{ "cells": [ { "cell_type": "markdown", "id": "871b7ef6", "metadata": {}, "source": [ "## Problem Statement:\n", "1. Identify why the attrition is higher ?\n", "2. Identify the root cause of attrition ?" ] }, { "cell_type": "code", "execution_count": 2, "id": "01798366", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T15:42:02.179675Z", "start_time": "2022-10-15T15:42:00.905817Z" } }, "outputs": [], "source": [ "import pandas as pd \n", "import numpy as np \n", "import matplotlib.pyplot as plt \n", "import seaborn as sns " ] }, { "cell_type": "code", "execution_count": 3, "id": "cd7b2e44", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T15:42:05.411725Z", "start_time": "2022-10-15T15:42:03.725746Z" } }, "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", "
EmployeeNumberAttritionAgeBusinessTravelDailyRateDepartmentDistanceFromHomeEducationEducationFieldEmployeeCount...RelationshipSatisfactionStandardHoursStockOptionLevelTotalWorkingYearsTrainingTimesLastYearWorkLifeBalanceYearsAtCompanyYearsInCurrentRoleYearsSinceLastPromotionYearsWithCurrManager
01Yes41Travel_Rarely1102Sales12Life Sciences1...18008016405
12No49Travel_Frequently279Research & Development81Life Sciences1...4801103310717
23Yes37Travel_Rarely1373Research & Development22Other1...28007330000
34No33Travel_Frequently1392Research & Development34Life Sciences1...38008338730
45No27Travel_Rarely591Research & Development21Medical1...48016332222
\n", "

5 rows × 35 columns

\n", "
" ], "text/plain": [ " EmployeeNumber Attrition Age BusinessTravel DailyRate \\\n", "0 1 Yes 41 Travel_Rarely 1102 \n", "1 2 No 49 Travel_Frequently 279 \n", "2 3 Yes 37 Travel_Rarely 1373 \n", "3 4 No 33 Travel_Frequently 1392 \n", "4 5 No 27 Travel_Rarely 591 \n", "\n", " Department DistanceFromHome Education EducationField \\\n", "0 Sales 1 2 Life Sciences \n", "1 Research & Development 8 1 Life Sciences \n", "2 Research & Development 2 2 Other \n", "3 Research & Development 3 4 Life Sciences \n", "4 Research & Development 2 1 Medical \n", "\n", " EmployeeCount ... RelationshipSatisfaction StandardHours \\\n", "0 1 ... 1 80 \n", "1 1 ... 4 80 \n", "2 1 ... 2 80 \n", "3 1 ... 3 80 \n", "4 1 ... 4 80 \n", "\n", " StockOptionLevel TotalWorkingYears TrainingTimesLastYear WorkLifeBalance \\\n", "0 0 8 0 1 \n", "1 1 10 3 3 \n", "2 0 7 3 3 \n", "3 0 8 3 3 \n", "4 1 6 3 3 \n", "\n", " YearsAtCompany YearsInCurrentRole YearsSinceLastPromotion \\\n", "0 6 4 0 \n", "1 10 7 1 \n", "2 0 0 0 \n", "3 8 7 3 \n", "4 2 2 2 \n", "\n", " YearsWithCurrManager \n", "0 5 \n", "1 7 \n", "2 0 \n", "3 0 \n", "4 2 \n", "\n", "[5 rows x 35 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset = pd.read_excel(\"/Users/rishavdas/Downloads/Data/HR_Employee_Attrition-1.xlsx\")\n", "dataset.head()" ] }, { "cell_type": "code", "execution_count": 3, "id": "923e5551", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T15:42:09.096194Z", "start_time": "2022-10-15T15:42:09.091856Z" } }, "outputs": [ { "data": { "text/plain": [ "(2940, 35)" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.shape" ] }, { "cell_type": "code", "execution_count": 4, "id": "efbe0080", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T15:42:21.673316Z", "start_time": "2022-10-15T15:42:21.653053Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 2940 entries, 0 to 2939\n", "Data columns (total 35 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 EmployeeNumber 2940 non-null int64 \n", " 1 Attrition 2940 non-null object\n", " 2 Age 2940 non-null int64 \n", " 3 BusinessTravel 2940 non-null object\n", " 4 DailyRate 2940 non-null int64 \n", " 5 Department 2940 non-null object\n", " 6 DistanceFromHome 2940 non-null int64 \n", " 7 Education 2940 non-null int64 \n", " 8 EducationField 2940 non-null object\n", " 9 EmployeeCount 2940 non-null int64 \n", " 10 EnvironmentSatisfaction 2940 non-null int64 \n", " 11 Gender 2940 non-null object\n", " 12 HourlyRate 2940 non-null int64 \n", " 13 JobInvolvement 2940 non-null int64 \n", " 14 JobLevel 2940 non-null int64 \n", " 15 JobRole 2940 non-null object\n", " 16 JobSatisfaction 2940 non-null int64 \n", " 17 MaritalStatus 2940 non-null object\n", " 18 MonthlyIncome 2940 non-null int64 \n", " 19 MonthlyRate 2940 non-null int64 \n", " 20 NumCompaniesWorked 2940 non-null int64 \n", " 21 Over18 2940 non-null object\n", " 22 OverTime 2940 non-null object\n", " 23 PercentSalaryHike 2940 non-null int64 \n", " 24 PerformanceRating 2940 non-null int64 \n", " 25 RelationshipSatisfaction 2940 non-null int64 \n", " 26 StandardHours 2940 non-null int64 \n", " 27 StockOptionLevel 2940 non-null int64 \n", " 28 TotalWorkingYears 2940 non-null int64 \n", " 29 TrainingTimesLastYear 2940 non-null int64 \n", " 30 WorkLifeBalance 2940 non-null int64 \n", " 31 YearsAtCompany 2940 non-null int64 \n", " 32 YearsInCurrentRole 2940 non-null int64 \n", " 33 YearsSinceLastPromotion 2940 non-null int64 \n", " 34 YearsWithCurrManager 2940 non-null int64 \n", "dtypes: int64(26), object(9)\n", "memory usage: 804.0+ KB\n" ] } ], "source": [ "dataset.info()" ] }, { "cell_type": "code", "execution_count": 5, "id": "91c9c990", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T15:42:37.849973Z", "start_time": "2022-10-15T15:42:37.836598Z" } }, "outputs": [ { "data": { "text/plain": [ "EmployeeNumber 0\n", "Attrition 0\n", "Age 0\n", "BusinessTravel 0\n", "DailyRate 0\n", "Department 0\n", "DistanceFromHome 0\n", "Education 0\n", "EducationField 0\n", "EmployeeCount 0\n", "EnvironmentSatisfaction 0\n", "Gender 0\n", "HourlyRate 0\n", "JobInvolvement 0\n", "JobLevel 0\n", "JobRole 0\n", "JobSatisfaction 0\n", "MaritalStatus 0\n", "MonthlyIncome 0\n", "MonthlyRate 0\n", "NumCompaniesWorked 0\n", "Over18 0\n", "OverTime 0\n", "PercentSalaryHike 0\n", "PerformanceRating 0\n", "RelationshipSatisfaction 0\n", "StandardHours 0\n", "StockOptionLevel 0\n", "TotalWorkingYears 0\n", "TrainingTimesLastYear 0\n", "WorkLifeBalance 0\n", "YearsAtCompany 0\n", "YearsInCurrentRole 0\n", "YearsSinceLastPromotion 0\n", "YearsWithCurrManager 0\n", "dtype: int64" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 5, "id": "2724bf53", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Index(['EmployeeNumber', 'Attrition', 'Age', 'BusinessTravel', 'DailyRate',\n", " 'Department', 'DistanceFromHome', 'Education', 'EducationField',\n", " 'EmployeeCount', 'EnvironmentSatisfaction', 'Gender', 'HourlyRate',\n", " 'JobInvolvement', 'JobLevel', 'JobRole', 