Loading the Data

load("HRData.rda")
attach(HR.df)

Number of rows & columns in the dataframe

dim(HR.df)

## [1] 8995   16

Column names of the dataframe

colnames(HR.df)

##  [1] "DOJExtended"              "DurationToAcceptOffer"   
##  [3] "NoticePeriod"             "OfferedBand"             
##  [5] "PercentHikeExpectedInCTC" "PercentHikeOfferedInCTC" 
##  [7] "PercentDifferenceCTC"     "JoiningBonus"            
##  [9] "CandidateRelocateActual"  "Gender"                  
## [11] "CandidateSource"          "RexInYrs"                
## [13] "LOB"                      "Location"                
## [15] "Age"                      "Status"

Descriptive Statistics of the dataframe

require('psych')
describe(HR.df)[1:5]

Percentage of the candidates (Joined / Not joined)

tab1 <- round(prop.table(table(Status))*100, 2)
tab1

## Status
##    Joined NotJoined 
##      81.3      18.7

Bar Chart for % of the Candidates Who Joined / Did Not Join the Company

bp <- barplot(
    tab1,
    main = "% of the Candidates who joined/ did not join the company",
    xlab = "Status",
    ylab = "Percentage(%)",
    col = c('lightblue', 'red'),
    legend = rownames(tab1),
                      beside = TRUE,
                      ylim = c(0, 90))
text(bp, 0, round(tab1, 1), cex = 1, pos = 3) 

Percentage of the candidates Joined / Did Not Join the Company, Split by DOJ extended

round(prop.table(table(DOJExtended, Status), 1)*100, 2)

##            Status
## DOJExtended Joined NotJoined
##         No   81.08     18.92
##         Yes  81.55     18.45

Bar Chart for % of Candidates Who Did Not Join, Split by DOJ Extended

tab2 <- round(prop.table(table(DOJExtended, Status), 1)*100, 2)[3:4]
bp <- barplot(
    tab2,
    main = "% of the Candidates, who did not join, split by DOJ Extended",
    xlab = "DOJ Extended",
    ylab = "Percentage(%)",
    col = 'lightblue',
    legend = rownames(tab2),
                      beside = TRUE,
                      ylim = c(0, 20))
text(bp, 0, round(tab2, 1), cex = 1, pos = 3) 

Percentage of Candidates Who (Joined / Did Not Join), split by Notice Period

round(prop.table(table(NoticePeriod, Status), 1)*100, 2)

##             Status
## NoticePeriod Joined NotJoined
##          0    93.44      6.56
##          30   85.17     14.83
##          45   75.48     24.52
##          60   73.22     26.78
##          75   68.18     31.82
##          90   66.19     33.81
##          120  52.38     47.62

Bar Chart for % of Candidates, Who Did Not Join, Split by Notice Period

tab3 <- round(prop.table(table(NoticePeriod, Status), 1)*100, 2)[,2]
bp <- barplot(
    tab3,
    main = "% of the Candidates, who did not join, split by Notice Period",
    xlab = "NoticePeriod",
    ylab = "Percentage(%)",
    col = 'lightblue',
    legend = rownames(tab3),
                      beside = TRUE)
text(bp, 0, round(tab3, 1), cex = 1, pos = 3)

Percentage of the Candidates Who (Joined / Did Not Join), split by Joining Bonus

round(prop.table(table(JoiningBonus, Status), 1)*100, 2)

##             Status
## JoiningBonus Joined NotJoined
##          No   81.34     18.66
##          Yes  80.58     19.42

Bar Chart for % of Candidates, Who Did Not Join, Split by Joining Bonus

tab4 <- round(prop.table(table(JoiningBonus, Status), 1)*100, 2)[,2]
bp <- barplot(
    tab4,
    main = "% of the Candidates, who did not join, split by Joining Bonus",
    xlab = "Joining Bonus",
    ylab = "Percentage(%)",
    col = 'lightblue',
    legend = rownames(tab4),
                      beside = TRUE)
text(bp, 0, round(tab4, 1), cex = 1, pos = 3)

Percentage of the Candidates Who (Joined / Did Not Join), Split by Gender

round(prop.table(table(Gender, Status), 1)*100, 2)

##         Status
## Gender   Joined NotJoined
##   Female  82.40     17.60
##   Male    81.07     18.93

Bar Chart for % of the Candidates Who Did Not join, Split by Gender

tab5 <- round(prop.table(table(Gender, Status), 1)*100, 2)[,2]
bp <- barplot(
    tab5,
    main = "% of the Candidates, who did not join, split by Gender",
    xlab = "Gender",
    ylab = "Percentage(%)",
    col = 'lightblue',
    legend = rownames(tab5),
                      beside = TRUE)
text(bp, 0, round(tab5, 1), cex = 1, pos = 3)

Percentage of the Candidates Who (Joined / Did Not Join), Split by Candidate Source

round(prop.table(table(CandidateSource, Status), 1)*100, 2)

