data.df <- read.csv(paste("Data - Deans Dilemma.csv",sep =""))
head(data.df)
## SlNo Gender Gender.B Percent_SSC Board_SSC Board_CBSE Board_ICSE
## 1 1 M 0 62.00 Others 0 0
## 2 2 M 0 76.33 ICSE 0 1
## 3 3 M 0 72.00 Others 0 0
## 4 4 M 0 60.00 CBSE 1 0
## 5 5 M 0 61.00 CBSE 1 0
## 6 6 M 0 55.00 ICSE 0 1
## Percent_HSC Board_HSC Stream_HSC Percent_Degree Course_Degree
## 1 88.00 Others Commerce 52.00 Science
## 2 75.33 Others Science 75.48 Computer Applications
## 3 78.00 Others Commerce 66.63 Engineering
## 4 63.00 CBSE Arts 58.00 Management
## 5 55.00 ISC Science 54.00 Engineering
## 6 64.00 CBSE Commerce 50.00 Commerce
## Degree_Engg Experience_Yrs Entrance_Test S.TEST Percentile_ET
## 1 0 0 MAT 1 55.0
## 2 0 1 MAT 1 86.5
## 3 1 0 None 0 0.0
## 4 0 0 MAT 1 75.0
## 5 1 1 MAT 1 66.0
## 6 0 0 None 0 0.0
## S.TEST.SCORE Percent_MBA Specialization_MBA Marks_Communication
## 1 55.0 58.80 Marketing & HR 50
## 2 86.5 66.28 Marketing & Finance 69
## 3 0.0 52.91 Marketing & Finance 50
## 4 75.0 57.80 Marketing & Finance 54
## 5 66.0 59.43 Marketing & HR 52
## 6 0.0 56.81 Marketing & Finance 53
## Marks_Projectwork Marks_BOCA Placement Placement_B Salary
## 1 65 74 Placed 1 270000
## 2 70 75 Placed 1 200000
## 3 61 59 Placed 1 240000
## 4 66 62 Placed 1 250000
## 5 65 67 Placed 1 180000
## 6 70 53 Placed 1 300000
library('psych')
describe(data.df)
## vars n mean sd median trimmed
## SlNo 1 391 196.00 113.02 196.00 196.00
## Gender* 2 391 1.68 0.47 2.00 1.72
## Gender.B 3 391 0.32 0.47 0.00 0.28
## Percent_SSC 4 391 64.65 10.96 64.50 64.76
## Board_SSC* 5 391 2.23 0.87 3.00 2.28
## Board_CBSE 6 391 0.29 0.45 0.00 0.24
## Board_ICSE 7 391 0.20 0.40 0.00 0.12
## Percent_HSC 8 391 63.80 11.42 63.00 63.34
## Board_HSC* 9 391 2.39 0.85 3.00 2.48
## Stream_HSC* 10 391 2.34 0.56 2.00 2.36
## Percent_Degree 11 391 62.98 8.92 63.00 62.91
## Course_Degree* 12 391 3.85 1.61 4.00 3.81
## Degree_Engg 13 391 0.09 0.29 0.00 0.00
## Experience_Yrs 14 391 0.48 0.67 0.00 0.36
## Entrance_Test* 15 391 5.85 1.35 6.00 6.08
## S.TEST 16 391 0.83 0.38 1.00 0.91
## Percentile_ET 17 391 54.93 31.17 62.00 56.87
## S.TEST.SCORE 18 391 54.93 31.17 62.00 56.87
## Percent_MBA 19 391 61.67 5.85 61.01 61.45
## Specialization_MBA* 20 391 1.47 0.56 1.00 1.42
## Marks_Communication 21 391 60.54 8.82 58.00 59.68
## Marks_Projectwork 22 391 68.36 7.15 69.00 68.60
## Marks_BOCA 23 391 64.38 9.58 63.00 64.08
## Placement* 24 391 1.80 0.40 2.00 1.87
## Placement_B 25 391 0.80 0.40 1.00 0.87
## Salary 26 391 219078.26 138311.65 240000.00 217011.50
## mad min max range skew kurtosis
## SlNo 145.29 1.00 391.00 390.00 0.00 -1.21
## Gender* 0.00 1.00 2.00 1.00 -0.75 -1.45
## Gender.B 0.00 0.00 1.00 1.00 0.75 -1.45
## Percent_SSC 12.60 37.00 87.20 50.20 -0.06 -0.72
## Board_SSC* 0.00 1.00 3.00 