From e2bab6506d421cc01166e1ef9f8e3f4c92fb6395 Mon Sep 17 00:00:00 2001 From: joaomatoslopes Date: Sat, 14 Oct 2023 16:16:21 +0100 Subject: [PATCH 1/2] Lab done --- ...mer_Analysis_Round_5_Joao-checkpoint.ipynb | 3058 +++++++++++++++++ Lab_Customer_Analysis_Round_5_Joao.ipynb | 3058 +++++++++++++++++ 2 files changed, 6116 insertions(+) create mode 100644 .ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb create mode 100644 Lab_Customer_Analysis_Round_5_Joao.ipynb 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..2a1b972 --- /dev/null +++ b/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb @@ -0,0 +1,3058 @@ +{ + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CustomerStateCustomer Lifetime ValueResponseCoverageEducationEffective To DateEmploymentStatusGenderIncome...Months Since Policy InceptionNumber of Open ComplaintsNumber of PoliciesPolicy TypePolicyRenew Offer TypeSales ChannelTotal Claim AmountVehicle ClassVehicle Size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
9129LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
9130PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
9131TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
9132UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
9133Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
9129LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
9130PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
9131TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
9132UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
9133Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
9129LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
9130PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
9131TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
9132UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
9133Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\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": "1e115b1e", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
1821AY88788Oregon15417.682200NoBasicCollege1/3/11EmployedF69841...6607Personal AutoPersonal L3Offer1Branch878.812468Luxury SUVMedsize
1822OJ33945Oregon8692.636838NoBasicHigh School or Below1/8/11EmployedF97768...1402Personal AutoPersonal L1Offer3Agent151.843731Two-Door CarMedsize
1823LO84523Oregon6503.143913NoBasicHigh School or Below2/4/11UnemployedM0...1201Personal AutoPersonal L2Offer2Web1588.682955Luxury CarMedsize
1824GJ43254Washington31642.104630NoExtendedCollege1/22/11EmployedM89057...9002Corporate AutoCorporate L2Offer1Call Center187.363583Two-Door CarMedsize
1825AR96516Oregon5914.951808NoBasicBachelor1/28/11EmployedF50217...209Personal AutoPersonal L1Offer2Web355.200000Two-Door CarMedsize
\n", + "

1826 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", + "1821 AY88788 Oregon 15417.682200 No Basic \n", + "1822 OJ33945 Oregon 8692.636838 No Basic \n", + "1823 LO84523 Oregon 6503.143913 No Basic \n", + "1824 GJ43254 Washington 31642.104630 No Extended \n", + "1825 AR96516 Oregon 5914.951808 No Basic \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", + "1821 College 1/3/11 Employed F 69841 \n", + "1822 High School or Below 1/8/11 Employed F 97768 \n", + "1823 High School or Below 2/4/11 Unemployed M 0 \n", + "1824 College 1/22/11 Employed M 89057 \n", + "1825 Bachelor 1/28/11 Employed F 50217 \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", + "1821 ... 66 0 \n", + "1822 ... 14 0 \n", + "1823 ... 12 0 \n", + "1824 ... 90 0 \n", + "1825 ... 2 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", + "1821 7 Personal Auto Personal L3 Offer1 \n", + "1822 2 Personal Auto Personal L1 Offer3 \n", + "1823 1 Personal Auto Personal L2 Offer2 \n", + "1824 2 Corporate Auto Corporate L2 Offer1 \n", + "1825 9 Personal Auto Personal L1 Offer2 \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", + "1821 Branch 878.812468 Luxury SUV Medsize \n", + "1822 Agent 151.843731 Two-Door Car Medsize \n", + "1823 Web 1588.682955 Luxury Car Medsize \n", + "1824 Call Center 187.363583 Two-Door Car Medsize \n", + "1825 Web 355.200000 Two-Door Car Medsize \n", + "\n", + "[1826 rows x 24 columns]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Test data\n", + "\n", + "test = df.iloc[0:int(len(df)*0.2)]\n", + "test = test.reset_index(drop = True)\n", + "test" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "cb9eb6f7", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0WH11924Washington4645.839058NoBasicCollege2/5/11UnemployedM0...3303Personal AutoPersonal L2Offer4Web697.186307Two-Door CarLarge
1DL26809Nevada6826.797741NoBasicCollege2/27/11UnemployedM0...2602Personal AutoPersonal L3Offer1Agent489.600000Two-Door CarSmall
2MV69686Oregon3982.180708NoExtendedDoctor1/3/11EmployedF38500...4911Corporate AutoCorporate L2Offer1Agent423.286512Four-Door CarLarge
3SC95565Nevada2887.779742NoBasicHigh School or Below2/15/11EmployedF62018...001Personal AutoPersonal L1Offer4Branch293.865315Two-Door CarMedsize
4RL31641Oregon2252.416825NoBasicCollege1/29/11UnemployedF0...8401Personal AutoPersonal L3Offer3Web468.000000Two-Door CarMedsize
..................................................................
7303LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
7304PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
7305TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
7306UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
7307Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\n", + "

7308 rows × 24 columns

\n", + "
" + ], + "text/plain": [ + " customer state customer_lifetime_value response coverage \\\n", + "0 WH11924 Washington 4645.839058 No Basic \n", + "1 DL26809 Nevada 6826.797741 No Basic \n", + "2 MV69686 Oregon 3982.180708 No Extended \n", + "3 SC95565 Nevada 2887.779742 No Basic \n", + "4 RL31641 Oregon 2252.416825 No Basic \n", + "... ... ... ... ... ... \n", + "7303 LA72316 California 23405.987980 No Basic \n", + "7304 PK87824 California 3096.511217 Yes Extended \n", + "7305 TD14365 California 8163.890428 No Extended \n", + "7306 UP19263 California 7524.442436 No Extended \n", + "7307 Y167826 California 2611.836866 No Extended \n", + "\n", + " education effective_to_date employmentstatus gender income \\\n", + "0 College 2/5/11 Unemployed M 0 \n", + "1 College 2/27/11 Unemployed M 0 \n", + "2 Doctor 1/3/11 Employed F 38500 \n", + "3 High School or Below 2/15/11 Employed F 62018 \n", + "4 College 1/29/11 Unemployed F 0 \n", + "... ... ... ... ... ... \n", + "7303 Bachelor 2/10/11 Employed M 71941 \n", + "7304 College 2/12/11 Employed F 21604 \n", + "7305 Bachelor 2/6/11 Unemployed M 0 \n", + "7306 College 2/3/11 Employed M 21941 \n", + "7307 College 2/14/11 Unemployed M 0 \n", + "\n", + " ... months_since_policy_inception number_of_open_complaints \\\n", + "0 ... 33 0 \n", + "1 ... 26 0 \n", + "2 ... 49 1 \n", + "3 ... 0 0 \n", + "4 ... 84 0 \n", + "... ... ... ... \n", + "7303 ... 89 0 \n", + "7304 ... 28 0 \n", + "7305 ... 37 3 \n", + "7306 ... 3 0 \n", + "7307 ... 90 0 \n", + "\n", + " number_of_policies policy_type policy renew_offer_type \\\n", + "0 3 Personal Auto Personal L2 Offer4 \n", + "1 2 Personal Auto Personal L3 Offer1 \n", + "2 1 Corporate Auto Corporate L2 Offer1 \n", + "3 1 Personal Auto Personal L1 Offer4 \n", + "4 1 Personal Auto Personal L3 Offer3 \n", + "... ... ... ... ... \n", + "7303 2 Personal Auto Personal L1 Offer2 \n", + "7304 1 Corporate Auto Corporate L3 Offer1 \n", + "7305 2 Corporate Auto Corporate L2 Offer1 \n", + "7306 3 Personal Auto Personal L2 Offer3 \n", + "7307 1 Corporate Auto Corporate L3 Offer4 \n", + "\n", + " sales_channel total_claim_amount vehicle_class vehicle_size \n", + "0 Web 697.186307 Two-Door Car Large \n", + "1 Agent 489.600000 Two-Door Car Small \n", + "2 Agent 423.286512 Four-Door Car Large \n", + "3 Branch 293.865315 Two-Door Car Medsize \n", + "4 Web 468.000000 Two-Door Car Medsize \n", + "... ... ... ... ... \n", + "7303 Web 198.234764 Four-Door Car Medsize \n", + "7304 Branch 379.200000 Four-Door Car Medsize \n", + "7305 Branch 790.784983 Four-Door Car Medsize \n", + "7306 Branch 691.200000 Four-Door Car Large \n", + "7307 Call Center 369.600000 Two-Door Car Medsize \n", + "\n", + "[7308 rows x 24 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train data\n", + "\n", + "train = df.iloc[int(len(df)*0.2):len(df)]\n", + "train = train.reset_index(drop = True)\n", + "train" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "d8f88108", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington0.013517NoBasicBachelor2/24/11EmployedF0.562847...0.0505050.00.000Corporate AutoCorporate L3Offer1Agent0.132889Two-Door CarMedsize
1QZ44356Arizona0.088586NoExtendedBachelor1/31/11UnemployedF0.000000...0.4242420.00.875Personal AutoPersonal L3Offer3Agent0.390992Four-Door CarMedsize
2AI49188Nevada0.193779NoPremiumBachelor2/19/11EmployedF0.487763...0.3838380.00.125Personal AutoPersonal L3Offer1Agent0.195685Two-Door CarMedsize
3WW63253California0.100450NoBasicBachelor1/20/11UnemployedM0.000000...0.6565660.00.750Corporate AutoCorporate L2Offer1Call Center0.183037SUVMedsize
4HB64268Washington0.014411NoBasicBachelor2/3/11EmployedM0.438443...0.4444440.00.000Personal AutoPersonal L1Offer1Agent0.047617Four-Door CarMedsize
..................................................................
1821AY88788Oregon0.238832NoBasicCollege1/3/11EmployedF0.698543...0.6666670.00.750Personal AutoPersonal L3Offer1Branch0.303655Luxury SUVMedsize
1822OJ33945Oregon0.119089NoBasicHigh School or Below1/8/11EmployedF0.977866...0.1414140.00.125Personal AutoPersonal L1Offer3Agent0.052357Two-Door CarMedsize
1823LO84523Oregon0.080104NoBasicHigh School or Below2/4/11UnemployedM0.000000...0.1212120.00.000Personal AutoPersonal L2Offer2Web0.549042Luxury CarMedsize
1824GJ43254Washington0.527717NoExtendedCollege1/22/11EmployedM0.890739...0.9090910.00.125Corporate AutoCorporate L2Offer1Call Center0.064636Two-Door CarMedsize
1825AR96516Oregon0.069630NoBasicBachelor1/28/11EmployedF0.502265...0.0202020.01.000Personal AutoPersonal L1Offer2Web0.122653Two-Door CarMedsize
\n", + "