'JobSatisfaction',\n", " 'MaritalStatus', 'MonthlyIncome', 'MonthlyRate', 'NumCompaniesWorked',\n", " 'Over18', 'OverTime', 'PercentSalaryHike', 'PerformanceRating',\n", " 'RelationshipSatisfaction', 'StandardHours', 'StockOptionLevel',\n", " 'TotalWorkingYears', 'TrainingTimesLastYear', 'WorkLifeBalance',\n", " 'YearsAtCompany', 'YearsInCurrentRole', 'YearsSinceLastPromotion',\n", " 'YearsWithCurrManager'],\n", " dtype='object')" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.columns" ] }, { "cell_type": "code", "execution_count": 6, "id": "75f464ad", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T15:44:23.384694Z", "start_time": "2022-10-15T15:44:23.366885Z" } }, "outputs": [], "source": [ "for i in dataset.select_dtypes('object').columns:\n", " dataset[i] = dataset[i].astype('category')" ] }, { "cell_type": "code", "execution_count": 7, "id": "555ea9f1", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T15:44:27.182415Z", "start_time": "2022-10-15T15:44:27.149923Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 2940 entries, 0 to 2939\n", "Data columns (total 35 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 EmployeeNumber 2940 non-null int64 \n", " 1 Attrition 2940 non-null category\n", " 2 Age 2940 non-null int64 \n", " 3 BusinessTravel 2940 non-null category\n", " 4 DailyRate 2940 non-null int64 \n", " 5 Department 2940 non-null category\n", " 6 DistanceFromHome 2940 non-null int64 \n", " 7 Education 2940 non-null int64 \n", " 8 EducationField 2940 non-null category\n", " 9 EmployeeCount 2940 non-null int64 \n", " 10 EnvironmentSatisfaction 2940 non-null int64 \n", " 11 Gender 2940 non-null category\n", " 12 HourlyRate 2940 non-null int64 \n", " 13 JobInvolvement 2940 non-null int64 \n", " 14 JobLevel 2940 non-null int64 \n", " 15 JobRole 2940 non-null category\n", " 16 JobSatisfaction 2940 non-null int64 \n", " 17 MaritalStatus 2940 non-null category\n", " 18 MonthlyIncome 2940 non-null int64 \n", " 19 MonthlyRate 2940 non-null int64 \n", " 20 NumCompaniesWorked 2940 non-null int64 \n", " 21 Over18 2940 non-null category\n", " 22 OverTime 2940 non-null category\n", " 23 PercentSalaryHike 2940 non-null int64 \n", " 24 PerformanceRating 2940 non-null int64 \n", " 25 RelationshipSatisfaction 2940 non-null int64 \n", " 26 StandardHours 2940 non-null int64 \n", " 27 StockOptionLevel 2940 non-null int64 \n", " 28 TotalWorkingYears 2940 non-null int64 \n", " 29 TrainingTimesLastYear 2940 non-null int64 \n", " 30 WorkLifeBalance 2940 non-null int64 \n", " 31 YearsAtCompany 2940 non-null int64 \n", " 32 YearsInCurrentRole 2940 non-null int64 \n", " 33 YearsSinceLastPromotion 2940 non-null int64 \n", " 34 YearsWithCurrManager 2940 non-null int64 \n", "dtypes: category(9), int64(26)\n", "memory usage: 624.6 KB\n" ] } ], "source": [ "dataset.info()" ] }, { "cell_type": "code", "execution_count": 7, "id": "904c15d6", "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", "
countmeanstdmin25%50%75%max
EmployeeNumber2940.01470.500000848.8492211.0735.751470.52205.252940.0
Age2940.036.9238109.13381918.030.0036.043.0060.0
DailyRate2940.0802.485714403.440447102.0465.00802.01157.001499.0
DistanceFromHome2940.09.1925178.1054851.02.007.014.0029.0
Education2940.02.9129251.0239911.02.003.04.005.0
EmployeeCount2940.01.0000000.0000001.01.001.01.001.0
EnvironmentSatisfaction2940.02.7217691.0928961.02.003.04.004.0
HourlyRate2940.065.89115620.32596930.048.0066.084.00100.0
JobInvolvement2940.02.7299320.7114401.02.003.03.004.0
JobLevel2940.02.0639461.1067521.01.002.03.005.0
JobSatisfaction2940.02.7285711.1026581.02.003.04.004.0
MonthlyIncome2940.06502.9312934707.1557701009.02911.004919.08380.0019999.0
MonthlyRate2940.014313.1034017116.5750212094.08045.0014235.520462.0026999.0
NumCompaniesWorked2940.02.6931972.4975840.01.002.04.009.0
PercentSalaryHike2940.015.2095243.65931511.012.0014.018.0025.0
PerformanceRating2940.03.1537410.3607623.03.003.03.004.0
RelationshipSatisfaction2940.02.7122451.0810251.02.003.04.004.0
StandardHours2940.080.0000000.00000080.080.0080.080.0080.0
StockOptionLevel2940.00.7938780.8519320.00.001.01.003.0
TotalWorkingYears2940.011.2795927.7794580.06.0010.015.0040.0
TrainingTimesLastYear2940.02.7993201.2890510.02.003.03.006.0
WorkLifeBalance2940.02.7612240.7063561.02.003.03.004.0
YearsAtCompany2940.07.0081636.1254830.03.005.09.0040.0
YearsInCurrentRole2940.04.2292523.6225210.02.003.07.0018.0
YearsSinceLastPromotion2940.02.1877553.2218820.00.001.03.0015.0
YearsWithCurrManager2940.04.1231293.5675290.02.003.07.0017.0
\n", "
" ], "text/plain": [ " count mean std min 25% \\\n", "EmployeeNumber 2940.0 1470.500000 848.849221 1.0 735.75 \n", "Age 2940.0 36.923810 9.133819 18.0 30.00 \n", "DailyRate 2940.0 802.485714 403.440447 102.0 465.00 \n", "DistanceFromHome 2940.0 9.192517 8.105485 1.0 2.00 \n", "Education 2940.0 2.912925 1.023991 1.0 2.00 \n", "EmployeeCount 2940.0 1.000000 0.000000 1.0 1.00 \n", "EnvironmentSatisfaction 2940.0 2.721769 1.092896 1.0 2.00 \n", "HourlyRate 2940.0 65.891156 20.325969 30.0 48.00 \n", "JobInvolvement 2940.0 2.729932 0.711440 1.0 2.00 \n", "JobLevel 2940.0 2.063946 1.106752 1.0 1.00 \n", "JobSatisfaction 2940.0 2.728571 1.102658 1.0 2.00 \n", "MonthlyIncome 2940.0 6502.931293 4707.155770 1009.0 2911.00 \n", "MonthlyRate 2940.0 14313.103401 7116.575021 2094.0 8045.00 \n", "NumCompaniesWorked 2940.0 2.693197 2.497584 0.0 1.00 \n", "PercentSalaryHike 2940.0 15.209524 3.659315 11.0 12.00 \n", "PerformanceRating 2940.0 3.153741 0.360762 3.0 3.00 \n", "RelationshipSatisfaction 2940.0 2.712245 1.081025 1.0 2.00 \n", "StandardHours 2940.0 80.000000 0.000000 80.0 80.00 \n", "StockOptionLevel 2940.0 0.793878 0.851932 0.0 0.00 \n", "TotalWorkingYears 2940.0 11.279592 7.779458 0.0 6.00 \n", "TrainingTimesLastYear 2940.0 2.799320 1.289051 0.0 2.00 \n", "WorkLifeBalance 2940.0 2.761224 0.706356 1.0 2.00 \n", "YearsAtCompany 2940.0 7.008163 6.125483 0.0 3.00 \n", "YearsInCurrentRole 2940.0 4.229252 3.622521 0.0 2.00 \n", "YearsSinceLastPromotion 2940.0 2.187755 3.221882 0.0 0.00 \n", "YearsWithCurrManager 2940.0 4.123129 3.567529 0.0 2.00 \n", "\n", " 50% 75% max \n", "EmployeeNumber 1470.5 2205.25 2940.0 \n", "Age 36.0 43.00 60.0 \n", "DailyRate 802.0 1157.00 1499.0 \n", "DistanceFromHome 7.0 14.00 29.0 \n", "Education 3.0 4.00 5.0 \n", "EmployeeCount 1.0 1.00 1.0 \n", "EnvironmentSatisfaction 3.0 4.00 4.0 \n", "HourlyRate 66.0 84.00 100.0 \n", "JobInvolvement 3.0 3.00 4.0 \n", "JobLevel 2.0 3.00 5.0 \n", "JobSatisfaction 