Corporate L2 Offer1 \n",
+ "4 1 Personal Auto Personal L1 Offer1 \n",
+ "... ... ... ... ... \n",
+ "9129 2 Personal Auto Personal L1 Offer2 \n",
+ "9130 1 Corporate Auto Corporate L3 Offer1 \n",
+ "9131 2 Corporate Auto Corporate L2 Offer1 \n",
+ "9132 3 Personal Auto Personal L2 Offer3 \n",
+ "9133 1 Corporate Auto Corporate L3 Offer4 \n",
+ "\n",
+ " Sales Channel Total Claim Amount Vehicle Class Vehicle Size \n",
+ "0 Agent 384.811147 Two-Door Car Medsize \n",
+ "1 Agent 1131.464935 Four-Door Car Medsize \n",
+ "2 Agent 566.472247 Two-Door Car Medsize \n",
+ "3 Call Center 529.881344 SUV Medsize \n",
+ "4 Agent 138.130879 Four-Door Car Medsize \n",
+ "... ... ... ... ... \n",
+ "9129 Web 198.234764 Four-Door Car Medsize \n",
+ "9130 Branch 379.200000 Four-Door Car Medsize \n",
+ "9131 Branch 790.784983 Four-Door Car Medsize \n",
+ "9132 Branch 691.200000 Four-Door Car Large \n",
+ "9133 Call Center 369.600000 Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 24 columns]"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Importing file\n",
+ "\n",
+ "df = pd.read_csv(r\"C:\\Users\\joaoa\\Desktop\\Ironhack\\Labs\\lab-customer-analysis-round-5\\files_for_lab\\csv_files\\marketing_customer_analysis.csv\")\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "10c11a0c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " total_claim_amount | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 384.811147 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " 1131.464935 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 566.472247 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " 529.881344 | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 138.130879 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " 198.234764 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 379.200000 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 790.784983 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " 691.200000 | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " 369.600000 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 24 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " months_since_policy_inception number_of_open_complaints \\\n",
+ "0 5 0 \n",
+ "1 42 0 \n",
+ "2 38 0 \n",
+ "3 65 0 \n",
+ "4 44 0 \n",
+ "... ... ... \n",
+ "9129 89 0 \n",
+ "9130 28 0 \n",
+ "9131 37 3 \n",
+ "9132 3 0 \n",
+ "9133 90 0 \n",
+ "\n",
+ " number_of_policies policy_type policy renew_offer_type \\\n",
+ "0 1 Corporate Auto Corporate L3 Offer1 \n",
+ "1 8 Personal Auto Personal L3 Offer3 \n",
+ "2 2 Personal Auto Personal L3 Offer1 \n",
+ "3 7 Corporate Auto Corporate L2 Offer1 \n",
+ "4 1 Personal Auto Personal L1 Offer1 \n",
+ "... ... ... ... ... \n",
+ "9129 2 Personal Auto Personal L1 Offer2 \n",
+ "9130 1 Corporate Auto Corporate L3 Offer1 \n",
+ "9131 2 Corporate Auto Corporate L2 Offer1 \n",
+ "9132 3 Personal Auto Personal L2 Offer3 \n",
+ "9133 1 Corporate Auto Corporate L3 Offer4 \n",
+ "\n",
+ " sales_channel total_claim_amount vehicle_class vehicle_size \n",
+ "0 Agent 384.811147 Two-Door Car Medsize \n",
+ "1 Agent 1131.464935 Four-Door Car Medsize \n",
+ "2 Agent 566.472247 Two-Door Car Medsize \n",
+ "3 Call Center 529.881344 SUV Medsize \n",
+ "4 Agent 138.130879 Four-Door Car Medsize \n",
+ "... ... ... ... ... \n",
+ "9129 Web 198.234764 Four-Door Car Medsize \n",
+ "9130 Branch 379.200000 Four-Door Car Medsize \n",
+ "9131 Branch 790.784983 Four-Door Car Medsize \n",
+ "9132 Branch 691.200000 Four-Door Car Large \n",
+ "9133 Call Center 369.600000 Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 24 columns]"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Standardizing columns names\n",
+ "\n",
+ "cols = []\n",
+ "for i in range(len(df.columns)):\n",
+ " cols.append(df.columns[i].lower().replace(\" \",\"_\"))\n",
+ "df.columns = cols\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "12c46e60",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "customer object\n",
+ "state object\n",
+ "customer_lifetime_value float64\n",
+ "response object\n",
+ "coverage object\n",
+ "education object\n",
+ "effective_to_date object\n",
+ "employmentstatus object\n",
+ "gender object\n",
+ "income int64\n",
+ "location_code object\n",
+ "marital_status object\n",
+ "monthly_premium_auto int64\n",
+ "months_since_last_claim int64\n",
+ "months_since_policy_inception int64\n",
+ "number_of_open_complaints int64\n",
+ "number_of_policies int64\n",
+ "policy_type object\n",
+ "policy object\n",
+ "renew_offer_type object\n",
+ "sales_channel object\n",
+ "total_claim_amount float64\n",
+ "vehicle_class object\n",
+ "vehicle_size object\n",
+ "dtype: object"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Looking for data types\n",
+ "\n",
+ "df.dtypes"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "86dd7344",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Total NaN values: 0\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "customer 0\n",
+ "state 0\n",
+ "customer_lifetime_value 0\n",
+ "response 0\n",
+ "coverage 0\n",
+ "education 0\n",
+ "effective_to_date 0\n",
+ "employmentstatus 0\n",
+ "gender 0\n",
+ "income 0\n",
+ "location_code 0\n",
+ "marital_status 0\n",
+ "monthly_premium_auto 0\n",
+ "months_since_last_claim 0\n",
+ "months_since_policy_inception 0\n",
+ "number_of_open_complaints 0\n",
+ "number_of_policies 0\n",
+ "policy_type 0\n",
+ "policy 0\n",
+ "renew_offer_type 0\n",
+ "sales_channel 0\n",
+ "total_claim_amount 0\n",
+ "vehicle_class 0\n",
+ "vehicle_size 0\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Checking null values\n",
+ "\n",
+ "print(\"Total NaN values:\", df.isna().sum().sum())\n",
