{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "credit data analysis.ipynb", "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": 35, "metadata": { "id": "uornDyP-_jp8" }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import seaborn as sns\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "markdown", "source": [ "# **Read Data**" ], "metadata": { "id": "Ia1hQADHFuuA" } }, { "cell_type": "code", "source": [ "cs = pd.read_csv('/content/Credit.csv')\n", "cs" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 505 }, "id": "M_MLTl4_AxPX", "outputId": "4bc1f033-d21d-4a50-a54f-3cd41105f813" }, "execution_count": 36, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age Gender Region \\\n", "0 1 0.766127 45.0 Male South \n", "1 0 0.957151 40.0 Female South \n", "2 0 0.658180 38.0 Female South \n", "3 0 0.233810 30.0 Female South \n", "4 0 0.907239 49.0 Male South \n", "... ... ... ... ... ... \n", "149997 0 0.246044 58.0 Male North \n", "149998 0 0.000000 30.0 Male North \n", "149999 0 0.850283 64.0 Male North \n", "150000 0 NaN NaN NaN NaN \n", "150001 1 NaN NaN NaN NaN \n", "\n", " MonthlyIncome Rented_OwnHouse Occupation Education \\\n", "0 9120.0 Ownhouse Self_Emp Matric \n", "1 2600.0 Ownhouse Self_Emp Graduate \n", "2 3042.0 Ownhouse Self_Emp PhD \n", "3 3300.0 Ownhouse Self_Emp Professional \n", "4 63588.0 Ownhouse Self_Emp Post-Grad \n", "... ... ... ... ... \n", "149997 NaN Rented Officer2 Professional \n", "149998 5716.0 Rented Non-officer Professional \n", "149999 8158.0 Ownhouse Self_Emp Professional \n", "150000 NaN NaN NaN NaN \n", "150001 NaN NaN NaN NaN \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio MonthlyIncome.1 \\\n", "0 2.0 0.802982 9120.0 \n", "1 0.0 0.121876 2600.0 \n", "2 1.0 0.085113 3042.0 \n", "3 0.0 0.036050 3300.0 \n", "4 1.0 0.024926 63588.0 \n", "... ... ... ... \n", "149997 0.0 3870.000000 NaN \n", "149998 0.0 0.000000 5716.0 \n", "149999 0.0 0.249908 8158.0 \n", "150000 NaN NaN NaN \n", "150001 NaN NaN NaN \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "... ... ... \n", "149997 18.0 0.0 \n", "149998 4.0 0.0 \n", "149999 8.0 0.0 \n", "150000 NaN NaN \n", "150001 NaN NaN \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "0 6.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 1.0 0.0 \n", "... ... ... \n", "149997 1.0 0.0 \n", "149998 0.0 0.0 \n", "149999 2.0 0.0 \n", "150000 NaN NaN \n", "150001 NaN NaN \n", "\n", " NumberOfDependents Good_Bad \n", "0 2.0 Bad \n", "1 1.0 Good \n", "2 0.0 Good \n", "3 0.0 Good \n", "4 0.0 Good \n", "... ... ... \n", "149997 0.0 Good \n", "149998 0.0 Good \n", "149999 0.0 Good \n", "150000 NaN NaN \n", "150001 NaN NaN \n", "\n", "[150002 rows x 18 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageGenderRegionMonthlyIncomeRented_OwnHouseOccupationEducationNumberOfTime30-59DaysPastDueNotWorseDebtRatioMonthlyIncome.1NumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependentsGood_Bad
010.76612745.0MaleSouth9120.0OwnhouseSelf_EmpMatric2.00.8029829120.013.00.06.00.02.0Bad
100.95715140.0FemaleSouth2600.0OwnhouseSelf_EmpGraduate0.00.1218762600.04.00.00.00.01.0Good
200.65818038.0FemaleSouth3042.0OwnhouseSelf_EmpPhD1.00.0851133042.02.01.00.00.00.0Good
300.23381030.0FemaleSouth3300.0OwnhouseSelf_EmpProfessional0.00.0360503300.05.00.00.00.00.0Good
400.90723949.0MaleSouth63588.0OwnhouseSelf_EmpPost-Grad1.00.02492663588.07.00.01.00.00.0Good
.........................................................
14999700.24604458.0MaleNorthNaNRentedOfficer2Professional0.03870.000000NaN18.00.01.00.00.0Good
14999800.00000030.0MaleNorth5716.0RentedNon-officerProfessional0.00.0000005716.04.00.00.00.00.0Good
14999900.85028364.0MaleNorth8158.0OwnhouseSelf_EmpProfessional0.00.2499088158.08.00.02.00.00.0Good
1500000NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1500011NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", "

