Capstone Project -Analysis of Employees of an organisation
Lisma Jena
28 December 2017
setwd("C:/Users/lenovo/Desktop/Dataset")
employees.df=read.csv("WA_Fn-UseC_-HR-Employee-Attrition.csv")
View(employees.df)dim(employees.df)## [1] 1470 35The above output shows that the data set contains 1470 rows and 35 columns.
Summary and Description of the Data set.
library(psych)## Warning: package 'psych' was built under R version 3.3.3describe(employees.df)[,c(1:5)]## vars n mean sd median
## ï..Age 1 1470 36.92 9.14 36.0
## Attrition* 2 1470 1.16 0.37 1.0
## BusinessTravel* 3 1470 2.61 0.67 3.0
## DailyRate 4 1470 802.49 403.51 802.0
## Department* 5 1470 2.26 0.53 2.0
## DistanceFromHome 6 1470 9.19 8.11 7.0
## Education 7 1470 2.91 1.02 3.0
## EducationField* 8 1470 3.25 1.33 3.0
## EmployeeCount 9 1470 1.00 0.00 1.0
## EmployeeNumber 10 1470 1024.87 602.02 1020.5
## EnvironmentSatisfaction 11 1470 2.72 1.09 3.0
## Gender* 12 1470 1.60 0.49 2.0
## HourlyRate 13 1470 65.89 20.33 66.0
## JobInvolvement 14 1470 2.73 0.71 3.0
## JobLevel 15 1470 2.06 1.11 2.0
## JobRole* 16 1470 5.46 2.46 6.0
## JobSatisfaction 17 1470 2.73 1.10 3.0
## MaritalStatus* 18 1470 2.10 0.73 2.0
## MonthlyIncome 19 1470 6502.93 4707.96 4919.0
## MonthlyRate 20 1470 14313.10 7117.79 14235.5
## NumCompaniesWorked 21 1470 2.69 2.50 2.0
## Over18* 22 1470 1.00 0.00 1.0
## OverTime* 23 1470 1.28 0.45 1.0
## PercentSalaryHike 24 1470 15.21 3.66 14.0
## PerformanceRating 25 1470 3.15 0.36 3.0
## RelationshipSatisfaction 26 1470 2.71 1.08 3.0
## StandardHours 27 1470 80.00 0.00 80.0
## StockOptionLevel 28 1470 0.79 0.85 1.0
## TotalWorkingYears 29 1470 11.28 7.78 10.0
## TrainingTimesLastYear 30 1470 2.80 1.29 3.0
## WorkLifeBalance 31 1470 2.76 0.71 3.0
## YearsAtCompany 32 1470 7.01 6.13 5.0
## YearsInCurrentRole 33 1470 4.23 3.62 3.0
## YearsSinceLastPromotion 34 1470 2.19 3.22 1.0
## YearsWithCurrManager 35 1470 4.12 3.57 3.0summary(employees.df)## ï..Age Attrition BusinessTravel DailyRate
## Min. :18.00 No :1233 Non-Travel : 150 Min. : 102.0
## 1st Qu.:30.00 Yes: 237 Travel_Frequently: 277 1st Qu.: 465.0
## Median :36.00 Travel_Rarely :1043 Median : 802.0
## Mean :36.92 Mean : 802.5
## 3rd Qu.:43.00 3rd Qu.:1157.0
## Max. :60.00 Max. :1499.0
##
## Department DistanceFromHome Education
## Human Resources : 63 Min. : 1.000 Min. :1.000
## Research & Development:961 1st Qu.: 2.000 1st Qu.:2.000
## Sales :446 Median : 7.000 Median :3.000
## Mean : 9.193 Mean :2.913
## 3rd Qu.:14.000 3rd Qu.:4.000
## Max. :29.000 Max. :5.000
##
## EducationField EmployeeCount EmployeeNumber
## Human Resources : 27 Min. :1 Min. : 1.0
## Life Sciences :606 1st Qu.:1 1st Qu.: 491.2
## Marketing :159 Median :1 Median :1020.5
## Medical :464 Mean :1 Mean :1024.9
## Other : 82 3rd Qu.:1 3rd Qu.:1555.8
## Technical Degree:132 Max. :1 Max. :2068.0
##
## EnvironmentSatisfaction Gender HourlyRate JobInvolvement
## Min. :1.000 Female:588 Min. : 30.00 Min. :1.00
## 1st Qu.:2.000 Male :882 1st Qu.: 48.00 