+ "df.isna().sum()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "0f18bf3c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " total_claim_amount | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 384.811147 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " 1131.464935 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 566.472247 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " 529.881344 | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 138.130879 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " 198.234764 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 379.200000 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 790.784983 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " 691.200000 | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " 369.600000 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 24 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " months_since_policy_inception number_of_open_complaints \\\n",
+ "0 5 0 \n",
+ "1 42 0 \n",
+ "2 38 0 \n",
+ "3 65 0 \n",
+ "4 44 0 \n",
+ "... ... ... \n",
+ "9129 89 0 \n",
+ "9130 28 0 \n",
+ "9131 37 3 \n",
+ "9132 3 0 \n",
+ "9133 90 0 \n",
+ "\n",
+ " number_of_policies policy_type policy renew_offer_type \\\n",
+ "0 1 Corporate Auto Corporate L3 Offer1 \n",
+ "1 8 Personal Auto Personal L3 Offer3 \n",
+ "2 2 Personal Auto Personal L3 Offer1 \n",
+ "3 7 Corporate Auto Corporate L2 Offer1 \n",
+ "4 1 Personal Auto Personal L1 Offer1 \n",
+ "... ... ... ... ... \n",
+ "9129 2 Personal Auto Personal L1 Offer2 \n",
+ "9130 1 Corporate Auto Corporate L3 Offer1 \n",
+ "9131 2 Corporate Auto Corporate L2 Offer1 \n",
+ "9132 3 Personal Auto Personal L2 Offer3 \n",
+ "9133 1 Corporate Auto Corporate L3 Offer4 \n",
+ "\n",
+ " sales_channel total_claim_amount vehicle_class vehicle_size \n",
+ "0 Agent 384.811147 Two-Door Car Medsize \n",
+ "1 Agent 1131.464935 Four-Door Car Medsize \n",
+ "2 Agent 566.472247 Two-Door Car Medsize \n",
+ "3 Call Center 529.881344 SUV Medsize \n",
+ "4 Agent 138.130879 Four-Door Car Medsize \n",
+ "... ... ... ... ... \n",
+ "9129 Web 198.234764 Four-Door Car Medsize \n",
+ "9130 Branch 379.200000 Four-Door Car Medsize \n",
+ "9131 Branch 790.784983 Four-Door Car Medsize \n",
+ "9132 Branch 691.200000 Four-Door Car Large \n",
+ "9133 Call Center 369.600000 Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 24 columns]"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Dropping duplicates if there are\n",
+ "\n",
+ "df = df.drop_duplicates()\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "b3949153",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "state unique values: ['Washington' 'Arizona' 'Nevada' 'California' 'Oregon']\n",
+ "response unique values: ['No' 'Yes']\n",
+ "coverage unique values: ['Basic' 'Extended' 'Premium']\n",
+ "education unique values: ['Bachelor' 'College' 'Master' 'High School or Below' 'Doctor']\n",
+ "employmentstatus unique values: ['Employed' 'Unemployed' 'Medical Leave' 'Disabled' 'Retired']\n",
+ "gender unique values: ['F' 'M']\n",
+ "number_of_open_complaints unique values: [0 2 1 3 5 4]\n",
+ "number_of_policies unique values: [1 8 2 7 9 4 3 6 5]\n",
+ "location_code unique values: ['Suburban' 'Rural' 'Urban']\n",
+ "marital_status unique values: ['Married' 'Single' 'Divorced']\n",
+ "policy_type unique values: ['Corporate Auto' 'Personal Auto' 'Special Auto']\n",
+ "policy unique values: ['Corporate L3' 'Personal L3' 'Corporate L2' 'Personal L1' 'Special L2'\n",
+ " 'Corporate L1' 'Personal L2' 'Special L1' 'Special L3']\n",
+ "renew_offer_type unique values: ['Offer1' 'Offer3' 'Offer2' 'Offer4']\n",
+ "sales_channel unique values: ['Agent' 'Call Center' 'Web' 'Branch']\n",
+ "vehicle_class unique values: ['Two-Door Car' 'Four-Door Car' 'SUV' 'Luxury SUV' 'Sports Car'\n",
+ " 'Luxury Car']\n",
+ "vehicle_size unique values: ['Medsize' 'Small' 'Large']\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Checking unique values\n",
+ "\n",
+ "print(\"state unique values:\", df[\"state\"].unique())\n",
+ "print(\"response unique values:\", df[\"response\"].unique())\n",
+ "print(\"coverage unique values:\", df[\"coverage\"].unique())\n",
+ "print(\"education unique values:\", df[\"education\"].unique())\n",
+ "print(\"employmentstatus unique values:\", df[\"employmentstatus\"].unique())\n",
+ "print(\"gender unique values:\", df[\"gender\"].unique())\n",
+ "print(\"number_of_open_complaints unique values:\", df[\"number_of_open_complaints\"].unique())\n",
+ "print(\"number_of_policies unique values:\", df[\"number_of_policies\"].unique())\n",
+ "print(\"location_code unique values:\", df[\"location_code\"].unique())\n",
+ "print(\"marital_status unique values:\", df[\"marital_status\"].unique())\n",
+ "print(\"policy_type unique values:\", df[\"policy_type\"].unique())\n",
+ "print(\"policy unique values:\", df[\"policy\"].unique())\n",
+ "print(\"renew_offer_type unique values:\", df[\"renew_offer_type\"].unique())\n",
+ "print(\"sales_channel unique values:\", df[\"sales_channel\"].unique())\n",
+ "print(\"vehicle_class unique values:\", df[\"vehicle_class\"].unique())\n",
+ "print(\"vehicle_size unique values:\", df[\"vehicle_size\"].unique())"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "56c7a443",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Min of customer_lifetime_value: 1898.007675\n",
+ "Max of customer_lifetime_value: 83325.38119\n",
+ "Min of income: 0\n",
+ "Max of income: 99981\n",
+ "Min of monthly_premium_auto: 61\n",
+ "Max of monthly_premium_auto: 298\n",
+ "Min of months_since_last_claim: 0\n",
+ "Max of months_since_last_claim: 35\n",
+ "Min of months_since_policy_inception: 0\n",
+ "Max of months_since_policy_inception: 99\n",
+ "Min of total_claim_amount: 0.099007\n",
+ "Max of total_claim_amount: 2893.239678\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Checking min values and max values\n",
+ "\n",
+ "print(\"Min of customer_lifetime_value:\", min(df[\"customer_lifetime_value\"]))\n",
+ "print(\"Max of customer_lifetime_value:\", max(df[\"customer_lifetime_value\"]))\n",
+ "print(\"Min of income:\", min(df[\"income\"]))\n",
+ "print(\"Max of income:\", max(df[\"income\"]))\n",
+ "print(\"Min of monthly_premium_auto:\", min(df[\"monthly_premium_auto\"]))\n",