##                    Status
## CandidateSource     Joined NotJoined
##   Agency             75.82     24.18
##   Direct             82.00     18.00
##   Employee Referral  88.00     12.00

Bar Chart for % of Candidates Who Did Not Join the Company, Split by Candidate Source

tab6 <- round(prop.table(table(CandidateSource, Status), 1)*100, 2)[,2]
bp <- barplot(
    tab6,
    main = "% of the Candidates, who did not join, split by Candidate Source",
    xlab = "Candidate Source",
    ylab = "Percentage(%)",
    col = 'lightblue',
    legend = rownames(tab6),
                      beside = TRUE)
text(bp, 0, round(tab6, 1), cex = 1, pos = 3)

Percentage of the Candidates Who (Joined / Did Not Join), Split by Offered Band

round(prop.table(table(OfferedBand, Status), 1)*100, 2)

##            Status
## OfferedBand Joined NotJoined
##          E0  76.30     23.70
##          E1  81.30     18.70
##          E2  80.97     19.03
##          E3  85.15     14.85

Bar Chart for % Candidates Who Did Not Join, Split by Offered Band

tab7 <- round(prop.table(table(OfferedBand, Status), 1)*100, 2)[,2]
bp <- barplot(
    tab7,
    main = "% of the Candidates, who did not join, split by Offered Band",
    xlab = "Offered Band",
    ylab = "Percentage(%)",
    col = 'lightblue',
    legend = rownames(tab7),
                      beside = TRUE)
text(bp, 0, round(tab7, 1), cex = 1, pos = 3)

Percentage of the Candidates Who (Joined / Did Not join), Split by Line of Business (LOB)

round(prop.table(table(LOB, Status), 1)*100, 2)

##             Status
## LOB          Joined NotJoined
##   AXON        77.46     22.54
##   BFSI        75.86     24.14
##   CSMP        81.52     18.48
##   EAS         73.41     26.59
##   ERS         78.11     21.89
##   ETS         83.07     16.93
##   Healthcare  82.26     17.74
##   INFRA       87.79     12.21
##   MMS        100.00      0.00

Bar Chart for % of the Candidates Who Did Not join, Split by Line of Business (LOB)

tab8 <- round(prop.table(table(LOB, Status), 1)*100, 2)[,2]
bp <- barplot(
    tab8,
    main = "% of the Candidates, who did not join, split by Line of Business",
    xlab = "LOB",
    ylab = "Percentage(%)",
    col = 'lightblue',
    legend = rownames(tab8),
                      beside = TRUE)
text(bp, 0, round(tab8, 1), cex = 1, pos = 3)

Average Age of the Candidates (Joined/Did Not join)

library(data.table)
dt <- data.table(HR.df)
dt[, .(AverageAgeofCandidates = round(mean(Age), 2)),
            by=list(Status)]

Mean Plot for the Age, Split by Status

require('gplots')

## Warning: package 'gplots' was built under R version 3.6.1

plotmeans(Age~Status, data=HR.df,barcol = 'blue',mean.labels = T,col = 'red',n.label = F,digits = 2)

Boxplot of Age, Split by Status (Joined / Did Not Join)

boxplot(Age~Status,main="Boxplot of Age by Status", xlab = "Status", ylab = "Age (in Years",col=c('lightblue','red'))

Average Age of the Candidates (Joined/Did Not join)

dt[, .(AverageNoticePeriod = round(mean(NoticePeriod), 2)),
            by=list(Status)]

Mean Plot for Notice Period, Split by Status (Joined / Did Not join)

plotmeans(
    NoticePeriod ~ Status,
    data = HR.df,
    mean.labels = T,
    col = 'red',
    barcol = 'blue',
    digits = 2,
    n.label = F
)

## Warning in arrows(x, li, x, pmax(y - gap, li), col = barcol, lwd = lwd, :
## zero-length arrow is of indeterminate angle and so skipped

## Warning in arrows(x, ui, x, pmin(y + gap, ui), col = barcol, lwd = lwd, :
## zero-length arrow is of indeterminate angle and so skipped

Boxplot for Notice Period of the Candidates, Split by Status (Joined / Did Not join)

boxplot(NoticePeriod~Status,main="Boxplot of Notice Period, Split by Status", xlab = "NoticePeriod", ylab = "Notice Period",col=c('lightblue','red'))

Average (Relevant Years of Experience) of the candidates (Joined / Not joined)

dt[, .(YearsOfExperience = round(mean(RexInYrs), 2)),
            by=list(Status)]

Mean Plot for the above

plotmeans(RexInYrs~Status, data=HR.df,barcol = 'blue',mean.labels = T,col = 'red',n.label = F,ylab = "Relevant Years of Experience",digits = 2)

Boxplot of Relevant Years of Experience of the candidates (Joined / Not joined)

boxplot(RexInYrs~Status,main="Boxplot of Relevant Years of Experience by Status", xlab = "Status", ylab = "Notice Period",col=c('lightblue','red'))