1st Qu.:2.00
## Median :3.000 Median : 66.00 Median :3.00
## Mean :2.722 Mean : 65.89 Mean :2.73
## 3rd Qu.:4.000 3rd Qu.: 83.75 3rd Qu.:3.00
## Max. :4.000 Max. :100.00 Max. :4.00
##
## JobLevel JobRole JobSatisfaction
## Min. :1.000 Sales Executive :326 Min. :1.000
## 1st Qu.:1.000 Research Scientist :292 1st Qu.:2.000
## Median :2.000 Laboratory Technician :259 Median :3.000
## Mean :2.064 Manufacturing Director :145 Mean :2.729
## 3rd Qu.:3.000 Healthcare Representative:131 3rd Qu.:4.000
## Max. :5.000 Manager :102 Max. :4.000
## (Other) :215
## MaritalStatus MonthlyIncome MonthlyRate NumCompaniesWorked
## Divorced:327 Min. : 1009 Min. : 2094 Min. :0.000
## Married :673 1st Qu.: 2911 1st Qu.: 8047 1st Qu.:1.000
## Single :470 Median : 4919 Median :14236 Median :2.000
## Mean : 6503 Mean :14313 Mean :2.693
## 3rd Qu.: 8379 3rd Qu.:20462 3rd Qu.:4.000
## Max. :19999 Max. :26999 Max. :9.000
##
## Over18 OverTime PercentSalaryHike PerformanceRating
## Y:1470 No :1054 Min. :11.00 Min. :3.000
## Yes: 416 1st Qu.:12.00 1st Qu.:3.000
## Median :14.00 Median :3.000
## Mean :15.21 Mean :3.154
## 3rd Qu.:18.00 3rd Qu.:3.000
## Max. :25.00 Max. :4.000
##
## RelationshipSatisfaction StandardHours StockOptionLevel TotalWorkingYears
## Min. :1.000 Min. :80 Min. :0.0000 Min. : 0.00
## 1st Qu.:2.000 1st Qu.:80 1st Qu.:0.0000 1st Qu.: 6.00
## Median :3.000 Median :80 Median :1.0000 Median :10.00
## Mean :2.712 Mean :80 Mean :0.7939 Mean :11.28
## 3rd Qu.:4.000 3rd Qu.:80 3rd Qu.:1.0000 3rd Qu.:15.00
## Max. :4.000 Max. :80 Max. :3.0000 Max. :40.00
##
## TrainingTimesLastYear WorkLifeBalance YearsAtCompany YearsInCurrentRole
## Min. :0.000 Min. :1.000 Min. : 0.000 Min. : 0.000
## 1st Qu.:2.000 1st Qu.:2.000 1st Qu.: 3.000 1st Qu.: 2.000
## Median :3.000 Median :3.000 Median : 5.000 Median : 3.000
## Mean :2.799 Mean :2.761 Mean : 7.008 Mean : 4.229
## 3rd Qu.:3.000 3rd Qu.:3.000 3rd Qu.: 9.000 3rd Qu.: 7.000
## Max. :6.000 Max. :4.000 Max. :40.000 Max. :18.000
##
## YearsSinceLastPromotion YearsWithCurrManager
## Min. : 0.000 Min. : 0.000
## 1st Qu.: 0.000 1st Qu.: 2.000
## Median : 1.000 Median : 3.000
## Mean : 2.188 Mean : 4.123
## 3rd Qu.: 3.000 3rd Qu.: 7.000
## Max. :15.000 Max. :17.000
## One way contigency tables
attach(employees.df)
table(Attrition)## Attrition
## No Yes
## 1233 237table(BusinessTravel)## BusinessTravel
## Non-Travel Travel_Frequently Travel_Rarely
## 150 277 1043table(Department)## Department
## Human Resources Research & Development Sales
## 63 961 446table(Education)## Education
## 1 2 3 4 5
## 170 282 572 398 48table(EducationField)## EducationField
## Human Resources Life Sciences Marketing Medical
## 27 606 159 464
## Other Technical Degree
## 82 132table(EnvironmentSatisfaction)## EnvironmentSatisfaction
## 1 2 3 4
## 284 287 453 446table(Gender)## Gender
## Female Male
## 588 882table(JobInvolvement)## JobInvolvement
## 1 2 3 4
## 83 375 868 144table(JobLevel)## JobLevel
## 1 2 3 4 5
## 543 534 218 106 