+ "print(\"Max of monthly_premium_auto:\", max(df[\"monthly_premium_auto\"]))\n",
+ "print(\"Min of months_since_last_claim:\", min(df[\"months_since_last_claim\"]))\n",
+ "print(\"Max of months_since_last_claim:\", max(df[\"months_since_last_claim\"]))\n",
+ "print(\"Min of months_since_policy_inception:\", min(df[\"months_since_policy_inception\"]))\n",
+ "print(\"Max of months_since_policy_inception:\", max(df[\"months_since_policy_inception\"]))\n",
+ "print(\"Min of total_claim_amount:\", min(df[\"total_claim_amount\"]))\n",
+ "print(\"Max of total_claim_amount:\", max(df[\"total_claim_amount\"]))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "584b19c7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_last_claim | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 32 | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 13 | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 18 | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 18 | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 12 | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 18 | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 14 | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 9 | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 34 | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 23 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " months_since_last_claim months_since_policy_inception \\\n",
+ "0 32 5 \n",
+ "1 13 42 \n",
+ "2 18 38 \n",
+ "3 18 65 \n",
+ "4 12 44 \n",
+ "... ... ... \n",
+ "9129 18 89 \n",
+ "9130 14 28 \n",
+ "9131 9 37 \n",
+ "9132 34 3 \n",
+ "9133 3 90 \n",
+ "\n",
+ " number_of_open_complaints number_of_policies policy_type \\\n",
+ "0 0 1 Corporate Auto \n",
+ "1 0 8 Personal Auto \n",
+ "2 0 2 Personal Auto \n",
+ "3 0 7 Corporate Auto \n",
+ "4 0 1 Personal Auto \n",
+ "... ... ... ... \n",
+ "9129 0 2 Personal Auto \n",
+ "9130 0 1 Corporate Auto \n",
+ "9131 3 2 Corporate Auto \n",
+ "9132 0 3 Personal Auto \n",
+ "9133 0 1 Corporate Auto \n",
+ "\n",
+ " policy renew_offer_type sales_channel vehicle_class vehicle_size \n",
+ "0 Corporate L3 Offer1 Agent Two-Door Car Medsize \n",
+ "1 Personal L3 Offer3 Agent Four-Door Car Medsize \n",
+ "2 Personal L3 Offer1 Agent Two-Door Car Medsize \n",
+ "3 Corporate L2 Offer1 Call Center SUV Medsize \n",
+ "4 Personal L1 Offer1 Agent Four-Door Car Medsize \n",
+ "... ... ... ... ... ... \n",
+ "9129 Personal L1 Offer2 Web Four-Door Car Medsize \n",
+ "9130 Corporate L3 Offer1 Branch Four-Door Car Medsize \n",
+ "9131 Corporate L2 Offer1 Branch Four-Door Car Medsize \n",
+ "9132 Personal L2 Offer3 Branch Four-Door Car Large \n",
+ "9133 Corporate L3 Offer4 Call Center Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 23 columns]"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Splitting X-Y\n",
+ "\n",
+ "Y = df[\"total_claim_amount\"]\n",
+ "X = df.drop([\"total_claim_amount\"], axis = 1)\n",
+ "X"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "d8f88108",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_last_claim | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 0.010629 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 0.562847 | \n",
+ " ... | \n",
+ " 0.914286 | \n",
+ " 0.050505 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 0.062406 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.371429 | \n",
+ " 0.424242 | \n",
+ " 0.0 | \n",
+ " 0.875 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 0.134960 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 0.487763 | \n",
+ " ... | \n",
+ " 0.514286 | \n",
+ " 0.383838 | \n",
+ " 0.0 | \n",
+ " 0.125 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 0.070589 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.514286 | \n",
+ " 0.656566 | \n",
+ " 0.0 | \n",
+ " 0.750 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 0.011245 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 0.438443 | \n",
+ " ... | \n",
+ " 0.342857 | \n",
+ " 0.444444 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 0.264137 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 0.719547 | \n",
+ " ... | \n",
+ " 0.514286 | \n",
+ " 0.898990 | \n",
+ " 0.0 | \n",
+ " 0.125 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 0.014719 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 0.216081 | \n",
+ " ... | \n",
+ " 0.400000 | \n",
+ " 0.282828 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 0.076951 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.257143 | \n",
+ " 0.373737 | \n",
+ " 0.6 | \n",
+ " 0.125 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 0.069098 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 0.219452 | \n",
+ " ... | \n",
+ " 0.971429 | \n",
+ " 0.030303 | \n",
+ " 0.0 | \n",
+ " 0.250 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 0.008766 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.085714 | \n",
+ " 0.909091 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 23 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 0.010629 No Basic \n",
+ "1 QZ44356 Arizona 0.062406 No Extended \n",
+ "2 AI49188 Nevada 0.134960 No Premium \n",
+ "3 WW63253 California 0.070589 No Basic \n",
+ "4 HB64268 Washington 0.011245 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 0.264137 No Basic \n",
+ "9130 PK87824 California 0.014719 Yes Extended \n",
+ "9131 TD14365 California 0.076951 No Extended \n",
+ "9132 UP19263 California 0.069098 No Extended \n",
+ "9133 Y167826 California 0.008766 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 0.562847 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0.000000 ... \n",
+ "2 Bachelor 2/19/11 Employed F 0.487763 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0.000000 ... \n",
+ "4 Bachelor 2/3/11 Employed M 0.438443 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 0.719547 ... \n",
+ "9130 College 2/12/11 Employed F 0.216081 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0.000000 ... \n",