1826 rows × 24 columns

\n", + "
" + ], + "text/plain": [ + " customer state customer_lifetime_value response coverage \\\n", + "0 BU79786 Washington 0.013517 No Basic \n", + "1 QZ44356 Arizona 0.088586 No Extended \n", + "2 AI49188 Nevada 0.193779 No Premium \n", + "3 WW63253 California 0.100450 No Basic \n", + "4 HB64268 Washington 0.014411 No Basic \n", + "... ... ... ... ... ... \n", + "1821 AY88788 Oregon 0.238832 No Basic \n", + "1822 OJ33945 Oregon 0.119089 No Basic \n", + "1823 LO84523 Oregon 0.080104 No Basic \n", + "1824 GJ43254 Washington 0.527717 No Extended \n", + "1825 AR96516 Oregon 0.069630 No Basic \n", + "\n", + " education effective_to_date employmentstatus gender \\\n", + "0 Bachelor 2/24/11 Employed F \n", + "1 Bachelor 1/31/11 Unemployed F \n", + "2 Bachelor 2/19/11 Employed F \n", + "3 Bachelor 1/20/11 Unemployed M \n", + "4 Bachelor 2/3/11 Employed M \n", + "... ... ... ... ... \n", + "1821 College 1/3/11 Employed F \n", + "1822 High School or Below 1/8/11 Employed F \n", + "1823 High School or Below 2/4/11 Unemployed M \n", + "1824 College 1/22/11 Employed M \n", + "1825 Bachelor 1/28/11 Employed F \n", + "\n", + " income ... months_since_policy_inception number_of_open_complaints \\\n", + "0 0.562847 ... 0.050505 0.0 \n", + "1 0.000000 ... 0.424242 0.0 \n", + "2 0.487763 ... 0.383838 0.0 \n", + "3 0.000000 ... 0.656566 0.0 \n", + "4 0.438443 ... 0.444444 0.0 \n", + "... ... ... ... ... \n", + "1821 0.698543 ... 0.666667 0.0 \n", + "1822 0.977866 ... 0.141414 0.0 \n", + "1823 0.000000 ... 0.121212 0.0 \n", + "1824 0.890739 ... 0.909091 0.0 \n", + "1825 0.502265 ... 0.020202 0.0 \n", + "\n", + " number_of_policies policy_type policy renew_offer_type \\\n", + "0 0.000 Corporate Auto Corporate L3 Offer1 \n", + "1 0.875 Personal Auto Personal L3 Offer3 \n", + "2 0.125 Personal Auto Personal L3 Offer1 \n", + "3 0.750 Corporate Auto Corporate L2 Offer1 \n", + "4 0.000 Personal Auto Personal L1 Offer1 \n", + "... ... ... ... ... \n", + "1821 0.750 Personal Auto Personal L3 Offer1 \n", + "1822 0.125 Personal Auto Personal L1 Offer3 \n", + "1823 0.000 Personal Auto Personal L2 Offer2 \n", + "1824 0.125 Corporate Auto Corporate L2 Offer1 \n", + "1825 1.000 Personal Auto Personal L1 Offer2 \n", + "\n", + " sales_channel total_claim_amount vehicle_class vehicle_size \n", + "0 Agent 0.132889 Two-Door Car Medsize \n", + "1 Agent 0.390992 Four-Door Car Medsize \n", + "2 Agent 0.195685 Two-Door Car Medsize \n", + "3 Call Center 0.183037 SUV Medsize \n", + "4 Agent 0.047617 Four-Door Car Medsize \n", + "... ... ... ... ... \n", + "1821 Branch 0.303655 Luxury SUV Medsize \n", + "1822 Agent 0.052357 Two-Door Car Medsize \n", + "1823 Web 0.549042 Luxury Car Medsize \n", + "1824 Call Center 0.064636 Two-Door Car Medsize \n", + "1825 Web 0.122653 Two-Door Car Medsize \n", + "\n", + "[1826 rows x 24 columns]" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Normalizing \"test\" numerical values\n", + "\n", + "num_test = test.select_dtypes(include=np.number)\n", + "scaler = MinMaxScaler() \n", + "normalized_test = scaler.fit_transform(num_test) \n", + "normalized_test = pd.DataFrame(normalized_test, columns = num_test.columns)\n", + "normalized_test\n", + "test[normalized_test.columns] = normalized_test\n", + "test" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "7bf18925", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0WH11924Washington0.033746NoBasicCollege2/5/11UnemployedM0.000000...0.3333330.00.250Personal AutoPersonal L2Offer4Web0.252596Two-Door CarLarge
1DL26809Nevada0.060530NoBasicCollege2/27/11UnemployedM0.000000...0.2626260.00.125Personal AutoPersonal L3Offer1Agent0.177375Two-Door CarSmall
2MV69686Oregon0.025595NoExtendedDoctor1/3/11EmployedF0.385150...0.4949490.20.000Corporate AutoCorporate L2Offer1Agent0.153346Four-Door CarLarge
3SC95565Nevada0.012155NoBasicHigh School or Below2/15/11EmployedF0.620422...0.0000000.00.000Personal AutoPersonal L1Offer4Branch0.106449Two-Door CarMedsize
4RL31641Oregon0.004352NoBasicCollege1/29/11UnemployedF0.000000...0.8484850.00.000Personal AutoPersonal L3Offer3Web0.169548Two-Door CarMedsize
..................................................................
7303LA72316California0.264137NoBasicBachelor2/10/11EmployedM0.719691...0.8989900.00.125Personal AutoPersonal L1Offer2Web0.071796Four-Door CarMedsize
7304PK87824California0.014719YesExtendedCollege2/12/11EmployedF0.216124...0.2828280.00.000Corporate AutoCorporate L3Offer1Branch0.137371Four-Door CarMedsize
7305TD14365California0.076951NoExtendedBachelor2/6/11UnemployedM0.000000...0.3737370.60.125Corporate AutoCorporate L2Offer1Branch0.286512Four-Door CarMedsize
7306UP19263California0.069098NoExtendedCollege2/3/11EmployedM0.219496...0.0303030.00.250Personal AutoPersonal L2Offer3Branch0.250427Four-Door CarLarge
7307Y167826California0.008766NoExtendedCollege2/14/11UnemployedM0.000000...0.9090910.00.000Corporate AutoCorporate L3Offer4Call Center0.133892Two-Door CarMedsize
\n", + "

7308 rows × 24 columns

\n", + "
" + ], + "text/plain": [ + " customer state customer_lifetime_value response coverage \\\n", + "0 WH11924 Washington 0.033746 No Basic \n", + "1 DL26809 Nevada 0.060530 No Basic \n", + "2 MV69686 Oregon 0.025595 No Extended \n", + "3 SC95565 Nevada 0.012155 No Basic \n", + "4 RL31641 Oregon 0.004352 No Basic \n", + "... ... ... ... ... ... \n", + "7303 LA72316 California 0.264137 No Basic \n", + "7304 PK87824 California 0.014719 Yes Extended \n", + "7305 TD14365 California 0.076951 No Extended \n", + "7306 UP19263 California 0.069098 No Extended \n", + "7307 Y167826 California 0.008766 No Extended \n", + "\n", + " education effective_to_date employmentstatus gender \\\n", + "0 College 2/5/11 Unemployed M \n", + "1 College 2/27/11 Unemployed M \n", + "2 Doctor 1/3/11 Employed F \n", + "3 High School or Below 2/15/11 Employed F \n", + "4 College 1/29/11 Unemployed F \n", + "... ... ... ... ... \n", + "7303 Bachelor 2/10/11 Employed M \n", + "7304 College 2/12/11 Employed F \n", + "7305 Bachelor 2/6/11 Unemployed M \n", + "7306 College 2/3/11 Employed M \n", + "7307 College 2/14/11 Unemployed M \n", + "\n", + " income ... months_since_policy_inception number_of_open_complaints \\\n", + "0 0.000000 ... 0.333333 0.0 \n", + "1 0.000000 ... 0.262626 0.0 \n", + "2 0.385150 ... 0.494949 0.2 \n", + "3 0.620422 ... 0.000000 0.0 \n", + "4 0.000000 ... 0.848485 0.0 \n", + "... ... ... ... ... \n", + "7303 0.719691 ... 0.898990 0.0 \n", + "7304 0.216124 ... 0.282828 0.0 \n", + "7305 0.000000 ... 0.373737 0.6 \n", + "7306 0.219496 ... 0.030303 0.0 \n", + "7307 0.000000 ... 0.909091 0.0 \n", + "\n", + " number_of_policies policy_type policy renew_offer_type \\\n", + "0 0.250 Personal Auto Personal L2 Offer4 \n", + "1 0.125 Personal Auto Personal L3 Offer1 \n", + "2 0.000 Corporate Auto Corporate L2 Offer1 \n", + "3 0.000 Personal Auto Personal L1 Offer4 \n", + "4 0.000 Personal Auto Personal L3 Offer3 \n", + "... ... ... ... ... \n", + "7303 0.125 Personal Auto Personal L1 Offer2 \n", + "7304 0.000 Corporate Auto Corporate L3 Offer1 \n", + "7305 0.125 Corporate Auto Corporate L2 Offer1 \n", + "7306 0.250 Personal Auto Personal L2 Offer3 \n", + "7307 0.000 Corporate Auto Corporate L3 Offer4 \n", + "\n", + " sales_channel total_claim_amount vehicle_class vehicle_size \n", + "0 Web 0.252596 Two-Door Car Large \n", + "1 Agent 0.177375 Two-Door Car Small \n", + "2 Agent 0.153346 Four-Door Car Large \n", + "3 Branch 0.106449 Two-Door Car Medsize \n", + "4 Web 0.169548 Two-Door Car Medsize \n", + "... ... ... ... ... \n", + "7303 Web 0.071796 Four-Door Car Medsize \n", + "7304 Branch 0.137371 Four-Door Car Medsize \n", + "7305 Branch 0.286512 Four-Door Car Medsize \n", + "7306 Branch 0.250427 Four-Door Car Large \n", + "7307 Call Center 0.133892 Two-Door Car Medsize \n", + "\n", + "[7308 rows x 24 columns]" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Normalizing \"train\" numerical values\n", + "\n", + "num_train = train.select_dtypes(include=np.number)\n", + "scaler = MinMaxScaler() \n", + "normalized_train = scaler.fit_transform(num_train) \n", + "normalized_train = pd.DataFrame(normalized_train, columns = num_train.columns)\n", + "normalized_train\n", + "train[normalized_train.columns] = normalized_train\n", + "train" + ] + } + ], + "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..2a1b972 --- /dev/null +++ b/Lab_Customer_Analysis_Round_5_Joao.ipynb @@ -0,0 +1,3058 @@ +{ + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
CustomerStateCustomer Lifetime ValueResponseCoverageEducationEffective To DateEmploymentStatusGenderIncome...Months Since Policy InceptionNumber of Open ComplaintsNumber of PoliciesPolicy TypePolicyRenew Offer TypeSales ChannelTotal Claim AmountVehicle ClassVehicle Size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
9129LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
9130PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
9131TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
9132UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
9133Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
9129LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
9130PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
9131TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
9132UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
9133Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
9129LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
9130PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
9131TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
9132UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
9133Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\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": "1e115b1e", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington2763.519279NoBasicBachelor2/24/11EmployedF56274...501Corporate AutoCorporate L3Offer1Agent384.811147Two-Door CarMedsize
1QZ44356Arizona6979.535903NoExtendedBachelor1/31/11UnemployedF0...4208Personal AutoPersonal L3Offer3Agent1131.464935Four-Door CarMedsize
2AI49188Nevada12887.431650NoPremiumBachelor2/19/11EmployedF48767...3802Personal AutoPersonal L3Offer1Agent566.472247Two-Door CarMedsize
3WW63253California7645.861827NoBasicBachelor1/20/11UnemployedM0...6507Corporate AutoCorporate L2Offer1Call Center529.881344SUVMedsize
4HB64268Washington2813.692575NoBasicBachelor2/3/11EmployedM43836...4401Personal AutoPersonal L1Offer1Agent138.130879Four-Door CarMedsize
..................................................................
1821AY88788Oregon15417.682200NoBasicCollege1/3/11EmployedF69841...6607Personal AutoPersonal L3Offer1Branch878.812468Luxury SUVMedsize
1822OJ33945Oregon8692.636838NoBasicHigh School or Below1/8/11EmployedF97768...1402Personal AutoPersonal L1Offer3Agent151.843731Two-Door CarMedsize
1823LO84523Oregon6503.143913NoBasicHigh School or Below2/4/11UnemployedM0...1201Personal AutoPersonal L2Offer2Web1588.682955Luxury CarMedsize
1824GJ43254Washington31642.104630NoExtendedCollege1/22/11EmployedM89057...9002Corporate AutoCorporate L2Offer1Call Center187.363583Two-Door CarMedsize
1825AR96516Oregon5914.951808NoBasicBachelor1/28/11EmployedF50217...209Personal AutoPersonal L1Offer2Web355.200000Two-Door CarMedsize
\n", + "

1826 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", + "1821 AY88788 Oregon 15417.682200 No Basic \n", + "1822 OJ33945 Oregon 8692.636838 No Basic \n", + "1823 LO84523 Oregon 6503.143913 No Basic \n", + "1824 GJ43254 Washington 31642.104630 No Extended \n", + "1825 AR96516 Oregon 5914.951808 No Basic \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", + "1821 College 1/3/11 Employed F 69841 \n", + "1822 High School or Below 1/8/11 Employed F 97768 \n", + "1823 High School or Below 2/4/11 Unemployed M 0 \n", + "1824 College 1/22/11 Employed M 89057 \n", + "1825 Bachelor 1/28/11 Employed F 50217 \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", + "1821 ... 66 0 \n", + "1822 ... 14 0 \n", + "1823 ... 12 0 \n", + "1824 ... 90 0 \n", + "1825 ... 2 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", + "1821 7 Personal Auto Personal L3 Offer1 \n", + "1822 2 Personal Auto Personal L1 Offer3 \n", + "1823 1 Personal Auto Personal L2 Offer2 \n", + "1824 2 Corporate Auto Corporate L2 Offer1 \n", + "1825 9 Personal Auto Personal L1 Offer2 \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", + "1821 Branch 878.812468 Luxury SUV Medsize \n", + "1822 Agent 151.843731 Two-Door Car Medsize \n", + "1823 Web 1588.682955 Luxury Car Medsize \n", + "1824 Call Center 187.363583 Two-Door Car Medsize \n", + "1825 Web 355.200000 Two-Door Car Medsize \n", + "\n", + "[1826 rows x 24 columns]" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Test data\n", + "\n", + "test = df.iloc[0:int(len(df)*0.2)]\n", + "test = test.reset_index(drop = True)\n", + "test" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "cb9eb6f7", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0WH11924Washington4645.839058NoBasicCollege2/5/11UnemployedM0...3303Personal AutoPersonal L2Offer4Web697.186307Two-Door CarLarge
1DL26809Nevada6826.797741NoBasicCollege2/27/11UnemployedM0...2602Personal AutoPersonal L3Offer1Agent489.600000Two-Door CarSmall
2MV69686Oregon3982.180708NoExtendedDoctor1/3/11EmployedF38500...4911Corporate AutoCorporate L2Offer1Agent423.286512Four-Door CarLarge
3SC95565Nevada2887.779742NoBasicHigh School or Below2/15/11EmployedF62018...001Personal AutoPersonal L1Offer4Branch293.865315Two-Door CarMedsize
4RL31641Oregon2252.416825NoBasicCollege1/29/11UnemployedF0...8401Personal AutoPersonal L3Offer3Web468.000000Two-Door CarMedsize
..................................................................
7303LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
7304PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
7305TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
7306UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
7307Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\n", + "