69table(JobSatisfaction)## JobSatisfaction
## 1 2 3 4
## 289 280 442 459table(MaritalStatus)## MaritalStatus
## Divorced Married Single
## 327 673 470table(OverTime)## OverTime
## No Yes
## 1054 416table(PerformanceRating)## PerformanceRating
## 3 4
## 1244 226table(RelationshipSatisfaction)## RelationshipSatisfaction
## 1 2 3 4
## 276 303 459 432table(StockOptionLevel)## StockOptionLevel
## 0 1 2 3
## 631 596 158 85table(WorkLifeBalance)## WorkLifeBalance
## 1 2 3 4
## 80 344 893 153Two way contigency table
xtabs(~Education+EducationField, data=employees.df)## EducationField
## Education Human Resources Life Sciences Marketing Medical Other
## 1 2 67 14 63 5
## 2 2 116 24 99 19
## 3 16 233 59 183 24
## 4 5 173 52 104 33
## 5 2 17 10 15 1
## EducationField
## Education Technical Degree
## 1 19
## 2 22
## 3 57
## 4 31
## 5 3xtabs(~Department+EducationField, data=employees.df)## EducationField
## Department Human Resources Life Sciences Marketing Medical
## Human Resources 27 16 0 13
## Research & Development 0 440 0 363
## Sales 0 150 159 88
## EducationField
## Department Other Technical Degree
## Human Resources 3 4
## Research & Development 64 94
## Sales 15 34xtabs(~JobLevel+JobInvolvement, data=employees.df)## JobInvolvement
## JobLevel 1 2 3 4
## 1 30 137 318 58
## 2 35 128 317 54
## 3 10 66 128 14
## 4 3 27 62 14
## 5 5 17 43 4xtabs(~WorkLifeBalance+EnvironmentSatisfaction, data=employees.df)## EnvironmentSatisfaction
## WorkLifeBalance 1 2 3 4
## 1 20 13 22 25
## 2 67 78 100 99
## 3 167 171 278 277
## 4 30 25 53 45xtabs(~OverTime+PerformanceRating, data=employees.df)## PerformanceRating
## OverTime 3 4
## No 893 161
## Yes 351 65aggregate(cbind(DailyRate,YearsAtCompany,MonthlyIncome) ~ Gender,
data = employees.df, mean)## Gender DailyRate YearsAtCompany MonthlyIncome
## 1 Female 808.2738 7.231293 6686.566
## 2 Male 798.6270 6.859410 6380.508library(car)## Warning: package 'car' was built under R version 3.3.3##
## Attaching package: 'car'## The following object is masked from 'package:psych':
##
## logitscatterplot(MonthlyIncome~YearsAtCompany,data=employees.df,main="Distribution of monthly income with work experience",ylab="Monthly Income",xlab = "Years at company")
boxplot(MonthlyIncome~YearsAtCompany,data=employees.df,main="Distribution of monthly income with work experience",ylab="Monthly Income",xlab = "Years at company",col="blue")
boxplot(MonthlyIncome~JobSatisfaction,data=employees.df,main="Distribution of monthly income with job satisfaction",ylab="Monthly Income",xlab = "Job Satisfaction")
boxplot(MonthlyIncome~JobSatisfaction,data=employees.df,main="Distribution of monthly income with job satisfaction",ylab="Monthly Income",xlab = "Job Satisfaction",col="red")
boxplot(PercentSalaryHike~JobSatisfaction,data=employees.df,main="Distribution of percent salary hike with job satisfaction",ylab="Percent Salary Hike",xlab = "Job Satisfaction",col="blue")