150002 rows × 18 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 36 } ] }, { "cell_type": "code", "source": [ "cs.info()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "YxnPG1YPBuRM", "outputId": "81607f83-4a9a-479c-a6d0-98c7ab6899d0" }, "execution_count": 37, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\n", "RangeIndex: 150002 entries, 0 to 150001\n", "Data columns (total 18 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 NPA Status 150002 non-null int64 \n", " 1 RevolvingUtilizationOfUnsecuredLines 150000 non-null float64\n", " 2 age 150000 non-null float64\n", " 3 Gender 150000 non-null object \n", " 4 Region 150000 non-null object \n", " 5 MonthlyIncome 120269 non-null float64\n", " 6 Rented_OwnHouse 150000 non-null object \n", " 7 Occupation 150000 non-null object \n", " 8 Education 150000 non-null object \n", " 9 NumberOfTime30-59DaysPastDueNotWorse 150000 non-null float64\n", " 10 DebtRatio 150000 non-null float64\n", " 11 MonthlyIncome.1 120269 non-null float64\n", " 12 NumberOfOpenCreditLinesAndLoans 150000 non-null float64\n", " 13 NumberOfTimes90DaysLate 150000 non-null float64\n", " 14 NumberRealEstateLoansOrLines 150000 non-null float64\n", " 15 NumberOfTime60-89DaysPastDueNotWorse 150000 non-null float64\n", " 16 NumberOfDependents 146076 non-null float64\n", " 17 Good_Bad 150000 non-null object \n", "dtypes: float64(11), int64(1), object(6)\n", "memory usage: 20.6+ MB\n" ] } ] }, { "cell_type": "code", "source": [ "cs.shape" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "CtY1v7AvB2Qm", "outputId": "04069c89-8a1a-4736-9a95-e904f9e74af6" }, "execution_count": 38, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "(150002, 18)" ] }, "metadata": {}, "execution_count": 38 } ] }, { "cell_type": "markdown", "source": [ "## **To Check And Remove Duplicates**" ], "metadata": { "id": "c8aaJ1icGDKQ" } }, { "cell_type": "code", "source": [ "cs[cs.duplicated()]" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 758 }, "id": "6sqvWMqdCKoN", "outputId": "dfbc76a0-5955-4411-c051-e24c63acacf8" }, "execution_count": 12, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age Gender \\\n", "7920 0 1.0 22.0 Male \n", "19814 0 1.0 68.0 Female \n", "19987 0 1.0 37.0 Female \n", "37075 0 1.0 23.0 Male \n", "40396 0 0.0 46.0 Female \n", "43095 0 1.0 22.0 Male \n", "44485 0 1.0 22.0 Female \n", "66276 0 0.0 82.0 Male \n", "67173 0 0.0 87.0 Male \n", "82357 0 0.0 24.0 Male \n", "99854 0 1.0 58.0 Male \n", "105018 0 0.0 87.0 Female \n", "106795 0 0.0 22.0 Male \n", "119531 0 0.0 22.0 Male \n", "121833 0 1.0 63.0 Female \n", "123531 0 1.0 22.0 Female \n", "124731 0 1.0 34.0 Female \n", "126176 0 1.0 55.0 Female \n", "127101 0 1.0 63.0 Female \n", "127270 0 1.0 32.0 Female \n", "\n", " Region MonthlyIncome Rented_OwnHouse Occupation Education \\\n", "7920 South 820.0 Ownhouse Self_Emp Matric \n", "19814 North NaN Ownhouse Officer3 Post-Grad \n", "19987 North NaN Ownhouse Self_Emp Post-Grad \n", "37075 North 0.0 Ownhouse Self_Emp Matric \n", "40396 North NaN Ownhouse Self_Emp Post-Grad \n", "43095 North 820.0 Ownhouse Officer1 Post-Grad \n", "44485 North NaN Ownhouse Officer3 Post-Grad \n", "66276 Central NaN Ownhouse Self_Emp Professional \n", "67173 Central NaN Rented Non-officer Professional \n", "82357 Central NaN Ownhouse Self_Emp Professional \n", "99854 Central NaN Ownhouse Non-officer Graduate \n", "105018 West NaN Rented Self_Emp Graduate \n", "106795 West NaN Rented Non-officer Graduate \n", "119531 West NaN Rented Non-officer Graduate \n", "121833 East NaN Rented Officer3 Post-Grad \n", "123531 East 1000.0 Rented Officer3 Post-Grad \n", "124731 East NaN Rented Officer3 Post-Grad \n", "126176 East NaN Rented Self_Emp Post-Grad \n", "127101 East NaN Rented Officer3 Post-Grad \n", "127270 East NaN Rented Officer1 Post-Grad \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio MonthlyIncome.1 \\\n", "7920 0.0 0.0 820.0 \n", "19814 0.0 0.0 NaN \n", "19987 0.0 0.0 NaN \n", "37075 0.0 0.0 0.0 \n", "40396 0.0 0.0 NaN \n", "43095 0.0 0.0 820.0 \n", "44485 98.0 0.0 NaN \n", "66276 0.0 0.0 NaN \n", "67173 0.0 0.0 NaN \n", "82357 0.0 0.0 NaN \n", "99854 0.0 0.0 NaN \n", "105018 0.0 0.0 NaN \n", "106795 0.0 0.0 NaN \n", "119531 0.0 0.0 NaN \n", "121833 0.0 0.0 NaN \n", "123531 0.0 0.0 1000.0 \n", "124731 98.0 0.0 NaN \n", "126176 0.0 0.0 NaN \n", "127101 0.0 0.0 NaN \n", "127270 0.0 0.0 NaN \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "7920 1.0 0.0 \n", "19814 2.0 0.0 \n", "19987 0.0 0.0 \n", "37075 1.0 0.0 \n", "40396 5.0 0.0 \n", "43095 1.0 0.0 \n", "44485 0.0 98.0 \n", "66276 3.0 0.0 \n", "67173 4.0 0.0 \n", "82357 1.0 0.0 \n", "99854 0.0 0.0 \n", "105018 4.0 0.0 \n", "106795 1.0 0.0 \n", "119531 1.0 0.0 \n", "121833 1.0 0.0 \n", "123531 1.0 0.0 \n", "124731 0.0 98.0 \n", "126176 0.0 0.0 \n", "127101 1.0 0.0 \n", "127270 0.0 0.0 \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "7920 0.0 0.0 \n", "19814 0.0 0.0 \n", "19987 0.0 0.0 \n", "37075 0.0 0.0 \n", "40396 0.0 0.0 \n", "43095 0.0 0.0 \n", "44485 0.0 98.0 \n", "66276 0.0 0.0 \n", "67173 0.0 0.0 \n", "82357 0.0 0.0 \n", "99854 0.0 0.0 \n", "105018 0.0 0.0 \n", "106795 0.0 0.0 \n", "119531 0.0 0.0 \n", "121833 0.0 0.0 \n", "123531 0.0 0.0 \n", "124731 0.0 98.0 \n", "126176 0.0 0.0 \n", "127101 0.0 0.0 \n", "127270 0.0 0.0 \n", "\n", " NumberOfDependents Good_Bad \n", "7920 0.0 Good \n", "19814 0.0 Good \n", "19987 0.0 Good \n", "37075 0.0 Good \n", "40396 0.0 Good \n", "43095 0.0 Good \n", "44485 0.0 Good \n", "66276 0.0 Good \n", "67173 0.0 Good \n", "82357 0.0 Good \n", "99854 0.0 Good \n", "105018 NaN Good \n", "106795 0.0 Good \n", "119531 0.0 Good \n", "121833 0.0 Good \n", "123531 0.0 Good \n", "124731 0.0 Good \n", "126176 0.0 Good \n", "127101 0.0 Good \n", "127270 0.0 Good " ], "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageGenderRegionMonthlyIncomeRented_OwnHouseOccupationEducationNumberOfTime30-59DaysPastDueNotWorseDebtRatioMonthlyIncome.1NumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependentsGood_Bad
792001.022.0MaleSouth820.0OwnhouseSelf_EmpMatric0.00.0820.01.00.00.00.00.0Good
1981401.068.0FemaleNorthNaNOwnhouseOfficer3Post-Grad0.00.0NaN2.00.00.00.00.0Good
1998701.037.0FemaleNorthNaNOwnhouseSelf_EmpPost-Grad0.00.0NaN0.00.00.00.00.0Good
3707501.023.0MaleNorth0.0OwnhouseSelf_EmpMatric0.00.00.01.00.00.00.00.0Good
4039600.046.0FemaleNorthNaNOwnhouseSelf_EmpPost-Grad0.00.0NaN5.00.00.00.00.0Good
4309501.022.0MaleNorth820.0OwnhouseOfficer1Post-Grad0.00.0820.01.00.00.00.00.0Good
4448501.022.0FemaleNorthNaNOwnhouseOfficer3Post-Grad98.00.0NaN0.098.00.098.00.0Good
6627600.082.0MaleCentralNaNOwnhouseSelf_EmpProfessional0.00.0NaN3.00.00.00.00.0Good
6717300.087.0MaleCentralNaNRentedNon-officerProfessional0.00.0NaN4.00.00.00.00.0Good
8235700.024.0MaleCentralNaNOwnhouseSelf_EmpProfessional0.00.0NaN1.00.00.00.00.0Good
9985401.058.0MaleCentralNaNOwnhouseNon-officerGraduate0.00.0NaN0.00.00.00.00.0Good
10501800.087.0FemaleWestNaNRentedSelf_EmpGraduate0.00.0NaN4.00.00.00.0NaNGood
10679500.022.0MaleWestNaNRentedNon-officerGraduate0.00.0NaN1.00.00.00.00.0Good
11953100.022.0MaleWestNaNRentedNon-officerGraduate0.00.0NaN1.00.00.00.00.0Good
12183301.063.0FemaleEastNaNRentedOfficer3Post-Grad0.00.0NaN1.00.00.00.00.0Good
12353101.022.0FemaleEast1000.0RentedOfficer3Post-Grad0.00.01000.01.00.00.00.00.0Good
12473101.034.0FemaleEastNaNRentedOfficer3Post-Grad98.00.0NaN0.098.00.098.00.0Good
12617601.055.0FemaleEastNaNRentedSelf_EmpPost-Grad0.00.0NaN0.00.00.00.00.0Good
12710101.063.0FemaleEastNaNRentedOfficer3Post-Grad0.00.0NaN1.00.00.00.00.0Good
12727001.032.0FemaleEastNaNRentedOfficer1Post-Grad0.00.0NaN0.00.00.00.00.0Good
\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 12 } ] }, { "cell_type": "code", "source": [ "cs.drop_duplicates(inplace = True)" ], "metadata": { "id": "PAFIVsdECbG0" }, "execution_count": 39, "outputs": [] }, { "cell_type": "code", "source": [ "cs[cs.duplicated()]" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 131 }, "id": "AyInKX6MFEdT", "outputId": "af5b0727-87ca-4c5b-aac3-852ceeb1f46b" }, "execution_count": 40, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Empty DataFrame\n", "Columns: [NPA Status, RevolvingUtilizationOfUnsecuredLines, age, Gender, Region, MonthlyIncome, Rented_OwnHouse, Occupation, Education, NumberOfTime30-59DaysPastDueNotWorse, DebtRatio, MonthlyIncome.1, NumberOfOpenCreditLinesAndLoans, NumberOfTimes90DaysLate, NumberRealEstateLoansOrLines, NumberOfTime60-89DaysPastDueNotWorse, NumberOfDependents, Good_Bad]\n", "Index: []" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageGenderRegionMonthlyIncomeRented_OwnHouseOccupationEducationNumberOfTime30-59DaysPastDueNotWorseDebtRatioMonthlyIncome.1NumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependentsGood_Bad
\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 40 } ] }, { "cell_type": "code", "source": [ "cs.drop(['MonthlyIncome.1'],axis = 1, inplace = True)\n", "cs" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 505 }, "id": "iaI_zbkAHPK_", "outputId": "6049399a-bcac-4935-bc1c-237060871ae8" }, "execution_count": 41, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age Gender Region \\\n", "0 1 0.766127 45.0 Male South \n", "1 0 0.957151 40.0 Female South \n", "2 0 0.658180 38.0 Female South \n", "3 0 0.233810 30.0 Female South \n", "4 0 0.907239 49.0 Male South \n", "... ... ... ... ... ... \n", "149997 0 0.246044 58.0 Male North \n", "149998 0 0.000000 30.0 Male North \n", "149999 0 0.850283 64.0 Male North \n", "150000 0 NaN NaN NaN NaN \n", "150001 1 NaN NaN NaN NaN \n", "\n", " MonthlyIncome Rented_OwnHouse Occupation Education \\\n", "0 9120.0 Ownhouse Self_Emp Matric \n", "1 2600.0 Ownhouse Self_Emp Graduate \n", "2 3042.0 Ownhouse Self_Emp PhD \n", "3 3300.0 Ownhouse Self_Emp Professional \n", "4 63588.0 Ownhouse Self_Emp Post-Grad \n", "... ... ... ... ... \n", "149997 NaN Rented Officer2 Professional \n", "149998 5716.0 Rented Non-officer Professional \n", "149999 8158.0 Ownhouse Self_Emp Professional \n", "150000 NaN NaN NaN NaN \n", "150001 NaN NaN NaN NaN \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio \\\n", "0 2.0 0.802982 \n", "1 0.0 0.121876 \n", "2 1.0 0.085113 \n", "3 0.0 0.036050 \n", "4 1.0 0.024926 \n", "... ... ... \n", "149997 0.0 3870.000000 \n", "149998 0.0 0.000000 \n", "149999 0.0 0.249908 \n", "150000 NaN NaN \n", "150001 NaN NaN \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "... ... ... \n", "149997 18.0 0.0 \n", "149998 4.0 0.0 \n", "149999 8.0 0.0 \n", "150000 NaN NaN \n", "150001 NaN NaN \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "0 6.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 1.0 0.0 \n", "... ... ... \n", "149997 1.0 0.0 \n", "149998 0.0 0.0 \n", "149999 2.0 0.0 \n", "150000 NaN NaN \n", "150001 NaN NaN \n", "\n", " NumberOfDependents Good_Bad \n", "0 2.0 Bad \n", "1 1.0 Good \n", "2 0.0 Good \n", "3 0.0 Good \n", "4 0.0 Good \n", "... ... ... \n", "149997 0.0 Good \n", "149998 0.0 Good \n", "149999 0.0 Good \n", "150000 NaN NaN \n", "150001 NaN NaN \n", "\n", "[149982 rows x 17 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageGenderRegionMonthlyIncomeRented_OwnHouseOccupationEducationNumberOfTime30-59DaysPastDueNotWorseDebtRatioNumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependentsGood_Bad
010.76612745.0MaleSouth9120.0OwnhouseSelf_EmpMatric2.00.80298213.00.06.00.02.0Bad
100.95715140.0FemaleSouth2600.0OwnhouseSelf_EmpGraduate0.00.1218764.00.00.00.01.0Good
200.65818038.0FemaleSouth3042.0OwnhouseSelf_EmpPhD1.00.0851132.01.00.00.00.0Good
300.23381030.0FemaleSouth3300.0OwnhouseSelf_EmpProfessional0.00.0360505.00.00.00.00.0Good
400.90723949.0MaleSouth63588.0OwnhouseSelf_EmpPost-Grad1.00.0249267.00.01.00.00.0Good
......................................................
14999700.24604458.0MaleNorthNaNRentedOfficer2Professional0.03870.00000018.00.01.00.00.0Good
14999800.00000030.0MaleNorth5716.0RentedNon-officerProfessional0.00.0000004.00.00.00.00.0Good
14999900.85028364.0MaleNorth8158.0OwnhouseSelf_EmpProfessional0.00.2499088.00.02.00.00.0Good
1500000NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
1500011NaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", "

