DD.df<-read.csv("Data - Deans Dilemma.csv", sep = ",")
View(DD.df)
summary(DD.df)
## SlNo Gender Gender.B Percent_SSC Board_SSC
## Min. : 1.0 F:127 Min. :0.0000 Min. :37.00 CBSE :113
## 1st Qu.: 98.5 M:264 1st Qu.:0.0000 1st Qu.:56.00 ICSE : 77
## Median :196.0 Median :0.0000 Median :64.50 Others:201
## Mean :196.0 Mean :0.3248 Mean :64.65
## 3rd Qu.:293.5 3rd Qu.:1.0000 3rd Qu.:74.00
## Max. :391.0 Max. :1.0000 Max. :87.20
##
## Board_CBSE Board_ICSE Percent_HSC Board_HSC
## Min. :0.000 Min. :0.0000 Min. :40.0 CBSE : 96
## 1st Qu.:0.000 1st Qu.:0.0000 1st Qu.:54.0 ISC : 48
## Median :0.000 Median :0.0000 Median :63.0 Others:247
## Mean :0.289 Mean :0.1969 Mean :63.8
## 3rd Qu.:1.000 3rd Qu.:0.0000 3rd Qu.:72.0
## Max. :1.000 Max. :1.0000 Max. :94.7
##
## Stream_HSC Percent_Degree Course_Degree
## Arts : 18 Min. :35.00 Arts : 13
## Commerce:222 1st Qu.:57.52 Commerce :117
## Science :151 Median :63.00 Computer Applications: 32
## Mean :62.98 Engineering : 37
## 3rd Qu.:69.00 Management :163
## Max. :89.00 Others : 5
## Science : 24
## Degree_Engg Experience_Yrs Entrance_Test S.TEST
## Min. :0.00000 Min. :0.0000 MAT :265 Min. :0.0000
## 1st Qu.:0.00000 1st Qu.:0.0000 None : 67 1st Qu.:1.0000
## Median :0.00000 Median :0.0000 K-MAT : 24 Median :1.0000
## Mean :0.09463 Mean :0.4783 CAT : 22 Mean :0.8286
## 3rd Qu.:0.00000 3rd Qu.:1.0000 PGCET : 8 3rd Qu.:1.0000
## Max. :1.00000 Max. :3.0000 GCET : 2 Max. :1.0000
## (Other): 3
## Percentile_ET S.TEST.SCORE Percent_MBA
## Min. : 0.00 Min. : 0.00 Min. :50.83
## 1st Qu.:41.19 1st Qu.:41.19 1st Qu.:57.20
## Median :62.00 Median :62.00 Median :61.01
## Mean :54.93 Mean :54.93 Mean :61.67
## 3rd Qu.:78.00 3rd Qu.:78.00 3rd Qu.:66.02
## Max. :98.69 Max. :98.69 Max. :77.89
##
## Specialization_MBA Marks_Communication Marks_Projectwork
## Marketing & Finance:222 Min. :50.00 Min. :50.00
## Marketing & HR :156 1st Qu.:53.00 1st Qu.:64.00
## Marketing & IB : 13 Median :58.00 Median :69.00
## Mean :60.54 Mean :68.36
## 3rd Qu.:67.00 3rd Qu.:74.00
## Max. :88.00 Max. :87.00
##
## Marks_BOCA Placement Placement_B Salary
## Min. :50.00 Not Placed: 79 Min. :0.000 Min. : 0
## 1st Qu.:57.00 Placed :312 1st Qu.:1.000 1st Qu.:172800
## Median :63.00 Median :1.000 Median :240000
## Mean :64.38 Mean :0.798 Mean :219078
## 3rd Qu.:72.50 3rd Qu.:1.000 3rd Qu.:300000
## Max. :96.00 Max. :1.000 Max. :940000
##
median(DD.df$Salary)
## [1] 240000
table(DD.df$Placement_B==1)
##
## FALSE TRUE
## 79 312
Placed<-table(DD.df$Placement_B==1)
prop<-prop.table(Placed)
100*prop
##
## FALSE TRUE
## 20.2046 79.7954
placed.df<- DD.df[(which(DD.df$Placement_B==1)),]
View(placed.df)
median(placed.df$Salary)
## [1] 260000
aggregate(placed.df$Salary, by=list(Sex = placed.df$Gender), mean)
## Sex x
## 1 F 253068.0
## 2 M 284241.9
hist(placed.df$Percent_MBA,
main = "Performane of student", xlab = "MBA Percentage", ylab = "Count")
notplaced.df<- DD.df[(which(DD.df$Placement_B==0)),]
View(notplaced.df)
par(mfrow=c(1, 2))
hist(placed.df$Percent_MBA,
main = "Performane of Placed student", xlab = "MBA Percentage", ylab = "Count")
hist(notplaced.df$Percent_MBA,
main = "Performane of Not Placed student", xlab = "MBA Percentage", ylab = "Count")
boxplot(placed.df$Salary ~ placed.df$Gender, horizontal=TRUE, yaxt="n",
ylab="Gender", xlab="Salary",
main="Comparison of Salaries of Males and Females")
axis(side=2, at=c(1,2), labels=c("Females", "Males"))
placedET.df<- DD.df[(which(DD.df$Placement_B==1 & DD.df$S.TEST==1)),]
View(placedET.df)
library(car)
scatterplotMatrix(
placedET.df[
,c("Salary","Percent_MBA","Percentile_ET")],
spread=FALSE, smoother.args=list(lty=2),
main="Scatter Plot Matrix")