boxplot(DistanceFromHome~EnvironmentSatisfaction,data=employees.df,main="Distribution of distance from home with enviornment satisfaction",ylab="Distance from home",xlab = "Enviornment Satisfaction",col="red")
library(corrplot)## Warning: package 'corrplot' was built under R version 3.3.3## corrplot 0.84 loadedcolnames(employees.df)## [1] "ï..Age" "Attrition"
## [3] "BusinessTravel" "DailyRate"
## [5] "Department" "DistanceFromHome"
## [7] "Education" "EducationField"
## [9] "EmployeeCount" "EmployeeNumber"
## [11] "EnvironmentSatisfaction" "Gender"
## [13] "HourlyRate" "JobInvolvement"
## [15] "JobLevel" "JobRole"
## [17] "JobSatisfaction" "MaritalStatus"
## [19] "MonthlyIncome" "MonthlyRate"
## [21] "NumCompaniesWorked" "Over18"
## [23] "OverTime" "PercentSalaryHike"
## [25] "PerformanceRating" "RelationshipSatisfaction"
## [27] "StandardHours" "StockOptionLevel"
## [29] "TotalWorkingYears" "TrainingTimesLastYear"
## [31] "WorkLifeBalance" "YearsAtCompany"
## [33] "YearsInCurrentRole" "YearsSinceLastPromotion"
## [35] "YearsWithCurrManager"dataColumns <-employees.df[,c("ï..Age","DailyRate","DistanceFromHome","Education","EmployeeCount","EnvironmentSatisfaction","HourlyRate","JobInvolvement","JobLevel","JobSatisfaction","MonthlyIncome","MonthlyRate","NumCompaniesWorked","PercentSalaryHike","PerformanceRating","RelationshipSatisfaction","StandardHours","StockOptionLevel","TotalWorkingYears","TrainingTimesLastYear","WorkLifeBalance","YearsAtCompany","YearsInCurrentRole","YearsSinceLastPromotion","YearsWithCurrManager")]Co relation matrix
res <- cor(dataColumns)## Warning in cor(dataColumns): the standard deviation is zeroround(res, 2)## ï..Age DailyRate DistanceFromHome Education
## ï..Age 1.00 0.01 0.00 0.21
## DailyRate 0.01 1.00 0.00 -0.02
## DistanceFromHome 0.00 0.00 1.00 0.02
## Education 0.21 -0.02 0.02 1.00
## EmployeeCount NA NA NA NA
## EnvironmentSatisfaction 0.01 0.02 -0.02 -0.03
## HourlyRate 0.02 0.02 0.03 0.02
## JobInvolvement 0.03 0.05 0.01 0.04
## JobLevel 0.51 0.00 0.01 0.10
## JobSatisfaction 0.00 0.03 0.00 -0.01
## MonthlyIncome 0.50 0.01 -0.02 0.09
## MonthlyRate 0.03 -0.03 0.03 -0.03
## NumCompaniesWorked 0.30 0.04 -0.03 0.13
## PercentSalaryHike 0.00 0.02 0.04 -0.01
## PerformanceRating 0.00 0.00 0.03 -0.02
## RelationshipSatisfaction 0.05 0.01 0.01 -0.01
## StandardHours NA NA NA NA
## StockOptionLevel 0.04 0.04 0.04 0.02
## TotalWorkingYears 0.68 0.01 0.00 0.15
## TrainingTimesLastYear -0.02 0.00 -0.04 -0.03
## WorkLifeBalance -0.02 -0.04 -0.03 0.01
## YearsAtCompany 0.31 -0.03 0.01 0.07
## YearsInCurrentRole 0.21 0.01 0.02 0.06
## YearsSinceLastPromotion 0.22 -0.03 0.01 0.05
## YearsWithCurrManager 0.20 -0.03 0.01 0.07
## EmployeeCount EnvironmentSatisfaction HourlyRate
## ï..Age NA 0.01 0.02
## DailyRate NA 0.02 0.02
## DistanceFromHome NA -0.02 0.03
## Education NA -0.03 0.02
## EmployeeCount 1 NA NA
## EnvironmentSatisfaction NA 1.00 -0.05
## HourlyRate NA -0.05 1.00
## JobInvolvement NA -0.01 0.04
## JobLevel NA 0.00 -0.03
## JobSatisfaction NA -0.01 -0.07
## MonthlyIncome NA -0.01 -0.02