+ "9132 College 2/3/11 Employed M 0.219452 ... \n",
+ "9133 College 2/14/11 Unemployed M 0.000000 ... \n",
+ "\n",
+ " months_since_last_claim months_since_policy_inception \\\n",
+ "0 0.914286 0.050505 \n",
+ "1 0.371429 0.424242 \n",
+ "2 0.514286 0.383838 \n",
+ "3 0.514286 0.656566 \n",
+ "4 0.342857 0.444444 \n",
+ "... ... ... \n",
+ "9129 0.514286 0.898990 \n",
+ "9130 0.400000 0.282828 \n",
+ "9131 0.257143 0.373737 \n",
+ "9132 0.971429 0.030303 \n",
+ "9133 0.085714 0.909091 \n",
+ "\n",
+ " number_of_open_complaints number_of_policies policy_type \\\n",
+ "0 0.0 0.000 Corporate Auto \n",
+ "1 0.0 0.875 Personal Auto \n",
+ "2 0.0 0.125 Personal Auto \n",
+ "3 0.0 0.750 Corporate Auto \n",
+ "4 0.0 0.000 Personal Auto \n",
+ "... ... ... ... \n",
+ "9129 0.0 0.125 Personal Auto \n",
+ "9130 0.0 0.000 Corporate Auto \n",
+ "9131 0.6 0.125 Corporate Auto \n",
+ "9132 0.0 0.250 Personal Auto \n",
+ "9133 0.0 0.000 Corporate Auto \n",
+ "\n",
+ " policy renew_offer_type sales_channel vehicle_class vehicle_size \n",
+ "0 Corporate L3 Offer1 Agent Two-Door Car Medsize \n",
+ "1 Personal L3 Offer3 Agent Four-Door Car Medsize \n",
+ "2 Personal L3 Offer1 Agent Two-Door Car Medsize \n",
+ "3 Corporate L2 Offer1 Call Center SUV Medsize \n",
+ "4 Personal L1 Offer1 Agent Four-Door Car Medsize \n",
+ "... ... ... ... ... ... \n",
+ "9129 Personal L1 Offer2 Web Four-Door Car Medsize \n",
+ "9130 Corporate L3 Offer1 Branch Four-Door Car Medsize \n",
+ "9131 Corporate L2 Offer1 Branch Four-Door Car Medsize \n",
+ "9132 Personal L2 Offer3 Branch Four-Door Car Large \n",
+ "9133 Corporate L3 Offer4 Call Center Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 23 columns]"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Normalizing X numerical values\n",
+ "\n",
+ "num_X = X.select_dtypes(include=np.number)\n",
+ "scaler = MinMaxScaler() \n",
+ "normalized_test = scaler.fit_transform(num_X) \n",
+ "normalized_test = pd.DataFrame(normalized_test, columns = num_X.columns)\n",
+ "normalized_test\n",
+ "X[normalized_test.columns] = normalized_test\n",
+ "X"
+ ]
+ }
+ ],
+ "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": "3.11.4"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Lab_Customer_Analysis_Round_5_Joao.ipynb b/Lab_Customer_Analysis_Round_5_Joao.ipynb
new file mode 100644
index 0000000..64f5032
--- /dev/null
+++ b/Lab_Customer_Analysis_Round_5_Joao.ipynb
@@ -0,0 +1,2250 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "f428a16d",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Importing libraries\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "\n",
+ "from sklearn.preprocessing import MinMaxScaler\n",
+ "from sklearn.model_selection import train_test_split"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "190485ab",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Customer | \n",
+ " State | \n",
+ " Customer Lifetime Value | \n",
+ " Response | \n",
+ " Coverage | \n",
+ " Education | \n",
+ " Effective To Date | \n",
+ " EmploymentStatus | \n",
+ " Gender | \n",
+ " Income | \n",
+ " ... | \n",
+ " Months Since Policy Inception | \n",
+ " Number of Open Complaints | \n",
+ " Number of Policies | \n",
+ " Policy Type | \n",
+ " Policy | \n",
+ " Renew Offer Type | \n",
+ " Sales Channel | \n",
+ " Total Claim Amount | \n",
+ " Vehicle Class | \n",
+ " Vehicle Size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 384.811147 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " 1131.464935 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 566.472247 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " 529.881344 | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 138.130879 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " 198.234764 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 379.200000 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 790.784983 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " 691.200000 | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " 369.600000 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 24 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Customer State Customer Lifetime Value Response Coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " Education Effective To Date EmploymentStatus Gender Income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " Months Since Policy Inception Number of Open Complaints \\\n",
+ "0 5 0 \n",
+ "1 42 0 \n",
+ "2 38 0 \n",
+ "3 65 0 \n",
+ "4 44 0 \n",
+ "... ... ... \n",
+ "9129 89 0 \n",
+ "9130 28 0 \n",
+ "9131 37 3 \n",
+ "9132 3 0 \n",
+ "9133 90 0 \n",
+ "\n",
+ " Number of Policies Policy Type Policy Renew Offer Type \\\n",
+ "0 1 Corporate Auto Corporate L3 Offer1 \n",
+ "1 8 Personal Auto Personal L3 Offer3 \n",
+ "2 2 Personal Auto Personal L3 Offer1 \n",
+ "3 7 Corporate Auto Corporate L2 Offer1 \n",
+ "4 1 Personal Auto Personal L1 Offer1 \n",
+ "... ... ... ... ... \n",
+ "9129 2 Personal Auto Personal L1 Offer2 \n",
+ "9130 1 Corporate Auto Corporate L3 Offer1 \n",
+ "9131 2 Corporate Auto Corporate L2 Offer1 \n",
+ "9132 3 Personal Auto Personal L2 Offer3 \n",
+ "9133 1 Corporate Auto Corporate L3 Offer4 \n",
+ "\n",
+ " Sales Channel Total Claim Amount Vehicle Class Vehicle Size \n",
+ "0 Agent 384.811147 Two-Door Car Medsize \n",
+ "1 Agent 1131.464935 Four-Door Car Medsize \n",
+ "2 Agent 566.472247 Two-Door Car Medsize \n",
+ "3 Call Center 529.881344 SUV Medsize \n",
+ "4 Agent 138.130879 Four-Door Car Medsize \n",
+ "... ... ... ... ... \n",
+ "9129 Web 198.234764 Four-Door Car Medsize \n",
+ "9130 Branch 379.200000 Four-Door Car Medsize \n",
+ "9131 Branch 790.784983 Four-Door Car Medsize \n",
+ "9132 Branch 691.200000 Four-Door Car Large \n",
+ "9133 Call Center 369.600000 Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 24 columns]"
+ ]
+ },
+ "execution_count": 2,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Importing file\n",
+ "\n",
