EDA-HRData(Manipulated)

LOADING DATA INTO R ENVIRONMENT

Loading the Data

# loading full data into R
HR.df <- read.csv("ManipulatedCleanHRData.csv")
attach(HR.df)

Number of rows & columns in the dataframe

# number of rows of columns
dim(HR.df)

## [1] 8995   17

Column names of the dataframe

# column names of the dataframe
colnames(HR.df)

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

Descriptive Statistics of the dataframe

# descriptive statistics of the dataframe
library(psych)
describe(HR.df)[, c(1:5)]

##                          vars    n       mean        sd  median
## CandidateRef                1 8995 2843647.38 486344.77 2807482
## DOJExtended*                2 8995       1.47      0.50       1
## DurationToAcceptOffer       3 8995      21.43     25.81      10
## NoticePeriod                4 8995      39.29     22.22      30
## OfferedBand*                5 8995       2.39      0.63       2
## PercentHikeExpectedInCTC    6 8995      43.86     29.79      40
## PercentHikeOfferedInCTC     7 8995      40.66     36.06      36
## PercentDifferenceCTC        8 8995      -1.57     19.61       0
## JoiningBonus*               9 8995       1.05      0.21       1
## CandidateRelocateActual*   10 8995       1.14      0.35       1
## Gender*                    11 8995       1.88      0.33       2
## CandidateSource*           12 8995       1.89      0.67       2
## RexInYrs                   13 8995       4.24      2.55       4
## LOB*                       14 8995       5.18      2.38       5
## Location*                  15 8995       4.94      3.00       3
## Age                        16 8995      29.91      4.10      29
## Status*                    17 8995       1.19      0.39       1

DISCRETE DATA DISTRIBUTION

Percentage of the candidates (Joined / Not joined)

# percentage of candidates who joined the company and who did not
tab <- round(prop.table(table(Status))*100, 2)
tab

## Status
##    Joined NotJoined 
##      81.3      18.7

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

# bar-plot
bp <- barplot(tab, 
        xlab = "Status", ylab = "Percentage (%)",
        main  = "% of the Candidates Who Joined / Did Not Join the Company",
        col = c("lightblue","red"),
        legend = rownames(tab),
        beside = TRUE)
text(bp, 0, round(tab, 1),cex = 2, pos = 3) 

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

# % of candidates who joined / did not join the company, split by DOJ extended
tab2 <- round(prop.table(table(DOJExtended, Status), 1)*100, 2)
tab2

##            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

# % of Candidates who Did Not Join, split by DOJ Extended
tab <- tab2[,2]
# bar-plot
bp <- barplot(tab, 
        xlab = "DOJ Extended", ylab = "Percentage (%)",
        main  = "% of Candidates, Who Did Not Join, Split by DOJ Extended",
        col = c("lightblue"),
        beside = TRUE)
text(bp, 0, round(tab, 1),cex=2,pos=3) 

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

# % of Candidates, who Joined / Did Not Join, split by Notice Period
tab3 <- round(prop.table(table(NoticePeriod, Status), 1)*100, 2)
tab3

##             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

# % of Candidates, who Did Not Join, split by Notice Period
tab <- tab3[,2]
# bar-plot
bp <- barplot(tab, 
        xlab = "NoticePeriod", ylab = "Percentage (%)",
        main  = "% of Candidates, Who Did Not Join, Split by Notice Period",
        col = c("lightblue"),
        beside = TRUE)
text(bp, 0, round(tab, 1),cex=1.7,pos=3) 

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

# % of candidates who joined / not joined the company, split by Notice JoiningBonus
tab4 <- round(prop.table(table(JoiningBonus, Status), 1)*100, 2)
tab4

##             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

# % of Candidates, Who Did Not Join, Split by Joining Bonus
tab <- tab4[,2]
# bar-plot
bp <- barplot(tab, 
        xlab = "Joining Bonus", ylab = "Percentage (%)",
        main  = "% of Candidates, Who Did Not Join, Split by Joining Bonus",
        col = c("lightblue"), width = 0.3, xlim = c(0,1),
        beside = TRUE)
text(bp, 0, round(tab, 1), cex= 2, pos=3) 