3.0 4.00 4.0 \n", "MonthlyIncome 4919.0 8380.00 19999.0 \n", "MonthlyRate 14235.5 20462.00 26999.0 \n", "NumCompaniesWorked 2.0 4.00 9.0 \n", "PercentSalaryHike 14.0 18.00 25.0 \n", "PerformanceRating 3.0 3.00 4.0 \n", "RelationshipSatisfaction 3.0 4.00 4.0 \n", "StandardHours 80.0 80.00 80.0 \n", "StockOptionLevel 1.0 1.00 3.0 \n", "TotalWorkingYears 10.0 15.00 40.0 \n", "TrainingTimesLastYear 3.0 3.00 6.0 \n", "WorkLifeBalance 3.0 3.00 4.0 \n", "YearsAtCompany 5.0 9.00 40.0 \n", "YearsInCurrentRole 3.0 7.00 18.0 \n", "YearsSinceLastPromotion 1.0 3.00 15.0 \n", "YearsWithCurrManager 3.0 7.00 17.0 " ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.describe().T" ] }, { "cell_type": "code", "execution_count": null, "id": "52c439c5", "metadata": {}, "outputs": [], "source": [ "3 steps of Analysis:\n", "1. Univariate Analysis \n", "\n", "2, Bivriate Analysis\n", "\n", "3. Multivariate analysis" ] }, { "cell_type": "code", "execution_count": 9, "id": "f2368047", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "No 2466\n", "Yes 474\n", "Name: Attrition, dtype: int64" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.Attrition.value_counts()" ] }, { "cell_type": "code", "execution_count": 8, "id": "e3ffe151", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "No 83.88%\n", "Yes 16.12%\n", "Name: Attrition, dtype: object" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.Attrition.value_counts(normalize=True).mul(100).round(2).astype('str') + '%'" ] }, { "cell_type": "code", "execution_count": null, "id": "d024353e", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "ee9aabb0", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "id": "29acd312", "metadata": {}, "source": [ "## Univariate Continous Data Analysis" ] }, { "cell_type": "code", "execution_count": 10, "id": "3ab7a0e3", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T16:09:21.619640Z", "start_time": "2022-10-15T16:09:21.607328Z" } }, "outputs": [], "source": [ "def continuos_univariate_analysis(data,\n", " feature,\n", " figsize=(12, 8),\n", " kde=False,\n", " ):\n", " f1, (ax_box,\n", " ax_hist) = plt.subplots(nrows=2,\n", " sharex=True,\n", " gridspec_kw={'height_ratios': (0.25, 0.75)},\n", " figsize=figsize)\n", " sns.color_palette(\"viridis\", as_cmap=True)\n", " sns.boxplot(data=data,\n", " x=feature,\n", " ax=ax_box,\n", " showmeans=True,\n", " color='yellow')\n", " sns.histplot(data=data, x=feature, ax=ax_hist, kde=kde, color='blue')\n", " ax_hist.axvline(data[feature].mean(), color='cyan', linestyle='--')\n", " ax_hist.axvline(data[feature].median(), color='orange', linestyle=\"-\")" ] }, { "cell_type": "code", "execution_count": 12, "id": "d4755681", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T16:09:23.825296Z", "start_time": "2022-10-15T16:09:23.578694Z" } }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "continuos_univariate_analysis(dataset, 'Age', kde=True)" ] }, { "cell_type": "markdown", "id": "8e6a4ab4", "metadata": {}, "source": [ "## Observations:\n", "1. Age is normally distributed \n", "2. Majority of the employees do have age between 28 - 43 years \n", "3. Slightly left skewed \n", "4. no outliers observed \n", "5. the orgnaization has more young employees\n", "6. Avg Age is 36 years \n", "7. No such significant difference in age observed for those who are leaving the organization \n" ] }, { "cell_type": "code", "execution_count": 40, "id": "a00df48d", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T16:39:12.843805Z", "start_time": "2022-10-15T16:39:12.831347Z" } }, "outputs": [ { "data": { "text/plain": [ "No 83.9%\n", "Yes 16.1%\n", "Name: Attrition, dtype: object" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.Attrition.value_counts(normalize=True).mul(100).round(1).astype('str')+'%'" ] }, { "cell_type": "code", "execution_count": 41, "id": "1fd98c65", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T16:41:41.425154Z", "start_time": "2022-10-15T16:41:41.419101Z" } }, "outputs": [ { "data": { "text/plain": [ "Attrition\n", "No 37.561233\n", "Yes 33.607595\n", "Name: Age, dtype: float64" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.groupby(['Attrition'])['Age'].mean()" ] }, { "cell_type": "code", "execution_count": 42, "id": "b9ede37e", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T16:43:22.095611Z", "start_time": "2022-10-15T16:43:21.821407Z" } }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtQAAAHgCAYAAACFLvrWAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAABMH0lEQVR4nO3deZhcVZn48e+b7uwJYQsQspAEWQSEAAEUkEVAQEVEFkHURBF0RAcRHGFcEB1GVAZlVEaD8hOVRRARBGQRBATZgglrCISwhUQI+571/P44t0kn6U6aVFXfrqrv53nOc6tu3br11kl15+1T7z0nUkpIkiRJWjW9yg5AkiRJqmcm1JIkSVIFTKglSZKkCphQS5IkSRUwoZYkSZIqYEItSZIkVaC17AAqsfbaa6fRo0eXHYYkSZIa3F133fVsSmloR4/VdUI9evRoJk+eXHYYkiRJanAR8Xhnj1nyIUmSJFXAhFqSJEmqgAm1JEmSVAETakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVqOt5qNV9zjrrLGbOnFl2GKWZM2cOAMOGDSs5Eq2KsWPHcuSRR5YdhiSpQZlQq0tmzpzJI4/czfDhb5YdSilee60fAG+++UTJkejteuqpfmWHIElqcCbU6rLhw9/kmGMeLTuMUpxxxhiApn3/9azt306SpFqxhlqSJEmqgAm1JEmSVAETakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVMKGWJEmSKmBCLUmSJFXAhFqSJEmqgAm1JEmSVAETakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVMKGWJEmSKmBCLUmSJFXAhFqSJEmqgAn1KjjrrLM466yzyg5DkiStAv8fV7W1lh1APZo5c2bZIUiSpFXk/+OqNkeoJUmSpAqYUEuSJEkVMKGWJEmSKmBCLUmSJFXAhFqSJEmqgAm1JEmSVAETakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVMKGWJEmSKmBCLUmSJFXAhFqSJEmqgAm1JEmSVIHWsgOQJEnqbi+88AL77bcfAH369OHYY4/ljDPOYPHixSxevJiFCxcudfzEiRO58MIL+dKXvsSPfvQj5s+fT69evVi8eDERQUqJiRMncuCBBwJw00038cMf/pCJEydywQUXsGjRIhYsWMDXvvY1dt5557ceb2lpYdGiRfTp04fTTjuNlBInnngip556KldffTVXXHEFu+yyC5MnT+bUU09lzJgxbz237VwzZ87kq1/9KvPnz2fixImcd955zJ8/f6nH2845ZsyYt95T2/6jjz6an/zkJ2/FOGHCBM4//3zmz5/PhAkTuOiiizj66KP52c9+tlRcALvssgs33XTTUn3V2trK4YcfzjnnnMN+++3Hn//857f6cPHixfzmN79569i2PmzTvh+OP/54FixYwH777ce11167XB/2JJFSKjuGVTZ+/Pg0efLkbn/dE088EYDvfe973f7aZTnxxBN5883bOeaYR8sOpRRnnJF/ATXC+39+XvCDaX352mbzWKNP/f78d9UZZ4yhX78dmurnVdKKnXjiidx3331L7WttbV0uie7Iyo5rSx4POOCADo9rbW3lkksu6fDxUaNGkVLiySefZNSoUTzxxBPLPf6zn/3sree2nesLX/gCTz75ZKev1fZ42/PbtO3vyntvO6ajuKqtfT90Fssll1xS0xg6EhF3pZTGd/SYJR9Sk7ng8d488FILFzzeu+xQJKkUL7zwwnL7upJMd+W4iy++mJtuuqnT4xYuXMikSZM6fPyJJ554K4nsKGl94oknuOiii9567sKFC7n44os7TTyXffyJJ57g0UfzwNDMmTPf2t+V9952TK2T6bbX6Ow9tcVy88031zyOt8MR6lUwceJE3njjDcaOHdvtr12WmTNn0rv3S/zXf00vO5RSNMoI9fPzgiPvGMD8xUGfXolf7vB6w49Sf+Mbm7BgwZCm+nmVtGLLjk5XW1dHu8vQNkrd2ah2vShjlLqhRqgj4qiImBwRk+fOnVt2OFJdueDx3iwu8ufFCUepJakGemoyDUtGmOs5mYae18d1d1FiSmkSMAnyCHUZMQwbNgxozhpq1a/n5wXXPd2bhSkAWJiCv/6rN4dusKChR6mHDp1Pv35jm+rnVdKKtV2MWCs9fYQaYOTIkXWdVLe29qwUtu5GqCWtmvaj020cpZbUjIYPH16zc0+cOJFjjz12hcdUktB/6lOfWu71VhZPe8cff/xS23p13HHHlR3CUkyopSbx4Mstb41Ot1mYgmkvtZQUkSSVY4011lhuX1dHPFd23IEHHsguu+zS6XGtra0cddRRHT4+atQoRo4c+dbtjh4/+OCD33pua2srBx544FvP6ei12j8+atSot6bNGzt27Fv7u/Le247pKK5qa98PncXS06bNM6GWmsT/jn+DP+/66nLtf8e/UXZoktTt2o9S9+nTh+OOO45+/frRp0+fDhPMiRMnMmDAAI477jj69OkD5DmUASLirWPatI1ST5w4kX79+tG7d/42sG1kte3xlpaWt2I4/vjjOf744xkwYADHH388H/zgB4E813PbvvbPbTvX8ccf/1ZMEydOfOt2+8fbP79N2/5jjz12qRgnTJjw1jkmTJjw1jHLxtUW27JaW1uZMGECsPRo/MSJE5cbYW/rwzbt+6Etnv3226/DPuxJnOVjFTgPdfNplFk+mpHzUEtaVjP+P67KNdQsH5IkSVJPYkItSZIkVcCEWpIkSaqACbUkSZJUARNqSZIkqQIm1JIkSVIFTKglSZKkCphQS5IkSRUwoZYkSZIqYEItSZIkVcCEWpIkSaqACbUkSZJUARNqSZIkqQIm1JIkSVIFWssOoB6NHTu27BAkSdIq8v9xVZsJ9So48sgjyw5BkiStIv8fV7VZ8iFJkiRVwIRakiRJqoAJtSRJklQBE2pJkiSpAibUkiRJUgVMqCVJkqQKmFBLkiRJFTChliRJkipgQi1JkiRVwIRakiRJqoAJtSRJklQBE2pJkiSpAibUkiRJUgVMqCVJkqQKmFBLkiRJFTChliRJkipgQi1JkiRVoLXsAFQ/nnqqH2ecMabsMEoxa1Y/gKZ9//Xsqaf6seGGZUchSWpkJtTqkrFjx5YdQqkGDpwDQL9+w0qORG/Xhhv6+ZUk1ZYJtbrkyCOPLDsESZKkHskaakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVMKGWJEmSKmBCLUmSJFXAhFqSJEmqgAm1JEmSVIFIKZUdwyqLiLnA42XHUafWBp4tO4g6Zv9Vxv6rjP1XGfuvMvZfZey/ypXVhxuklIZ29EBdJ9RadRExOaU0vuw46pX9Vxn7rzL2X2Xsv8rYf5Wx/yrXE/vQkg9JkiSpAibUkiRJUgVMqJvXpLIDqHP2X2Wapv8iIkXEb9vdb42IuRFx+Sqeb3Vgerv7u3V2roi4ISJW+LVoRLy6KnHUuab5/NWI/VcZ+69yPa4PTaibVEqpx30Y64n9V5km67/XgC0ion9xfy/gqQrOtzqwVaVBNbMm+/xVnf1XGfuvcj2xD02oJan2/gJ8sLh9GHB+2wMRsWZE/Cki7omI2yJiy2L/tyPi7GKUeWZE/HvxlFOBDSNiakT8sNg3KCL+EBEPRsS5ERHtXzwijoiIH7W7f2REnL7MMbsVr7XceSJiu4j4R0TcHRF3RMTgiOgXEf8vIu6NiCkRsXtx7MTi/fw5Ih6NiC9GxFeKY26LiDWL4zaMiKsi4q6I+HtEbFqtzpak7mZCLUm1dwFwaET0A7YEbm/32MnAlJTSlsB/Ar9p99imwN7A9sBJEdEbOAF4JKU0LqX01eK4rYEvA5sBY4GdOnj9DxfPB/g08P86iHO580REH+D3wDEppa2APYE3gKMBUkrvIv+RcE7x/gC2AD5exH0K8HpKaWvgVuBTxTGTgC+llLYFjgfO7LDnJKkOtJYdgCQ1upTSPRExmpx4XrnMwzsDBxbHXR8Ra0XEkOKxK1JK84B5EfEMsG4nL3FHSmkWQERMBUYDN7d7/dci4nrgQxExDeidUrq3i+d5CZiTUrqzONfLxeM7Az8p9j0YEY8DGxfn+VtK6RXglYh4Cfhzsf9eYMuIGATsCFzUbjC9byfvTZJ6PBNqSeoelwGnAbsBa7XbHx0c27ZAwLx2+xbR+e/srhz3S/II+IN0PDrd2XmiXTztdRR3R+dZ3O7+4uKcvYAXU0rjVnAOSaoblnxIUvc4G/hOByPDNwGHQ65jBp5tGwXuxCvA4Lf74iml24GR5FKM81dyeHsPAutHxHZFjIMjonWZuDcGRtFu9pGVxPIy8GhEHFw8PyLCCy0l1S0TaknqBimlWSmlMzp46NvA+Ii4h3zB4YSVnOc54JaIuK/dRYlddSFwS0rpha4+IaU0H/gY8JOIuBu4FuhHrnluiYh7yTXWE4vylK46HDiiOOf9wP5v47mS1KO49LgkNYlivuofpZSuKzsWSWokjlBLUoOLiNUj4iHgDZNpSao+R6glSZKkCjhCLUmSJFXAhFqSJEmqgAm1JEmSVAETakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVMKGWJEmSKmBCLUmSJFXAhFqSJEmqgAm1JEmSVAETakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVMKGWJEmSKmBCLUmSJFXAhFqSJEmqgAm1JEmSVAETakmSJKkCJtSSJElSBUyoJUmSpAqYUEuSJEkVMKGWJEmSKtBadgCVWHvttdPo0aPLDkPN4OXpebvaJuXGUQXFO6H+34kkSd3nrrvuejalNLSjx+o6oR49ejSTJ08uOww1g7/ulrd73lBmFFWxW7G9ocQYJEmqNxHxeGeP1XVCLentG1F2AJIkNRgTaqnJ/K7sACRJajBelChJkiRVwIRaajJfLpokSaoOSz6kJjO17AAkSWowjlBLkiRJFTChliRJkipgQi1JkiRVwBpqqclsXHYAkiQ1GBNqqclMKjsASZIajCUfkiRJUgVMqKUmc1TRJElSdZhQ91AjRowmImrWRowYXfZbVEkeKpokSaoOa6h7qKeeepyTTko1O//JJ0fNzi1JktRMHKGWJEmSKmBCLUmSJFXAkg+pyYwrOwBJkhpMzUeoI6IlIqZExOXF/TUj4tqIeLjYrtHu2BMjYkZETI+IvWsdm9SMflw0SZJUHd1R8nEMMK3d/ROA61JKGwHXFfeJiM2AQ4HNgX2AMyOipRvikyRJklZZTRPqiBgBfBD4Zbvd+wPnFLfPAT7Sbv8FKaV5KaVHgRnA9rWMT2pGnyiaJEmqjlqPUP8Y+A9gcbt966aU5gAU23WK/cOBJ9sdN6vYJ6mKZhVNkiRVR80S6oj4EPBMSumurj6lg33LTcQcEUdFxOSImDx37tyKYpQkSZIqVcsR6p2AD0fEY8AFwPsi4nfA0xExDKDYPlMcPwsY2e75I4DZy540pTQppTQ+pTR+6NChNQy/0bXUdCVGV2OUJEnNombT5qWUTgROBIiI3YDjU0qfiIgfAhOAU4vtpcVTLgPOi4jTgfWBjYA7ahWfFtV0JUZwNUZJktQcypiH+lTgwog4AngCOBggpXR/RFwIPAAsBI5OKS0qIT6pob2n7AAkSWow3ZJQp5RuAG4obj8H7NHJcacAp3RHTFKz+l7ZAUiS1GBcelySJEmqgAm11GQOLJokSaqOMmqoJZXoubIDkCSpwThCLUmSJFXAhFqSJEmqgAm1JEmSVAFrqKUm0+GclZIkaZWZUEtN5ptlByBJUoOx5EOSJEmqgAm11GT2LZokSaoOSz6kJvNG2QFIktRgHKGWJEmSKmBCLUmSJFXAhFqSJEmqgDXUUpP5UNkBSJLUYEyopSZzfNkBSJLUYCz5kCRJkipgQi01md2KJkmSqsOEWpIkSaqACbUkSZJUARNqSZIkqQIm1JIkSVIFnDZPajKHlB2AJEkNxoRaajJfKDsASZIajCUfUpN5vWiSJKk6apZQR0S/iLgjIu6OiPsj4uRi/7cj4qmImFq0D7R7zokRMSMipkfE3rWKTWpmHyiaJEmqjlqWfMwD3pdSejUiegM3R8Rfisd+lFI6rf3BEbEZcCiwObA+8NeI2DiltKiGMUqSJEkVqdkIdcpeLe72LlpawVP2By5IKc1LKT0KzAC2r1V8kiRJUjXUtIY6IloiYirwDHBtSun24qEvRsQ9EXF2RKxR7BsOPNnu6bOKfZIkSVKPVdOEOqW0KKU0DhgBbB8RWwD/B2wIjAPmAP9THB4dnWLZHRFxVERMjojJc+fOrUnckiRJUld1yywfKaUXgRuAfVJKTxeJ9mLgLJaUdcwCRrZ72ghgdgfnmpRSGp9SGj906NDaBi41oIlFkyRJ1VHLWT6GRsTqxe3+wJ7AgxExrN1hBwD3FbcvAw6NiL4RMQbYCLijVvFJzWoiJtSSJFVTLWf5GAacExEt5MT9wpTS5RHx24gYRy7neAz4HEBK6f6IuBB4AFgIHO0MH1L1PVts1y41CkmSGkfNEuqU0j3A1h3s/+QKnnMKcEqtYpIEBxXbG8oMQpKkBuJKiZIkSVIFTKglSZKkCphQS5IkSRUwoZYkSZIqUMtZPiT1QP9WdgCSJDUYE2qpyXys7AAkSWowlnxITebJokmSpOpwhFpqMm0Twd9QZhCSJDUQR6glSZKkCphQS5IkSRUwoZYkSZIqYEItSZIkVcCLEtUlixfDCy/A00/nNm8e9O0LffrA6qvDBhvAoEFlR6muOK7sACRJajAm1Fqh11+Hu+6CO++EV17J+yKgd2+YP3/pY9daC97xDth2Wxg6tPtjVdfsV3YAkiQ1GBNqdWj+fLj++pxML1wIG24Iu+8O660Ha6+dE+qU8nHPPguPPQaPPw6TJ8Ptt+cRaziIxYuhl4VFPcr0YrtJqVFIktQ4TKi1nH/9Cy6+OCfKW28N7343rLPO8sdF5LKP4cNz22kneO01mDo1J+JwEdtuC9/7Huy9dz5e5ftcsb2hzCAkSWogjh1qKXfeCb/8Jbz5Jnzyk/DhD3ecTHdm4MCcWH/pSwCH89JLsO++sMceMG1araKWJEkqjwm13vKPf8CVV8KYMfD5z8PYsat+rjwafR4PPgg/+Uketd5qK/jWt3KyXg0jRowmImraRowYXZ1gJUlSw7LkQwDccQdcey1sthkceGD16p779IEvfhEOOQSOPx6++1244AL47W9hhx0qO/dTTz3OSSel6gTaiZNPtk5FkiStmCPU4q674C9/gU03hY9+tDYXEa6zDvzmNzlpnzcvl4V85zv5gkdJkqR6ZkLd5B57DK64AjbaKI9Mt7TU9vX23BPuvhsOPRROOgl22QVmzqzta2pp3yiaJEmqDhPqJvbaa/DHP8Kaa+ZkurWbCoBWXx1+9zs47zx44IFcW/3rX+dp+FR7exZNkiRVhwl10wr+9Ke8cMtBB+Xp77rbYYfBPffkhWA+/elcZ/3CC90fR7OZWjRJklQdJtRN6zhmzMjzQ6+3XnlRjBoF110Hp54Kf/oTjBsHt9xSXjzN4MtFkyRJ1WFC3YTmzgX4b975Thg/vuxoct32176Wp+1rbYVdd4VTToFFi8qOTJIkaeVqllBHRL+IuCMi7o6I+yPi5GL/mhFxbUQ8XGzXaPecEyNiRkRMj4i9axVbM0spzzUNr/ChD/Ws1Qu32w6mTMmlH9/4Buy1F8yeXXZUkiRJK1bLEep5wPtSSlsB44B9IuLdwAnAdSmljYDrivtExGbAocDmwD7AmRFR4zknms/99+eZPeDrDBhQcjAdWG01OPdcOPtsuP32fMFi/gNAkiSpZ6pZQp2yV4u7vYuWgP2Bc4r95wAfKW7vD1yQUpqXUnoUmAFsX6v4mtH8+XDNNTBsGMCkssPpVES+SHHyZFh/ffjgB+G443L8kiRJPU1Na6gjoiUipgLPANemlG4H1k0pzQEotusUhw8Hnmz39FnFPlXJjTfCK6/AvvsCLC47nJV65zvzKPXRR8Ppp8OOO8KMGWVHVf/+u2iSJKk6appQp5QWpZTGASOA7SNiixUc3lE173IzE0fEURExOSImz81X16kLXngBbrstz6IxcmTZ0XRdv37w05/m+bJnzoStt3bO6krtWDRJklQd3TLLR0rpReAGcm300xExDKDYPlMcNgton+qNAJa7JC2lNCmlND6lNH7o0KG1DLuh3HRTXlL8fe8rO5JVc8ABMHUqbLNNLgc56CCAtUqOqj79o2iSJKk6ajnLx9CIWL243Z+8ONuDwGXAhOKwCcClxe3LgEMjom9EjAE2Au6oVXzN5Pnn83Lf224LgweXHc2qGzUKrr8evv99+POfAe7l4YfLjqr+/GfRJElSddRyhHoY8LeIuAe4k1xDfTlwKrBXRDwM7FXcJ6V0P3Ah8ABwFXB0SsmZiKvgppvyXM877