Average of DurationToAcceptOffer (Number of days taken by the candidate to accept the offer) of candidates (Joined / Not joined)

dt[, .(DurationToAcceptOffer = round(mean(DurationToAcceptOffer), 2)),
            by=list(Status)]

Mean plot for the above

plotmeans(DurationToAcceptOffer~Status, data=HR.df,barcol = 'blue',mean.labels = T,col = 'red',n.label = F,ylab = "Duration To Accept Offer",digits = 2)

Average (Age, Relevant Years of Experience and Number of days taken by the candidate to accept the offer) of candidates (Joined / Not joined) by Gender (Male / Female)

dt[,list(AverageAgeofCandidates = round(mean(Age), 2), 
                  YearsOfExperience = round(mean(RexInYrs), 2), 
                  DurationtoAcceptOffer = round(mean(DurationToAcceptOffer), 2),NoticePeriod = round(mean(NoticePeriod), 2)),
            by=list(Status, Gender)][order(Status, Gender)]

Correlation Matrix for all the Continuous Variable

require("Hmisc")
rcorr(as.matrix(HR.df[,c(2,3,6,7,12,15)]))

##                         DurationToAcceptOffer NoticePeriod
## DurationToAcceptOffer                    1.00         0.36
## NoticePeriod                             0.36         1.00
## PercentHikeOfferedInCTC                  0.01        -0.01
## PercentDifferenceCTC                    -0.01        -0.02
## RexInYrs                                 0.11         0.18
## Age                                      0.02         0.00
##                         PercentHikeOfferedInCTC PercentDifferenceCTC
## DurationToAcceptOffer                      0.01                -0.01
## NoticePeriod                              -0.01                -0.02
## PercentHikeOfferedInCTC                    1.00                 0.60
## PercentDifferenceCTC                       0.60                 1.00
## RexInYrs                                  -0.11                 0.08
## Age                                       -0.08                 0.04
##                         RexInYrs   Age
## DurationToAcceptOffer       0.11  0.02
## NoticePeriod                0.18  0.00
## PercentHikeOfferedInCTC    -0.11 -0.08
## PercentDifferenceCTC        0.08  0.04
## RexInYrs                    1.00  0.57
## Age                         0.57  1.00
## 
## n= 8995 
## 
## 
## P
##                         DurationToAcceptOffer NoticePeriod
## DurationToAcceptOffer                         0.0000      
## NoticePeriod            0.0000                            
## PercentHikeOfferedInCTC 0.4883                0.2019      
## PercentDifferenceCTC    0.3730                0.1531      
## RexInYrs                0.0000                0.0000      
## Age                     0.0562                0.6376      
##                         PercentHikeOfferedInCTC PercentDifferenceCTC
## DurationToAcceptOffer   0.4883                  0.3730              
## NoticePeriod            0.2019                  0.1531              
## PercentHikeOfferedInCTC                         0.0000              
## PercentDifferenceCTC    0.0000                                      
## RexInYrs                0.0000                  0.0000              
## Age                     0.0000                  0.0003              
##                         RexInYrs Age   
## DurationToAcceptOffer   0.0000   0.0562
## NoticePeriod            0.0000   0.6376
## PercentHikeOfferedInCTC 0.0000   0.0000
## PercentDifferenceCTC    0.0000   0.0003
## RexInYrs                         0.0000
## Age                     0.0000

Plotting Correlation Matrix

library('PerformanceAnalytics')

## Warning: package 'PerformanceAnalytics' was built under R version 3.6.1

## Warning: package 'xts' was built under R version 3.6.1

chart.Correlation(HR.df[,c(2,3,6,7,12,15)])

Scatter Plot of Experience and Duration to Accept Offer by Status (Joined / Not Joined)

plot(RexInYrs, DurationToAcceptOffer, xlab = "Duration to Accept Offer (in Days)", ylab = "Relevant Experience (in Years)", main = "Scatterplot of Experience and Duration to Accept Offer",col=Status)
legend("topright",
       levels(Status),
       col = c('black','red'),
       pch = 1)

Scatter Plot of Experience and Notice Period by Status (Joined / Not Joined)

plot(RexInYrs,NoticePeriod, xlab = "Relevant Experience (in Years)", ylab = "Notice Period (in Days)", main = "Scatterplot of Experience and Notice Period",col=Status)
legend("topright",
       levels(Status),
       col = c('black','red'),
       pch = 1)

Scatter Plot of Experience and Percent Hike (CTC) Expected by Candidate by Status (Joined / Not Joined)

plot(RexInYrs,PercentHikeExpectedInCTC, xlab = "Relevant Experience (in Years)", ylab = "Percent Hike (CTC) Expected by Candidate", main = "Scatterplot of Experience and Percent Hike (CTC) Expected by Candidate",col=Status)
legend("topright",
       levels(Status),
       col = c('black','red'),
       pch = 1)

Scatter Plot of Experience and Percent Hike (CTC) Offered by Candidate by Status (Joined / Not Joined)