2.00 -0.45 -1.53
## Board_CBSE 0.00 0.00 1.00 1.00 0.93 -1.14
## Board_ICSE 0.00 0.00 1.00 1.00 1.52 0.31
## Percent_HSC 13.34 40.00 94.70 54.70 0.29 -0.67
## Board_HSC* 0.00 1.00 3.00 2.00 -0.83 -1.13
## Stream_HSC* 0.00 1.00 3.00 2.00 -0.12 -0.72
## Percent_Degree 8.90 35.00 89.00 54.00 0.05 0.24
## Course_Degree* 1.48 1.00 7.00 6.00 0.00 -1.08
## Degree_Engg 0.00 0.00 1.00 1.00 2.76 5.63
## Experience_Yrs 0.00 0.00 3.00 3.00 1.27 1.17
## Entrance_Test* 0.00 1.00 9.00 8.00 -2.52 7.04
## S.TEST 0.00 0.00 1.00 1.00 -1.74 1.02
## Percentile_ET 25.20 0.00 98.69 98.69 -0.74 -0.69
## S.TEST.SCORE 25.20 0.00 98.69 98.69 -0.74 -0.69
## Percent_MBA 6.39 50.83 77.89 27.06 0.34 -0.52
## Specialization_MBA* 0.00 1.00 3.00 2.00 0.70 -0.56
## Marks_Communication 8.90 50.00 88.00 38.00 0.74 -0.25
## Marks_Projectwork 7.41 50.00 87.00 37.00 -0.26 -0.27
## Marks_BOCA 11.86 50.00 96.00 46.00 0.29 -0.85
## Placement* 0.00 1.00 2.00 1.00 -1.48 0.19
## Placement_B 0.00 0.00 1.00 1.00 -1.48 0.19
## Salary 88956.00 0.00 940000.00 940000.00 0.24 1.74
## se
## SlNo 5.72
## Gender* 0.02
## Gender.B 0.02
## Percent_SSC 0.55
## Board_SSC* 0.04
## Board_CBSE 0.02
## Board_ICSE 0.02
## Percent_HSC 0.58
## Board_HSC* 0.04
## Stream_HSC* 0.03
## Percent_Degree 0.45
## Course_Degree* 0.08
## Degree_Engg 0.01
## Experience_Yrs 0.03
## Entrance_Test* 0.07
## S.TEST 0.02
## Percentile_ET 1.58
## S.TEST.SCORE 1.58
## Percent_MBA 0.30
## Specialization_MBA* 0.03
## Marks_Communication 0.45
## Marks_Projectwork 0.36
## Marks_BOCA 0.48
## Placement* 0.02
## Placement_B 0.02
## Salary 6994.72
View(data.df)
median(data.df$Salary)
## [1] 240000
round(prop.table(table(data.df$Placement))*100,digits = 2)
##
## Not Placed Placed
## 20.2 79.8
placed <- data.df[ which(data.df$Placement=='Placed'), ]
median(placed$Salary)
## [1] 260000
aggregate(Salary ~ Gender , data = placed ,mean)
## Gender Salary
## 1 F 253068.0
## 2 M 284241.9
hist(placed$Percent_MBA,
main = "MBA percentage of placed students",
xlab = "MBA Percentage",
ylab = "Count",
col = "lightblue",
breaks = 10,
xlim = c(50, 80),
ylim = c(0 ,50))
notplaced <- data.df[which(data.df$Placement == "Not Placed"),]
head(notplaced)
## SlNo Gender Gender.B Percent_SSC Board_SSC Board_CBSE Board_ICSE
## 11 11 F 1 79.60 Others 0 0
## 16 16 F 1 49.00 Others 0 0
## 20 20 M 0 66.00 Others 0 0
## 40 40 F 1 60.00 CBSE 1 0
## 42 42 F 1 40.00 CBSE 1 0
## 43 43 M 0 77.12 Others 0 0
## Percent_HSC Board_HSC Stream_HSC Percent_Degree Course_Degree
## 11 87.0 ISC Commerce 72.35 Management
## 16 52.2 Others Commerce 85.00 Commerce
## 20 46.0 Others Commerce 65.00 Management
## 40 75.0 CBSE Commerce 68.00 Commerce
## 42 40.0 Others Commerce 51.00 Management
## 43 85.0 Others Commerce 56.77 Management
## Degree_Engg Experience_Yrs Entrance_Test