149982 rows × 17 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 41 } ] }, { "cell_type": "code", "source": [ "cs.dtypes" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "d9t-PEdZMLS2", "outputId": "ecc72043-6434-4c2a-8693-767e257f81ab" }, "execution_count": 42, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "NPA Status int64\n", "RevolvingUtilizationOfUnsecuredLines float64\n", "age float64\n", "Gender object\n", "Region object\n", "MonthlyIncome float64\n", "Rented_OwnHouse object\n", "Occupation object\n", "Education object\n", "NumberOfTime30-59DaysPastDueNotWorse float64\n", "DebtRatio float64\n", "NumberOfOpenCreditLinesAndLoans float64\n", "NumberOfTimes90DaysLate float64\n", "NumberRealEstateLoansOrLines float64\n", "NumberOfTime60-89DaysPastDueNotWorse float64\n", "NumberOfDependents float64\n", "Good_Bad object\n", "dtype: object" ] }, "metadata": {}, "execution_count": 42 } ] }, { "cell_type": "markdown", "source": [ "# **To Check for NULL Values And Remove Them**" ], "metadata": { "id": "tFLah5C_GOpY" } }, { "cell_type": "code", "source": [ "cs.isnull().sum()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "K5kqoDj1FUxx", "outputId": "b14a68bd-98d4-48f1-a0b8-d48ce040ecbe" }, "execution_count": 43, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "NPA Status 0\n", "RevolvingUtilizationOfUnsecuredLines 2\n", "age 2\n", "Gender 2\n", "Region 2\n", "MonthlyIncome 29717\n", "Rented_OwnHouse 2\n", "Occupation 2\n", "Education 2\n", "NumberOfTime30-59DaysPastDueNotWorse 2\n", "DebtRatio 2\n", "NumberOfOpenCreditLinesAndLoans 2\n", "NumberOfTimes90DaysLate 2\n", "NumberRealEstateLoansOrLines 2\n", "NumberOfTime60-89DaysPastDueNotWorse 2\n", "NumberOfDependents 3925\n", "Good_Bad 2\n", "dtype: int64" ] }, "metadata": {}, "execution_count": 43 } ] }, { "cell_type": "markdown", "source": [ "**Use Seaboarn Heatmap**" ], "metadata": { "id": "K7CH5mijILgS" } }, { "cell_type": "code", "source": [ "sns.heatmap(cs.isnull())" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 496 }, "id": "H74_8-sgG4kp", "outputId": "6b34c8d5-7972-4904-9b37-9d86dc79d9eb" }, "execution_count": 44, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 44 }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": { "needs_background": "light" } } ] }, { "cell_type": "code", "source": [ "cs1 = cs.fillna(cs.mode().iloc[0])" ], "metadata": { "id": "Q0eSaotfvIzU" }, "execution_count": 45, "outputs": [] }, { "cell_type": "code", "source": [ "\n", "cs1" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 505 }, "id": "mJSL8XOevcCG", "outputId": "4b503854-d885-4497-abcd-7f58c87a1232" }, "execution_count": 48, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age Gender \\\n", "0 1 0.766127 45.0 Male \n", "1 0 0.957151 40.0 Female \n", "2 0 0.658180 38.0 Female \n", "3 0 0.233810 30.0 Female \n", "4 0 0.907239 49.0 Male \n", "... ... ... ... ... \n", "149997 0 0.246044 58.0 Male \n", "149998 0 0.000000 30.0 Male \n", "149999 0 0.850283 64.0 Male \n", "150000 0 0.000000 49.0 Male \n", "150001 1 0.000000 49.0 Male \n", "\n", " Region MonthlyIncome Rented_OwnHouse Occupation Education \\\n", "0 South 9120.0 Ownhouse Self_Emp Matric \n", "1 South 2600.0 Ownhouse Self_Emp Graduate \n", "2 South 3042.0 Ownhouse Self_Emp PhD \n", "3 South 3300.0 Ownhouse Self_Emp Professional \n", "4 South 63588.0 Ownhouse Self_Emp Post-Grad \n", "... ... ... ... ... ... \n", "149997 North 5000.0 Rented Officer2 Professional \n", "149998 North 5716.0 Rented Non-officer Professional \n", "149999 North 8158.0 Ownhouse Self_Emp Professional \n", "150000 Central 5000.0 Ownhouse Self_Emp Professional \n", "150001 Central 5000.0 Ownhouse Self_Emp Professional \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio \\\n", "0 2.0 0.802982 \n", "1 0.0 0.121876 \n", "2 1.0 0.085113 \n", "3 0.0 0.036050 \n", "4 1.0 0.024926 \n", "... ... ... \n", "149997 0.0 3870.000000 \n", "149998 0.0 0.000000 \n", "149999 0.0 0.249908 \n", "150000 0.0 0.000000 \n", "150001 0.0 0.000000 \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "... ... ... \n", "149997 18.0 0.0 \n", "149998 4.0 0.0 \n", "149999 8.0 0.0 \n", "150000 6.0 0.0 \n", "150001 6.0 0.0 \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "0 6.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 1.0 0.0 \n", "... ... ... \n", "149997 1.0 0.0 \n", "149998 0.0 0.0 \n", "149999 2.0 0.0 \n", "150000 0.0 0.0 \n", "150001 0.0 0.0 \n", "\n", " NumberOfDependents Good_Bad \n", "0 2.0 Bad \n", "1 1.0 Good \n", "2 0.0 Good \n", "3 0.0 Good \n", "4 0.0 Good \n", "... ... ... \n", "149997 0.0 Good \n", "149998 0.0 Good \n", "149999 0.0 Good \n", "150000 0.0 Good \n", "150001 0.0 Good \n", "\n", "[149982 rows x 17 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageGenderRegionMonthlyIncomeRented_OwnHouseOccupationEducationNumberOfTime30-59DaysPastDueNotWorseDebtRatioNumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependentsGood_Bad
010.76612745.0MaleSouth9120.0OwnhouseSelf_EmpMatric2.00.80298213.00.06.00.02.0Bad
100.95715140.0FemaleSouth2600.0OwnhouseSelf_EmpGraduate0.00.1218764.00.00.00.01.0Good
200.65818038.0FemaleSouth3042.0OwnhouseSelf_EmpPhD1.00.0851132.01.00.00.00.0Good
300.23381030.0FemaleSouth3300.0OwnhouseSelf_EmpProfessional0.00.0360505.00.00.00.00.0Good
400.90723949.0MaleSouth63588.0OwnhouseSelf_EmpPost-Grad1.00.0249267.00.01.00.00.0Good
......................................................
14999700.24604458.0MaleNorth5000.0RentedOfficer2Professional0.03870.00000018.00.01.00.00.0Good
14999800.00000030.0MaleNorth5716.0RentedNon-officerProfessional0.00.0000004.00.00.00.00.0Good
14999900.85028364.0MaleNorth8158.0OwnhouseSelf_EmpProfessional0.00.2499088.00.02.00.00.0Good
15000000.00000049.0MaleCentral5000.0OwnhouseSelf_EmpProfessional0.00.0000006.00.00.00.00.0Good
15000110.00000049.0MaleCentral5000.0OwnhouseSelf_EmpProfessional0.00.0000006.00.00.00.00.0Good
\n", "