+ "df = pd.read_csv(r\"C:\\Users\\joaoa\\Desktop\\Ironhack\\Labs\\lab-customer-analysis-round-5\\files_for_lab\\csv_files\\marketing_customer_analysis.csv\")\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "10c11a0c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " total_claim_amount | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 384.811147 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " 1131.464935 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 566.472247 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " 529.881344 | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 138.130879 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " 198.234764 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 379.200000 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 790.784983 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " 691.200000 | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " 369.600000 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 24 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " months_since_policy_inception number_of_open_complaints \\\n",
+ "0 5 0 \n",
+ "1 42 0 \n",
+ "2 38 0 \n",
+ "3 65 0 \n",
+ "4 44 0 \n",
+ "... ... ... \n",
+ "9129 89 0 \n",
+ "9130 28 0 \n",
+ "9131 37 3 \n",
+ "9132 3 0 \n",
+ "9133 90 0 \n",
+ "\n",
+ " number_of_policies policy_type policy renew_offer_type \\\n",
+ "0 1 Corporate Auto Corporate L3 Offer1 \n",
+ "1 8 Personal Auto Personal L3 Offer3 \n",
+ "2 2 Personal Auto Personal L3 Offer1 \n",
+ "3 7 Corporate Auto Corporate L2 Offer1 \n",
+ "4 1 Personal Auto Personal L1 Offer1 \n",
+ "... ... ... ... ... \n",
+ "9129 2 Personal Auto Personal L1 Offer2 \n",
+ "9130 1 Corporate Auto Corporate L3 Offer1 \n",
+ "9131 2 Corporate Auto Corporate L2 Offer1 \n",
+ "9132 3 Personal Auto Personal L2 Offer3 \n",
+ "9133 1 Corporate Auto Corporate L3 Offer4 \n",
+ "\n",
+ " sales_channel total_claim_amount vehicle_class vehicle_size \n",
+ "0 Agent 384.811147 Two-Door Car Medsize \n",
+ "1 Agent 1131.464935 Four-Door Car Medsize \n",
+ "2 Agent 566.472247 Two-Door Car Medsize \n",
+ "3 Call Center 529.881344 SUV Medsize \n",
+ "4 Agent 138.130879 Four-Door Car Medsize \n",
+ "... ... ... ... ... \n",
+ "9129 Web 198.234764 Four-Door Car Medsize \n",
+ "9130 Branch 379.200000 Four-Door Car Medsize \n",
+ "9131 Branch 790.784983 Four-Door Car Medsize \n",
+ "9132 Branch 691.200000 Four-Door Car Large \n",
+ "9133 Call Center 369.600000 Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 24 columns]"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Standardizing columns names\n",
+ "\n",
+ "cols = []\n",
+ "for i in range(len(df.columns)):\n",
+ " cols.append(df.columns[i].lower().replace(\" \",\"_\"))\n",
+ "df.columns = cols\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "12c46e60",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "customer object\n",
+ "state object\n",
+ "customer_lifetime_value float64\n",
+ "response object\n",
+ "coverage object\n",
+ "education object\n",
+ "effective_to_date object\n",
+ "employmentstatus object\n",
+ "gender object\n",
+ "income int64\n",
+ "location_code object\n",
+ "marital_status object\n",
+ "monthly_premium_auto int64\n",
+ "months_since_last_claim int64\n",
+ "months_since_policy_inception int64\n",
+ "number_of_open_complaints int64\n",
+ "number_of_policies int64\n",
+ "policy_type object\n",
+ "policy object\n",
+ "renew_offer_type object\n",
+ "sales_channel object\n",
+ "total_claim_amount float64\n",
+ "vehicle_class object\n",
+ "vehicle_size object\n",
+ "dtype: object"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Looking for data types\n",
+ "\n",
+ "df.dtypes"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "86dd7344",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Total NaN values: 0\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "customer 0\n",
+ "state 0\n",
+ "customer_lifetime_value 0\n",
+ "response 0\n",
+ "coverage 0\n",
+ "education 0\n",
+ "effective_to_date 0\n",
+ "employmentstatus 0\n",
+ "gender 0\n",
+ "income 0\n",
+ "location_code 0\n",
+ "marital_status 0\n",
+ "monthly_premium_auto 0\n",
+ "months_since_last_claim 0\n",
+ "months_since_policy_inception 0\n",
+ "number_of_open_complaints 0\n",
+ "number_of_policies 0\n",
+ "policy_type 0\n",
+ "policy 0\n",
+ "renew_offer_type 0\n",
+ "sales_channel 0\n",
+ "total_claim_amount 0\n",
+ "vehicle_class 0\n",
+ "vehicle_size 0\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Checking null values\n",
+ "\n",
+ "print(\"Total NaN values:\", df.isna().sum().sum())\n",
+ "df.isna().sum()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "0f18bf3c",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " total_claim_amount | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 384.811147 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " 1131.464935 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 566.472247 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " 529.881344 | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " 138.130879 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " 198.234764 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 379.200000 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " 790.784983 | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " 691.200000 | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " 369.600000 | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 24 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " months_since_policy_inception number_of_open_complaints \\\n",
+ "0 5 0 \n",
+ "1 42 0 \n",
+ "2 38 0 \n",
+ "3 65 0 \n",
+ "4 44 0 \n",
+ "... ... ... \n",
+ "9129 89 0 \n",
+ "9130 28 0 \n",
+ "9131 37 3 \n",
+ "9132 3 0 \n",
+ "9133 90 0 \n",
+ "\n",
+ " number_of_policies policy_type policy renew_offer_type \\\n",
+ "0 1 Corporate Auto Corporate L3 Offer1 \n",
+ "1 8 Personal Auto Personal L3 Offer3 \n",
+ "2 2 Personal Auto Personal L3 Offer1 \n",