VR2JJVraYH/+A+4806A5zjvPLjiCliwoOzIJElSs2qt1YlTSvcAW3ew/zlgj06ecwpwSq1iakbPP5+X995hh/oenV7WVlsBjOfd736T226DRx/NZSHDq34ZawsRwd++nu/tvld1J+4ePnwDZs16rKrnlCRJ3atmCbV6hkYanV7ePPbeGzbeOC9b/qtf5fe56655xcXqWMRJJyVGj9gNgJNOuqFaJwbg5JN70Mo6kiRplbj0eANrG50ePx4GDSo7mtoZMwb+7d/yqPXNN8NZZ8GcOWVHJUmSmoUJdQO74468SMqOTTBHWr9+sP/+cNhh8PrrOan+299gkVX4y/lx0SRJUnWYUDeoefNgyhTYfPPGqp1emY03hi98Ad71rlzu8stfwtNPlx1VzzKuaJIkqTpMqBvUlCl5qe53v7vsSLpf//75AsWPfSyvDDlpUk6uF/f8xSG7xV+LJkmSqsOLEhvQ4sW53GPkSFh//bKjKc+mm+a5q6+8Mpd/TJ8OH/kINPt6QP9VbPcsNQpJkhqHI9QN6OGH81LjO+xQdiTlGzAgr6p40EG5T37xC7jlFkerJUlS9ThC3YBuuw1WWw3e+c6yI+k5Nt8cNtggLwLz17/Cgw/m0eq1XL1ckiRVyBHqBvPMM/DYY7DddtDLf92lDBoEhxwCH/0oPPss/Pzn+Y+PlMqOTJIk1TNHqBvMXXflRHqbbcqOpGeKyDOAjB4Nl18OV18N06bl0eo11ig7OkmSVI8cw2wgCxfCvffmUo8BA8qOpmcbPBgOPTTPXf3003m0+r77yo6qe/yiaJIkqTocoW4gDz4Ib7wBW29ddiT1IQLGjcsrLf7hD3DxxfD447D33tVcurzn2aTsACRJajCOUDeQKVNgyBAYO7bsSOrLkCEwcWJeUXLyZPjVr+C558qOqnb+XDRJklQdJtQN4sUXYebMPOIaUXY09aelBfbaKy9d/tJLeTGYRi0B+Z+iSZKk6jChbhBTpuSt5R6V2Xhj+NznYN11cwkInMmiRWVHJUmSejIT6gaweDFMnQobbpjLF1SZIUNgwoRcAgL/xm9+g0m1JEnqlAl1A3j0UXj5ZUenq6mtBAQOY/ZsmDMH5s8vOypJktQTmVA3gHvvhb59YROnb6iBC/j0pyEBc/6Vl3WXJElqz4S6zi1YkBcm2Wyzxp7qrUzrrw/DhkHvVjj//Lx4Tj37bdEkSVJ1mILVuYceyqUI73pX2ZE0ttYWWG+9XKd++eV5JpDdd6/PGVVGlh2AJEkNxhHqOnfvvTBoEGywQdmRNL5evfLqiltvDX//O1x5JaRUdlRv3++LJkmSqsMR6jr2xhu5pnf77XOyp9praYH99oP+/eEf/4B58/Ly5S0tZUfWdf9XbD9WahSSJDUOE+o69sADeco8yz26V0SeAaRfP7j++lxyc9BB1rBLktSsHNesY/fdB2utlS+YU/d773th331h+nS46CLnqpYkqVmZUNepl1+Gxx7Lo9P1eGFco9h+e/jAB/LFoSbVkiQ1JxPqOnX//Xm7xRblxiHYbrslI9V/+INJtSRJzaZmCXVEjIyIv0XEtIi4PyKOKfZ/OyKeioipRftAu+ecGBEzImJ6ROxdq9gawbRpeRq3tdYqOxJBHqneZx948EG47LKePfvHH4omSZKqo5aXUS0Ejksp/TMiBgN3RcS1xWM/Simd1v7giNgMOBTYHFgf+GtEbJxScrxvGS+/DE8+medBVs+xww551o+//S1fsLjPPj2zHGftsgOQJKnB1CyhTinNAeYUt1+JiGnA8BU8ZX/ggpTSPODRiJgBbA/cWqsY69W0aXm72WblxqHlvfe9eTrD227LU+vttlvZES3v18V2YokxSJLUSLqlhjoiRgNbA7cXu74YEfdExNkRsUaxbzjwZLunzaKDBDwijoqIyRExee7cubUMu8eaNg2GDoW1HWrscSLg/e+HcePgxhth8uSyI1rer1mSVEuSpMrVPKGOiEHAxcCXU0ovk9eV2BAYRx7B/p+2Qzt4+nKVqCmlSSml8Sml8UOHDq1N0D3Yq6/C4487Ot2TReTFXzbaKK+m+NBDZUckSZJqqaYJdUT0JifT56aU/giQUno6pbQopbQYOItc1gF5RHpku6ePAGbXMr56ZLlHfejVKy/2st56eeaP2X6SJUlqWLWc5SOAXwHTUkqnt9vffhmSA4D7ituXAYdGRN+IGANsBNxRq/jq1bRpeWaPJhycrzt9+sDHPw4DB8J558GLL5YdkSRJqoVajlDvBHwSeN8yU+T9ICLujYh7gN2BYwFSSvcDFwIPAFcBRzvDx9Jeey0v5rLZZj1z9ggtb9AgOPxwWLgQLrggL1MuSZIaSy1n+biZjuuir1zBc04BTqlVTPVu+vQ8v/E731l2JF3VQpj5s/bacPDBcO65cMklcMgh5f5B1OkPoCRJWiW1nIdaVfbgg7D66rkutz4s4qSTarfCyckn10+yvuGGsPfecNVVcP31sMce5cUyoLyXliSpIbn0eJ2YPx9mzoRNNrHco15tvz1ssw3cfPOSpePLcGbRJElSdZhQ14kZM2DRIth007Ij0aqKgA98AEaOzMuTlzWN+oVFkyRJ1WFCXSemT88r740aVXYkqkRLS55Or7UVLrwQYGDZIUmSpAqZUNeBRYvy4iAbb5znN1Z9W201OPBAeO45gLNItSszlyRJ3aBL6VlE7NSVfaqNJ56AN9/M9dNqDGPHwu67AxzGT39adjSSJKkSXR3v/EkX96kGpk/PJQIbblh2JKqmnXcGuIyvfAVuvbXsaCRJ0qpa4bR5EfEeYEdgaER8pd1DqwEttQxMWUp5uryxY/PKe2ocebaWCYwa9QIHHwz//Cess07tX/eG2r+EJElNZWUj1H2AQeTEe3C79jJwUG1DE8DTT8NLL1nu0bhe5OKLcz31xz+e6+UlSVJ9WeEIdUrpRuDGiPh1SunxbopJ7Uyfnrcbb1xuHKqdcePgzDPhM5+B734Xvv3t2r7eacX2+Nq+jCRJTaOrKyX2jYhJwOj2z0kpva8WQWmJhx+G4cNh0KCyI1EtffrTcMMNOaHec8+2+urauLzYmlBLklQdXU2oLwJ+DvwS8EvpbvLaa/DUU7DbbmVHou7w05/mVRQPPxzuvjsvMy9Jknq+rs7ysTCl9H8ppTtSSne1tZpGJmbMyNuNNio3DnWPwYPh/PNh9mz43OdwfmpJkupEVxPqP0fEFyJiWESs2dZqGpl4+GEYOBCGDSs7EnWX7beH73wnr6J4zjllRyNJkrqiqyUfE4rtV9vtS8DY6oajJVp45BHYdNO26dXULP7jP+Caa+CLX4Sddqr+NxT9q3s6SZKaXpcS6pTSmFoHomW9hzfftNyjGbW0wG9/C1tumafSu+WW6s5B/pfqnUqSJNHFhDoiPtXR/pTSb6objpb4IL165QVd1HxGjIBf/hIOPBC+9S049dSyI5IkSZ3pasnHdu1u9wP2AP4JmFDXzAcYNQr69Ss7DpXlox+Fo46CH/wA9toL9tijOuf9brH9ZnVOJ0lS0+tqyceX2t+PiCHAb2sSkXjiCYAtLfcQp58ON94IEyfCvfdWZyq964qtCbUkSdXR1Vk+lvU6YLpXI1dembcm1Bo4EH7zG5gzB445puxoJElSR7qUUEfEnyPisqJdAUwHLq1taM0rJ9SPsvbaZUeinmD77eHEE3Ni/ac/lR2NJElaVldrqE9rd3sh8HhKaVYN4ml6b74J110HcAURXyw7HPUQ3/wmXHFFrqnecUdYZ52yI5IkSW26NEKdUroReBAYDKwBzK9lUM3sxhvh9dcBrig7FPUgffrkEeqXXoLPf76yVRTXKpokSaqOrpZ8HALcARwMHALcHhEH1TKwZnXFFdC/P8ANJUeinmaLLeC734VLLoHf/W7Vz3Nx0SRJUnV09aLErwPbpZQmpJQ+BWyPkwRUXUo5oX7f+wDeLDsc9UDHHZdXT/zSl+DJJ8uORpIkQdcT6l4ppWfa3X9uZc+NiJER8beImBYR90fEMcX+NSPi2oh4uNiu0e45J0bEjIiYHhF7v+13U+ceeghmzoQPfKDsSNRTtbTAOefAwoVwxBGrVvpxYtEkSVJ1dDWhvioiro6IiRExkVzge+VKnrMQOC6l9E7g3cDREbEZcAJwXUppI/KUuCcAFI8dCmwO7AOcGREtb/cN1bMrirLpD36w3DjUs224IZx2Glx7Lfzf/739599aNEmSVB0rG2V+R0TslFL6KvALYEtgK/L/x5NW9NyU0pyU0j+L268A04DhwP7AOcVh5wAfKW7vD1yQUpqXUnoUmEEuLWkaV1wBm28OG2xQdiTq6T73Odh7b/jqV/O3GpIkqTwrG6H+MfAKQErpjymlr6SUjiWPTv+4qy8SEaOBrYHbgXVTSnOKc84B2iYAGw60rwqdVexrCi+/DH//u+Ue6poIOOssaG2FT38aFi8uOyJJkprXyhLq0Smle5bdmVKaDIzuygtExCDypAJfTim9vKJDO9i3XIVoRBwVEZMjYvLcuXO7EkJd+OtfYcECyz3UdSNHwo9/DDfdBD/7WdnRSJLUvFaWUPdbwWP9V3byiOhNTqbPTSn9sdj9dEQMKx4fBrRd7DgLGNnu6SOA2cueM6U0KaU0PqU0fujQoSsLoW5ceSUMGZIX7ZC6auLE/K3G174GM2Z07TkjiiZJkqpjZQn1nRFx5LI7I+II4K4VPTEiAvgVMC2ldHq7hy4DJhS3J7BkCfPLgEMjom9EjAE2Is993fBSygn1+98PvXuXHY3qSQRMmgR9++bketGilT/nd0WTJEnVsbKlx78MXBIRh7MkgR4P9AEOWMlzdwI+CdwbEVOLff8JnApcWCTlT5AXiyGldH9EXAg8QJ4h5OiUUhfSg/o3ZQrMmWO5h1bN8OHwv/8Ln/pU3h57bNkRSZLUXFaYUKeUngZ2jIjdgS2K3VeklK5f2YlTSjfTcV00wB6dPOcU4JSVnbvRXFlMQLjPPuXGofr1iU/AH/4A//mfuQRkk006P/bLxfbH3RCXJEnNYGUj1ACklP4G/K3GsTStK66A7baDddctOxLVqwj4xS/ytIsTJ8LNN+dFYDoytTsDkySpCXR1YRfVyLPPwu23O12eKrfeevCTn8Btt8Hpp6/8eEmSVB0m1CW76qp8UaL106qGww6DAw6Ab34THnig7GgkSWoOJtQlu+IKWGcd2HbbsiNRI4jIy5EPGpRLPxYuLDsiSZIanwl1iRYuhKuvhn33hV7+S6hK1l0XzjwT7rwTTjtt+cc3LpokSaoO07gS3XYbvPCC5R6qvkMOgYMPhpNOgvvuW/qxSUWTJEnVYUJdoiuvzDMx7LVX2ZGoEf3sZ3n1zYkT87L2kiSpNkyoS3TFFbDzzrD66mVHokY0dGiup77rLvj+95fsP6pokiSpOkyoS/Lkk3DPPU6XpxYiombtmGNGc9hh8J3vwN1351d8qGiSJKk6urSwi6rvL3/JW+unm90iTjop1ezsJ58c/OQncP31ufTj9tuBPjV7OUmSmpIj1CW54grYYAPYbLOyI1GjW2utvIri1Knw3/9ddjSSJDUeE+oSzJsHf/1rLveIKDsaNYP994dPfAJOOQVefaXsaCRJaiwm1CW48UZ4/XXLPdS9zjgjX6j42KXwrkVlRyNJUuMwoS7BFVdAv36w++5lR6LGt+Six7XWCubM+RDPfRJ+2vrdql34OGLE6LLfpCRJpfKixBJceWVOpgcMKDsSNb7lL3q89FK4++5v8tnPfpP116/8FU4+2bolSVJzc4S6mz30EMyYYbmHyjP/bGg5H/70J1i4sOxoJEmqfybU3eyKK/LW+adVltfWgDW3hLlz4YYbyo5GkqT6Z0Ldza68EjbdFMaMKTsSNbP+/WHrreEf/4BZs8qORpKk+mZC3Y1efjnP8LHffmVHIsH73w+DB+ea6gULyo5GkqT6ZULdja65JicuH/pQ2ZFIeaaZD38Ynn0W/va3sqORJKl+mVB3o8svh9VXhx13LDsSNbMRT+YGsOGGsO22cOut8OST5cYlSVK9MqHuJosW5frpffeFVicrVIn2vC63NnvtBUOG5Fk/LP2QJOntM6HuJnfemWdVsH5aPU3fvnlp8uefh+uvLzsaSZLqjwl1N7n8cmhpgb33LjsSNbsLD8mtvTFjYLvt4Lbb4PHHy4lLkqR6ZULdTS6/HHbaCdZcs+xI1OxeH5DbsvbcE9ZYI8/6MX9+98clSVK9qllCHRFnR8QzEXFfu33fjoinImJq0T7Q7rETI2JGREyPiIYax33iCbj7bmf3UM/Wp0+e9eOFF+C661Z+vCRJymo5Qv1rYJ8O9v8opTSuaFcCRMRmwKHA5sVzzoyIlhrG1q3aVke0flo93ejRsP32cMcd8NhjZUcjSVJ9qFlCnVK6CXi+i4fvD1yQUpqXUnoUmAFsX6vYutvll+fpyTbZpOxIpJXbY49cmmTphyRJXVNGDfUXI+KeoiRkjWLfcKD9LLizin1177XX8tfnH/oQRJQdjQRjZubWmT598qwfL74I117bbWFJklS3ujuh/j9gQ2AcMAf4n2J/R6lm6ugEEXFUREyOiMlz586tSZDVdP31MG+e9dPqOXa9KbcVGTUK3v1umDwZHn64e+KSJKledWtCnVJ6OqW0KKW0GDiLJWUds4CR7Q4dAczu5ByTUkrjU0rjhw4dWtuAq+Dyy2HwYNhll7Ijkd6ePfaAddbJC7688krZ0UiS1HN1a0IdEcPa3T0AaJsB5DLg0IjoGxFjgI2AO7oztlpIKSfUe++dv0aXeoJzD89tZVpb4aCDch31JZfkz7MkSVpeLafNOx+4FdgkImZFxBHADyLi3oi4B9gdOBYgpXQ/cCHwAHAVcHRKaVGtYusuU6bA7NmWe6hnWdA7t64YOhT23RcefRRuuaW2cUmSVK9aa3XilNJhHez+1QqOPwU4pVbxlOHyy/OFiPvuW3Yk0qrbemuYOTNfDzB6NIwYUXZEkiT1LK6UWEOXXw477JDrUKV6FZG/ZVltNbj4YnjzzbIjkiSpZzGhrpF//QvuvNPFXNQY+vWDAw+El17KfyhaTy1J0hIm1DVy5ZV5a/20epqNH8rt7Ro5EnbfHe6/H6ZOrXpYkiTVrZrVUDe7P/85JyDvelfZkUhL2/Efq/7cnXbKFyj+5S8wfLjlTJIkgSPUNfHGG3DNNbncw9UR1Uh69YIDDsjTQF54ofXUkiSBCXVNXHstvP56TjyknubXE3NbVYMHw8EHw/PP50VfOl7oVJKk5mFCXQOXXAJDhsCuu5YdiVQbG2wA738/TJ8OcELZ4UiSVCoT6ipbuDDXT3/oQ9C7i4tnSPVohx3arhH4L665puxoJEkqjwl1ld18Mzz3nOUeanxt81PDfRx2GDz2WMkBSZJUEhPqKvvTn6BvX9h777IjkWqvTx+Aj7JoEXz0o/mCXEmSmo0JdRWllOun3/9+GDSo7Gikjm1+f27V8wjnngtTpsC//ZuLvkiSmo8JdRVNnQpPPAEf+UjZkUid2+7O3Krpgx+Ek06Cc86B//3f6p5bkqSezoS6ii65JM/T63Lj6skW9M6t2r71rfzH5Fe+smSlUEmSmoEJdRVdcgnsvDMMHVp2JFLnzj08t2rr1Qt+9zvYais49FC4997qv4YkST2RCXWVTJ8O992XL8ySmtXAgXnayMGD8wwg//pX2RFJklR7JtRV8oc/5O2BB5Ybh1S24cNzUv3ss7m2+pVXyo5IkqTaMqGukosugve8B0aMKDsSqXzbbJP/yLz77vxH5vz5ZUckSVLtmFBXwcMP58Th4IPLjkTqOfbdF375S7j2WvjMZ2Dx4rIjkiSpNlrLDqARWO6hejJuave91sSJMHs2fP3rsPba8KMf5RUWJUlqJCbUVXDRRbDDDjBqVNmRSCvXnQk1wIknwjPPwBln5IsVv/vd7n19SZJqzYS6Qo88kleIO+20siORuub1AXk74PXueb2IPDL92mvwX/+VZwI54YTueW1JkrqDCXWFLPdQvbnwkLyd+Ovue80I+PnP4fXX84h1375w7LHd9/qSJNWSCXWFLroIttsORo8uOxKpZ2tpgV//Os/48ZWv5O3XvlZ2VJIkVc6EugIPPwx33QU//GHZkUj1oXdvOP/8vD3hhJxUf/ObZUclSVJlTKgrcP75+avsQw8tOxKpfrS2wm9/C336wLe+lWurv/c9Z/+QJNUvE+pVlBKcdx7ssouLuUhvV0sLnH029O8P3/9+XqL8rLPyyLXevhEjRvPUU4/X7PzDh2/ArFmP1ez8klTvapZQR8TZwIeAZ1JKWxT71gR+D4wGHgMOSSm9UDx2InAEsAj495TS1bWKrRqmTIHp03MtqFRPxt9ZdgRZr15w5pkwbBicdFKeWu+ii/IsIHp7nnrqcU46KdXs/Cef7NcHkrQitVwp8dfAPsvsOwG4LqW0EXBdcZ+I2Aw4FNi8eM6ZEdFSw9gqdt55eTTN2T1Ub7a4P7eeICKXfUyaBFdfDe99Lzz5ZNlRSZL09tQsoU4p3QQ8v8zu/YFzitvnAB9pt/+ClNK8lNKjwAxg+1rFVqlFi3L99D77wFprlR2N9Pa8tFpuPcmRR8Jll8GMGXnWnFtvLTsiSZK6rpYj1B1ZN6U0B6DYrlPsHw60H5eaVexbTkQcFRGTI2Ly3LlzaxpsZ/7+97yc8sc/XsrLSxW55KO59TQf/CDcdhsMGgS77Qa/+lW+VkGSpJ6uuxPqznRUoNfhf6UppUkppfEppfFDhw6tcVgdO++8XOe5336lvLzUsDbbDG6/PZd+fPazMGECvPpq2VFJkrRi3Z1QPx0RwwCK7TPF/lnAyHbHjQBmd3NsXTJvXl4d8YADvHhKqoW11sr11N/+Nvzud7kE5J57yo5KkqTOdXdCfRkwobg9Abi03f5DI6JvRIwBNgLu6ObYumTRIvjGN+Dzny87EqlxtbTkmT+uuw5efDEn1f/937BwYdmRSZK0vJol1BFxPnArsElEzIqII4BTgb0i4mFgr+I+KaX7gQuBB4CrgKNTSotqFVslBgzIU+XttFPZkUiNb/fd8+j0Rz4CX/86vOc9cN99ZUf19o0YMZqIqFmTJJWrZvNQp5QO6+ShPTo5/hTglFrFIyl7zz/KjuDtGToUfv97OOgg+MIXYOut4Zhj8nR7q/Ww2Uo64zzRktTYespFiZK6ySYP5VZvDj4YHngAJk6E00+HTTaBc87JZViSJJXJhFpqMs+ulVs9Gjo0L1F+++0walROrt/1rnyh8OLFZUcnSWpWJtRSk7l8v9zqWdviLxdemOeqPvhg2GabPCvI/PllRydJajYm1JLqUq9eOZG+775c+jF/PnzykzBmTJ4R5Kmnyo5QktQsTKgl1bWWFvjUp3Ji/Ze/wOab5xlBRo2CffeF88+Hl18uO0pJUiMzoZbUEHr1gn32gWuugYcfhv/8T7j/fvj4x3Pt9T77wJlnwoMPuqS5JKm6ajZtniSV5R3vgO9+F04+GW65BS69NLejj86Pr7tuXt58221h3DjYaitYbz3o7imdU8qL1cyfn9uiRfkPg7bW0pK3ra3Qu3f3xiZJ6joTaqnJ7HJT2RF0n169cuL83vfCD38IM2bAjTfmdvPNeXaQNoMGwdixuQZ72LCcdA8dmhdz6tt3+bZwIcybB2++uaTNmwevvQavvAKvvrpkC5e+Vec9f34+ru12V0fLW1uhf38YOBCGDMltjTVyjDCMlLr/DwJJUmZCLTWZsTOrfcaWmq7WN3z4Bsya9VjF54mAjTbK7bOfzftefBHuvjuvxvjII7nNmJFHtZ99trLXGzAABg/OiTqMZPHivG/11aFPn9z69l1yu0+fPCK9ePHSbdGinLy//jq88UZO2J9/Hh59tP2MJrP54Q9h+HAYMQJGjszNUW1J6h4m1FKT+dd6ebvev6p1xkV1uwrg6qvDrrvmtqyFC3NS/cYbeUS5fZs/P48Y9+uXW9++S7YDB+bW0rLkXBHb8OlPV7ePUspJ9ty5cM45X2TTTX/KrFn5DwLI8W2wQS5/2WSTPJotSaoNE2qpyVy1T95O/HWpYfR4ra25rrqniliSvMPP+PCHfwrk0pMnn1wy4n711bmtvz688515IZwhQ0oNXZIajgm1JDWQfv2WlLYAvPBCXrL9gQfguuty23BD2HrrPHLd6v8CklQxf5VKUgNbYw3YaafcXngBpk7N7Q9/yKPb48fn2U4GDy470vo2YsRonnrq8Zq+RrWuJ5BUfSbUktQk1lgDdt8914zPnAl33JFnPPn732HLLfNsKGuuWXaU9emppx6v6bUEUNvrCSRVxoRakppMr175YsV3vCPPGHLbbTBlSp7xZIstcmKdp+OTJHWFCbXUZPa4ruwI3q76mJavXq25JnzgA7DLLvCPf8DkyXDvvbDZZnnfuuuWHaEk9Xwm1FKTGflk2RG8XbWelq+1pgl7vRg0CN7//lxrfdttuRzkgQdyYg0blh2eJPVoJtRSk3lyZN7WX2JdK7VN2KG+al8HDoQ99oAdd4Rbb83JNUzj3/8dvvlNS0EkqSO9yg5AUve6bo/cpBXp3x/e9z740pcAfsWZZ+bp9k45JS8oI0kdGTFiNBFRszZixOiy32KHHKGWJHUqT6f3b9x33+c58UT4xjfgzDPhu9+FCROWXhFSkmo9401P/cbPEWpJ0kptuilccgncfHNe0vyII2CbbfJCMZLU7EyoJUldttNOcMst8Pvfw8svw557wn77wYMPlh2ZJJXHhFqS9LZEwCGHwLRp8IMfwE035fmrv/hFePbZsqOTpO5nQi01mX2uyk2qVL9+8NWvwowZ8PnPw89/nheLOe00mDev7OgkqfuYUK+iWl/FKtXKev/KTaqWoUPhpz/NC8LsvHNOst/5TrjoIki1nZFQknqEUmb5iIjHgFeARcDClNL4iFgT+D0wGngMOCSl9EIZ8XVFs17Fqvo3c2zejp1ZbhxqPO98J1x+OVx7LRx3XC4L2XFHOP102GGHsqOTpNopc4R695TSuJTS+OL+CcB1KaWNgOuK+5Kq7KZdcpNqZa+9YMoUOOsseOQRePe74dBDYfr0siOT5DfstdGT5qHeH9ituH0OcAPwtbKCkSStupYW+Oxn4WMfyxcunn56LgH5xCfyiovveEfZEUrNyW/Ya6OsEeoEXBMRd0XEUcW+dVNKcwCK7TolxSZJqpLBg/MiMI8+CsceCxdemOe0PuKIvE+SGkFZCfVOKaVtgH2BoyOiy19AR8RRETE5IibPnTu3dhFKkqpmnXXy7B8zZ+bp9c49FzbeGI46Ch56qOzoJKkypSTUKaXZxfYZ4BJge+DpiBgGUGyf6eS5k1JK41NK44cOHdpdIUuSqmDYMPjxj3Nt9VFHwW9+k0esDzggr8LorCCqRK3rg0eMGF32W1QP1e011BExEOiVUnqluP1+4DvAZcAE4NRie2l3xyY1gw/9uewIJBg+HH72M/jWt/KUe2eeCX/6E2y1FXzhC/Dxj8OgQWVHqXpjfbDKUsZFiesClxRXgrYC56WUroqIO4ELI+II4Ang4BJikxre2s+VHYG0xLrr5hrrE06A3/0uJ9af+xwcfzwcfDB88pOwyy7Qy1UTpC5ZvBheegleeAFefDFv2zf4by6/HN58E954I2/ffBMWLoRFi3JbvHjJ7ZYW6N0bWlvztq3175//6B04EFZbDdZcE9ZYA3rWfBfdp9vfdUppJrBVB/ufA/bo7nikZjN947zdxLpV9SADB+ZE+qij4NZb85R7F14IZ58NI0fCRz+ay0J22in/xy6Vo6WmU8Otv/5Y7rvvEV5+mQ7bK68sfb8tcW7fXnppZaVTxzNtWk6I+/WDAQNyMtzamv9wbWlZ0nr1ysn1ggW5LVy45Pbrr8Mzz8Crr+ZjlniVX/wi/7E8bFj++V133Xy+RuavJanJ3Lpj3ppQqyeKyIvB7LhjLgm59FI477y8rPkZZ8Baa8Gee8Iee+Q2Zkx+jtQ9Fq2wpGTBAnjttZxsvvZaHvmdN6/j1tFjs2fn5HZlBg/Oo8KDB+dR4fXWywsrrbFG52311fN28OA+fPWr1SuLSSkn1S+8AM8/D5de+mMGDfoajzwCd9+dj+ndG0aMgA03zG3ddRvv59aEWpLUIw0YAIcdlturr8LVV8Nll8Ff/wq//30+Zr318iqM228PW24Jm20Go0dbIqLqe+MNgHE8+GAeBW7fXnsttwULOn9+BPTtu6T165dLJtZaC/r0yftuvfWb/PjH32W11XirtSXPbW3QoJ71+Y7IMQ4eDKNGwaWXnsDhh+dlRF5+GZ58Ep54Ah5/PP/s/vWv+T1sskn+I2D06MYYvTahliT1eIMGwYEH5pZSXnXx+uvhttvgjjvySHab/v3zf9KjRsEGG8Daa+fRuSFDlt727ZuPj1gyWhaRv76eP3/JV9sLFqz8PnyFv/89x9bauqS1tCypPR0wYEnNae/e3dl76qqUclnF3Lm5PftsbnPn5lFnmPLWH3MtLfmzNGRIHlUeMCD/2w4cuOR2//5LEujevVc+Knvrrf/FMcd8t9Zvs9usthpsvnlukPv2kUfg4YfhnnvgrrtyH73rXbD11vkP5HplQi1JqisReaq9TTfNM4JAHiV84IEl7bHH8ojYP/8Jzz23bI1nLfwP11/f9aN7984J16BBORlbc808UtnW+vSpXaTKUsojqLNnw5w5S7Y5cc769YOhQ/No6tprw7XXHsiRR17MkCE5aW60soVaGzwYxo3LbcGCPC/9vffmxPqOO3JCPW5cTrAHDCg52LfJhFqSVPeGDIH3vCe3ZaWUv45/8cWceLdt58/Pj7VdwNW2jcgJbdtsBu1vd3S/d29Ye+3BfP3rrxCRL9xqmzGh7fb8+Uvqatu3V1/Nif899ywd8+DBOblYf/0lTZVJCZ5+Ovf3Y4/lMoS25DkiLz608cb5Qrp11skJ9MCBSyfN1177R/8tqqR37/yHyiab5HKae++FqVPhqqvg2mvzH8w77JBrr+vhDxcTaqnJHPDHsiNQ/antzAYAw4dvwKxZj9Xk3BF5JHjQoPyfc228+tbsIy0tS8pJumrBgnxB13PP5fbss/Cvf8GMGe1nbHiSj3wkX7C5666wzTaWjqzI4sVLJ9CPP54vBIRc8rPRRkv+WFl3XfuyTP375+sgtt8+f+6nTs0XNN5/f56z/j3vyfXWPal2fFkm1FKTGfJy2RGo/qx4ZoNqaPYFM3r3zknduusuvX/+/JxgzJ4NV199A9OmfeKtevGBA/M0grvumtt22zV3qciiRQBbc+utOXlun0CvsUYe8Rw9OrchQ8qLUyu23nqwzz7wvvflpPq22+APf8j/ZjvsADC47BA7ZEItNZn7iotDtri/3DgkrVyfPvniylGj4OqrP8n06Z/g6afhppvgxhtz+/rX87H9++eRvF12yQn2u9+da4Ab1cKFeSTzxhvhhhvg738H+CfXXJNr0ttmkNhgAxPoetSnT/4jcdtt4aGHcmJ9zTUAs7jhBthtt3LjW5YJtdRkJm+XtybU6llqW1ZSy5KS7rbuunkVyYOL9YSffTYnk20J9skn5zKRvn3ziF7bCPZ73lN/F3q1N38+TJmS/5i44Qa4+eZ8USHk2uePfQwmTfo4xx57HqutVmqoFah9eVW96dVryUXIs2fDWWddzNZbf7rssJZjQi1J6gFqW1bSyCUla6+dV5E84IB8/4UXcrLZlmCfckpe3r137zzi15Zg77hjvvixp3r55bxq5s0353b77W1zQefk6rDD8ijlrrvmCwkBJk06n9VWO6+0mCtnedWK5AtCP8OQISbUkiSphtZYA/bbLzfIiekttyxJsH/4Q/je95ZMPzh+fG7bbpunLBs4sPtjfumlXL4xZcqSdv/9+cLCXr3yHMVHHQU775xbPc9XrMZkQi1JUgNbbTXYd9/cIE/X949/5JrUyZPhuuvgt7/Nj/Xqlacx22gjeMc7lmzf8Q4YObKyFe3eeCPPtvHoo0vazJl5ysBHHlly3Hrr5QT6ox/NyfMOO/TskXQJTKglSWoqAwfCXnvl1mb27Ly4xuTJeWaFGTPyBWBts2RAXvFx6NAlczS3LYM9YEBOxNumNHvzzZw8v/FGngqwbbXBp59eOo5+/WDMmJw8f+YzeVvvq+WpeZlQS03mkAvLjkBST9M2H3NbmQjkcovZs3NyPWNGHlF+5pnc5s7N21dfzSPeixcvWSSnX78840j//rn8ZKON8gWRo0blBHrs2Lxdb736WLBD6goTaqnJDHh95cdIUq9eeSGcESN63hRlUk/Tg9eckVQLU8flJkmSqsMRaqnJtCXT46aWGYXU3ZzfV1LtmFBLkpqA81xLqh0TakmS6kJtR9l79erL4sXz6vb8UplMqCVJqgu1H2Wv5/O3vYZUBi9KlCRJkirgCLXUZA4/t+wIJElqLCbUUpPpvaDsCCRJaiyWfEhN5s7tcpMkSdVhQi01mfs3z02SJFVHj0uoI2KfiJgeETMi4oSy45EkSZJWpEcl1BHRAvwM2BfYDDgsIjYrNypJkiSpcz0qoQa2B2aklGamlOYDFwD7lxyTJEmS1KmellAPB55sd39WsU+SJEnqkSKl2q5a9HZExMHA3imlzxb3Pwlsn1L6UrtjjgKOKu5uAkzv9kAbw9rAs2UHUcfsv8rYf5Wx/ypj/1XG/quM/Ve5svpwg5TS0I4e6GnzUM8CRra7PwKY3f6AlNIkYFJ3BtWIImJySml82XHUK/uvMvZfZey/yth/lbH/KmP/Va4n9mFPK/m4E9goIsZERB/gUOCykmOSJEmSOtWjRqhTSgsj4ovA1UALcHZK6f6Sw5IkSZI61aMSaoCU0pXAlWXH0QQsm6mM/VcZ+68y9l9l7L/K2H+Vsf8q1+P6sEddlChJkiTVm55WQy1JkiTVFRPqBhERIyPibxExLSLuj4hjiv3fjoinImJq0T7Q7jknFku8T4+Ivdvt3zYi7i0e+9+IiDLeU3eLiMeK9z01IiYX+9aMiGsj4uFiu0a74+2/QkRs0u4zNjUiXo6IL/v561xEnB0Rz0TEfe32Ve3zFhF9I+L3xf7bI2J0t77BGuuk/34YEQ9GxD0RcUlErF7sHx0Rb7T7HP683XPsvyX7qvbz2uj9B5324e/b9d9jETG12O9nsJ3oPGep39+BKSVbAzRgGLBNcXsw8BB5+fZvA8d3cPxmwN1AX2AM8AjQUjx2B/AeIIC/APuW/f66qQ8fA9ZeZt8PgBOK2ycA37f/VtqPLcC/gA38/K2wn3YBtgHuq8XnDfgC8PPi9qHA78t+z93Qf+8HWovb32/Xf6PbH7fMeey/Jfuq9vPa6P3XWR8u8/j/AN/yM9jhe+4sZ6nb34GOUDeIlNKclNI/i9uvANNY8SqT+wMXpJTmpZQeBWYA20fEMGC1lNKtKX8KfwN8pLbR92j7A+cUt89hSV/Yf53bA3gkpfT4Co5p+v5LKd0EPL/M7mp+3tqf6w/AHo002t9R/6WUrkkpLSzu3kZey6BT9t9yn7/O+PnrwIr6sHivhwDnr+gczdqHK8hZ6vZ3oAl1Ayq+1tgauL3Y9cXiK9Cz23190tky78OL28vubwYJuCYi7oq8IifAuimlOZB/AQDrFPvtv84dytL/ifj567pqft7eek6RZL4ErFWzyHuez5BHq9qMiYgpEXFjRLy32Gf/La9aP6/N2n9t3gs8nVJ6uN0+P4MdWCZnqdvfgSbUDSYiBgEXA19OKb0M/B+wITAOmEP+CgryVyPLSivY3wx2SiltA+wLHB0Ru6zgWPuvA5EXZPowcFGxy89fdaxKfzVtX0bE14GFwLnFrjnAqJTS1sBXgPMiYjXsv2VV8+e1GfuvvcNYemDBz2AHOshZOj20g3096jNoQt1AIqI3+YN5bkrpjwAppadTSotSSouBs4Dti8M7W+Z9Fkt/Tbrc8u+NKqU0u9g+A1xC7quni6+U2r6ae6Y43P7r2L7AP1NKT4Ofv1VQzc/bW8+JiFZgCF3/ir9uRcQE4EPA4cVXwBRfEz9X3L6LXH+5MfbfUqr889p0/demeL8fBX7fts/P4PI6ylmo49+BJtQNoqgL+hUwLaV0erv9w9oddgDQdjXyZcChxVWwY4CNgDuKr1heiYh3F+f8FHBpt7yJEkXEwIgY3HabfHHTfeR+mlAcNoElfWH/dWypURk/f29bNT9v7c91EHB9W4LZqCJiH+BrwIdTSq+32z80IlqK22PJ/TfT/ltalX9em67/2tkTeDCl9FYpgp/BpXWWs1DPvwOrdXWjrdwG7Ez+KuMeYGrRPgD8Fri32H8ZMKzdc75O/it5Ou1mUgDGk3+RPgL8lGIBoEZuwFjyFcR3A/cDXy/2rwVcBzxcbNe0/zrtwwHAc8CQdvv8/HXeX+eTvwZeQB5JOaKanzegH7n0Zgb5KvixZb/nbui/GeSaybbfgW1X+B9Y/FzfDfwT2M/+67D/qvbz2uj911kfFvt/DXx+mWP9DC7dH53lLHX7O9CVEiVJkqQKWPIhSZIkVcCEWpIkSaqACbUkSZJUARNqSZIkqQIm1JIkSVIFTKglqYYiIkXEb9vdb42IuRFx+Sqeb/WI+EK7+7t1dq6IuCEixq/kfK+uShySpCVMqCWptl4DtoiI/sX9vYCnKjjf6sAXVnaQJKn7mFBLUu39BfhgcXvZ1STXjIg/RcQ9EXFbRGxZ7P92RJxdjDLPjIh/L55yKrBhREyNiB8W+wZFxB8i4sGIOLdYMYx2r3FERPyo3f0jI+L0ZY7ZrXit5c4TEdtFxD8i4u6IuCMiBkdEv4j4fxFxb0RMiYjdi2MnFu/nzxHxaER8MSK+UhxzW0SsWRy3YURcFRF3RcTfI2LTanW2JHU3E2pJqr0LyMvm9gO2BG5v99jJwJSU0pbAfwK/affYpsDewPbASRHRGzgBeCSlNC6l9NXiuK2BLwObkVf93KmD1/9w8XyATwP/r4M4lztPRPQBfg8ck1Lairys8hvA0QAppXeR/0g4p3h/AFsAHy/iPgV4PaW0NXAreWlggEnAl1JK2wLHA2d22HOSVAdayw5AkhpdSumeiBhNTjyvXObhncnLEpNSuj4i1oqIIcVjV6SU5gHzIuIZYN1OXuKOlNIsgIiYCowGbm73+q9FxPXAhyJiGtA7pXRvF8/zEjAnpXRnca6Xi8d3Bn5S7HswIh4HNi7O87eU0ivAKxHxEvDnYv+9wJYRMQjYEbio3WB6307emyT1eCbUktQ9LgNOA3YD1mq3Pzo4NhXbee32LaLz39ldOe6X5BHwB+l4dLqz80S7eNrrKO6OzrO43f3FxTl7AS+mlMat4BySVDcs+ZCk7nE28J0ORoZvAg6HXMcMPNs2CtyJV4DBb/fFU0q3AyPJpRjnr+Tw9h4E1o+I7YoYB0dE6zJxbwyMAqZ3MZaXgUcj4uDi+RERW72NmCSpRzGhlqRukFKalVI6o4OHvg2Mj4h7yBccTljJeZ4DbomI+9pdlNhVFwK3pJRe6OoTUkrzgY8BP4mIu4FrgX7kmueWiLiXXGM9sShP6arDgSOKc94P7P82nitJPUqk1NE3eZKkRlPMV/2jlNJ1ZcciSY3EEWpJanDFYjAPAW+YTEtS9TlCLUmSJFXAEWpJkiSpAibUkiRJUgVMqCVJkqQKmFBLkiRJFTChliRJkipgQi1JkiRV4P8DFA6cdBtDP+EAAAAASUVORK5CYII=", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "continuos_univariate_analysis(dataset, 'MonthlyIncome', kde=True)" ] }, { "cell_type": "code", "execution_count": 14, "id": "69933d3d", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T16:50:16.477680Z", "start_time": "2022-10-15T16:50:16.465548Z" } }, "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", "
EmployeeNumber
JobRole
Manager162
Research Director90
\n", "
" ], "text/plain": [ " EmployeeNumber\n", "JobRole \n", "Manager 162\n", "Research Director 90" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset[dataset['MonthlyIncome']>16000].groupby('JobRole').agg({'EmployeeNumber':'count'})" ] }, { "cell_type": "code", "execution_count": 15, "id": "0fd1a1a4", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T16:58:28.042867Z", "start_time": "2022-10-15T16:58:28.015763Z" } }, "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", "
MonthlyIncome
AttritionJobRole
YesManager19509.333333
Research Director19395.500000
\n", "
" ], "text/plain": [ " MonthlyIncome\n", "Attrition JobRole \n", "Yes Manager 19509.333333\n", " Research Director 19395.500000" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset[(dataset['MonthlyIncome'] > 16000)\n", " & (dataset['Attrition'] == 'Yes')].groupby(\n", " ['Attrition', 'JobRole']).agg({'MonthlyIncome': 'mean'})" ] }, { "cell_type": "code", "execution_count": 19, "id": "e9460b5c", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T17:02:50.474820Z", "start_time": "2022-10-15T17:02:50.446894Z" } }, "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", "
AttritionNoYes
JobRole
Healthcare Representative7453.5573778548.222222