149982 rows × 17 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 48 } ] }, { "cell_type": "code", "source": [ "cs1.isnull().sum()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "R0mQzM_HyXDK", "outputId": "4df06f80-9efd-408c-a369-e2c279a03d68" }, "execution_count": 49, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "NPA Status 0\n", "RevolvingUtilizationOfUnsecuredLines 0\n", "age 0\n", "Gender 0\n", "Region 0\n", "MonthlyIncome 0\n", "Rented_OwnHouse 0\n", "Occupation 0\n", "Education 0\n", "NumberOfTime30-59DaysPastDueNotWorse 0\n", "DebtRatio 0\n", "NumberOfOpenCreditLinesAndLoans 0\n", "NumberOfTimes90DaysLate 0\n", "NumberRealEstateLoansOrLines 0\n", "NumberOfTime60-89DaysPastDueNotWorse 0\n", "NumberOfDependents 0\n", "Good_Bad 0\n", "dtype: int64" ] }, "metadata": {}, "execution_count": 49 } ] }, { "cell_type": "code", "source": [ "cs1['NumberOfTime30-59DaysPastDueNotWorse'].value_counts().sort_index()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "FxRspXlAylWB", "outputId": "e0975616-fde0-4c29-a858-fec44d0a9ca5" }, "execution_count": 52, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "0.0 126002\n", "1.0 16033\n", "2.0 4598\n", "3.0 1754\n", "4.0 747\n", "5.0 342\n", "6.0 140\n", "7.0 54\n", "8.0 25\n", "9.0 12\n", "10.0 4\n", "11.0 1\n", "12.0 2\n", "13.0 1\n", "96.0 5\n", "98.0 262\n", "Name: NumberOfTime30-59DaysPastDueNotWorse, dtype: int64" ] }, "metadata": {}, "execution_count": 52 } ] }, { "cell_type": "code", "source": [ "cs1['NumberOfTimes90DaysLate'].value_counts().sort_index()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "gJ5Kkfht0k0y", "outputId": "c98fce04-cf3c-47c0-a744-82c1b5a1db9c" }, "execution_count": 54, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "0.0 141646\n", "1.0 5243\n", "2.0 1555\n", "3.0 667\n", "4.0 291\n", "5.0 131\n", "6.0 80\n", "7.0 38\n", "8.0 21\n", "9.0 19\n", "10.0 8\n", "11.0 5\n", "12.0 2\n", "13.0 4\n", "14.0 2\n", "15.0 2\n", "17.0 1\n", "96.0 5\n", "98.0 262\n", "Name: NumberOfTimes90DaysLate, dtype: int64" ] }, "metadata": {}, "execution_count": 54 } ] }, { "cell_type": "code", "source": [ "cs1['NumberOfTime60-89DaysPastDueNotWorse'].value_counts().sort_index()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ByKC7gCf1LAs", "outputId": "2a19732e-0519-4e3b-aa0c-af36020a2bf6" }, "execution_count": 55, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "0.0 142380\n", "1.0 5731\n", "2.0 1118\n", "3.0 318\n", "4.0 105\n", "5.0 34\n", "6.0 16\n", "7.0 9\n", "8.0 2\n", "9.0 1\n", "11.0 1\n", "96.0 5\n", "98.0 262\n", "Name: NumberOfTime60-89DaysPastDueNotWorse, dtype: int64" ] }, "metadata": {}, "execution_count": 55 } ] }, { "cell_type": "code", "source": [ "\n", "cs2 = cs1.drop(cs1[cs1.NumberOfTimes90DaysLate > 17].index)\n" ], "metadata": { "id": "qum-odUuzLuZ" }, "execution_count": 59, "outputs": [] }, { "cell_type": "code", "source": [ "cs2['NumberOfTime60-89DaysPastDueNotWorse'].value_counts().sort_index()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MLkE1Ab32mYL", "outputId": "f07646dd-b677-4227-9f00-84c1bf1e790c" }, "execution_count": 61, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "0.0 142380\n", "1.0 5731\n", "2.0 1118\n", "3.0 318\n", "4.0 105\n", "5.0 34\n", "6.0 16\n", "7.0 9\n", "8.0 2\n", "9.0 1\n", "11.0 1\n", "Name: NumberOfTime60-89DaysPastDueNotWorse, dtype: int64" ] }, "metadata": {}, "execution_count": 61 } ] }, { "cell_type": "code", "source": [ "cs2" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 505 }, "id": "BzRE_s9h281a", "outputId": "287cd705-c9d7-4d8b-e480-54696d649690" }, "execution_count": 62, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age Gender \\\n", "0 1 0.766127 45.0 Male \n", "1 0 0.957151 40.0 Female \n", "2 0 0.658180 38.0 Female \n", "3 0 0.233810 30.0 Female \n", "4 0 0.907239 49.0 Male \n", "... ... ... ... ... \n", "149997 0 0.246044 58.0 Male \n", "149998 0 0.000000 30.0 Male \n", "149999 0 0.850283 64.0 Male \n", "150000 0 0.000000 49.0 Male \n", "150001 1 0.000000 49.0 Male \n", "\n", " Region MonthlyIncome Rented_OwnHouse Occupation Education \\\n", "0 South 9120.0 Ownhouse Self_Emp Matric \n", "1 South 2600.0 Ownhouse Self_Emp Graduate \n", "2 South 3042.0 Ownhouse Self_Emp PhD \n", "3 South 3300.0 Ownhouse Self_Emp Professional \n", "4 South 63588.0 Ownhouse Self_Emp Post-Grad \n", "... ... ... ... ... ... \n", "149997 North 5000.0 Rented Officer2 Professional \n", "149998 North 5716.0 Rented Non-officer Professional \n", "149999 North 8158.0 Ownhouse Self_Emp Professional \n", "150000 Central 5000.0 Ownhouse Self_Emp Professional \n", "150001 Central 5000.0 Ownhouse Self_Emp Professional \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio \\\n", "0 2.0 0.802982 \n", "1 0.0 0.121876 \n", "2 1.0 0.085113 \n", "3 0.0 0.036050 \n", "4 1.0 0.024926 \n", "... ... ... \n", "149997 0.0 3870.000000 \n", "149998 0.0 0.000000 \n", "149999 0.0 0.249908 \n", "150000 0.0 0.000000 \n", "150001 0.0 0.000000 \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "... ... ... \n", "149997 18.0 0.0 \n", "149998 4.0 0.0 \n", "149999 8.0 0.0 \n", "150000 6.0 0.0 \n", "150001 6.0 0.0 \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "0 6.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 1.0 0.0 \n", "... ... ... \n", "149997 1.0 0.0 \n", "149998 0.0 0.0 \n", "149999 2.0 0.0 \n", "150000 0.0 0.0 \n", "150001 0.0 0.0 \n", "\n", " NumberOfDependents Good_Bad \n", "0 2.0 Bad \n", "1 1.0 Good \n", "2 0.0 Good \n", "3 0.0 Good \n", "4 0.0 Good \n", "... ... ... \n", "149997 0.0 Good \n", "149998 0.0 Good \n", "149999 0.0 Good \n", "150000 0.0 Good \n", "150001 0.0 Good \n", "\n", "[149715 rows x 17 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageGenderRegionMonthlyIncomeRented_OwnHouseOccupationEducationNumberOfTime30-59DaysPastDueNotWorseDebtRatioNumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependentsGood_Bad
010.76612745.0MaleSouth9120.0OwnhouseSelf_EmpMatric2.00.80298213.00.06.00.02.0Bad
100.95715140.0FemaleSouth2600.0OwnhouseSelf_EmpGraduate0.00.1218764.00.00.00.01.0Good
200.65818038.0FemaleSouth3042.0OwnhouseSelf_EmpPhD1.00.0851132.01.00.00.00.0Good
300.23381030.0FemaleSouth3300.0OwnhouseSelf_EmpProfessional0.00.0360505.00.00.00.00.0Good
400.90723949.0MaleSouth63588.0OwnhouseSelf_EmpPost-Grad1.00.0249267.00.01.00.00.0Good
......................................................
14999700.24604458.0MaleNorth5000.0RentedOfficer2Professional0.03870.00000018.00.01.00.00.0Good
14999800.00000030.0MaleNorth5716.0RentedNon-officerProfessional0.00.0000004.00.00.00.00.0Good
14999900.85028364.0MaleNorth8158.0OwnhouseSelf_EmpProfessional0.00.2499088.00.02.00.00.0Good
15000000.00000049.0MaleCentral5000.0OwnhouseSelf_EmpProfessional0.00.0000006.00.00.00.00.0Good
15000110.00000049.0MaleCentral5000.0OwnhouseSelf_EmpProfessional0.00.0000006.00.00.00.00.0Good
\n", "