7308 rows × 24 columns

\n", + "
" + ], + "text/plain": [ + " customer state customer_lifetime_value response coverage \\\n", + "0 WH11924 Washington 4645.839058 No Basic \n", + "1 DL26809 Nevada 6826.797741 No Basic \n", + "2 MV69686 Oregon 3982.180708 No Extended \n", + "3 SC95565 Nevada 2887.779742 No Basic \n", + "4 RL31641 Oregon 2252.416825 No Basic \n", + "... ... ... ... ... ... \n", + "7303 LA72316 California 23405.987980 No Basic \n", + "7304 PK87824 California 3096.511217 Yes Extended \n", + "7305 TD14365 California 8163.890428 No Extended \n", + "7306 UP19263 California 7524.442436 No Extended \n", + "7307 Y167826 California 2611.836866 No Extended \n", + "\n", + " education effective_to_date employmentstatus gender income \\\n", + "0 College 2/5/11 Unemployed M 0 \n", + "1 College 2/27/11 Unemployed M 0 \n", + "2 Doctor 1/3/11 Employed F 38500 \n", + "3 High School or Below 2/15/11 Employed F 62018 \n", + "4 College 1/29/11 Unemployed F 0 \n", + "... ... ... ... ... ... \n", + "7303 Bachelor 2/10/11 Employed M 71941 \n", + "7304 College 2/12/11 Employed F 21604 \n", + "7305 Bachelor 2/6/11 Unemployed M 0 \n", + "7306 College 2/3/11 Employed M 21941 \n", + "7307 College 2/14/11 Unemployed M 0 \n", + "\n", + " ... months_since_policy_inception number_of_open_complaints \\\n", + "0 ... 33 0 \n", + "1 ... 26 0 \n", + "2 ... 49 1 \n", + "3 ... 0 0 \n", + "4 ... 84 0 \n", + "... ... ... ... \n", + "7303 ... 89 0 \n", + "7304 ... 28 0 \n", + "7305 ... 37 3 \n", + "7306 ... 3 0 \n", + "7307 ... 90 0 \n", + "\n", + " number_of_policies policy_type policy renew_offer_type \\\n", + "0 3 Personal Auto Personal L2 Offer4 \n", + "1 2 Personal Auto Personal L3 Offer1 \n", + "2 1 Corporate Auto Corporate L2 Offer1 \n", + "3 1 Personal Auto Personal L1 Offer4 \n", + "4 1 Personal Auto Personal L3 Offer3 \n", + "... ... ... ... ... \n", + "7303 2 Personal Auto Personal L1 Offer2 \n", + "7304 1 Corporate Auto Corporate L3 Offer1 \n", + "7305 2 Corporate Auto Corporate L2 Offer1 \n", + "7306 3 Personal Auto Personal L2 Offer3 \n", + "7307 1 Corporate Auto Corporate L3 Offer4 \n", + "\n", + " sales_channel total_claim_amount vehicle_class vehicle_size \n", + "0 Web 697.186307 Two-Door Car Large \n", + "1 Agent 489.600000 Two-Door Car Small \n", + "2 Agent 423.286512 Four-Door Car Large \n", + "3 Branch 293.865315 Two-Door Car Medsize \n", + "4 Web 468.000000 Two-Door Car Medsize \n", + "... ... ... ... ... \n", + "7303 Web 198.234764 Four-Door Car Medsize \n", + "7304 Branch 379.200000 Four-Door Car Medsize \n", + "7305 Branch 790.784983 Four-Door Car Medsize \n", + "7306 Branch 691.200000 Four-Door Car Large \n", + "7307 Call Center 369.600000 Two-Door Car Medsize \n", + "\n", + "[7308 rows x 24 columns]" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train data\n", + "\n", + "train = df.iloc[int(len(df)*0.2):len(df)]\n", + "train = train.reset_index(drop = True)\n", + "train" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "d8f88108", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington0.013517NoBasicBachelor2/24/11EmployedF0.562847...0.0505050.00.000Corporate AutoCorporate L3Offer1Agent0.132889Two-Door CarMedsize
1QZ44356Arizona0.088586NoExtendedBachelor1/31/11UnemployedF0.000000...0.4242420.00.875Personal AutoPersonal L3Offer3Agent0.390992Four-Door CarMedsize
2AI49188Nevada0.193779NoPremiumBachelor2/19/11EmployedF0.487763...0.3838380.00.125Personal AutoPersonal L3Offer1Agent0.195685Two-Door CarMedsize
3WW63253California0.100450NoBasicBachelor1/20/11UnemployedM0.000000...0.6565660.00.750Corporate AutoCorporate L2Offer1Call Center0.183037SUVMedsize
4HB64268Washington0.014411NoBasicBachelor2/3/11EmployedM0.438443...0.4444440.00.000Personal AutoPersonal L1Offer1Agent0.047617Four-Door CarMedsize
..................................................................
1821AY88788Oregon0.238832NoBasicCollege1/3/11EmployedF0.698543...0.6666670.00.750Personal AutoPersonal L3Offer1Branch0.303655Luxury SUVMedsize
1822OJ33945Oregon0.119089NoBasicHigh School or Below1/8/11EmployedF0.977866...0.1414140.00.125Personal AutoPersonal L1Offer3Agent0.052357Two-Door CarMedsize
1823LO84523Oregon0.080104NoBasicHigh School or Below2/4/11UnemployedM0.000000...0.1212120.00.000Personal AutoPersonal L2Offer2Web0.549042Luxury CarMedsize
1824GJ43254Washington0.527717NoExtendedCollege1/22/11EmployedM0.890739...0.9090910.00.125Corporate AutoCorporate L2Offer1Call Center0.064636Two-Door CarMedsize
1825AR96516Oregon0.069630NoBasicBachelor1/28/11EmployedF0.502265...0.0202020.01.000Personal AutoPersonal L1Offer2Web0.122653Two-Door CarMedsize
\n", + "

1826 rows × 24 columns

\n", + "
" + ], + "text/plain": [ + " customer state customer_lifetime_value response coverage \\\n", + "0 BU79786 Washington 0.013517 No Basic \n", + "1 QZ44356 Arizona 0.088586 No Extended \n", + "2 AI49188 Nevada 0.193779 No Premium \n", + "3 WW63253 California 0.100450 No Basic \n", + "4 HB64268 Washington 0.014411 No Basic \n", + "... ... ... ... ... ... \n", + "1821 AY88788 Oregon 0.238832 No Basic \n", + "1822 OJ33945 Oregon 0.119089 No Basic \n", + "1823 LO84523 Oregon 0.080104 No Basic \n", + "1824 GJ43254 Washington 0.527717 No Extended \n", + "1825 AR96516 Oregon 0.069630 No Basic \n", + "\n", + " education effective_to_date employmentstatus gender \\\n", + "0 Bachelor 2/24/11 Employed F \n", + "1 Bachelor 1/31/11 Unemployed F \n", + "2 Bachelor 2/19/11 Employed F \n", + "3 Bachelor 1/20/11 Unemployed M \n", + "4 Bachelor 2/3/11 Employed M \n", + "... ... ... ... ... \n", + "1821 College 1/3/11 Employed F \n", + "1822 High School or Below 1/8/11 Employed F \n", + "1823 High School or Below 2/4/11 Unemployed M \n", + "1824 College 1/22/11 Employed M \n", + "1825 Bachelor 1/28/11 Employed F \n", + "\n", + " income ... months_since_policy_inception number_of_open_complaints \\\n", + "0 0.562847 ... 0.050505 0.0 \n", + "1 0.000000 ... 0.424242 0.0 \n", + "2 0.487763 ... 0.383838 0.0 \n", + "3 0.000000 ... 0.656566 0.0 \n", + "4 0.438443 ... 0.444444 0.0 \n", + "... ... ... ... ... \n", + "1821 0.698543 ... 0.666667 0.0 \n", + "1822 0.977866 ... 0.141414 0.0 \n", + "1823 0.000000 ... 0.121212 0.0 \n", + "1824 0.890739 ... 0.909091 0.0 \n", + "1825 0.502265 ... 0.020202 0.0 \n", + "\n", + " number_of_policies policy_type policy renew_offer_type \\\n", + "0 0.000 Corporate Auto Corporate L3 Offer1 \n", + "1 0.875 Personal Auto Personal L3 Offer3 \n", + "2 0.125 Personal Auto Personal L3 Offer1 \n", + "3 0.750 Corporate Auto Corporate L2 Offer1 \n", + "4 0.000 Personal Auto Personal L1 Offer1 \n", + "... ... ... ... ... \n", + "1821 0.750 Personal Auto Personal L3 Offer1 \n", + "1822 0.125 Personal Auto Personal L1 Offer3 \n", + "1823 0.000 Personal Auto Personal L2 Offer2 \n", + "1824 0.125 Corporate Auto Corporate L2 Offer1 \n", + "1825 1.000 Personal Auto Personal L1 Offer2 \n", + "\n", + " sales_channel total_claim_amount vehicle_class vehicle_size \n", + "0 Agent 0.132889 Two-Door Car Medsize \n", + "1 Agent 0.390992 Four-Door Car Medsize \n", + "2 Agent 0.195685 Two-Door Car Medsize \n", + "3 Call Center 0.183037 SUV Medsize \n", + "4 Agent 0.047617 Four-Door Car Medsize \n", + "... ... ... ... ... \n", + "1821 Branch 0.303655 Luxury SUV Medsize \n", + "1822 Agent 0.052357 Two-Door Car Medsize \n", + "1823 Web 0.549042 Luxury Car Medsize \n", + "1824 Call Center 0.064636 Two-Door Car Medsize \n", + "1825 Web 0.122653 Two-Door Car Medsize \n", + "\n", + "[1826 rows x 24 columns]" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Normalizing \"test\" numerical values\n", + "\n", + "num_test = test.select_dtypes(include=np.number)\n", + "scaler = MinMaxScaler() \n", + "normalized_test = scaler.fit_transform(num_test) \n", + "normalized_test = pd.DataFrame(normalized_test, columns = num_test.columns)\n", + "normalized_test\n", + "test[normalized_test.columns] = normalized_test\n", + "test" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "7bf18925", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0WH11924Washington0.033746NoBasicCollege2/5/11UnemployedM0.000000...0.3333330.00.250Personal AutoPersonal L2Offer4Web0.252596Two-Door CarLarge
1DL26809Nevada0.060530NoBasicCollege2/27/11UnemployedM0.000000...0.2626260.00.125Personal AutoPersonal L3Offer1Agent0.177375Two-Door CarSmall
2MV69686Oregon0.025595NoExtendedDoctor1/3/11EmployedF0.385150...0.4949490.20.000Corporate AutoCorporate L2Offer1Agent0.153346Four-Door CarLarge
3SC95565Nevada0.012155NoBasicHigh School or Below2/15/11EmployedF0.620422...0.0000000.00.000Personal AutoPersonal L1Offer4Branch0.106449Two-Door CarMedsize
4RL31641Oregon0.004352NoBasicCollege1/29/11UnemployedF0.000000...0.8484850.00.000Personal AutoPersonal L3Offer3Web0.169548Two-Door CarMedsize
..................................................................
7303LA72316California0.264137NoBasicBachelor2/10/11EmployedM0.719691...0.8989900.00.125Personal AutoPersonal L1Offer2Web0.071796Four-Door CarMedsize
7304PK87824California0.014719YesExtendedCollege2/12/11EmployedF0.216124...0.2828280.00.000Corporate AutoCorporate L3Offer1Branch0.137371Four-Door CarMedsize
7305TD14365California0.076951NoExtendedBachelor2/6/11UnemployedM0.000000...0.3737370.60.125Corporate AutoCorporate L2Offer1Branch0.286512Four-Door CarMedsize
7306UP19263California0.069098NoExtendedCollege2/3/11EmployedM0.219496...0.0303030.00.250Personal AutoPersonal L2Offer3Branch0.250427Four-Door CarLarge
7307Y167826California0.008766NoExtendedCollege2/14/11UnemployedM0.000000...0.9090910.00.000Corporate AutoCorporate L3Offer4Call Center0.133892Two-Door CarMedsize
\n", + "