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

# Percentage of the Candidates Who (Joined / Did Not join), split by Gender
tab5 <- round(prop.table(table(Gender, Status), 1)*100, 2)
tab5

##         Status
## Gender   Joined NotJoined
##   Female  74.86     25.14
##   Male    82.18     17.82

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

# % of the Candidates who Did Not join, split by Gender
tab <- tab5[,2]
# bar-plot
bp <- barplot(tab, 
        xlab = "Gender", ylab = "Percentage (%)",
        main  = " % of the Candidates, Who Did Not join, Split by Gender",
        col = c("lightblue"),width = 0.3,xlim = c(0,1),
        beside = TRUE)
text(bp, 0, round(tab, 1),cex = 2 ,pos = 3) 

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

# Percentage of the candidates who (Joined / Did Not join), split by Candidate Source
tab6 <- round(prop.table(table(CandidateSource, Status), 1)*100, 2)
tab6

##                    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

# % % of Candidates Who Did Not Join the Company, Split by Candidate Source
tab <- tab6[,2]
# bar-plot
bp <- barplot(tab, 
        xlab = "Candidate Source", ylab = "Percentage (%)",
        main  = "% of Candidates, Who Did Not Join the Company, Split by Candidate Source",
        col = c("lightblue"),
        beside = TRUE)
text(bp, 0, round(tab, 1),cex = 2, pos = 3) 

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

# Percentage of the Candidates Who (Joined / Did Not Join), Split by Offered Band
tab7 <- round(prop.table(table(OfferedBand, Status), 1)*100, 2)
tab7

##            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

# % Candidates Who Did Not Join, Split by Offered Band
tab <- tab7[,2]
# bar-plot
bp <- barplot(tab, 
        xlab = "Offered Band", ylab = "Percentage (%)",
        main  = "% of Candidates, Who Did Not Join, Split by Offered Band",
        col = c("lightblue"),
        beside = TRUE)
text(bp, 0, round(tab, 1), cex = 2, pos =3 ) 

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

# Percentage of the candidates (Joined / Did Not joined), Split by Line of Business (LOB)
tab8 <- round(prop.table(table(LOB, Status), 1)*100, 2)
tab8

##             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)

# % of the Candidates Who Did Not join, Split by Line of Business (LOB)
tab <- tab8[,2]
# bar-plot
bp <- barplot(tab, 
        xlab = "LOB", ylab = "Percentage (%)",
        main  = "% of the Candidates, Who Did Not join, Split by Line of Business (LOB)",
        col = c("lightblue"),las = 3,
        beside = TRUE)
text(bp, 0, round(tab, 1),cex = 1.7, pos = 3) 

CONTINUOUS DATA DISTRIBUTION

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

# average age of candidates by status
library(data.table)
dt <- data.table(HR.df)
dt[, .(AverageAgeofCandidates = round(mean(Age), 2)),
            by=list(Status)]

##       Status AverageAgeofCandidates
## 1:    Joined                  30.00
## 2: NotJoined                  29.52

Mean Plot for the Age, Split by Status

# plotting mean age Split by Status
library(gplots)
plotmeans(Age ~ Status,data = HR.df,
          ylab = "Age(in Years)",
          mean.labels= TRUE,
          n.label = FALSE, digits= 2,
          col = "red", lwd = 1.5)

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

# boxplot of age by status
boxplot(Age ~ Status, data = HR.df,
       xlab = "Status", 
       ylab = "Age (in Years)",
       main = "Boxplot of Age by Status",
       col = c("lightblue","red"))

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

# average Notice Period of candidates by status
library(data.table)
dt <- data.table(HR.df)
dt[, .( AverageNoticePeriod = round(mean(NoticePeriod), 2)),
                          by= list(Status)]

##       Status AverageNoticePeriod
## 1:    Joined               37.24
## 2: NotJoined               48.19

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

# plotting average notice period by status
plotmeans(NoticePeriod ~ Status,data = HR.df,
          mean.labels= TRUE, ylab = "Notice Period",
          n.label = FALSE, digits= 2,
          col = "red", lwd = 1.5)