149715 rows × 17 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 62 } ] }, { "cell_type": "code", "source": [ "sns.heatmap(cs2.isnull())" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 496 }, "id": "1BNGVJbW3B6x", "outputId": "659303bd-c8b6-4900-eab1-5c804a84164b" }, "execution_count": 64, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 64 }, { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": { "needs_background": "light" } } ] }, { "cell_type": "code", "source": [ "cs2" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 505 }, "id": "wzQ-pyD-6twG", "outputId": "98ef8fbe-31f0-4255-93b5-8cd34f5734f9" }, "execution_count": 71, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age Gender \\\n", "0 1 0.766127 45.0 Male \n", "1 0 0.957151 40.0 Female \n", "2 0 0.658180 38.0 Female \n", "3 0 0.233810 30.0 Female \n", "4 0 0.907239 49.0 Male \n", "... ... ... ... ... \n", "149997 0 0.246044 58.0 Male \n", "149998 0 0.000000 30.0 Male \n", "149999 0 0.850283 64.0 Male \n", "150000 0 0.000000 49.0 Male \n", "150001 1 0.000000 49.0 Male \n", "\n", " Region MonthlyIncome Rented_OwnHouse Occupation Education \\\n", "0 South 9120.0 Ownhouse Self_Emp Matric \n", "1 South 2600.0 Ownhouse Self_Emp Graduate \n", "2 South 3042.0 Ownhouse Self_Emp PhD \n", "3 South 3300.0 Ownhouse Self_Emp Professional \n", "4 South 63588.0 Ownhouse Self_Emp Post-Grad \n", "... ... ... ... ... ... \n", "149997 North 5000.0 Rented Officer2 Professional \n", "149998 North 5716.0 Rented Non-officer Professional \n", "149999 North 8158.0 Ownhouse Self_Emp Professional \n", "150000 Central 5000.0 Ownhouse Self_Emp Professional \n", "150001 Central 5000.0 Ownhouse Self_Emp Professional \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio \\\n", "0 2.0 0.802982 \n", "1 0.0 0.121876 \n", "2 1.0 0.085113 \n", "3 0.0 0.036050 \n", "4 1.0 0.024926 \n", "... ... ... \n", "149997 0.0 3870.000000 \n", "149998 0.0 0.000000 \n", "149999 0.0 0.249908 \n", "150000 0.0 0.000000 \n", "150001 0.0 0.000000 \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "... ... ... \n", "149997 18.0 0.0 \n", "149998 4.0 0.0 \n", "149999 8.0 0.0 \n", "150000 6.0 0.0 \n", "150001 6.0 0.0 \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "0 6.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 1.0 0.0 \n", "... ... ... \n", "149997 1.0 0.0 \n", "149998 0.0 0.0 \n", "149999 2.0 0.0 \n", "150000 0.0 0.0 \n", "150001 0.0 0.0 \n", "\n", " NumberOfDependents Good_Bad \n", "0 2.0 Bad \n", "1 1.0 Good \n", "2 0.0 Good \n", "3 0.0 Good \n", "4 0.0 Good \n", "... ... ... \n", "149997 0.0 Good \n", "149998 0.0 Good \n", "149999 0.0 Good \n", "150000 0.0 Good \n", "150001 0.0 Good \n", "\n", "[149715 rows x 17 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageGenderRegionMonthlyIncomeRented_OwnHouseOccupationEducationNumberOfTime30-59DaysPastDueNotWorseDebtRatioNumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependentsGood_Bad
010.76612745.0MaleSouth9120.0OwnhouseSelf_EmpMatric2.00.80298213.00.06.00.02.0Bad
100.95715140.0FemaleSouth2600.0OwnhouseSelf_EmpGraduate0.00.1218764.00.00.00.01.0Good
200.65818038.0FemaleSouth3042.0OwnhouseSelf_EmpPhD1.00.0851132.01.00.00.00.0Good
300.23381030.0FemaleSouth3300.0OwnhouseSelf_EmpProfessional0.00.0360505.00.00.00.00.0Good
400.90723949.0MaleSouth63588.0OwnhouseSelf_EmpPost-Grad1.00.0249267.00.01.00.00.0Good
......................................................
14999700.24604458.0MaleNorth5000.0RentedOfficer2Professional0.03870.00000018.00.01.00.00.0Good
14999800.00000030.0MaleNorth5716.0RentedNon-officerProfessional0.00.0000004.00.00.00.00.0Good
14999900.85028364.0MaleNorth8158.0OwnhouseSelf_EmpProfessional0.00.2499088.00.02.00.00.0Good
15000000.00000049.0MaleCentral5000.0OwnhouseSelf_EmpProfessional0.00.0000006.00.00.00.00.0Good
15000110.00000049.0MaleCentral5000.0OwnhouseSelf_EmpProfessional0.00.0000006.00.00.00.00.0Good
\n", "