S.TEST Percentile_ET
## 11 0 0 K-MAT 1 98.69
## 16 0 0 MAT 1 74.28
## 20 0 0 PGCET 1 0.00
## 40 0 1 MAT 1 60.00
## 42 0 0 PGCET 1 49.00
## 43 0 0 CAT 1 35.00
## S.TEST.SCORE Percent_MBA Specialization_MBA Marks_Communication
## 11 98.69 69.78 Marketing & HR 71
## 16 74.28 53.29 Marketing & Finance 50
## 20 0.00 54.65 Marketing & Finance 53
## 40 60.00 67.28 Marketing & Finance 58
## 42 49.00 51.75 Marketing & Finance 50
## 43 35.00 56.34 Marketing & IB 56
## Marks_Projectwork Marks_BOCA Placement Placement_B Salary
## 11 67 60 Not Placed 0 0
## 16 65 74 Not Placed 0 0
## 20 60 65 Not Placed 0 0
## 40 71 65 Not Placed 0 0
## 42 59 53 Not Placed 0 0
## 43 66 58 Not Placed 0 0
par(mfrow = c(1,2))
with(placed , hist(placed$Percent_MBA,
main = "Placed students",
xlab = "MBA Percentage",
ylab = "Count",
col = "grey",
breaks = 3,
xlim = c(50,80),
ylim = c(0,200)
))
with(notplaced , hist(notplaced$Percent_MBA,
main = "Not placed students",
xlab = "MBA Percentage",
ylab = "Count",
col = "lightblue",
breaks = 3,
xlim = c(50,80),
ylim = c(0,40)))
boxplot(placed$Salary ~ placed$Gender,
horizontal = TRUE,
ylab = "Gender",
xlab ="Salary",
main = "Gender Wise salary distribution",
col = c("red","blue"))
PlacedET <- data.df[which(data.df$Placement_B == '1' & data.df$S.TEST == '1'),]
head(PlacedET)
## SlNo Gender Gender.B Percent_SSC Board_SSC Board_CBSE Board_ICSE
## 1 1 M 0 62.00 Others 0 0
## 2 2 M 0 76.33 ICSE 0 1
## 4 4 M 0 60.00 CBSE 1 0
## 5 5 M 0 61.00 CBSE 1 0
## 8 8 M 0 68.00 ICSE 0 1
## 9 9 M 0 82.80 CBSE 1 0
## Percent_HSC Board_HSC Stream_HSC Percent_Degree Course_Degree
## 1 88.00 Others Commerce 52.00 Science
## 2 75.33 Others Science 75.48 Computer Applications
## 4 63.00 CBSE Arts 58.00 Management
## 5 55.00 ISC Science 54.00 Engineering
## 8 77.00 ISC Commerce 72.50 Management
## 9 70.60 CBSE Commerce 69.30 Commerce
## Degree_Engg Experience_Yrs Entrance_Test S.TEST Percentile_ET
## 1 0 0 MAT 1 55.00
## 2 0 1 MAT 1 86.50
## 4 0 0 MAT 1 75.00
## 5 1 1 MAT 1 66.00
## 8 0 0 MAT 1 43.12
## 9 0 0 MAT 1 96.80
## S.TEST.SCORE Percent_MBA Specialization_MBA Marks_Communication
## 1 55.00 58.80 Marketing & HR 50
## 2 86.50 66.28 Marketing & Finance 69
## 4 75.00 57.80 Marketing & Finance 54
## 5 66.00 59.43 Marketing & HR 52
## 8 43.12 57.23 Marketing & Finance 74
## 9 96.80 55.50 Marketing & Finance 65
## Marks_Projectwork Marks_BOCA Placement Placement_B Salary
## 1 65 74 Placed 1 270000
## 2 70 75 Placed 1 200000
## 4 66 62 Placed 1 250000
## 5 65 67 Placed 1 180000
## 8 72 50 Placed 1 235000
## 9 76 70 Placed 1 425000
library('car')
##
## Attaching package: 'car'
## The following object is masked from 'package:psych':
##
## logit
scatterplotMatrix(formula = ~ Salary + Percent_MBA + Percentile_ET, data =PlacedET, main = "Scatter Plot Matrix")