## MonthlyRate NA 0.04 -0.02
## NumCompaniesWorked NA 0.01 0.02
## PercentSalaryHike NA -0.03 -0.01
## PerformanceRating NA -0.03 0.00
## RelationshipSatisfaction NA 0.01 0.00
## StandardHours NA NA NA
## StockOptionLevel NA 0.00 0.05
## TotalWorkingYears NA 0.00 0.00
## TrainingTimesLastYear NA -0.02 -0.01
## WorkLifeBalance NA 0.03 0.00
## YearsAtCompany NA 0.00 -0.02
## YearsInCurrentRole NA 0.02 -0.02
## YearsSinceLastPromotion NA 0.02 -0.03
## YearsWithCurrManager NA 0.00 -0.02
## JobInvolvement JobLevel JobSatisfaction
## ï..Age 0.03 0.51 0.00
## DailyRate 0.05 0.00 0.03
## DistanceFromHome 0.01 0.01 0.00
## Education 0.04 0.10 -0.01
## EmployeeCount NA NA NA
## EnvironmentSatisfaction -0.01 0.00 -0.01
## HourlyRate 0.04 -0.03 -0.07
## JobInvolvement 1.00 -0.01 -0.02
## JobLevel -0.01 1.00 0.00
## JobSatisfaction -0.02 0.00 1.00
## MonthlyIncome -0.02 0.95 -0.01
## MonthlyRate -0.02 0.04 0.00
## NumCompaniesWorked 0.02 0.14 -0.06
## PercentSalaryHike -0.02 -0.03 0.02
## PerformanceRating -0.03 -0.02 0.00
## RelationshipSatisfaction 0.03 0.02 -0.01
## StandardHours NA NA NA
## StockOptionLevel 0.02 0.01 0.01
## TotalWorkingYears -0.01 0.78 -0.02
## TrainingTimesLastYear -0.02 -0.02 -0.01
## WorkLifeBalance -0.01 0.04 -0.02
## YearsAtCompany -0.02 0.53 0.00
## YearsInCurrentRole 0.01 0.39 0.00
## YearsSinceLastPromotion -0.02 0.35 -0.02
## YearsWithCurrManager 0.03 0.38 -0.03
## MonthlyIncome MonthlyRate NumCompaniesWorked
## ï..Age 0.50 0.03 0.30
## DailyRate 0.01 -0.03 0.04
## DistanceFromHome -0.02 0.03 -0.03
## Education 0.09 -0.03 0.13
## EmployeeCount NA NA NA
## EnvironmentSatisfaction -0.01 0.04 0.01
## HourlyRate -0.02 -0.02 0.02
## JobInvolvement -0.02 -0.02 0.02
## JobLevel 0.95 0.04 0.14
## JobSatisfaction -0.01 0.00 -0.06
## MonthlyIncome 1.00 0.03 0.15
## MonthlyRate 0.03 1.00 0.02
## NumCompaniesWorked 0.15 0.02 1.00
## PercentSalaryHike -0.03 -0.01 -0.01
## PerformanceRating -0.02 -0.01 -0.01
## RelationshipSatisfaction 0.03 0.00 0.05
## StandardHours NA NA NA
## StockOptionLevel 0.01 -0.03 0.03
## TotalWorkingYears 0.77 0.03 0.24
## TrainingTimesLastYear -0.02 0.00 -0.07
## WorkLifeBalance 0.03 0.01 -0.01
## YearsAtCompany 0.51 -0.02 -0.12
## YearsInCurrentRole 0.36 -0.01 -0.09
## YearsSinceLastPromotion 0.34 0.00 -0.04
## YearsWithCurrManager 0.34 -0.04 -0.11
## PercentSalaryHike PerformanceRating
## ï..Age 0.00 0.00
## DailyRate 0.02 0.00
## DistanceFromHome 0.04 0.03
## Education -0.01 -0.02
## EmployeeCount NA NA
## EnvironmentSatisfaction -0.03 -0.03
## HourlyRate -0.01 0.00
## JobInvolvement -0.02 -0.03
## JobLevel -0.03 -0.02
## JobSatisfaction 0.02 0.00
## MonthlyIncome -0.03 -0.02
## MonthlyRate -0.01 -0.01
## NumCompaniesWorked -0.01 -0.01
## PercentSalaryHike 1.00 0.77
## PerformanceRating 0.77 1.00
## RelationshipSatisfaction -0.04 -0.03
## StandardHours NA NA
## StockOptionLevel 0.01 0.00
## TotalWorkingYears -0.02 0.01
## TrainingTimesLastYear -0.01 -0.02
## WorkLifeBalance 0.00 0.00
## YearsAtCompany -0.04 0.00
## YearsInCurrentRole 0.00 0.03
## YearsSinceLastPromotion -0.02 0.02
## YearsWithCurrManager -0.01 0.02
## RelationshipSatisfaction StandardHours
## ï..Age 0.05 NA
## DailyRate 0.01 NA
## DistanceFromHome 0.01 NA
## Education -0.01 NA
## EmployeeCount NA NA
## EnvironmentSatisfaction 0.01 NA
## HourlyRate 0.00 NA
## JobInvolvement 0.03 NA
## JobLevel 0.02 NA
## JobSatisfaction -0.01 NA
## MonthlyIncome 0.03 NA
## MonthlyRate 0.00 NA
## NumCompaniesWorked 0.05 NA
## PercentSalaryHike -0.04 NA
## PerformanceRating -0.03 NA
## RelationshipSatisfaction 1.00 NA
## StandardHours NA 1
## StockOptionLevel -0.05 NA
## TotalWorkingYears 0.02 NA
## TrainingTimesLastYear 0.00 NA
## WorkLifeBalance 0.02 NA
## YearsAtCompany 0.02 NA
## YearsInCurrentRole -0.02 NA
## YearsSinceLastPromotion 0.03 NA
## YearsWithCurrManager 0.00 NA
## StockOptionLevel TotalWorkingYears
## ï..Age 0.04 0.68
## DailyRate 0.04 0.01
## DistanceFromHome 0.04 0.00
## Education 0.02 0.15
## EmployeeCount NA NA
## EnvironmentSatisfaction 0.00 0.00
## HourlyRate 0.05 0.00
## JobInvolvement 0.02 -0.01
## JobLevel 0.01 0.78
## JobSatisfaction 0.01 -0.02
## MonthlyIncome 0.01 0.77
## MonthlyRate -0.03 0.03
## NumCompaniesWorked 0.03 0.24
## PercentSalaryHike 0.01 -0.02
## PerformanceRating 0.00 0.01
## RelationshipSatisfaction -0.05 0.02
## StandardHours NA NA
## StockOptionLevel 1.00 0.01
## TotalWorkingYears 0.01 1.00
## TrainingTimesLastYear 0.01 -0.04
## WorkLifeBalance 0.00 0.00
## YearsAtCompany 0.02 0.63
## YearsInCurrentRole 0.05 0.46
## YearsSinceLastPromotion 0.01 0.40
## YearsWithCurrManager 0.02 0.46
## TrainingTimesLastYear WorkLifeBalance
## ï..Age -0.02 -0.02
## DailyRate 0.00 -0.04
## DistanceFromHome -0.04 -0.03
## Education -0.03 0.01
## EmployeeCount NA NA
## EnvironmentSatisfaction -0.02 0.03
## HourlyRate -0.01 0.00
## JobInvolvement -0.02 -0.01
## JobLevel -0.02 0.04
## JobSatisfaction -0.01 -0.02
## MonthlyIncome -0.02 0.03
## MonthlyRate 0.00 0.01
## NumCompaniesWorked -0.07 -0.01
## PercentSalaryHike -0.01 0.00
## PerformanceRating -0.02 0.00
## RelationshipSatisfaction 0.00 0.02
## StandardHours NA NA
## StockOptionLevel 0.01 0.00
## TotalWorkingYears -0.04 0.00
## TrainingTimesLastYear 1.00 0.03
## WorkLifeBalance 0.03 1.00
## YearsAtCompany 0.00 0.01
## YearsInCurrentRole -0.01 0.05
## YearsSinceLastPromotion 0.00 0.01
## YearsWithCurrManager 0.00 0.00
## YearsAtCompany YearsInCurrentRole
## ï..Age 0.31 0.21
## DailyRate -0.03 0.01
## DistanceFromHome 0.01 0.02
## Education 0.07 0.06
## EmployeeCount NA NA
## EnvironmentSatisfaction 0.00 0.02
## HourlyRate -0.02 -0.02
## JobInvolvement -0.02 0.01
## JobLevel 0.53 0.39
## JobSatisfaction 0.00 0.00
## MonthlyIncome 0.51 0.36
## MonthlyRate -0.02 -0.01
## NumCompaniesWorked -0.12 -0.09
## PercentSalaryHike -0.04 0.00
## PerformanceRating 0.00 0.03
## RelationshipSatisfaction 0.02 -0.02
## StandardHours NA NA
## StockOptionLevel 0.02 0.05
## TotalWorkingYears 0.63 0.46
## TrainingTimesLastYear 