Human Resources4391.7500003715.750000
Laboratory Technician3337.2233502919.258065
Manager13498.47368412729.500000
Manufacturing Director7289.9259267365.500000
Research Director13158.600000NaN
Research Scientist3328.1224492780.468085
Sales Executive6804.6171007489.000000
Sales Representative2798.4400002364.727273
\n", "
" ], "text/plain": [ "Attrition No Yes\n", "JobRole \n", "Healthcare Representative 7453.557377 8548.222222\n", "Human Resources 4391.750000 3715.750000\n", "Laboratory Technician 3337.223350 2919.258065\n", "Manager 13498.473684 12729.500000\n", "Manufacturing Director 7289.925926 7365.500000\n", "Research Director 13158.600000 NaN\n", "Research Scientist 3328.122449 2780.468085\n", "Sales Executive 6804.617100 7489.000000\n", "Sales Representative 2798.440000 2364.727273" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset[dataset['MonthlyIncome']<=16000].groupby(['Attrition', 'JobRole']).agg({'MonthlyIncome':'mean'}).reset_index()\\\n", " .pivot_table(index='JobRole', columns='Attrition', values='MonthlyIncome')" ] }, { "cell_type": "code", "execution_count": 18, "id": "7b789cce", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T17:07:26.393828Z", "start_time": "2022-10-15T17:07:26.378188Z" } }, "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", "
MonthlyIncomeEmployeeNumber
Attrition
No5601.9361512224
Yes4470.784483464
\n", "
" ], "text/plain": [ " MonthlyIncome EmployeeNumber\n", "Attrition \n", "No 5601.936151 2224\n", "Yes 4470.784483 464" ] }, "execution_count": 18, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset[dataset['MonthlyIncome'] <= 16000].groupby(['Attrition']).agg({\n", " 'MonthlyIncome':\n", " 'mean',\n", " 'EmployeeNumber':\n", " 'count'\n", "})" ] }, { "cell_type": "markdown", "id": "6eb23a68", "metadata": {}, "source": [ "## Observation:\n", "1. Majority of the employees are earning between 2900 dollars to 8000 dollar per month \n", "2. On avg, monthly income is 6000 dollars\n", "3. Those who are earning more than 16000 dollars are treated as outliers \n", "4. 242 employees are earning more than 16000 dollars \n", "5. less than 1% attrition happend for higher salary bracket \n", "6. Those are in higher salary bracket, mostly they are from leadership stacks (Manager/Directors)\n", "7. On avg, those who left the organization were earning less amount of 800 dollars than others \n", "**MonthlyIncome impacts Attrition linearly**" ] }, { "cell_type": "code", "execution_count": 51, "id": "c5778a32", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T17:09:50.974427Z", "start_time": "2022-10-15T17:09:50.704153Z" } }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "continuos_univariate_analysis(dataset, 'DistanceFromHome', kde=True)" ] }, { "cell_type": "code", "execution_count": 20, "id": "ccb378a4", "metadata": {}, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "continuos_univariate_analysis(dataset, 'MonthlyRate', kde=True)" ] }, { "cell_type": "code", "execution_count": 52, "id": "20c5056c", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T17:13:43.784244Z", "start_time": "2022-10-15T17:13:43.765193Z" } }, "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", "
DistanceFromHomeAge
Attrition
No8.91565337.561233
Yes10.63291133.607595
\n", "
" ], "text/plain": [ " DistanceFromHome Age\n", "Attrition \n", "No 8.915653 37.561233\n", "Yes 10.632911 33.607595" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.groupby(['Attrition']).agg({'DistanceFromHome':'mean', 'Age':'mean'})" ] }, { "cell_type": "markdown", "id": "c46f32d9", "metadata": {}, "source": [ "**Binning Technique**" ] }, { "cell_type": "code", "execution_count": 69, "id": "bed5c524", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T17:27:10.396623Z", "start_time": "2022-10-15T17:27:10.378366Z" } }, "outputs": [ { "data": { "text/plain": [ "(-0.001, 10.0] 2052\n", "(10.0, 15.0] 230\n", "(15.0, 30.0] 658\n", "Name: DistanceFromHome, dtype: int64" ] }, "execution_count": 69, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset['DistanceFromHome'].value_counts(bins=[0,10, 15, 30], sort=False)" ] }, { "cell_type": "code", "execution_count": 66, "id": "d0997be0", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T17:25:22.857280Z", "start_time": "2022-10-15T17:25:22.848450Z" } }, "outputs": [], "source": [ "bins = [0, 10, 15, 30]\n", "labels = [\"Short_distance\", \"Moderate_distance\", \"Higher_distance\"]\n", "dataset['distance_class'] = pd.cut(x=dataset['DistanceFromHome'],\n", " bins=bins,\n", " labels=labels,\n", " include_lowest=True)" ] }, { "cell_type": "code", "execution_count": 70, "id": "c8fff089", "metadata": { "ExecuteTime": { "end_time": "2022-10-15T17:28:11.433581Z", "start_time": "2022-10-15T17:28:11.406077Z" } }, "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", "
EmployeeNumberMonthlyIncome
Attritiondistance_class
NoShort_distance17646875.893424
Moderate_distance1806796.722222
Higher_distance5226699.329502
YesShort_distance2884557.256944
Moderate_distance506402.760000
Higher_distance1364679.808824
\n", "
" ], "text/plain": [ " EmployeeNumber MonthlyIncome\n", "Attrition distance_class \n", "No Short_distance 1764 6875.893424\n", " Moderate_distance 180 6796.722222\n", " Higher_distance 522 6699.329502\n", "Yes Short_distance 288 4557.256944\n", " Moderate_distance 50 6402.760000\n", " Higher_distance 136 4679.808824" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataset.groupby(['Attrition', 'distance_class']).agg({'EmployeeNumber':'count', 'MonthlyIncome':'mean'})" ] }, { "cell_type": "markdown", "id": "3a10dbe2", "metadata": {}, "source": [ "## Observation :\n", "\n", "1. Majority of them live between 0 - 10 km of distance from office location \n", "2. very less of number of employees are staying far from office \n", "3. No significant distance observed between those who left and those who stayed(only 2km on avg greater than those who left) \n", "4. Those who stay far away/nearby from the office with lower salary than average are likely to leave the organization \n", "\n", "**Distance with lower income matters**" ] }, { "cell_type": "code", "execution_count": null, "id": "d3431d04", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3.8.8 ('base')", "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": "3.8.8" }, "vscode": { "interpreter": { "hash": "ecd35c037bd360a9223f97d1b9b8f2c86e12889559e066ee9e282756f5cb5240" } } }, "nbformat": 4, "nbformat_minor": 5 }