7308 rows × 24 columns

\n", + "
" + ], + "text/plain": [ + " customer state customer_lifetime_value response coverage \\\n", + "0 WH11924 Washington 0.033746 No Basic \n", + "1 DL26809 Nevada 0.060530 No Basic \n", + "2 MV69686 Oregon 0.025595 No Extended \n", + "3 SC95565 Nevada 0.012155 No Basic \n", + "4 RL31641 Oregon 0.004352 No Basic \n", + "... ... ... ... ... ... \n", + "7303 LA72316 California 0.264137 No Basic \n", + "7304 PK87824 California 0.014719 Yes Extended \n", + "7305 TD14365 California 0.076951 No Extended \n", + "7306 UP19263 California 0.069098 No Extended \n", + "7307 Y167826 California 0.008766 No Extended \n", + "\n", + " education effective_to_date employmentstatus gender \\\n", + "0 College 2/5/11 Unemployed M \n", + "1 College 2/27/11 Unemployed M \n", + "2 Doctor 1/3/11 Employed F \n", + "3 High School or Below 2/15/11 Employed F \n", + "4 College 1/29/11 Unemployed F \n", + "... ... ... ... ... \n", + "7303 Bachelor 2/10/11 Employed M \n", + "7304 College 2/12/11 Employed F \n", + "7305 Bachelor 2/6/11 Unemployed M \n", + "7306 College 2/3/11 Employed M \n", + "7307 College 2/14/11 Unemployed M \n", + "\n", + " income ... months_since_policy_inception number_of_open_complaints \\\n", + "0 0.000000 ... 0.333333 0.0 \n", + "1 0.000000 ... 0.262626 0.0 \n", + "2 0.385150 ... 0.494949 0.2 \n", + "3 0.620422 ... 0.000000 0.0 \n", + "4 0.000000 ... 0.848485 0.0 \n", + "... ... ... ... ... \n", + "7303 0.719691 ... 0.898990 0.0 \n", + "7304 0.216124 ... 0.282828 0.0 \n", + "7305 0.000000 ... 0.373737 0.6 \n", + "7306 0.219496 ... 0.030303 0.0 \n", + "7307 0.000000 ... 0.909091 0.0 \n", + "\n", + " number_of_policies policy_type policy renew_offer_type \\\n", + "0 0.250 Personal Auto Personal L2 Offer4 \n", + "1 0.125 Personal Auto Personal L3 Offer1 \n", + "2 0.000 Corporate Auto Corporate L2 Offer1 \n", + "3 0.000 Personal Auto Personal L1 Offer4 \n", + "4 0.000 Personal Auto Personal L3 Offer3 \n", + "... ... ... ... ... \n", + "7303 0.125 Personal Auto Personal L1 Offer2 \n", + "7304 0.000 Corporate Auto Corporate L3 Offer1 \n", + "7305 0.125 Corporate Auto Corporate L2 Offer1 \n", + "7306 0.250 Personal Auto Personal L2 Offer3 \n", + "7307 0.000 Corporate Auto Corporate L3 Offer4 \n", + "\n", + " sales_channel total_claim_amount vehicle_class vehicle_size \n", + "0 Web 0.252596 Two-Door Car Large \n", + "1 Agent 0.177375 Two-Door Car Small \n", + "2 Agent 0.153346 Four-Door Car Large \n", + "3 Branch 0.106449 Two-Door Car Medsize \n", + "4 Web 0.169548 Two-Door Car Medsize \n", + "... ... ... ... ... \n", + "7303 Web 0.071796 Four-Door Car Medsize \n", + "7304 Branch 0.137371 Four-Door Car Medsize \n", + "7305 Branch 0.286512 Four-Door Car Medsize \n", + "7306 Branch 0.250427 Four-Door Car Large \n", + "7307 Call Center 0.133892 Two-Door Car Medsize \n", + "\n", + "[7308 rows x 24 columns]" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Normalizing \"train\" numerical values\n", + "\n", + "num_train = train.select_dtypes(include=np.number)\n", + "scaler = MinMaxScaler() \n", + "normalized_train = scaler.fit_transform(num_train) \n", + "normalized_train = pd.DataFrame(normalized_train, columns = num_train.columns)\n", + "normalized_train\n", + "train[normalized_train.columns] = normalized_train\n", + "train" + ] + } + ], + "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 +} From 948be11f9db3a48690086d366414010de122121b Mon Sep 17 00:00:00 2001 From: joaomatoslopes Date: Sat, 14 Oct 2023 16:43:43 +0100 Subject: [PATCH 2/2] Lab done --- ...mer_Analysis_Round_5_Joao-checkpoint.ipynb | 1412 ++++------------- Lab_Customer_Analysis_Round_5_Joao.ipynb | 1412 ++++------------- 2 files changed, 604 insertions(+), 2220 deletions(-) diff --git a/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb b/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb index 2a1b972..64f5032 100644 --- a/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb +++ b/.ipynb_checkpoints/Lab_Customer_Analysis_Round_5_Joao-checkpoint.ipynb @@ -1420,7 +1420,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "1e115b1e", + "id": "584b19c7", "metadata": {}, "outputs": [ { @@ -1455,6 +1455,7 @@ " gender\n", " income\n", " ...\n", + " months_since_last_claim\n", " months_since_policy_inception\n", " number_of_open_complaints\n", " number_of_policies\n", @@ -1462,7 +1463,6 @@ " policy\n", " renew_offer_type\n", " sales_channel\n", - " total_claim_amount\n", " vehicle_class\n", " vehicle_size\n", " \n", @@ -1481,6 +1481,7 @@ " F\n", " 56274\n", " ...\n", + " 32\n", " 5\n", " 0\n", " 1\n", @@ -1488,7 +1489,6 @@ " Corporate L3\n", " Offer1\n", " Agent\n", - " 384.811147\n", " Two-Door Car\n", " Medsize\n", " \n", @@ -1505,6 +1505,7 @@ " F\n", " 0\n", " ...\n", + " 13\n", " 42\n", " 0\n", " 8\n", @@ -1512,7 +1513,6 @@ " Personal L3\n", " Offer3\n", " Agent\n", - " 1131.464935\n", " Four-Door Car\n", " Medsize\n", " \n", @@ -1529,6 +1529,7 @@ " F\n", " 48767\n", " ...\n", + " 18\n", " 38\n", " 0\n", " 2\n", @@ -1536,7 +1537,6 @@ " Personal L3\n", " Offer1\n", " Agent\n", - " 566.472247\n", " Two-Door Car\n", " Medsize\n", " \n", @@ -1553,6 +1553,7 @@ " M\n", " 0\n", " ...\n", + " 18\n", " 65\n", " 0\n", " 7\n", @@ -1560,7 +1561,6 @@ " Corporate L2\n", " Offer1\n", " Call Center\n", - " 529.881344\n", " SUV\n", " Medsize\n", " \n", @@ -1577,6 +1577,7 @@ " M\n", " 43836\n", " ...\n", + " 12\n", " 44\n", " 0\n", " 1\n", @@ -1584,7 +1585,6 @@ " Personal L1\n", " Offer1\n", " Agent\n", - " 138.130879\n", " Four-Door Car\n", " Medsize\n", " \n", @@ -1613,1024 +1613,216 @@ " ...\n", " \n", " \n", - " 1821\n", - " AY88788\n", - " Oregon\n", - " 15417.682200\n", - " No\n", - " Basic\n", - " College\n", - " 1/3/11\n", - " Employed\n", - " F\n", - " 69841\n", - " ...\n", - " 66\n", - " 0\n", - " 7\n", - " Personal Auto\n", - " Personal L3\n", - " Offer1\n", - " Branch\n", - " 878.812468\n", - " Luxury SUV\n", - " Medsize\n", - " \n", - " \n", - " 1822\n", - " OJ33945\n", - " Oregon\n", - " 8692.636838\n", - " No\n", - " Basic\n", - " High School or Below\n", - " 1/8/11\n", - " Employed\n", - " F\n", - " 97768\n", - " ...\n", - " 14\n", - " 0\n", - " 2\n", - " Personal Auto\n", - " Personal L1\n", - " Offer3\n", - " Agent\n", - " 151.843731\n", - " Two-Door Car\n", - " Medsize\n", - " \n", - " \n", - " 1823\n", - " LO84523\n", - " Oregon\n", - " 6503.143913\n", + " 9129\n", + " LA72316\n", + " California\n", + " 23405.987980\n", " No\n", " Basic\n", - " High School or Below\n", - " 2/4/11\n", - " Unemployed\n", - " M\n", - " 0\n", - " ...\n", - " 12\n", - " 0\n", - " 1\n", - " Personal Auto\n", - " Personal L2\n", - " Offer2\n", - " Web\n", - " 1588.682955\n", - " Luxury Car\n", - " Medsize\n", - " \n", - " \n", - " 1824\n", - " GJ43254\n", - " Washington\n", - " 31642.104630\n", - " No\n", - " Extended\n", - " College\n", - " 1/22/11\n", + " Bachelor\n", + " 2/10/11\n", " Employed\n", " M\n", - " 89057\n", + " 71941\n", " ...\n", - " 90\n", + " 18\n", + " 89\n", " 0\n", " 2\n", - " Corporate Auto\n", - " Corporate L2\n", - " Offer1\n", - " Call Center\n", - " 187.363583\n", - " Two-Door Car\n", - " Medsize\n", - " \n", - " \n", - " 1825\n", - " AR96516\n", - " Oregon\n", - " 5914.951808\n", - " No\n", - " Basic\n", - " Bachelor\n", - " 1/28/11\n", - " Employed\n", - " F\n", - " 50217\n", - " ...\n", - " 2\n", - " 0\n", - " 9\n", " Personal Auto\n", " Personal L1\n", " Offer2\n", " Web\n", - " 355.200000\n", - " Two-Door Car\n", - " Medsize\n", - " \n", - " \n", - "\n", - "

1826 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", - "1821 AY88788 Oregon 15417.682200 No Basic \n", - "1822 OJ33945 Oregon 8692.636838 No Basic \n", - "1823 LO84523 Oregon 6503.143913 No Basic \n", - "1824 GJ43254 Washington 31642.104630 No Extended \n", - "1825 AR96516 Oregon 5914.951808 No Basic \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", - "1821 College 1/3/11 Employed F 69841 \n", - "1822 High School or Below 1/8/11 Employed F 97768 \n", - "1823 High School or Below 2/4/11 Unemployed M 0 \n", - "1824 College 1/22/11 Employed M 89057 \n", - "1825 Bachelor 1/28/11 Employed F 50217 \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", - "1821 ... 66 0 \n", - "1822 ... 14 0 \n", - "1823 ... 12 0 \n", - "1824 ... 90 0 \n", - "1825 ... 2 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", - "1821 7 Personal Auto Personal L3 Offer1 \n", - "1822 2 Personal Auto Personal L1 Offer3 \n", - "1823 1 Personal Auto Personal L2 Offer2 \n", - "1824 2 Corporate Auto Corporate L2 Offer1 \n", - "1825 9 Personal Auto Personal L1 Offer2 \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", - "1821 Branch 878.812468 Luxury SUV Medsize \n", - "1822 Agent 151.843731 Two-Door Car Medsize \n", - "1823 Web 1588.682955 Luxury Car Medsize \n", - "1824 Call Center 187.363583 Two-Door Car Medsize \n", - "1825 Web 355.200000 Two-Door Car Medsize \n", - "\n", - "[1826 rows x 24 columns]" - ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Test data\n", - "\n", - "test = df.iloc[0:int(len(df)*0.2)]\n", - "test = test.reset_index(drop = True)\n", - "test" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "id": "cb9eb6f7", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0WH11924Washington4645.839058NoBasicCollege2/5/11UnemployedM0...3303Personal AutoPersonal L2Offer4Web697.186307Two-Door CarLarge
1DL26809Nevada6826.797741NoBasicCollege2/27/11UnemployedM0...2602Personal AutoPersonal L3Offer1Agent489.600000Two-Door CarSmall
2MV69686Oregon3982.180708NoExtendedDoctor1/3/11EmployedF38500...4911Corporate AutoCorporate L2Offer1Agent423.286512Four-Door CarLarge
3SC95565Nevada2887.779742NoBasicHigh School or Below2/15/11EmployedF62018...001Personal AutoPersonal L1Offer4Branch293.865315Two-Door CarMedsize
4RL31641Oregon2252.416825NoBasicCollege1/29/11UnemployedF0...8401Personal AutoPersonal L3Offer3Web468.000000Two-Door CarMedsize
..................................................................
7303LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
7304PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
7305TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
7306UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
7307Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\n", - "