149715 rows × 17 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 71 } ] }, { "cell_type": "code", "source": [ "gender = pd.get_dummies(cs2['Gender'], drop_first = True)\n", "gender" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 424 }, "id": "5NtlKb5N38KG", "outputId": "ec9753e1-354f-43e1-ccdd-6530a62acd4b" }, "execution_count": 72, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Male\n", "0 1\n", "1 0\n", "2 0\n", "3 0\n", "4 1\n", "... ...\n", "149997 1\n", "149998 1\n", "149999 1\n", "150000 1\n", "150001 1\n", "\n", "[149715 rows x 1 columns]" ], "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", "
Male
01
10
20
30
41
......
1499971
1499981
1499991
1500001
1500011
\n", "

149715 rows × 1 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 72 } ] }, { "cell_type": "code", "source": [ "region = pd.get_dummies(cs2['Region'], drop_first= True)\n", "region" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 424 }, "id": "p5WARv_T7Unq", "outputId": "9c0b48e1-2f43-47fa-b8d0-575d364d7d5c" }, "execution_count": 73, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " East North South West\n", "0 0 0 1 0\n", "1 0 0 1 0\n", "2 0 0 1 0\n", "3 0 0 1 0\n", "4 0 0 1 0\n", "... ... ... ... ...\n", "149997 0 1 0 0\n", "149998 0 1 0 0\n", "149999 0 1 0 0\n", "150000 0 0 0 0\n", "150001 0 0 0 0\n", "\n", "[149715 rows x 4 columns]" ], "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", "
EastNorthSouthWest
00010
10010
20010
30010
40010
...............
1499970100
1499980100
1499990100
1500000000
1500010000
\n", "

149715 rows × 4 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 73 } ] }, { "cell_type": "code", "source": [ "rent = pd.get_dummies(cs2['Rented_OwnHouse'], drop_first = True)\n", "rent" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 424 }, "id": "uZKLrFxi7mZt", "outputId": "4d5d108d-63b7-42ca-a75b-5d5ca1848be2" }, "execution_count": 74, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Rented\n", "0 0\n", "1 0\n", "2 0\n", "3 0\n", "4 0\n", "... ...\n", "149997 1\n", "149998 1\n", "149999 0\n", "150000 0\n", "150001 0\n", "\n", "[149715 rows x 1 columns]" ], "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", "
Rented
00
10
20
30
40
......
1499971
1499981
1499990
1500000
1500010
\n", "

149715 rows × 1 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 74 } ] }, { "cell_type": "code", "source": [ "occupation = pd.get_dummies(cs2['Occupation'], drop_first = True)\n", "occupation" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 424 }, "id": "5HAxYYmB79Ke", "outputId": "91ef3b85-2c30-4587-b179-53b7ba3920c8" }, "execution_count": 76, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Officer1 Officer2 Officer3 Self_Emp\n", "0 0 0 0 1\n", "1 0 0 0 1\n", "2 0 0 0 1\n", "3 0 0 0 1\n", "4 0 0 0 1\n", "... ... ... ... ...\n", "149997 0 1 0 0\n", "149998 0 0 0 0\n", "149999 0 0 0 1\n", "150000 0 0 0 1\n", "150001 0 0 0 1\n", "\n", "[149715 rows x 4 columns]" ], "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", "
Officer1Officer2Officer3Self_Emp
00001
10001
20001
30001
40001
...............
1499970100
1499980000
1499990001
1500000001
1500010001
\n", "

149715 rows × 4 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 76 } ] }, { "cell_type": "code", "source": [ "edu = pd.get_dummies(cs2['Education'], drop_first = True)\n", "edu" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 424 }, "id": "pZ0QwMtP8OUj", "outputId": "63684aa1-6eb4-4a58-d731-a63d6a6975fd" }, "execution_count": 77, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Matric PhD Post-Grad Professional\n", "0 1 0 0 0\n", "1 0 0 0 0\n", "2 0 1 0 0\n", "3 0 0 0 1\n", "4 0 0 1 0\n", "... ... ... ... ...\n", "149997 0 0 0 1\n", "149998 0 0 0 1\n", "149999 0 0 0 1\n", "150000 0 0 0 1\n", "150001 0 0 0 1\n", "\n", "[149715 rows x 4 columns]" ], "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", "
MatricPhDPost-GradProfessional
01000
10000
20100
30001
40010
...............
1499970001
1499980001
1499990001
1500000001
1500010001
\n", "