0.00 -0.01
## WorkLifeBalance 0.01 0.05
## YearsAtCompany 1.00 0.76
## YearsInCurrentRole 0.76 1.00
## YearsSinceLastPromotion 0.62 0.55
## YearsWithCurrManager 0.77 0.71
## YearsSinceLastPromotion YearsWithCurrManager
## ï..Age 0.22 0.20
## DailyRate -0.03 -0.03
## DistanceFromHome 0.01 0.01
## Education 0.05 0.07
## EmployeeCount NA NA
## EnvironmentSatisfaction 0.02 0.00
## HourlyRate -0.03 -0.02
## JobInvolvement -0.02 0.03
## JobLevel 0.35 0.38
## JobSatisfaction -0.02 -0.03
## MonthlyIncome 0.34 0.34
## MonthlyRate 0.00 -0.04
## NumCompaniesWorked -0.04 -0.11
## PercentSalaryHike -0.02 -0.01
## PerformanceRating 0.02 0.02
## RelationshipSatisfaction 0.03 0.00
## StandardHours NA NA
## StockOptionLevel 0.01 0.02
## TotalWorkingYears 0.40 0.46
## TrainingTimesLastYear 0.00 0.00
## WorkLifeBalance 0.01 0.00
## YearsAtCompany 0.62 0.77
## YearsInCurrentRole 0.55 0.71
## YearsSinceLastPromotion 1.00 0.51
## YearsWithCurrManager 0.51 1.00N <- cor(dataColumns)## Warning in cor(dataColumns): the standard deviation is zeropairs(dataColumns[1:6])
pairs(dataColumns[7:12])
pairs(dataColumns[13:18])
table_travel<-table(employees.df$BusinessTravel, employees.df$Attrition)
chisq.test(table_travel)##
## Pearson's Chi-squared test
##
## data: table_travel
## X-squared = 24.182, df = 2, p-value = 5.609e-06t.test(DistanceFromHome~Attrition, data=employees.df)##
## Welch Two Sample t-test
##
## data: DistanceFromHome by Attrition
## t = -2.8882, df = 322.72, p-value = 0.004137
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -2.8870025 -0.5475146
## sample estimates:
## mean in group No mean in group Yes
## 8.915653 10.632911t.test(JobLevel~Attrition, data=employees.df)##
## Welch Two Sample t-test
##
## data: JobLevel by Attrition
## t = 7.3859, df = 376.25, p-value = 9.845e-13
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.3733861 0.6443231
## sample estimates:
## mean in group No mean in group Yes
## 2.145985 1.637131table_role<-table(employees.df$JobRole, employees.df$Attrition)
chisq.test(table_role)##
## Pearson's Chi-squared test
##
## data: table_role
## X-squared = 86.19, df = 8, p-value = 2.752e-15table_job_sat<-table(employees.df$JobSatisfaction, employees.df$Attrition)
chisq.test(table_job_sat)##
## Pearson's Chi-squared test
##
## data: table_job_sat
## X-squared = 17.505, df = 3, p-value = 0.0005563So we can conclude that Attrition depends on : Business Travel ,Distance From Home ,Job Level ,Job Role ,Job Satisfaction
Relation between attrition and other variables:
library(ggplot2)##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphalibrary(grid)
library(gridExtra)## Warning: package 'gridExtra' was built under R version 3.3.3a<-ggplot(employees.df,aes(ï..Age,fill=Attrition))+geom_density()+facet_grid(~Attrition)
b<-ggplot(employees.df,aes(BusinessTravel,fill=Attrition))+geom_bar()
grid.arrange(a,b,ncol=2)
It can be infered that employee with the age close to 30 face attrition.Employee who travel rarely leave the most.