+ "3 7 Corporate Auto Corporate L2 Offer1 \n",
+ "4 1 Personal Auto Personal L1 Offer1 \n",
+ "... ... ... ... ... \n",
+ "9129 2 Personal Auto Personal L1 Offer2 \n",
+ "9130 1 Corporate Auto Corporate L3 Offer1 \n",
+ "9131 2 Corporate Auto Corporate L2 Offer1 \n",
+ "9132 3 Personal Auto Personal L2 Offer3 \n",
+ "9133 1 Corporate Auto Corporate L3 Offer4 \n",
+ "\n",
+ " sales_channel total_claim_amount vehicle_class vehicle_size \n",
+ "0 Agent 384.811147 Two-Door Car Medsize \n",
+ "1 Agent 1131.464935 Four-Door Car Medsize \n",
+ "2 Agent 566.472247 Two-Door Car Medsize \n",
+ "3 Call Center 529.881344 SUV Medsize \n",
+ "4 Agent 138.130879 Four-Door Car Medsize \n",
+ "... ... ... ... ... \n",
+ "9129 Web 198.234764 Four-Door Car Medsize \n",
+ "9130 Branch 379.200000 Four-Door Car Medsize \n",
+ "9131 Branch 790.784983 Four-Door Car Medsize \n",
+ "9132 Branch 691.200000 Four-Door Car Large \n",
+ "9133 Call Center 369.600000 Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 24 columns]"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Dropping duplicates if there are\n",
+ "\n",
+ "df = df.drop_duplicates()\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "b3949153",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "state unique values: ['Washington' 'Arizona' 'Nevada' 'California' 'Oregon']\n",
+ "response unique values: ['No' 'Yes']\n",
+ "coverage unique values: ['Basic' 'Extended' 'Premium']\n",
+ "education unique values: ['Bachelor' 'College' 'Master' 'High School or Below' 'Doctor']\n",
+ "employmentstatus unique values: ['Employed' 'Unemployed' 'Medical Leave' 'Disabled' 'Retired']\n",
+ "gender unique values: ['F' 'M']\n",
+ "number_of_open_complaints unique values: [0 2 1 3 5 4]\n",
+ "number_of_policies unique values: [1 8 2 7 9 4 3 6 5]\n",
+ "location_code unique values: ['Suburban' 'Rural' 'Urban']\n",
+ "marital_status unique values: ['Married' 'Single' 'Divorced']\n",
+ "policy_type unique values: ['Corporate Auto' 'Personal Auto' 'Special Auto']\n",
+ "policy unique values: ['Corporate L3' 'Personal L3' 'Corporate L2' 'Personal L1' 'Special L2'\n",
+ " 'Corporate L1' 'Personal L2' 'Special L1' 'Special L3']\n",
+ "renew_offer_type unique values: ['Offer1' 'Offer3' 'Offer2' 'Offer4']\n",
+ "sales_channel unique values: ['Agent' 'Call Center' 'Web' 'Branch']\n",
+ "vehicle_class unique values: ['Two-Door Car' 'Four-Door Car' 'SUV' 'Luxury SUV' 'Sports Car'\n",
+ " 'Luxury Car']\n",
+ "vehicle_size unique values: ['Medsize' 'Small' 'Large']\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Checking unique values\n",
+ "\n",
+ "print(\"state unique values:\", df[\"state\"].unique())\n",
+ "print(\"response unique values:\", df[\"response\"].unique())\n",
+ "print(\"coverage unique values:\", df[\"coverage\"].unique())\n",
+ "print(\"education unique values:\", df[\"education\"].unique())\n",
+ "print(\"employmentstatus unique values:\", df[\"employmentstatus\"].unique())\n",
+ "print(\"gender unique values:\", df[\"gender\"].unique())\n",
+ "print(\"number_of_open_complaints unique values:\", df[\"number_of_open_complaints\"].unique())\n",
+ "print(\"number_of_policies unique values:\", df[\"number_of_policies\"].unique())\n",
+ "print(\"location_code unique values:\", df[\"location_code\"].unique())\n",
+ "print(\"marital_status unique values:\", df[\"marital_status\"].unique())\n",
+ "print(\"policy_type unique values:\", df[\"policy_type\"].unique())\n",
+ "print(\"policy unique values:\", df[\"policy\"].unique())\n",
+ "print(\"renew_offer_type unique values:\", df[\"renew_offer_type\"].unique())\n",
+ "print(\"sales_channel unique values:\", df[\"sales_channel\"].unique())\n",
+ "print(\"vehicle_class unique values:\", df[\"vehicle_class\"].unique())\n",
+ "print(\"vehicle_size unique values:\", df[\"vehicle_size\"].unique())"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "56c7a443",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Min of customer_lifetime_value: 1898.007675\n",
+ "Max of customer_lifetime_value: 83325.38119\n",
+ "Min of income: 0\n",
+ "Max of income: 99981\n",
+ "Min of monthly_premium_auto: 61\n",
+ "Max of monthly_premium_auto: 298\n",
+ "Min of months_since_last_claim: 0\n",
+ "Max of months_since_last_claim: 35\n",
+ "Min of months_since_policy_inception: 0\n",
+ "Max of months_since_policy_inception: 99\n",
+ "Min of total_claim_amount: 0.099007\n",
+ "Max of total_claim_amount: 2893.239678\n"
+ ]
+ }
+ ],
+ "source": [
+ "# Checking min values and max values\n",
+ "\n",
+ "print(\"Min of customer_lifetime_value:\", min(df[\"customer_lifetime_value\"]))\n",
+ "print(\"Max of customer_lifetime_value:\", max(df[\"customer_lifetime_value\"]))\n",
+ "print(\"Min of income:\", min(df[\"income\"]))\n",
+ "print(\"Max of income:\", max(df[\"income\"]))\n",
+ "print(\"Min of monthly_premium_auto:\", min(df[\"monthly_premium_auto\"]))\n",
+ "print(\"Max of monthly_premium_auto:\", max(df[\"monthly_premium_auto\"]))\n",
+ "print(\"Min of months_since_last_claim:\", min(df[\"months_since_last_claim\"]))\n",
+ "print(\"Max of months_since_last_claim:\", max(df[\"months_since_last_claim\"]))\n",
+ "print(\"Min of months_since_policy_inception:\", min(df[\"months_since_policy_inception\"]))\n",
+ "print(\"Max of months_since_policy_inception:\", max(df[\"months_since_policy_inception\"]))\n",
+ "print(\"Min of total_claim_amount:\", min(df[\"total_claim_amount\"]))\n",
+ "print(\"Max of total_claim_amount:\", max(df[\"total_claim_amount\"]))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "584b19c7",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_last_claim | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 2763.519279 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 56274 | \n",
+ " ... | \n",
+ " 32 | \n",
+ " 5 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 6979.535903 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 13 | \n",
+ " 42 | \n",
+ " 0 | \n",