149715 rows × 4 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 77 } ] }, { "cell_type": "code", "source": [ "goodbad = pd.get_dummies(cs2['Good_Bad'],drop_first =True)\n", "goodbad" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 424 }, "id": "J6Zh0Ynx8hPk", "outputId": "892befd3-37ea-4a9f-db18-f86a616b4c90" }, "execution_count": 78, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " Good\n", "0 0\n", "1 1\n", "2 1\n", "3 1\n", "4 1\n", "... ...\n", "149997 1\n", "149998 1\n", "149999 1\n", "150000 1\n", "150001 1\n", "\n", "[149715 rows x 1 columns]" ], "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", "
Good
00
11
21
31
41
......
1499971
1499981
1499991
1500001
1500011
\n", "

149715 rows × 1 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 78 } ] }, { "cell_type": "code", "source": [ "cs3 = cs2.drop(['Gender','Education','Occupation','Region','Rented_OwnHouse'],axis = 1)\n", "cs3.drop(['Good_Bad'],axis = 1, inplace = True)\n", "cs3" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 505 }, "id": "QCeeKse2825j", "outputId": "9b006f77-63da-46ba-9135-9f7edad089f5" }, "execution_count": 81, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age MonthlyIncome \\\n", "0 1 0.766127 45.0 9120.0 \n", "1 0 0.957151 40.0 2600.0 \n", "2 0 0.658180 38.0 3042.0 \n", "3 0 0.233810 30.0 3300.0 \n", "4 0 0.907239 49.0 63588.0 \n", "... ... ... ... ... \n", "149997 0 0.246044 58.0 5000.0 \n", "149998 0 0.000000 30.0 5716.0 \n", "149999 0 0.850283 64.0 8158.0 \n", "150000 0 0.000000 49.0 5000.0 \n", "150001 1 0.000000 49.0 5000.0 \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio \\\n", "0 2.0 0.802982 \n", "1 0.0 0.121876 \n", "2 1.0 0.085113 \n", "3 0.0 0.036050 \n", "4 1.0 0.024926 \n", "... ... ... \n", "149997 0.0 3870.000000 \n", "149998 0.0 0.000000 \n", "149999 0.0 0.249908 \n", "150000 0.0 0.000000 \n", "150001 0.0 0.000000 \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "... ... ... \n", "149997 18.0 0.0 \n", "149998 4.0 0.0 \n", "149999 8.0 0.0 \n", "150000 6.0 0.0 \n", "150001 6.0 0.0 \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "0 6.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 1.0 0.0 \n", "... ... ... \n", "149997 1.0 0.0 \n", "149998 0.0 0.0 \n", "149999 2.0 0.0 \n", "150000 0.0 0.0 \n", "150001 0.0 0.0 \n", "\n", " NumberOfDependents \n", "0 2.0 \n", "1 1.0 \n", "2 0.0 \n", "3 0.0 \n", "4 0.0 \n", "... ... \n", "149997 0.0 \n", "149998 0.0 \n", "149999 0.0 \n", "150000 0.0 \n", "150001 0.0 \n", "\n", "[149715 rows x 11 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageMonthlyIncomeNumberOfTime30-59DaysPastDueNotWorseDebtRatioNumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorseNumberOfDependents
010.76612745.09120.02.00.80298213.00.06.00.02.0
100.95715140.02600.00.00.1218764.00.00.00.01.0
200.65818038.03042.01.00.0851132.01.00.00.00.0
300.23381030.03300.00.00.0360505.00.00.00.00.0
400.90723949.063588.01.00.0249267.00.01.00.00.0
....................................
14999700.24604458.05000.00.03870.00000018.00.01.00.00.0
14999800.00000030.05716.00.00.0000004.00.00.00.00.0
14999900.85028364.08158.00.00.2499088.00.02.00.00.0
15000000.00000049.05000.00.00.0000006.00.00.00.00.0
15000110.00000049.05000.00.00.0000006.00.00.00.00.0
\n", "

149715 rows × 11 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 81 } ] }, { "cell_type": "code", "source": [ "cs3 = pd.concat([cs3,gender,edu,region,goodbad,occupation,rent],axis = 1)\n", "cs3" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 505 }, "id": "o2vctHxR9YNw", "outputId": "8ebca3ae-c77a-4032-ee1e-02c470730744" }, "execution_count": 82, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age MonthlyIncome \\\n", "0 1 0.766127 45.0 9120.0 \n", "1 0 0.957151 40.0 2600.0 \n", "2 0 0.658180 38.0 3042.0 \n", "3 0 0.233810 30.0 3300.0 \n", "4 0 0.907239 49.0 63588.0 \n", "... ... ... ... ... \n", "149997 0 0.246044 58.0 5000.0 \n", "149998 0 0.000000 30.0 5716.0 \n", "149999 0 0.850283 64.0 8158.0 \n", "150000 0 0.000000 49.0 5000.0 \n", "150001 1 0.000000 49.0 5000.0 \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio \\\n", "0 2.0 0.802982 \n", "1 0.0 0.121876 \n", "2 1.0 0.085113 \n", "3 0.0 0.036050 \n", "4 1.0 0.024926 \n", "... ... ... \n", "149997 0.0 3870.000000 \n", "149998 0.0 0.000000 \n", "149999 0.0 0.249908 \n", "150000 0.0 0.000000 \n", "150001 0.0 0.000000 \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "... ... ... \n", "149997 18.0 0.0 \n", "149998 4.0 0.0 \n", "149999 8.0 0.0 \n", "150000 6.0 0.0 \n", "150001 6.0 0.0 \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse \\\n", "0 6.0 0.0 \n", "1 0.0 0.0 \n", "2 0.0 0.0 \n", "3 0.0 0.0 \n", "4 1.0 0.0 \n", "... ... ... \n", "149997 1.0 0.0 \n", "149998 0.0 0.0 \n", "149999 2.0 0.0 \n", "150000 0.0 0.0 \n", "150001 0.0 0.0 \n", "\n", " ... East North South West Good Officer1 Officer2 Officer3 \\\n", "0 ... 0 0 1 0 0 0 0 0 \n", "1 ... 0 0 1 0 1 0 0 0 \n", "2 ... 0 0 1 0 1 0 0 0 \n", "3 ... 0 0 1 0 1 0 0 0 \n", "4 ... 0 0 1 0 1 0 0 0 \n", "... ... ... ... ... ... ... ... ... ... \n", "149997 ... 0 1 0 0 1 0 1 0 \n", "149998 ... 0 1 0 0 1 0 0 0 \n", "149999 ... 0 1 0 0 1 0 0 0 \n", "150000 ... 0 0 0 0 1 0 0 0 \n", "150001 ... 0 0 0 0 1 0 0 0 \n", "\n", " Self_Emp Rented \n", "0 1 0 \n", "1 1 0 \n", "2 1 0 \n", "3 1 0 \n", "4 1 0 \n", "... ... ... \n", "149997 0 1 \n", "149998 0 1 \n", "149999 1 0 \n", "150000 1 0 \n", "150001 1 0 \n", "\n", "[149715 rows x 26 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageMonthlyIncomeNumberOfTime30-59DaysPastDueNotWorseDebtRatioNumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorse...EastNorthSouthWestGoodOfficer1Officer2Officer3Self_EmpRented
010.76612745.09120.02.00.80298213.00.06.00.0...0010000010
100.95715140.02600.00.00.1218764.00.00.00.0...0010100010
200.65818038.03042.01.00.0851132.01.00.00.0...0010100010
300.23381030.03300.00.00.0360505.00.00.00.0...0010100010
400.90723949.063588.01.00.0249267.00.01.00.0...0010100010
..................................................................
14999700.24604458.05000.00.03870.00000018.00.01.00.0...0100101001
14999800.00000030.05716.00.00.0000004.00.00.00.0...0100100001
14999900.85028364.08158.00.00.2499088.00.02.00.0...0100100010
15000000.00000049.05000.00.00.0000006.00.00.00.0...0000100010
15000110.00000049.05000.00.00.0000006.00.00.00.0...0000100010
\n", "