## 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 of Notice Period by status
boxplot(NoticePeriod ~ Status, data = HR.df,
       xlab = "Status", 
       ylab = "Notice Period",
       main = "Boxplot of Notice Period, Split by Status",
       col = c("lightblue","red"))

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

# average age and relevant experience by status
library(data.table)
dt <- data.table(HR.df)
dt[, .(YearsOfExperience = round(mean(RexInYrs), 2)),
                      by = list(Status)]

##       Status YearsOfExperience
## 1:    Joined              4.19
## 2: NotJoined              4.44

Mean Plot for the above

# plotting average Relevant Years of Experience by status
plotmeans(RexInYrs ~ Status,data = HR.df,
          mean.labels= TRUE, ylab = "Relevant Years of Experience",
          n.label = FALSE, digits= 2,
          col = "red", lwd = 1.5)

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

# boxplot of Notice Period by status
boxplot(RexInYrs ~ Status, data = HR.df,
       xlab = "Status", 
       ylab = "Relevant Years of Experience",
       main = "Boxplot of Relevant Years of Experience by Status",
       col = c("lightblue","red"))

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

# average of DurationToAcceptOffer by status
dt <- data.table(HR.df)
dt[, .(DurationToAcceptOffer = round(mean(DurationToAcceptOffer), 2)),
                          by = list(Status)]

##       Status DurationToAcceptOffer
## 1:    Joined                 20.62
## 2: NotJoined                 24.96

Mean Plot for the above

# plotting mean of DurationToAcceptOffer by status
plotmeans(DurationToAcceptOffer ~ Status,data = HR.df,
          mean.labels= TRUE, ylab = "Duration To Accept Offer",
          n.label = FALSE, digits= 2,
          col = "red", lwd = 1.5)

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)

# average age, relevent experience and number of days to accet offer by status and gender
dt <- data.table(HR.df)
dt[,list(AgeofCandidates = 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)]

##       Status Gender AgeofCandidates YearsOfExperience DurationtoAcceptOffer
## 1:    Joined Female           29.93              3.56                 20.75
## 2:    Joined   Male           30.01              4.27                 20.61
## 3: NotJoined Female           28.02              3.61                 24.10
## 4: NotJoined   Male           29.81              4.60                 25.12
##    NoticePeriod
## 1:        36.03
## 2:        37.40
## 3:        46.65
## 4:        48.49

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

# average age, relevent experience and number of days to accet offer by status and DOJExtended
dt <- data.table(HR.df)
dt[,list(AgeofCandidates = round(mean(Age), 2), 
         YearsOfExperience = round(mean(RexInYrs), 2), 
         DurationtoAcceptOffer = round(mean(DurationToAcceptOffer), 2),
         NoticePeriod = round(mean(NoticePeriod), 2)),
                   by = list(Status, DOJExtended)][order(Status, DOJExtended)]

##       Status DOJExtended AgeofCandidates YearsOfExperience
## 1:    Joined          No           29.77              3.96
## 2:    Joined         Yes           30.27              4.46
## 3: NotJoined          No           29.38              4.25
## 4: NotJoined         Yes           29.67              4.66
##    DurationtoAcceptOffer NoticePeriod
## 1:                 12.02        33.86
## 2:                 30.36        41.08
## 3:                 18.11        47.20
## 4:                 32.95        49.35

CORRELATION

Correlation Matrix for all the Continuous Variable

library(dplyr)
# creating subset of continuous variables
SubsetHR <- select(HR.df, DurationToAcceptOffer, NoticePeriod, RexInYrs, Age, PercentHikeExpectedInCTC, PercentHikeOfferedInCTC, PercentDifferenceCTC)
library("Hmisc")
cm2 <- rcorr(as.matrix(SubsetHR))
cm2