7308 rows × 24 columns

\n", - "
" - ], - "text/plain": [ - " customer state customer_lifetime_value response coverage \\\n", - "0 WH11924 Washington 4645.839058 No Basic \n", - "1 DL26809 Nevada 6826.797741 No Basic \n", - "2 MV69686 Oregon 3982.180708 No Extended \n", - "3 SC95565 Nevada 2887.779742 No Basic \n", - "4 RL31641 Oregon 2252.416825 No Basic \n", - "... ... ... ... ... ... \n", - "7303 LA72316 California 23405.987980 No Basic \n", - "7304 PK87824 California 3096.511217 Yes Extended \n", - "7305 TD14365 California 8163.890428 No Extended \n", - "7306 UP19263 California 7524.442436 No Extended \n", - "7307 Y167826 California 2611.836866 No Extended \n", - "\n", - " education effective_to_date employmentstatus gender income \\\n", - "0 College 2/5/11 Unemployed M 0 \n", - "1 College 2/27/11 Unemployed M 0 \n", - "2 Doctor 1/3/11 Employed F 38500 \n", - "3 High School or Below 2/15/11 Employed F 62018 \n", - "4 College 1/29/11 Unemployed F 0 \n", - "... ... ... ... ... ... \n", - "7303 Bachelor 2/10/11 Employed M 71941 \n", - "7304 College 2/12/11 Employed F 21604 \n", - "7305 Bachelor 2/6/11 Unemployed M 0 \n", - "7306 College 2/3/11 Employed M 21941 \n", - "7307 College 2/14/11 Unemployed M 0 \n", - "\n", - " ... months_since_policy_inception number_of_open_complaints \\\n", - "0 ... 33 0 \n", - "1 ... 26 0 \n", - "2 ... 49 1 \n", - "3 ... 0 0 \n", - "4 ... 84 0 \n", - "... ... ... ... \n", - "7303 ... 89 0 \n", - "7304 ... 28 0 \n", - "7305 ... 37 3 \n", - "7306 ... 3 0 \n", - "7307 ... 90 0 \n", - "\n", - " number_of_policies policy_type policy renew_offer_type \\\n", - "0 3 Personal Auto Personal L2 Offer4 \n", - "1 2 Personal Auto Personal L3 Offer1 \n", - "2 1 Corporate Auto Corporate L2 Offer1 \n", - "3 1 Personal Auto Personal L1 Offer4 \n", - "4 1 Personal Auto Personal L3 Offer3 \n", - "... ... ... ... ... \n", - "7303 2 Personal Auto Personal L1 Offer2 \n", - "7304 1 Corporate Auto Corporate L3 Offer1 \n", - "7305 2 Corporate Auto Corporate L2 Offer1 \n", - "7306 3 Personal Auto Personal L2 Offer3 \n", - "7307 1 Corporate Auto Corporate L3 Offer4 \n", - "\n", - " sales_channel total_claim_amount vehicle_class vehicle_size \n", - "0 Web 697.186307 Two-Door Car Large \n", - "1 Agent 489.600000 Two-Door Car Small \n", - "2 Agent 423.286512 Four-Door Car Large \n", - "3 Branch 293.865315 Two-Door Car Medsize \n", - "4 Web 468.000000 Two-Door Car Medsize \n", - "... ... ... ... ... \n", - "7303 Web 198.234764 Four-Door Car Medsize \n", - "7304 Branch 379.200000 Four-Door Car Medsize \n", - "7305 Branch 790.784983 Four-Door Car Medsize \n", - "7306 Branch 691.200000 Four-Door Car Large \n", - "7307 Call Center 369.600000 Two-Door Car Medsize \n", - "\n", - "[7308 rows x 24 columns]" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train data\n", - "\n", - "train = df.iloc[int(len(df)*0.2):len(df)]\n", - "train = train.reset_index(drop = True)\n", - "train" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "id": "d8f88108", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", + " \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", - " \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", - " \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", + " \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", " \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", " \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", - " \n", - " \n", - " \n", - " \n", " \n", " \n", " \n", " \n", "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington0.013517NoBasicBachelor2/24/11EmployedF0.562847...0.0505050.00.000Corporate AutoCorporate L3Offer1Agent0.132889Two-Door CarMedsize
1QZ44356Arizona0.088586NoExtendedBachelor1/31/11UnemployedF0.000000...0.4242420.00.875Personal AutoPersonal L3Offer3Agent0.390992Four-Door CarMedsize
2AI49188Nevada0.193779NoPremiumBachelor2/19/11EmployedF0.487763...0.3838380.00.125Personal AutoPersonal L3Offer1Agent0.195685Two-Door CarMedsize
3WW63253California0.100450NoBasicBachelor1/20/11UnemployedM0.000000...0.6565660.00.750Corporate AutoCorporate L2Offer1Call Center0.183037SUVMedsize
4HB64268Washington0.014411NoBasicBachelor2/3/11EmployedM0.438443...0.4444440.00.000Personal AutoPersonal L1Offer1Agent0.047617Four-Door CarMedsize
..................................................................
1821AY88788Oregon0.238832NoBasic9130PK87824California3096.511217YesExtendedCollege1/3/112/12/11EmployedF0.69854321604...0.6666670.00.750Personal AutoPersonal L3142801Corporate AutoCorporate L3Offer1Branch0.303655Luxury SUVFour-Door CarMedsize
1822OJ33945Oregon0.1190899131TD14365California8163.890428NoBasicHigh School or Below1/8/11EmployedF0.977866ExtendedBachelor2/6/11UnemployedM0...0.1414140.00.125Personal AutoPersonal L1Offer3Agent0.052357Two-Door Car93732Corporate AutoCorporate L2Offer1BranchFour-Door CarMedsize
1823LO84523Oregon0.0801049132UP19263California7524.442436NoBasicHigh School or Below2/4/11UnemployedExtendedCollege2/3/11EmployedM0.00000021941...0.1212120.00.00034303Personal AutoPersonal L2Offer2Web0.549042Luxury CarMedsizeOffer3BranchFour-Door CarLarge
1824GJ43254Washington0.5277179133Y167826California2611.836866NoExtendedCollege1/22/11Employed2/14/11UnemployedM0.8907390...0.9090910.00.12539001Corporate AutoCorporate L2Offer1Corporate L3Offer4Call Center0.064636Two-Door CarMedsize
1825AR96516Oregon0.069630NoBasicBachelor1/28/11EmployedF0.502265...0.0202020.01.000Personal AutoPersonal L1Offer2Web0.122653Two-Door CarMedsize
\n", - "

1826 rows × 24 columns

\n", + "

9134 rows × 23 columns

\n", "
" ], "text/plain": [ " customer state customer_lifetime_value response coverage \\\n", - "0 BU79786 Washington 0.013517 No Basic \n", - "1 QZ44356 Arizona 0.088586 No Extended \n", - "2 AI49188 Nevada 0.193779 No Premium \n", - "3 WW63253 California 0.100450 No Basic \n", - "4 HB64268 Washington 0.014411 No Basic \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", - "1821 AY88788 Oregon 0.238832 No Basic \n", - "1822 OJ33945 Oregon 0.119089 No Basic \n", - "1823 LO84523 Oregon 0.080104 No Basic \n", - "1824 GJ43254 Washington 0.527717 No Extended \n", - "1825 AR96516 Oregon 0.069630 No Basic \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 \\\n", - "0 Bachelor 2/24/11 Employed F \n", - "1 Bachelor 1/31/11 Unemployed F \n", - "2 Bachelor 2/19/11 Employed F \n", - "3 Bachelor 1/20/11 Unemployed M \n", - "4 Bachelor 2/3/11 Employed M \n", - "... ... ... ... ... \n", - "1821 College 1/3/11 Employed F \n", - "1822 High School or Below 1/8/11 Employed F \n", - "1823 High School or Below 2/4/11 Unemployed M \n", - "1824 College 1/22/11 Employed M \n", - "1825 Bachelor 1/28/11 Employed F \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", - " income ... months_since_policy_inception number_of_open_complaints \\\n", - "0 0.562847 ... 0.050505 0.0 \n", - "1 0.000000 ... 0.424242 0.0 \n", - "2 0.487763 ... 0.383838 0.0 \n", - "3 0.000000 ... 0.656566 0.0 \n", - "4 0.438443 ... 0.444444 0.0 \n", - "... ... ... ... ... \n", - "1821 0.698543 ... 0.666667 0.0 \n", - "1822 0.977866 ... 0.141414 0.0 \n", - "1823 0.000000 ... 0.121212 0.0 \n", - "1824 0.890739 ... 0.909091 0.0 \n", - "1825 0.502265 ... 0.020202 0.0 \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_policies policy_type policy renew_offer_type \\\n", - "0 0.000 Corporate Auto Corporate L3 Offer1 \n", - "1 0.875 Personal Auto Personal L3 Offer3 \n", - "2 0.125 Personal Auto Personal L3 Offer1 \n", - "3 0.750 Corporate Auto Corporate L2 Offer1 \n", - "4 0.000 Personal Auto Personal L1 Offer1 \n", - "... ... ... ... ... \n", - "1821 0.750 Personal Auto Personal L3 Offer1 \n", - "1822 0.125 Personal Auto Personal L1 Offer3 \n", - "1823 0.000 Personal Auto Personal L2 Offer2 \n", - "1824 0.125 Corporate Auto Corporate L2 Offer1 \n", - "1825 1.000 Personal Auto Personal L1 Offer2 \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", - " sales_channel total_claim_amount vehicle_class vehicle_size \n", - "0 Agent 0.132889 Two-Door Car Medsize \n", - "1 Agent 0.390992 Four-Door Car Medsize \n", - "2 Agent 0.195685 Two-Door Car Medsize \n", - "3 Call Center 0.183037 SUV Medsize \n", - "4 Agent 0.047617 Four-Door Car Medsize \n", - "... ... ... ... ... \n", - "1821 Branch 0.303655 Luxury SUV Medsize \n", - "1822 Agent 0.052357 Two-Door Car Medsize \n", - "1823 Web 0.549042 Luxury Car Medsize \n", - "1824 Call Center 0.064636 Two-Door Car Medsize \n", - "1825 Web 0.122653 Two-Door Car Medsize \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", - "[1826 rows x 24 columns]" + "[9134 rows x 23 columns]" ] }, - "execution_count": 11, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# Normalizing \"test\" numerical values\n", + "# Splitting X-Y\n", "\n", - "num_test = test.select_dtypes(include=np.number)\n", - "scaler = MinMaxScaler() \n", - "normalized_test = scaler.fit_transform(num_test) \n", - "normalized_test = pd.DataFrame(normalized_test, columns = num_test.columns)\n", - "normalized_test\n", - "test[normalized_test.columns] = normalized_test\n", - "test" + "Y = df[\"total_claim_amount\"]\n", + "X = df.drop([\"total_claim_amount\"], axis = 1)\n", + "X" ] }, { "cell_type": "code", - "execution_count": 12, - "id": "7bf18925", + "execution_count": 10, + "id": "d8f88108", "metadata": {}, "outputs": [ { @@ -2665,6 +1857,7 @@ " gender\n", " income\n", " ...\n", + " months_since_last_claim\n", " months_since_policy_inception\n", " number_of_open_complaints\n", " number_of_policies\n", @@ -2672,7 +1865,6 @@ " policy\n", " renew_offer_type\n", " sales_channel\n", - " total_claim_amount\n", " vehicle_class\n", " vehicle_size\n", " \n", @@ -2680,122 +1872,122 @@ " \n", " \n", " 0\n", - " WH11924\n", + " BU79786\n", " Washington\n", - " 0.033746\n", + " 0.010629\n", " No\n", " Basic\n", - " College\n", - " 2/5/11\n", - " Unemployed\n", - " M\n", - " 0.000000\n", + " Bachelor\n", + " 2/24/11\n", + " Employed\n", + " F\n", + " 0.562847\n", " ...\n", - " 0.333333\n", + " 0.914286\n", + " 0.050505\n", " 0.0\n", - " 0.250\n", - " Personal Auto\n", - " Personal L2\n", - " Offer4\n", - " Web\n", - " 0.252596\n", + " 0.000\n", + " Corporate Auto\n", + " Corporate L3\n", + " Offer1\n", + " Agent\n", " Two-Door Car\n", - " Large\n", + " Medsize\n", " \n", " \n", " 1\n", - " DL26809\n", - " Nevada\n", - " 0.060530\n", + " QZ44356\n", + " Arizona\n", + " 0.062406\n", " No\n", - " Basic\n", - " College\n", - " 2/27/11\n", + " Extended\n", + " Bachelor\n", + " 1/31/11\n", " Unemployed\n", - " M\n", + " F\n", " 0.000000\n", " ...\n", - " 0.262626\n", + " 0.371429\n", + " 0.424242\n", " 0.0\n", - " 0.125\n", + " 0.875\n", " Personal Auto\n", " Personal L3\n", - " Offer1\n", + " Offer3\n", " Agent\n", - " 0.177375\n", - " Two-Door Car\n", - " Small\n", + " Four-Door Car\n", + " Medsize\n", " \n", " \n", " 2\n", - " MV69686\n", - " Oregon\n", - " 0.025595\n", + " AI49188\n", + " Nevada\n", + " 0.134960\n", " No\n", - " Extended\n", - " Doctor\n", - " 1/3/11\n", + " Premium\n", + " Bachelor\n", + " 2/19/11\n", " Employed\n", " F\n", - " 0.385150\n", + " 0.487763\n", " ...\n", - " 0.494949\n", - " 0.2\n", - " 0.000\n", - " Corporate Auto\n", - " Corporate L2\n", + " 0.514286\n", + " 0.383838\n", + " 0.0\n", + " 0.125\n", + " Personal Auto\n", + " Personal L3\n", " Offer1\n", " Agent\n", - " 0.153346\n", - " Four-Door Car\n", - " Large\n", + " Two-Door Car\n", + " Medsize\n", " \n", " \n", " 3\n", - " SC95565\n", - " Nevada\n", - " 0.012155\n", + " WW63253\n", + " California\n", + " 0.070589\n", " No\n", " Basic\n", - " High School or Below\n", - " 2/15/11\n", - " Employed\n", - " F\n", - " 0.620422\n", - " ...\n", + " Bachelor\n", + " 1/20/11\n", + " Unemployed\n", + " M\n", " 0.000000\n", + " ...\n", + " 0.514286\n", + " 0.656566\n", " 0.0\n", - " 0.000\n", - " Personal Auto\n", - " Personal L1\n", - " Offer4\n", - " Branch\n", - " 0.106449\n", - " Two-Door Car\n", + " 0.750\n", + " Corporate Auto\n", + " Corporate L2\n", + " Offer1\n", + " Call Center\n", + " SUV\n", " Medsize\n", " \n", " \n", " 4\n", - " RL31641\n", - " Oregon\n", - " 0.004352\n", + " HB64268\n", + " Washington\n", + " 0.011245\n", " No\n", " Basic\n", - " College\n", - " 1/29/11\n", - " Unemployed\n", - " F\n", - " 0.000000\n", + " Bachelor\n", + " 2/3/11\n", + " Employed\n", + " M\n", + " 0.438443\n", " ...\n", - " 0.848485\n", + " 0.342857\n", + " 0.444444\n", " 0.0\n", " 0.000\n", " Personal Auto\n", - " Personal L3\n", - " Offer3\n", - " Web\n", - " 0.169548\n", - " Two-Door Car\n", + " Personal L1\n", + " Offer1\n", + " Agent\n", + " Four-Door Car\n", " Medsize\n", " \n", " \n", @@ -2823,7 +2015,7 @@ " ...\n", " \n", " \n", - " 7303\n", + " 9129\n", " LA72316\n", " California\n", " 0.264137\n", @@ -2833,8 +2025,9 @@ " 2/10/11\n", " Employed\n", " M\n", - " 0.719691\n", + " 0.719547\n", " ...\n", + " 0.514286\n", " 0.898990\n", " 0.0\n", " 0.125\n", @@ -2842,12 +2035,11 @@ " Personal L1\n", " Offer2\n", " Web\n", - " 0.071796\n", " Four-Door Car\n", " Medsize\n", " \n", " \n", - " 7304\n", + " 9130\n", " PK87824\n", " California\n", " 0.014719\n", @@ -2857,8 +2049,9 @@ " 2/12/11\n", " Employed\n", " F\n", - " 0.216124\n", + " 0.216081\n", " ...\n", + " 0.400000\n", " 0.282828\n", " 0.0\n", " 0.000\n", @@ -2866,12 +2059,11 @@ " Corporate L3\n", " Offer1\n", " Branch\n", - " 0.137371\n", " Four-Door Car\n", " Medsize\n", " \n", " \n", - " 7305\n", + " 9131\n", " TD14365\n", " California\n", " 0.076951\n", @@ -2883,6 +2075,7 @@ " M\n", " 0.000000\n", " ...\n", + " 0.257143\n", " 0.373737\n", " 0.6\n", " 0.125\n", @@ -2890,12 +2083,11 @@ " Corporate L2\n", " Offer1\n", " Branch\n", - " 0.286512\n", " Four-Door Car\n", " Medsize\n", " \n", " \n", - " 7306\n", + " 9132\n", " UP19263\n", " California\n", " 0.069098\n", @@ -2905,8 +2097,9 @@ " 2/3/11\n", " Employed\n", " M\n", - " 0.219496\n", + " 0.219452\n", " ...\n", + " 0.971429\n", " 0.030303\n", " 0.0\n", " 0.250\n", @@ -2914,12 +2107,11 @@ " Personal L2\n", " Offer3\n", " Branch\n", - " 0.250427\n", " Four-Door Car\n", " Large\n", " \n", " \n", - " 7307\n", + " 9133\n", " Y167826\n", " California\n", " 0.008766\n", @@ -2931,6 +2123,7 @@ " M\n", " 0.000000\n", " ...\n", + " 0.085714\n", " 0.909091\n", " 0.0\n", " 0.000\n", @@ -2938,99 +2131,98 @@ " Corporate L3\n", " Offer4\n", " Call Center\n", - " 0.133892\n", " Two-Door Car\n", " Medsize\n", " \n", " \n", "\n", - "