+ " 8 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 12887.431650 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 48767 | \n",
+ " ... | \n",
+ " 18 | \n",
+ " 38 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 7645.861827 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 18 | \n",
+ " 65 | \n",
+ " 0 | \n",
+ " 7 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 2813.692575 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 43836 | \n",
+ " ... | \n",
+ " 12 | \n",
+ " 44 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 23405.987980 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 71941 | \n",
+ " ... | \n",
+ " 18 | \n",
+ " 89 | \n",
+ " 0 | \n",
+ " 2 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 3096.511217 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 21604 | \n",
+ " ... | \n",
+ " 14 | \n",
+ " 28 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 8163.890428 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 9 | \n",
+ " 37 | \n",
+ " 3 | \n",
+ " 2 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 7524.442436 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 21941 | \n",
+ " ... | \n",
+ " 34 | \n",
+ " 3 | \n",
+ " 0 | \n",
+ " 3 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 2611.836866 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0 | \n",
+ " ... | \n",
+ " 3 | \n",
+ " 90 | \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 23 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 2763.519279 No Basic \n",
+ "1 QZ44356 Arizona 6979.535903 No Extended \n",
+ "2 AI49188 Nevada 12887.431650 No Premium \n",
+ "3 WW63253 California 7645.861827 No Basic \n",
+ "4 HB64268 Washington 2813.692575 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 23405.987980 No Basic \n",
+ "9130 PK87824 California 3096.511217 Yes Extended \n",
+ "9131 TD14365 California 8163.890428 No Extended \n",
+ "9132 UP19263 California 7524.442436 No Extended \n",
+ "9133 Y167826 California 2611.836866 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 56274 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0 ... \n",
+ "2 Bachelor 2/19/11 Employed F 48767 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0 ... \n",
+ "4 Bachelor 2/3/11 Employed M 43836 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 71941 ... \n",
+ "9130 College 2/12/11 Employed F 21604 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0 ... \n",
+ "9132 College 2/3/11 Employed M 21941 ... \n",
+ "9133 College 2/14/11 Unemployed M 0 ... \n",
+ "\n",
+ " months_since_last_claim months_since_policy_inception \\\n",
+ "0 32 5 \n",
+ "1 13 42 \n",
+ "2 18 38 \n",
+ "3 18 65 \n",
+ "4 12 44 \n",
+ "... ... ... \n",
+ "9129 18 89 \n",
+ "9130 14 28 \n",
+ "9131 9 37 \n",
+ "9132 34 3 \n",
+ "9133 3 90 \n",
+ "\n",
+ " number_of_open_complaints number_of_policies policy_type \\\n",
+ "0 0 1 Corporate Auto \n",
+ "1 0 8 Personal Auto \n",
+ "2 0 2 Personal Auto \n",
+ "3 0 7 Corporate Auto \n",
+ "4 0 1 Personal Auto \n",
+ "... ... ... ... \n",
+ "9129 0 2 Personal Auto \n",
+ "9130 0 1 Corporate Auto \n",
+ "9131 3 2 Corporate Auto \n",
+ "9132 0 3 Personal Auto \n",
+ "9133 0 1 Corporate Auto \n",
+ "\n",
+ " policy renew_offer_type sales_channel vehicle_class vehicle_size \n",
+ "0 Corporate L3 Offer1 Agent Two-Door Car Medsize \n",
+ "1 Personal L3 Offer3 Agent Four-Door Car Medsize \n",
+ "2 Personal L3 Offer1 Agent Two-Door Car Medsize \n",
+ "3 Corporate L2 Offer1 Call Center SUV Medsize \n",
+ "4 Personal L1 Offer1 Agent Four-Door Car Medsize \n",
+ "... ... ... ... ... ... \n",
+ "9129 Personal L1 Offer2 Web Four-Door Car Medsize \n",
+ "9130 Corporate L3 Offer1 Branch Four-Door Car Medsize \n",
+ "9131 Corporate L2 Offer1 Branch Four-Door Car Medsize \n",
+ "9132 Personal L2 Offer3 Branch Four-Door Car Large \n",
+ "9133 Corporate L3 Offer4 Call Center Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 23 columns]"
+ ]
+ },
+ "execution_count": 9,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Splitting X-Y\n",
+ "\n",
+ "Y = df[\"total_claim_amount\"]\n",
+ "X = df.drop([\"total_claim_amount\"], axis = 1)\n",
+ "X"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "d8f88108",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " customer | \n",
+ " state | \n",
+ " customer_lifetime_value | \n",
+ " response | \n",
+ " coverage | \n",
+ " education | \n",
+ " effective_to_date | \n",
+ " employmentstatus | \n",
+ " gender | \n",
+ " income | \n",
+ " ... | \n",
+ " months_since_last_claim | \n",
+ " months_since_policy_inception | \n",
+ " number_of_open_complaints | \n",
+ " number_of_policies | \n",
+ " policy_type | \n",
+ " policy | \n",
+ " renew_offer_type | \n",
+ " sales_channel | \n",
+ " vehicle_class | \n",
+ " vehicle_size | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " | 0 | \n",
+ " BU79786 | \n",
+ " Washington | \n",
+ " 0.010629 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/24/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 0.562847 | \n",
+ " ... | \n",
+ " 0.914286 | \n",
+ " 0.050505 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 1 | \n",
+ " QZ44356 | \n",
+ " Arizona | \n",
+ " 0.062406 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 1/31/11 | \n",
+ " Unemployed | \n",
+ " F | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.371429 | \n",
+ " 0.424242 | \n",
+ " 0.0 | \n",
+ " 0.875 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer3 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 2 | \n",
+ " AI49188 | \n",
+ " Nevada | \n",
+ " 0.134960 | \n",
+ " No | \n",
+ " Premium | \n",
+ " Bachelor | \n",
+ " 2/19/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 0.487763 | \n",
+ " ... | \n",
+ " 0.514286 | \n",
+ " 0.383838 | \n",
+ " 0.0 | \n",
+ " 0.125 | \n",
+ " Personal Auto | \n",
+ " Personal L3 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 3 | \n",
+ " WW63253 | \n",
+ " California | \n",