c<-ggplot(employees.df,aes(DailyRate,fill=Attrition))+geom_bar()
d<-ggplot(employees.df,aes(Department,fill=Attrition))+geom_bar()
grid.arrange(c,d,ncol=2)
Hence attrition was lowest fom the HR department.
e<-ggplot(employees.df,aes(DistanceFromHome,fill=Attrition))+geom_bar()
f<-ggplot(employees.df,aes(Education,fill=Attrition))+geom_bar()
grid.arrange(e,f,ncol=2)
Employees who have left the organization are near to the Office.
g<-ggplot(employees.df,aes(EducationField,fill=Attrition))+geom_bar()
h<-ggplot(employees.df,aes(EmployeeCount,fill=Attrition))+geom_bar()
grid.arrange(g,h,ncol=2)
i<-ggplot(employees.df,aes(EmployeeNumber,fill=Attrition))+geom_bar()
j<-ggplot(employees.df,aes(EnvironmentSatisfaction,fill=Attrition))+geom_bar()
grid.arrange(i,j,ncol=2)
k<-ggplot(employees.df,aes(Gender,fill=Attrition))+geom_bar()
l<-ggplot(employees.df,aes(HourlyRate,fill=Attrition))+geom_bar()
grid.arrange(k,l,ncol=2)
m<-ggplot(employees.df,aes(JobInvolvement,fill=Attrition))+geom_bar()
n<-ggplot(employees.df,aes(JobLevel,fill=Attrition))+geom_bar()
grid.arrange(m,n,ncol=2)
o<-ggplot(employees.df,aes(JobRole,fill=Attrition))+geom_bar()
p<-ggplot(employees.df,aes(JobSatisfaction,fill=Attrition))+geom_bar()
grid.arrange(o,p,ncol=2)
q<-ggplot(employees.df,aes(MaritalStatus,fill=Attrition))+geom_bar()
r<-ggplot(employees.df,aes(MonthlyIncome,fill=Attrition))+geom_density()
grid.arrange(q,r,ncol=2)
s<-ggplot(employees.df,aes(MonthlyRate,fill=Attrition))+geom_bar()
t<-ggplot(employees.df,aes(NumCompaniesWorked,fill=Attrition))+geom_bar()
grid.arrange(s,t,ncol=2)
u<-ggplot(employees.df,aes(Over18,fill=Attrition))+geom_bar()
v<-ggplot(employees.df,aes(OverTime,fill=Attrition))+geom_bar()
grid.arrange(u,v,ncol=2)
w<-ggplot(employees.df,aes(PercentSalaryHike,fill=Attrition))+geom_bar()
x<-ggplot(employees.df,aes(PerformanceRating,fill=Attrition))+geom_bar()
grid.arrange(w,x,ncol=2)
y<-ggplot(employees.df,aes(RelationshipSatisfaction,fill=Attrition))+geom_bar()
z<-ggplot(employees.df,aes(StandardHours,fill=Attrition))+geom_bar()
grid.arrange(w,z,ncol=2)
Employees whose percent salary hike is lesser usually leave.
a1<-ggplot(employees.df,aes(StockOptionLevel,fill=Attrition))+geom_bar()
a2<-ggplot(employees.df,aes(TotalWorkingYears,fill=Attrition))+geom_bar()
grid.arrange(a1,a2,ncol=2)
a3<-ggplot(employees.df,aes(TrainingTimesLastYear,fill=Attrition))+geom_bar()
a4<-ggplot(employees.df,aes(WorkLifeBalance,fill=Attrition))+geom_bar()
grid.arrange(a3,a4,ncol=2)
a5<-ggplot(employees.df,aes(YearsAtCompany,fill=Attrition))+geom_bar()
a6<-ggplot(employees.df,aes(YearsInCurrentRole,fill=Attrition))+geom_bar()
grid.arrange(a5,a6,ncol=2)
a7<-ggplot(employees.df,aes(YearsSinceLastPromotion,fill=Attrition))+geom_bar()
a8<-ggplot(employees.df,aes(YearsWithCurrManager,fill=Attrition))+geom_bar()
grid.arrange(a7,a8,ncol=2)
A large proportion of employees having no experience with current manager leave.