7308 rows × 24 columns

\n", + "

9134 rows × 23 columns

\n", "" ], "text/plain": [ " customer state customer_lifetime_value response coverage \\\n", - "0 WH11924 Washington 0.033746 No Basic \n", - "1 DL26809 Nevada 0.060530 No Basic \n", - "2 MV69686 Oregon 0.025595 No Extended \n", - "3 SC95565 Nevada 0.012155 No Basic \n", - "4 RL31641 Oregon 0.004352 No Basic \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", - "7303 LA72316 California 0.264137 No Basic \n", - "7304 PK87824 California 0.014719 Yes Extended \n", - "7305 TD14365 California 0.076951 No Extended \n", - "7306 UP19263 California 0.069098 No Extended \n", - "7307 Y167826 California 0.008766 No Extended \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 \\\n", - "0 College 2/5/11 Unemployed M \n", - "1 College 2/27/11 Unemployed M \n", - "2 Doctor 1/3/11 Employed F \n", - "3 High School or Below 2/15/11 Employed F \n", - "4 College 1/29/11 Unemployed F \n", - "... ... ... ... ... \n", - "7303 Bachelor 2/10/11 Employed M \n", - "7304 College 2/12/11 Employed F \n", - "7305 Bachelor 2/6/11 Unemployed M \n", - "7306 College 2/3/11 Employed M \n", - "7307 College 2/14/11 Unemployed M \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", - " income ... months_since_policy_inception number_of_open_complaints \\\n", - "0 0.000000 ... 0.333333 0.0 \n", - "1 0.000000 ... 0.262626 0.0 \n", - "2 0.385150 ... 0.494949 0.2 \n", - "3 0.620422 ... 0.000000 0.0 \n", - "4 0.000000 ... 0.848485 0.0 \n", - "... ... ... ... ... \n", - "7303 0.719691 ... 0.898990 0.0 \n", - "7304 0.216124 ... 0.282828 0.0 \n", - "7305 0.000000 ... 0.373737 0.6 \n", - "7306 0.219496 ... 0.030303 0.0 \n", - "7307 0.000000 ... 0.909091 0.0 \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_policies policy_type policy renew_offer_type \\\n", - "0 0.250 Personal Auto Personal L2 Offer4 \n", - "1 0.125 Personal Auto Personal L3 Offer1 \n", - "2 0.000 Corporate Auto Corporate L2 Offer1 \n", - "3 0.000 Personal Auto Personal L1 Offer4 \n", - "4 0.000 Personal Auto Personal L3 Offer3 \n", - "... ... ... ... ... \n", - "7303 0.125 Personal Auto Personal L1 Offer2 \n", - "7304 0.000 Corporate Auto Corporate L3 Offer1 \n", - "7305 0.125 Corporate Auto Corporate L2 Offer1 \n", - "7306 0.250 Personal Auto Personal L2 Offer3 \n", - "7307 0.000 Corporate Auto Corporate L3 Offer4 \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", - " sales_channel total_claim_amount vehicle_class vehicle_size \n", - "0 Web 0.252596 Two-Door Car Large \n", - "1 Agent 0.177375 Two-Door Car Small \n", - "2 Agent 0.153346 Four-Door Car Large \n", - "3 Branch 0.106449 Two-Door Car Medsize \n", - "4 Web 0.169548 Two-Door Car Medsize \n", - "... ... ... ... ... \n", - "7303 Web 0.071796 Four-Door Car Medsize \n", - "7304 Branch 0.137371 Four-Door Car Medsize \n", - "7305 Branch 0.286512 Four-Door Car Medsize \n", - "7306 Branch 0.250427 Four-Door Car Large \n", - "7307 Call Center 0.133892 Two-Door Car Medsize \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", - "[7308 rows x 24 columns]" + "[9134 rows x 23 columns]" ] }, - "execution_count": 12, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# Normalizing \"train\" numerical values\n", + "# Normalizing X numerical values\n", "\n", - "num_train = train.select_dtypes(include=np.number)\n", + "num_X = X.select_dtypes(include=np.number)\n", "scaler = MinMaxScaler() \n", - "normalized_train = scaler.fit_transform(num_train) \n", - "normalized_train = pd.DataFrame(normalized_train, columns = num_train.columns)\n", - "normalized_train\n", - "train[normalized_train.columns] = normalized_train\n", - "train" + "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" ] } ], diff --git a/Lab_Customer_Analysis_Round_5_Joao.ipynb b/Lab_Customer_Analysis_Round_5_Joao.ipynb index 2a1b972..64f5032 100644 --- a/Lab_Customer_Analysis_Round_5_Joao.ipynb +++ b/Lab_Customer_Analysis_Round_5_Joao.ipynb @@ -1420,7 +1420,7 @@ { "cell_type": "code", "execution_count": 9, - "id": "1e115b1e", + "id": "584b19c7", "metadata": {}, "outputs": [ { @@ -1455,6 +1455,7 @@ " gender\n", " income\n", " ...\n", + " months_since_last_claim\n", " months_since_policy_inception\n", " number_of_open_complaints\n", " number_of_policies\n", @@ -1462,7 +1463,6 @@ " policy\n", " renew_offer_type\n", " sales_channel\n", - " total_claim_amount\n", " vehicle_class\n", " vehicle_size\n", " \n", @@ -1481,6 +1481,7 @@ " F\n", " 56274\n", " ...\n", + " 32\n", " 5\n", " 0\n", " 1\n", @@ -1488,7 +1489,6 @@ " Corporate L3\n", " Offer1\n", " Agent\n", - " 384.811147\n", " Two-Door Car\n", " Medsize\n", " \n", @@ -1505,6 +1505,7 @@ " F\n", " 0\n", " ...\n", + " 13\n", " 42\n", " 0\n", " 8\n", @@ -1512,7 +1513,6 @@ " Personal L3\n", " Offer3\n", " Agent\n", - " 1131.464935\n", " Four-Door Car\n", " Medsize\n", " \n", @@ -1529,6 +1529,7 @@ " F\n", " 48767\n", " ...\n", + " 18\n", " 38\n", " 0\n", " 2\n", @@ -1536,7 +1537,6 @@ " Personal L3\n", " Offer1\n", " Agent\n", - " 566.472247\n", " Two-Door Car\n", " Medsize\n", " \n", @@ -1553,6 +1553,7 @@ " M\n", " 0\n", " ...\n", + " 18\n", " 65\n", " 0\n", " 7\n", @@ -1560,7 +1561,6 @@ " Corporate L2\n", " Offer1\n", " Call Center\n", - " 529.881344\n", " SUV\n", " Medsize\n", " \n", @@ -1577,6 +1577,7 @@ " M\n", " 43836\n", " ...\n", + " 12\n", " 44\n", " 0\n", " 1\n", @@ -1584,7 +1585,6 @@ " Personal L1\n", " Offer1\n", " Agent\n", - " 138.130879\n", " Four-Door Car\n", " Medsize\n", " \n", @@ -1613,1024 +1613,216 @@ " ...\n", " \n", " \n", - " 1821\n", - " AY88788\n", - " Oregon\n", - " 15417.682200\n", - " No\n", - " Basic\n", - " College\n", - " 1/3/11\n", - " Employed\n", - " F\n", - " 69841\n", - " ...\n", - " 66\n", - " 0\n", - " 7\n", - " Personal Auto\n", - " Personal L3\n", - " Offer1\n", - " Branch\n", - " 878.812468\n", - " Luxury SUV\n", - " Medsize\n", - " \n", - " \n", - " 1822\n", - " OJ33945\n", - " Oregon\n", - " 8692.636838\n", - " No\n", - " Basic\n", - " High School or Below\n", - " 1/8/11\n", - " Employed\n", - " F\n", - " 97768\n", - " ...\n", - " 14\n", - " 0\n", - " 2\n", - " Personal Auto\n", - " Personal L1\n", - " Offer3\n", - " Agent\n", - " 151.843731\n", - " Two-Door Car\n", - " Medsize\n", - " \n", - " \n", - " 1823\n", - " LO84523\n", - " Oregon\n", - " 6503.143913\n", + " 9129\n", + " LA72316\n", + " California\n", + " 23405.987980\n", " No\n", " Basic\n", - " High School or Below\n", - " 2/4/11\n", - " Unemployed\n", - " M\n", - " 0\n", - " ...\n", - " 12\n", - " 0\n", - " 1\n", - " Personal Auto\n", - " Personal L2\n", - " Offer2\n", - " Web\n", - " 1588.682955\n", - " Luxury Car\n", - " Medsize\n", - " \n", - " \n", - " 1824\n", - " GJ43254\n", - " Washington\n", - " 31642.104630\n", - " No\n", - " Extended\n", - " College\n", - " 1/22/11\n", + " Bachelor\n", + " 2/10/11\n", " Employed\n", " M\n", - " 89057\n", + " 71941\n", " ...\n", - " 90\n", + " 18\n", + " 89\n", " 0\n", " 2\n", - " Corporate Auto\n", - " Corporate L2\n", - " Offer1\n", - " Call Center\n", - " 187.363583\n", - " Two-Door Car\n", - " Medsize\n", - " \n", - " \n", - " 1825\n", - " AR96516\n", - " Oregon\n", - " 5914.951808\n", - " No\n", - " Basic\n", - " Bachelor\n", - " 1/28/11\n", - " Employed\n", - " F\n", - " 50217\n", - " ...\n", - " 2\n", - " 0\n", - " 9\n", " Personal Auto\n", " Personal L1\n", " Offer2\n", " Web\n", - " 355.200000\n", - " Two-Door Car\n", - " Medsize\n", - " \n", - " \n", - "\n", - "