+ " 0.070589 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 1/20/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.514286 | \n",
+ " 0.656566 | \n",
+ " 0.0 | \n",
+ " 0.750 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Call Center | \n",
+ " SUV | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 4 | \n",
+ " HB64268 | \n",
+ " Washington | \n",
+ " 0.011245 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 0.438443 | \n",
+ " ... | \n",
+ " 0.342857 | \n",
+ " 0.444444 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer1 | \n",
+ " Agent | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 9129 | \n",
+ " LA72316 | \n",
+ " California | \n",
+ " 0.264137 | \n",
+ " No | \n",
+ " Basic | \n",
+ " Bachelor | \n",
+ " 2/10/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 0.719547 | \n",
+ " ... | \n",
+ " 0.514286 | \n",
+ " 0.898990 | \n",
+ " 0.0 | \n",
+ " 0.125 | \n",
+ " Personal Auto | \n",
+ " Personal L1 | \n",
+ " Offer2 | \n",
+ " Web | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9130 | \n",
+ " PK87824 | \n",
+ " California | \n",
+ " 0.014719 | \n",
+ " Yes | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/12/11 | \n",
+ " Employed | \n",
+ " F | \n",
+ " 0.216081 | \n",
+ " ... | \n",
+ " 0.400000 | \n",
+ " 0.282828 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9131 | \n",
+ " TD14365 | \n",
+ " California | \n",
+ " 0.076951 | \n",
+ " No | \n",
+ " Extended | \n",
+ " Bachelor | \n",
+ " 2/6/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.257143 | \n",
+ " 0.373737 | \n",
+ " 0.6 | \n",
+ " 0.125 | \n",
+ " Corporate Auto | \n",
+ " Corporate L2 | \n",
+ " Offer1 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ " | 9132 | \n",
+ " UP19263 | \n",
+ " California | \n",
+ " 0.069098 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/3/11 | \n",
+ " Employed | \n",
+ " M | \n",
+ " 0.219452 | \n",
+ " ... | \n",
+ " 0.971429 | \n",
+ " 0.030303 | \n",
+ " 0.0 | \n",
+ " 0.250 | \n",
+ " Personal Auto | \n",
+ " Personal L2 | \n",
+ " Offer3 | \n",
+ " Branch | \n",
+ " Four-Door Car | \n",
+ " Large | \n",
+ "
\n",
+ " \n",
+ " | 9133 | \n",
+ " Y167826 | \n",
+ " California | \n",
+ " 0.008766 | \n",
+ " No | \n",
+ " Extended | \n",
+ " College | \n",
+ " 2/14/11 | \n",
+ " Unemployed | \n",
+ " M | \n",
+ " 0.000000 | \n",
+ " ... | \n",
+ " 0.085714 | \n",
+ " 0.909091 | \n",
+ " 0.0 | \n",
+ " 0.000 | \n",
+ " Corporate Auto | \n",
+ " Corporate L3 | \n",
+ " Offer4 | \n",
+ " Call Center | \n",
+ " Two-Door Car | \n",
+ " Medsize | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
9134 rows × 23 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " customer state customer_lifetime_value response coverage \\\n",
+ "0 BU79786 Washington 0.010629 No Basic \n",
+ "1 QZ44356 Arizona 0.062406 No Extended \n",
+ "2 AI49188 Nevada 0.134960 No Premium \n",
+ "3 WW63253 California 0.070589 No Basic \n",
+ "4 HB64268 Washington 0.011245 No Basic \n",
+ "... ... ... ... ... ... \n",
+ "9129 LA72316 California 0.264137 No Basic \n",
+ "9130 PK87824 California 0.014719 Yes Extended \n",
+ "9131 TD14365 California 0.076951 No Extended \n",
+ "9132 UP19263 California 0.069098 No Extended \n",
+ "9133 Y167826 California 0.008766 No Extended \n",
+ "\n",
+ " education effective_to_date employmentstatus gender income ... \\\n",
+ "0 Bachelor 2/24/11 Employed F 0.562847 ... \n",
+ "1 Bachelor 1/31/11 Unemployed F 0.000000 ... \n",
+ "2 Bachelor 2/19/11 Employed F 0.487763 ... \n",
+ "3 Bachelor 1/20/11 Unemployed M 0.000000 ... \n",
+ "4 Bachelor 2/3/11 Employed M 0.438443 ... \n",
+ "... ... ... ... ... ... ... \n",
+ "9129 Bachelor 2/10/11 Employed M 0.719547 ... \n",
+ "9130 College 2/12/11 Employed F 0.216081 ... \n",
+ "9131 Bachelor 2/6/11 Unemployed M 0.000000 ... \n",
+ "9132 College 2/3/11 Employed M 0.219452 ... \n",
+ "9133 College 2/14/11 Unemployed M 0.000000 ... \n",
+ "\n",
+ " months_since_last_claim months_since_policy_inception \\\n",
+ "0 0.914286 0.050505 \n",
+ "1 0.371429 0.424242 \n",
+ "2 0.514286 0.383838 \n",
+ "3 0.514286 0.656566 \n",
+ "4 0.342857 0.444444 \n",
+ "... ... ... \n",
+ "9129 0.514286 0.898990 \n",
+ "9130 0.400000 0.282828 \n",
+ "9131 0.257143 0.373737 \n",
+ "9132 0.971429 0.030303 \n",
+ "9133 0.085714 0.909091 \n",
+ "\n",
+ " number_of_open_complaints number_of_policies policy_type \\\n",
+ "0 0.0 0.000 Corporate Auto \n",
+ "1 0.0 0.875 Personal Auto \n",
+ "2 0.0 0.125 Personal Auto \n",
+ "3 0.0 0.750 Corporate Auto \n",
+ "4 0.0 0.000 Personal Auto \n",
+ "... ... ... ... \n",
+ "9129 0.0 0.125 Personal Auto \n",
+ "9130 0.0 0.000 Corporate Auto \n",
+ "9131 0.6 0.125 Corporate Auto \n",
+ "9132 0.0 0.250 Personal Auto \n",
+ "9133 0.0 0.000 Corporate Auto \n",
+ "\n",
+ " policy renew_offer_type sales_channel vehicle_class vehicle_size \n",
+ "0 Corporate L3 Offer1 Agent Two-Door Car Medsize \n",
+ "1 Personal L3 Offer3 Agent Four-Door Car Medsize \n",
+ "2 Personal L3 Offer1 Agent Two-Door Car Medsize \n",
+ "3 Corporate L2 Offer1 Call Center SUV Medsize \n",
+ "4 Personal L1 Offer1 Agent Four-Door Car Medsize \n",
+ "... ... ... ... ... ... \n",
+ "9129 Personal L1 Offer2 Web Four-Door Car Medsize \n",
+ "9130 Corporate L3 Offer1 Branch Four-Door Car Medsize \n",
+ "9131 Corporate L2 Offer1 Branch Four-Door Car Medsize \n",
+ "9132 Personal L2 Offer3 Branch Four-Door Car Large \n",
+ "9133 Corporate L3 Offer4 Call Center Two-Door Car Medsize \n",
+ "\n",
+ "[9134 rows x 23 columns]"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Normalizing X numerical values\n",
+ "\n",
+ "num_X = X.select_dtypes(include=np.number)\n",
+ "scaler = MinMaxScaler() \n",
+ "normalized_test = scaler.fit_transform(num_X) \n",
+ "normalized_test = pd.DataFrame(normalized_test, columns = num_X.columns)\n",
+ "normalized_test\n",
+ "X[normalized_test.columns] = normalized_test\n",
+ "X"
+ ]
+ }
+ ],
+ "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": "3.11.4"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}