149715 rows × 26 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 82 } ] }, { "cell_type": "code", "source": [ "df = cs3['Good']\n", "idf = cs3.drop(['Good'],axis =1)" ], "metadata": { "id": "byajtJH_-Phk" }, "execution_count": 88, "outputs": [] }, { "cell_type": "code", "source": [ "df.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "coFBZi7B-rUT", "outputId": "36aee4c1-feec-40f2-e335-37bb0fe9b415" }, "execution_count": 89, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "0 0\n", "1 1\n", "2 1\n", "3 1\n", "4 1\n", "Name: Good, dtype: uint8" ] }, "metadata": {}, "execution_count": 89 } ] }, { "cell_type": "code", "source": [ "idf.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 317 }, "id": "eBf8SnwmBMfJ", "outputId": "f767a7af-4906-4c0e-ed3c-aa3fce6a4b3a" }, "execution_count": 90, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " NPA Status RevolvingUtilizationOfUnsecuredLines age MonthlyIncome \\\n", "0 1 0.766127 45.0 9120.0 \n", "1 0 0.957151 40.0 2600.0 \n", "2 0 0.658180 38.0 3042.0 \n", "3 0 0.233810 30.0 3300.0 \n", "4 0 0.907239 49.0 63588.0 \n", "\n", " NumberOfTime30-59DaysPastDueNotWorse DebtRatio \\\n", "0 2.0 0.802982 \n", "1 0.0 0.121876 \n", "2 1.0 0.085113 \n", "3 0.0 0.036050 \n", "4 1.0 0.024926 \n", "\n", " NumberOfOpenCreditLinesAndLoans NumberOfTimes90DaysLate \\\n", "0 13.0 0.0 \n", "1 4.0 0.0 \n", "2 2.0 1.0 \n", "3 5.0 0.0 \n", "4 7.0 0.0 \n", "\n", " NumberRealEstateLoansOrLines NumberOfTime60-89DaysPastDueNotWorse ... \\\n", "0 6.0 0.0 ... \n", "1 0.0 0.0 ... \n", "2 0.0 0.0 ... \n", "3 0.0 0.0 ... \n", "4 1.0 0.0 ... \n", "\n", " Professional East North South West Officer1 Officer2 Officer3 \\\n", "0 0 0 0 1 0 0 0 0 \n", "1 0 0 0 1 0 0 0 0 \n", "2 0 0 0 1 0 0 0 0 \n", "3 1 0 0 1 0 0 0 0 \n", "4 0 0 0 1 0 0 0 0 \n", "\n", " Self_Emp Rented \n", "0 1 0 \n", "1 1 0 \n", "2 1 0 \n", "3 1 0 \n", "4 1 0 \n", "\n", "[5 rows x 25 columns]" ], "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", "
NPA StatusRevolvingUtilizationOfUnsecuredLinesageMonthlyIncomeNumberOfTime30-59DaysPastDueNotWorseDebtRatioNumberOfOpenCreditLinesAndLoansNumberOfTimes90DaysLateNumberRealEstateLoansOrLinesNumberOfTime60-89DaysPastDueNotWorse...ProfessionalEastNorthSouthWestOfficer1Officer2Officer3Self_EmpRented
010.76612745.09120.02.00.80298213.00.06.00.0...0001000010
100.95715140.02600.00.00.1218764.00.00.00.0...0001000010
200.65818038.03042.01.00.0851132.01.00.00.0...0001000010
300.23381030.03300.00.00.0360505.00.00.00.0...1001000010
400.90723949.063588.01.00.0249267.00.01.00.0...0001000010
\n", "

5 rows × 25 columns

\n", "
\n", " \n", " \n", " \n", "\n", " \n", "
\n", "
\n", " " ] }, "metadata": {}, "execution_count": 90 } ] }, { "cell_type": "code", "source": [ "from sklearn.model_selection import train_test_split" ], "metadata": { "id": "qclh_1JoBPYs" }, "execution_count": 92, "outputs": [] }, { "cell_type": "code", "source": [ "x_train,x_test,y_train,y_test = train_test_split(idf,df,test_size = 0.25, shuffle=101)" ], "metadata": { "id": "MbGopmYuBbcy" }, "execution_count": 104, "outputs": [] }, { "cell_type": "code", "source": [ "x_train.shape" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "1tNTaxczCC1h", "outputId": "738d7569-6254-42c1-e20e-09668dabe595" }, "execution_count": 105, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "(112286, 25)" ] }, "metadata": {}, "execution_count": 105 } ] }, { "cell_type": "code", "source": [ "x_test.shape" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "zhBT_3pSCGJh", "outputId": "d276f962-182d-421d-ca95-d3442ef368d7" }, "execution_count": 106, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "(37429, 25)" ] }, "metadata": {}, "execution_count": 106 } ] }, { "cell_type": "code", "source": [ "y_train.shape" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Wu0mlP5ICQBP", "outputId": "5d785245-c2fc-4567-8b60-e41cc58b946a" }, "execution_count": 107, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "(112286,)" ] }, "metadata": {}, "execution_count": 107 } ] }, { "cell_type": "code", "source": [ "y_test.shape" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "llsZXXg1CShI", "outputId": "4f10e511-c074-4d88-dbf4-67a0dfd2f1cf" }, "execution_count": 108, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "(37429,)" ] }, "metadata": {}, "execution_count": 108 } ] }, { "cell_type": "code", "source": [ "from sklearn.linear_model import LogisticRegression" ], "metadata": { "id": "ZcDo3gvxCV-w" }, "execution_count": 109, "outputs": [] }, { "cell_type": "code", "source": [ "cs3_model = LogisticRegression()" ], "metadata": { "id": "H3VlB1sgCj-x" }, "execution_count": 110, "outputs": [] }, { "cell_type": "code", "source": [ "cs3_model.fit(x_train, y_train)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "9BdKvNEXCtiB", "outputId": "28dc24df-6215-4f38-d9c9-82bec2679a8f" }, "execution_count": 111, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.7/dist-packages/sklearn/linear_model/_logistic.py:818: ConvergenceWarning: lbfgs failed to converge (status=1):\n", "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n", "\n", "Increase the number of iterations (max_iter) or scale the data as shown in:\n", " https://scikit-learn.org/stable/modules/preprocessing.html\n", "Please also refer to the documentation for alternative solver options:\n", " https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n", " extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG,\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "LogisticRegression()" ] }, "metadata": {}, "execution_count": 111 } ] }, { "cell_type": "code", "source": [ "cs3_model.score(idf, df)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "OOSaz-0sC12H", "outputId": "0dcf6476-5362-4fd7-8af3-3a0832dc833e" }, "execution_count": 112, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "0.9526767524964098" ] }, "metadata": {}, "execution_count": 112 } ] }, { "cell_type": "code", "source": [ "" ], "metadata": { "id": "qxRB984mDXye" }, "execution_count": null, "outputs": [] } ] }