##                          DurationToAcceptOffer NoticePeriod RexInYrs   Age
## DurationToAcceptOffer                     1.00         0.36     0.11  0.02
## NoticePeriod                              0.36         1.00     0.18  0.00
## RexInYrs                                  0.11         0.18     1.00  0.57
## Age                                       0.02         0.00     0.57  1.00
## PercentHikeExpectedInCTC                  0.02        -0.01    -0.22 -0.14
## PercentHikeOfferedInCTC                   0.01        -0.01    -0.11 -0.08
## PercentDifferenceCTC                     -0.01        -0.02     0.08  0.04
##                          PercentHikeExpectedInCTC PercentHikeOfferedInCTC
## DurationToAcceptOffer                        0.02                    0.01
## NoticePeriod                                -0.01                   -0.01
## RexInYrs                                    -0.22                   -0.11
## Age                                         -0.14                   -0.08
## PercentHikeExpectedInCTC                     1.00                    0.67
## PercentHikeOfferedInCTC                      0.67                    1.00
## PercentDifferenceCTC                        -0.16                    0.60
##                          PercentDifferenceCTC
## DurationToAcceptOffer                   -0.01
## NoticePeriod                            -0.02
## RexInYrs                                 0.08
## Age                                      0.04
## PercentHikeExpectedInCTC                -0.16
## PercentHikeOfferedInCTC                  0.60
## PercentDifferenceCTC                     1.00
## 
## n= 8995 
## 
## 
## P
##                          DurationToAcceptOffer NoticePeriod RexInYrs Age   
## DurationToAcceptOffer                          0.0000       0.0000   0.0562
## NoticePeriod             0.0000                             0.0000   0.6376
## RexInYrs                 0.0000                0.0000                0.0000
## Age                      0.0562                0.6376       0.0000         
## PercentHikeExpectedInCTC 0.0743                0.6178       0.0000   0.0000
## PercentHikeOfferedInCTC  0.4883                0.2019       0.0000   0.0000
## PercentDifferenceCTC     0.3730                0.1531       0.0000   0.0003
##                          PercentHikeExpectedInCTC PercentHikeOfferedInCTC
## DurationToAcceptOffer    0.0743                   0.4883                 
## NoticePeriod             0.6178                   0.2019                 
## RexInYrs                 0.0000                   0.0000                 
## Age                      0.0000                   0.0000                 
## PercentHikeExpectedInCTC                          0.0000                 
## PercentHikeOfferedInCTC  0.0000                                          
## PercentDifferenceCTC     0.0000                   0.0000                 
##                          PercentDifferenceCTC
## DurationToAcceptOffer    0.3730              
## NoticePeriod             0.1531              
## RexInYrs                 0.0000              
## Age                      0.0003              
## PercentHikeExpectedInCTC 0.0000              
## PercentHikeOfferedInCTC  0.0000              
## PercentDifferenceCTC

Plotting Correlation Matrix

# plotting correlation matrix
library("PerformanceAnalytics")
chart.Correlation(SubsetHR, histogram=TRUE, pch=19)

SCATTER PLOTS

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

# scatterplot of experience and duration to accept offer
library(lattice)
xyplot(DurationToAcceptOffer ~ RexInYrs, data = HR.df,
       group = Status,
       xlab = "Relevant Experience (in Years)", 
       ylab = "Duration to Accept Offer (in Days)",
       main = "Scatterplot of Experience and Duration to Accept Offer",
       auto.key = TRUE)

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

# scatterplot of experience and notice period
xyplot(NoticePeriod ~ RexInYrs, data = HR.df,
       group = Status,
       xlab = "Relevant Experience (in Years)", 
       ylab = "Notice Period (in Days)",
       main = "Scatterplot of Experience and Notice Period",
       auto.key = TRUE)

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

# scatterplot of experience and percent hike expected by candidate
xyplot(PercentHikeExpectedInCTC ~ RexInYrs, data = HR.df,
       group = Status,
       xlab = "Relevant Experience (in Years)", 
       ylab = "Percent Hike (CTC) Expeceted by Candidate",
       main = "Scatterplot of Experience and Percent Hike (CTC) Expecetd by Candidate",
       auto.key = TRUE)

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

# scatterplot of experience and percent hike offered by company
xyplot(PercentHikeOfferedInCTC ~ RexInYrs, data = HR.df,
       group = Status,
       xlab = "Relevant Experience (in Years)", 
       ylab = "Percent Hike (CTC) Offered by Company",
       main = "Scatterplot of Experience and Percent Hike (CTC) Offered by Company",
       auto.key = TRUE)