1826 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", - "1821 AY88788 Oregon 15417.682200 No Basic \n", - "1822 OJ33945 Oregon 8692.636838 No Basic \n", - "1823 LO84523 Oregon 6503.143913 No Basic \n", - "1824 GJ43254 Washington 31642.104630 No Extended \n", - "1825 AR96516 Oregon 5914.951808 No Basic \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", - "1821 College 1/3/11 Employed F 69841 \n", - "1822 High School or Below 1/8/11 Employed F 97768 \n", - "1823 High School or Below 2/4/11 Unemployed M 0 \n", - "1824 College 1/22/11 Employed M 89057 \n", - "1825 Bachelor 1/28/11 Employed F 50217 \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", - "1821 ... 66 0 \n", - "1822 ... 14 0 \n", - "1823 ... 12 0 \n", - "1824 ... 90 0 \n", - "1825 ... 2 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", - "1821 7 Personal Auto Personal L3 Offer1 \n", - "1822 2 Personal Auto Personal L1 Offer3 \n", - "1823 1 Personal Auto Personal L2 Offer2 \n", - "1824 2 Corporate Auto Corporate L2 Offer1 \n", - "1825 9 Personal Auto Personal L1 Offer2 \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", - "1821 Branch 878.812468 Luxury SUV Medsize \n", - "1822 Agent 151.843731 Two-Door Car Medsize \n", - "1823 Web 1588.682955 Luxury Car Medsize \n", - "1824 Call Center 187.363583 Two-Door Car Medsize \n", - "1825 Web 355.200000 Two-Door Car Medsize \n", - "\n", - "[1826 rows x 24 columns]" - ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Test data\n", - "\n", - "test = df.iloc[0:int(len(df)*0.2)]\n", - "test = test.reset_index(drop = True)\n", - "test" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "id": "cb9eb6f7", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0WH11924Washington4645.839058NoBasicCollege2/5/11UnemployedM0...3303Personal AutoPersonal L2Offer4Web697.186307Two-Door CarLarge
1DL26809Nevada6826.797741NoBasicCollege2/27/11UnemployedM0...2602Personal AutoPersonal L3Offer1Agent489.600000Two-Door CarSmall
2MV69686Oregon3982.180708NoExtendedDoctor1/3/11EmployedF38500...4911Corporate AutoCorporate L2Offer1Agent423.286512Four-Door CarLarge
3SC95565Nevada2887.779742NoBasicHigh School or Below2/15/11EmployedF62018...001Personal AutoPersonal L1Offer4Branch293.865315Two-Door CarMedsize
4RL31641Oregon2252.416825NoBasicCollege1/29/11UnemployedF0...8401Personal AutoPersonal L3Offer3Web468.000000Two-Door CarMedsize
..................................................................
7303LA72316California23405.987980NoBasicBachelor2/10/11EmployedM71941...8902Personal AutoPersonal L1Offer2Web198.234764Four-Door CarMedsize
7304PK87824California3096.511217YesExtendedCollege2/12/11EmployedF21604...2801Corporate AutoCorporate L3Offer1Branch379.200000Four-Door CarMedsize
7305TD14365California8163.890428NoExtendedBachelor2/6/11UnemployedM0...3732Corporate AutoCorporate L2Offer1Branch790.784983Four-Door CarMedsize
7306UP19263California7524.442436NoExtendedCollege2/3/11EmployedM21941...303Personal AutoPersonal L2Offer3Branch691.200000Four-Door CarLarge
7307Y167826California2611.836866NoExtendedCollege2/14/11UnemployedM0...9001Corporate AutoCorporate L3Offer4Call Center369.600000Two-Door CarMedsize
\n", - "

7308 rows × 24 columns

\n", - "
" - ], - "text/plain": [ - " customer state customer_lifetime_value response coverage \\\n", - "0 WH11924 Washington 4645.839058 No Basic \n", - "1 DL26809 Nevada 6826.797741 No Basic \n", - "2 MV69686 Oregon 3982.180708 No Extended \n", - "3 SC95565 Nevada 2887.779742 No Basic \n", - "4 RL31641 Oregon 2252.416825 No Basic \n", - "... ... ... ... ... ... \n", - "7303 LA72316 California 23405.987980 No Basic \n", - "7304 PK87824 California 3096.511217 Yes Extended \n", - "7305 TD14365 California 8163.890428 No Extended \n", - "7306 UP19263 California 7524.442436 No Extended \n", - "7307 Y167826 California 2611.836866 No Extended \n", - "\n", - " education effective_to_date employmentstatus gender income \\\n", - "0 College 2/5/11 Unemployed M 0 \n", - "1 College 2/27/11 Unemployed M 0 \n", - "2 Doctor 1/3/11 Employed F 38500 \n", - "3 High School or Below 2/15/11 Employed F 62018 \n", - "4 College 1/29/11 Unemployed F 0 \n", - "... ... ... ... ... ... \n", - "7303 Bachelor 2/10/11 Employed M 71941 \n", - "7304 College 2/12/11 Employed F 21604 \n", - "7305 Bachelor 2/6/11 Unemployed M 0 \n", - "7306 College 2/3/11 Employed M 21941 \n", - "7307 College 2/14/11 Unemployed M 0 \n", - "\n", - " ... months_since_policy_inception number_of_open_complaints \\\n", - "0 ... 33 0 \n", - "1 ... 26 0 \n", - "2 ... 49 1 \n", - "3 ... 0 0 \n", - "4 ... 84 0 \n", - "... ... ... ... \n", - "7303 ... 89 0 \n", - "7304 ... 28 0 \n", - "7305 ... 37 3 \n", - "7306 ... 3 0 \n", - "7307 ... 90 0 \n", - "\n", - " number_of_policies policy_type policy renew_offer_type \\\n", - "0 3 Personal Auto Personal L2 Offer4 \n", - "1 2 Personal Auto Personal L3 Offer1 \n", - "2 1 Corporate Auto Corporate L2 Offer1 \n", - "3 1 Personal Auto Personal L1 Offer4 \n", - "4 1 Personal Auto Personal L3 Offer3 \n", - "... ... ... ... ... \n", - "7303 2 Personal Auto Personal L1 Offer2 \n", - "7304 1 Corporate Auto Corporate L3 Offer1 \n", - "7305 2 Corporate Auto Corporate L2 Offer1 \n", - "7306 3 Personal Auto Personal L2 Offer3 \n", - "7307 1 Corporate Auto Corporate L3 Offer4 \n", - "\n", - " sales_channel total_claim_amount vehicle_class vehicle_size \n", - "0 Web 697.186307 Two-Door Car Large \n", - "1 Agent 489.600000 Two-Door Car Small \n", - "2 Agent 423.286512 Four-Door Car Large \n", - "3 Branch 293.865315 Two-Door Car Medsize \n", - "4 Web 468.000000 Two-Door Car Medsize \n", - "... ... ... ... ... \n", - "7303 Web 198.234764 Four-Door Car Medsize \n", - "7304 Branch 379.200000 Four-Door Car Medsize \n", - "7305 Branch 790.784983 Four-Door Car Medsize \n", - "7306 Branch 691.200000 Four-Door Car Large \n", - "7307 Call Center 369.600000 Two-Door Car Medsize \n", - "\n", - "[7308 rows x 24 columns]" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Train data\n", - "\n", - "train = df.iloc[int(len(df)*0.2):len(df)]\n", - "train = train.reset_index(drop = True)\n", - "train" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "id": "d8f88108", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", + " \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", - " \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", - " \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", + " \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", " \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", " \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", - " \n", - " \n", - " \n", - " \n", " \n", " \n", " \n", " \n", "
customerstatecustomer_lifetime_valueresponsecoverageeducationeffective_to_dateemploymentstatusgenderincome...months_since_policy_inceptionnumber_of_open_complaintsnumber_of_policiespolicy_typepolicyrenew_offer_typesales_channeltotal_claim_amountvehicle_classvehicle_size
0BU79786Washington0.013517NoBasicBachelor2/24/11EmployedF0.562847...0.0505050.00.000Corporate AutoCorporate L3Offer1Agent0.132889Two-Door CarMedsize
1QZ44356Arizona0.088586NoExtendedBachelor1/31/11UnemployedF0.000000...0.4242420.00.875Personal AutoPersonal L3Offer3Agent0.390992Four-Door CarMedsize
2AI49188Nevada0.193779NoPremiumBachelor2/19/11EmployedF0.487763...0.3838380.00.125Personal AutoPersonal L3Offer1Agent0.195685Two-Door CarMedsize
3WW63253California0.100450NoBasicBachelor1/20/11UnemployedM0.000000...0.6565660.00.750Corporate AutoCorporate L2Offer1Call Center0.183037SUVMedsize
4HB64268Washington0.014411NoBasicBachelor2/3/11EmployedM0.438443...0.4444440.00.000Personal AutoPersonal L1Offer1Agent0.047617Four-Door CarMedsize
..................................................................
1821AY88788Oregon0.238832NoBasic9130PK87824California3096.511217YesExtendedCollege1/3/112/12/11EmployedF0.69854321604...0.6666670.00.750Personal AutoPersonal L3142801Corporate AutoCorporate L3Offer1Branch0.303655Luxury SUVFour-Door CarMedsize
1822OJ33945Oregon0.1190899131TD14365California8163.890428NoBasicHigh School or Below1/8/11EmployedF0.977866ExtendedBachelor2/6/11UnemployedM0...0.1414140.00.125Personal AutoPersonal L1Offer3Agent0.052357Two-Door Car93732Corporate AutoCorporate L2Offer1BranchFour-Door CarMedsize
1823LO84523Oregon0.0801049132UP19263California7524.442436NoBasicHigh School or Below2/4/11UnemployedExtendedCollege2/3/11EmployedM0.00000021941...0.1212120.00.00034303Personal AutoPersonal L2Offer2Web0.549042Luxury CarMedsizeOffer3BranchFour-Door CarLarge
1824GJ43254Washington0.5277179133Y167826California2611.836866NoExtendedCollege1/22/11Employed2/14/11UnemployedM0.8907390...0.9090910.00.12539001Corporate AutoCorporate L2Offer1Corporate L3Offer4Call Center0.064636Two-Door CarMedsize
1825AR96516Oregon0.069630NoBasicBachelor1/28/11EmployedF0.502265...0.0202020.01.000Personal AutoPersonal L1Offer2Web0.122653Two-Door CarMedsize
\n", - "

1826 rows × 24 columns

\n", + "

9134 rows × 23 columns

\n", "
" ], "text/plain": [ " customer state customer_lifetime_value response coverage \\\n", - "0 BU79786 Washington 0.013517 No Basic \n", - "1 QZ44356 Arizona 0.088586 No Extended \n", - "2 AI49188 Nevada 0.193779 No Premium \n", - "3 WW63253 California 0.100450 No Basic \n", - "4 HB64268 Washington 0.014411 No Basic \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", - "1821 AY88788 Oregon 0.238832 No Basic \n", - "1822 OJ33945 Oregon 0.119089 No Basic \n", - "1823 LO84523 Oregon 0.080104 No Basic \n", - "1824 GJ43254 Washington 0.527717 No Extended \n", - "1825 AR96516 Oregon 0.069630 No Basic \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 \\\n", - "0 Bachelor 2/24/11 Employed F \n", - "1 Bachelor 1/31/11 Unemployed F \n", - "2 Bachelor 2/19/11 Employed F \n", - "3 Bachelor 1/20/11 Unemployed M \n", - "4 Bachelor 2/3/11 Employed M \n", - "... ... ... ... ... \n", - "1821 College 1/3/11 Employed F \n", - "1822 High School or Below 1/8/11 Employed F \n", - "1823 High School or Below 2/4/11 Unemployed M \n", - "1824 College 1/22/11 Employed M \n", - "1825 Bachelor 1/28/11 Employed F \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", - " income ... months_since_policy_inception number_of_open_complaints \\\n", - "0 0.562847 ... 0.050505 0.0 \n", - "1 0.000000 ... 0.424242 0.0 \n", - "2 0.487763 ... 0.383838 0.0 \n", - "3 0.000000 ... 0.656566 0.0 \n", - "4 0.438443 ... 0.444444 0.0 \n", - "... ... ... ... ... \n", - "1821 0.698543 ... 0.666667 0.0 \n", - "1822 0.977866 ... 0.141414 0.0 \n", - "1823 0.000000 ... 0.121212 0.0 \n", - "1824 0.890739 ... 0.909091 0.0 \n", - "1825 0.502265 ... 0.020202 0.0 \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_policies policy_type policy renew_offer_type \\\n", - "0 0.000 Corporate Auto Corporate L3 Offer1 \n", - "1 0.875 Personal Auto Personal L3 Offer3 \n", - "2 0.125 Personal Auto Personal L3 Offer1 \n", - "3 0.750 Corporate Auto Corporate L2 Offer1 \n", - "4 0.000 Personal Auto Personal L1 Offer1 \n", - "... ... ... ... ... \n", - "1821 0.750 Personal Auto Personal L3 Offer1 \n", - "1822 0.125 Personal Auto Personal L1 Offer3 \n", - "1823 0.000 Personal Auto Personal L2 Offer2 \n", - "1824 0.125 Corporate Auto Corporate L2 Offer1 \n", - "1825 1.000 Personal Auto Personal L1 Offer2 \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", - " sales_channel total_claim_amount vehicle_class vehicle_size \n", - "0 Agent 0.132889 Two-Door Car Medsize \n", - "1 Agent 0.390992 Four-Door Car Medsize \n", - "2 Agent 0.195685 Two-Door Car Medsize \n", - "3 Call Center 0.183037 SUV Medsize \n", - "4 Agent 0.047617 Four-Door Car Medsize \n", - "... ... ... ... ... \n", - "1821 Branch 0.303655 Luxury SUV Medsize \n", - "1822 Agent 0.052357 Two-Door Car Medsize \n", - "1823 Web 0.549042 Luxury Car Medsize \n", - "1824 Call Center 0.064636 Two-Door Car Medsize \n", - "1825 Web 0.122653 Two-Door Car Medsize \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", - "[1826 rows x 24 columns]" + "[9134 rows x 23 columns]" ] }, - "execution_count": 11, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# Normalizing \"test\" numerical values\n", + "# Splitting X-Y\n", "\n", - "num_test = test.select_dtypes(include=np.number)\n", - "scaler = MinMaxScaler() \n", - "normalized_test = scaler.fit_transform(num_test) \n", - "normalized_test = pd.DataFrame(normalized_test, columns = num_test.columns)\n", - "normalized_test\n", - "test[normalized_test.columns] = normalized_test\n", - "test" + "Y = df[\"total_claim_amount\"]\n", + "X = df.drop([\"total_claim_amount\"], axis = 1)\n", + "X" ] }, { "cell_type": "code", - "execution_count": 12, - "id": "7bf18925", + "execution_count": 10, + "id": "d8f88108", "metadata": {}, "outputs": [ { @@ -2665,6 +1857,7 @@ " gender\n", " income\n", " ...\n", + " months_since_last_claim\n", " months_since_policy_inception\n", " number_of_open_complaints\n", " number_of_policies\n", @@ -2672,7 +1865,6 @@ " policy\n", " renew_offer_type\n", " sales_channel\n", - " total_claim_amount\n", " vehicle_class\n", " vehicle_size\n", " \n", @@ -2680,122 +1872,122 @@ " \n", " \n", " 0\n", - " WH11924\n", + " BU79786\n", " Washington\n", - " 0.033746\n", + " 0.010629\n", " No\n", " Basic\n", - " College\n", - " 2/5/11\n", - " Unemployed\n", - " M\n", - " 0.000000\n", + " Bachelor\n", + " 2/24/11\n", + " Employed\n", + " F\n", + " 0.562847\n", " ...\n", - " 0.333333\n", + " 0.914286\n", + " 0.050505\n", " 0.0\n", - " 0.250\n", - " Personal Auto\n", - " Personal L2\n", - " Offer4\n", - " Web\n", - " 0.252596\n", + " 0.000\n", + " Corporate Auto\n", + " Corporate L3\n", + " Offer1\n", + " Agent\n", " Two-Door Car\n", - " Large\n", + " Medsize\n", " \n", " \n", " 1\n", - " DL26809\n", - " Nevada\n", - " 0.060530\n", + " QZ44356\n", + " Arizona\n", + " 0.062406\n", " No\n", - " Basic\n", - " College\n", - " 2/27/11\n", + " Extended\n", + " Bachelor\n", + " 1/31/11\n", " Unemployed\n", - " M\n", + " F\n", " 0.000000\n", " ...\n", - " 0.262626\n", + " 0.371429\n", + " 0.424242\n", " 0.0\n", - " 0.125\n", + " 0.875\n", " Personal Auto\n", " Personal L3\n", - " Offer1\n", + " Offer3\n", " Agent\n", - " 0.177375\n", - " Two-Door Car\n", - " Small\n", + " Four-Door Car\n", + " Medsize\n", " \n", " \n", " 2\n", - " MV69686\n", - " Oregon\n", - " 0.025595\n", + " AI49188\n", + " Nevada\n", + " 0.134960\n", " No\n", - " Extended\n", - " Doctor\n", - " 1/3/11\n", + " Premium\n", + " Bachelor\n", + " 2/19/11\n", " Employed\n", " F\n", - " 0.385150\n", + " 0.487763\n", " ...\n", - " 0.494949\n", - " 0.2\n", - " 0.000\n", - " Corporate Auto\n", - " Corporate L2\n", + " 0.514286\n", + " 0.383838\n", + " 0.0\n", + " 0.125\n", + " Personal Auto\n", + " Personal L3\n", " Offer1\n", " Agent\n", - " 0.153346\n", - " Four-Door Car\n", - " Large\n", + " Two-Door Car\n", + " Medsize\n", " \n", " \n", " 3\n", - " SC95565\n", - " Nevada\n", - " 0.012155\n", + " WW63253\n", + " California\n", + " 0.070589\n", " No\n", " Basic\n", - " High School or Below\n", - " 2/15/11\n", - " Employed\n", - " F\n", - " 0.620422\n", - " ...\n", + " Bachelor\n", + " 1/20/11\n", + " Unemployed\n", + " M\n", " 0.000000\n", + " ...\n", + " 0.514286\n", + " 0.656566\n", " 0.0\n", - " 0.000\n", - " Personal Auto\n", - " Personal L1\n", - " Offer4\n", - " Branch\n", - " 0.106449\n", - " Two-Door Car\n", + " 0.750\n", + " Corporate Auto\n", + " Corporate L2\n", + " Offer1\n", + " Call Center\n", + " SUV\n", " Medsize\n", " \n", " \n", " 4\n", - " RL31641\n", - " Oregon\n", - " 0.004352\n", + " HB64268\n", + " Washington\n", + " 0.011245\n", " No\n", " Basic\n", - " College\n", - " 1/29/11\n", - " Unemployed\n", - " F\n", - " 0.000000\n", + " Bachelor\n", + " 2/3/11\n", + " Employed\n", + " M\n", + " 0.438443\n", " ...\n", - " 0.848485\n", + " 0.342857\n", + " 0.444444\n", " 0.0\n", " 0.000\n", " Personal Auto\n", - " Personal L3\n", - " Offer3\n", - " Web\n", - " 0.169548\n", - " Two-Door Car\n", + " Personal L1\n", + " Offer1\n", + " Agent\n", + " Four-Door Car\n", " Medsize\n", " \n", " \n", @@ -2823,7 +2015,7 @@ " ...\n", " \n", " \n", - " 7303\n", + " 9129\n", " LA72316\n", " California\n", " 0.264137\n", @@ -2833,8 +2025,9 @@ " 2/10/11\n", " Employed\n", " M\n", - " 0.719691\n", + " 0.719547\n", " ...\n", + " 0.514286\n", " 0.898990\n", " 0.0\n", " 0.125\n", @@ -2842,12 +2035,11 @@ " Personal L1\n", " Offer2\n", " Web\n", - " 0.071796\n", " Four-Door Car\n", " Medsize\n", " \n", " \n", - " 7304\n", + " 9130\n", " PK87824\n", " California\n", " 0.014719\n", @@ -2857,8 +2049,9 @@ " 2/12/11\n", " Employed\n", " F\n", - " 0.216124\n", + " 0.216081\n", " ...\n", + " 0.400000\n", " 0.282828\n", " 0.0\n", " 0.000\n", @@ -2866,12 +2059,11 @@ " Corporate L3\n", " Offer1\n", " Branch\n", - " 0.137371\n", " Four-Door Car\n", " Medsize\n", " \n", " \n", - " 7305\n", + " 9131\n", " TD14365\n", " California\n", " 0.076951\n", @@ -2883,6 +2075,7 @@ " M\n", " 0.000000\n", " ...\n", + " 0.257143\n", " 0.373737\n", " 0.6\n", " 0.125\n", @@ -2890,12 +2083,11 @@ " Corporate L2\n", " Offer1\n", " Branch\n", - " 0.286512\n", " Four-Door Car\n", " Medsize\n", " \n", " \n", - " 7306\n", + " 9132\n", " UP19263\n", " California\n", " 0.069098\n", @@ -2905,8 +2097,9 @@ " 2/3/11\n", " Employed\n", " M\n", - " 0.219496\n", + " 0.219452\n", " ...\n", + " 0.971429\n", " 0.030303\n", " 0.0\n", " 0.250\n", @@ -2914,12 +2107,11 @@ " Personal L2\n", " Offer3\n", " Branch\n", - " 0.250427\n", " Four-Door Car\n", " Large\n", " \n", " \n", - " 7307\n", + " 9133\n", " Y167826\n", " California\n", " 0.008766\n", @@ -2931,6 +2123,7 @@ " M\n", " 0.000000\n", " ...\n", + " 0.085714\n", " 0.909091\n", " 0.0\n", " 0.000\n", @@ -2938,99 +2131,98 @@ " Corporate L3\n", " Offer4\n", " Call Center\n", - " 0.133892\n", " Two-Door Car\n", " Medsize\n", " \n", " \n", "\n", - "

7308 rows × 24 columns

\n", + "

9134 rows × 23 columns

\n", "" ], "text/plain": [ " customer state customer_lifetime_value response coverage \\\n", - "0 WH11924 Washington 0.033746 No Basic \n", - "1 DL26809 Nevada 0.060530 No Basic \n", - "2 MV69686 Oregon 0.025595 No Extended \n", - "3 SC95565 Nevada 0.012155 No Basic \n", - "4 RL31641 Oregon 0.004352 No Basic \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", - "7303 LA72316 California 0.264137 No Basic \n", - "7304 PK87824 California 0.014719 Yes Extended \n", - "7305 TD14365 California 0.076951 No Extended \n", - "7306 UP19263 California 0.069098 No Extended \n", - "7307 Y167826 California 0.008766 No Extended \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 \\\n", - "0 College 2/5/11 Unemployed M \n", - "1 College 2/27/11 Unemployed M \n", - "2 Doctor 1/3/11 Employed F \n", - "3 High School or Below 2/15/11 Employed F \n", - "4 College 1/29/11 Unemployed F \n", - "... ... ... ... ... \n", - "7303 Bachelor 2/10/11 Employed M \n", - "7304 College 2/12/11 Employed F \n", - "7305 Bachelor 2/6/11 Unemployed M \n", - "7306 College 2/3/11 Employed M \n", - "7307 College 2/14/11 Unemployed M \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", - " income ... months_since_policy_inception number_of_open_complaints \\\n", - "0 0.000000 ... 0.333333 0.0 \n", - "1 0.000000 ... 0.262626 0.0 \n", - "2 0.385150 ... 0.494949 0.2 \n", - "3 0.620422 ... 0.000000 0.0 \n", - "4 0.000000 ... 0.848485 0.0 \n", - "... ... ... ... ... \n", - "7303 0.719691 ... 0.898990 0.0 \n", - "7304 0.216124 ... 0.282828 0.0 \n", - "7305 0.000000 ... 0.373737 0.6 \n", - "7306 0.219496 ... 0.030303 0.0 \n", - "7307 0.000000 ... 0.909091 0.0 \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_policies policy_type policy renew_offer_type \\\n", - "0 0.250 Personal Auto Personal L2 Offer4 \n", - "1 0.125 Personal Auto Personal L3 Offer1 \n", - "2 0.000 Corporate Auto Corporate L2 Offer1 \n", - "3 0.000 Personal Auto Personal L1 Offer4 \n", - "4 0.000 Personal Auto Personal L3 Offer3 \n", - "... ... ... ... ... \n", - "7303 0.125 Personal Auto Personal L1 Offer2 \n", - "7304 0.000 Corporate Auto Corporate L3 Offer1 \n", - "7305 0.125 Corporate Auto Corporate L2 Offer1 \n", - "7306 0.250 Personal Auto Personal L2 Offer3 \n", - "7307 0.000 Corporate Auto Corporate L3 Offer4 \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", - " sales_channel total_claim_amount vehicle_class vehicle_size \n", - "0 Web 0.252596 Two-Door Car Large \n", - "1 Agent 0.177375 Two-Door Car Small \n", - "2 Agent 0.153346 Four-Door Car Large \n", - "3 Branch 0.106449 Two-Door Car Medsize \n", - "4 Web 0.169548 Two-Door Car Medsize \n", - "... ... ... ... ... \n", - "7303 Web 0.071796 Four-Door Car Medsize \n", - "7304 Branch 0.137371 Four-Door Car Medsize \n", - "7305 Branch 0.286512 Four-Door Car Medsize \n", - "7306 Branch 0.250427 Four-Door Car Large \n", - "7307 Call Center 0.133892 Two-Door Car Medsize \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", - "[7308 rows x 24 columns]" + "[9134 rows x 23 columns]" ] }, - "execution_count": 12, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "# Normalizing \"train\" numerical values\n", + "# Normalizing X numerical values\n", "\n", - "num_train = train.select_dtypes(include=np.number)\n", + "num_X = X.select_dtypes(include=np.number)\n", "scaler = MinMaxScaler() \n", - "normalized_train = scaler.fit_transform(num_train) \n", - "normalized_train = pd.DataFrame(normalized_train, columns = num_train.columns)\n", - "normalized_train\n", - "train[normalized_train.columns] = normalized_train\n", - "train" + "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" ] } ],