Problem-4: Part-A & B
library(ISLR)
getwd()
## [1] "C:/Users/fflood2000/Documents"
college = read.csv("Textbook Data_College.csv")
fix(college)
rownames(college) = college[, 1]
college = college[, -1]
fix(college)
Problem-4: Part-C (i)-(iii)
summary(college)
## Private Apps Accept Enroll Top10perc
## No :212 Min. : 81 Min. : 72 Min. : 35 Min. : 1.0
## Yes:565 1st Qu.: 776 1st Qu.: 604 1st Qu.: 242 1st Qu.:15.0
## Median : 1558 Median : 1110 Median : 434 Median :23.0
## Mean : 3002 Mean : 2019 Mean : 780 Mean :27.6
## 3rd Qu.: 3624 3rd Qu.: 2424 3rd Qu.: 902 3rd Qu.:35.0
## Max. :48094 Max. :26330 Max. :6392 Max. :96.0
## Top25perc F.Undergrad P.Undergrad Outstate
## Min. : 9.0 Min. : 139 Min. : 1 Min. : 2340
## 1st Qu.: 41.0 1st Qu.: 992 1st Qu.: 95 1st Qu.: 7320
## Median : 54.0 Median : 1707 Median : 353 Median : 9990
## Mean : 55.8 Mean : 3700 Mean : 855 Mean :10441
## 3rd Qu.: 69.0 3rd Qu.: 4005 3rd Qu.: 967 3rd Qu.:12925
## Max. :100.0 Max. :31643 Max. :21836 Max. :21700
## Room.Board Books Personal PhD
## Min. :1780 Min. : 96 Min. : 250 Min. : 8.0
## 1st Qu.:3597 1st Qu.: 470 1st Qu.: 850 1st Qu.: 62.0
## Median :4200 Median : 500 Median :1200 Median : 75.0
## Mean :4358 Mean : 549 Mean :1341 Mean : 72.7
## 3rd Qu.:5050 3rd Qu.: 600 3rd Qu.:1700 3rd Qu.: 85.0
## Max. :8124 Max. :2340 Max. :6800 Max. :103.0
## Terminal S.F.Ratio perc.alumni Expend
## Min. : 24.0 Min. : 2.5 Min. : 0.0 Min. : 3186
## 1st Qu.: 71.0 1st Qu.:11.5 1st Qu.:13.0 1st Qu.: 6751
## Median : 82.0 Median :13.6 Median :21.0 Median : 8377
## Mean : 79.7 Mean :14.1 Mean :22.7 Mean : 9660
## 3rd Qu.: 92.0 3rd Qu.:16.5 3rd Qu.:31.0 3rd Qu.:10830
## Max. :100.0 Max. :39.8 Max. :64.0 Max. :56233
## Grad.Rate
## Min. : 10.0
## 1st Qu.: 53.0
## Median : 65.0
## Mean : 65.5
## 3rd Qu.: 78.0
## Max. :118.0
dim(college)
## [1] 777 18
attach(college)
pairs(college[, 1:10])
plot(Private, Outstate, main = "HW-1 Prob 4(c) (iii)", xlab = "Private College",
ylab = "Out of State", col = 2)
Problem-4: Part-C (iv)-(v)
elite = rep("No", nrow(college))
nrow(college)
## [1] 777
elite[Top10perc > 50] = "Yes"
elite = as.factor(elite)
college = data.frame(college, elite) #adds new column: elite
summary(college)
## Private Apps Accept Enroll Top10perc
## No :212 Min. : 81 Min. : 72 Min. : 35 Min. : 1.0
## Yes:565 1st Qu.: 776 1st Qu.: 604 1st Qu.: 242 1st Qu.:15.0
## Median : 1558 Median : 1110 Median : 434 Median :23.0
## Mean : 3002 Mean : 2019 Mean : 780 Mean :27.6
## 3rd Qu.: 3624 3rd Qu.: 2424 3rd Qu.: 902 3rd Qu.:35.0
## Max. :48094 Max. :26330 Max. :6392 Max. :96.0
## Top25perc F.Undergrad P.Undergrad Outstate
## Min. : 9.0 Min. : 139 Min. : 1 Min. : 2340
## 1st Qu.: 41.0 1st Qu.: 992 1st Qu.: 95 1st Qu.: 7320
## Median : 54.0 Median : 1707 Median : 353 Median : 9990
## Mean : 55.8 Mean : 3700 Mean : 855 Mean :10441
## 3rd Qu.: 69.0 3rd Qu.: 4005 3rd Qu.: 967 3rd Qu.:12925
## Max. :100.0 Max. :31643 Max. :21836 Max. :21700
## Room.Board Books Personal PhD
## Min. :1780 Min. : 96 Min. : 250 Min. : 8.0
## 1st Qu.:3597 1st Qu.: 470 1st Qu.: 850 1st Qu.: 62.0
## Median :4200 Median : 500 Median :1200 Median : 75.0
## Mean :4358 Mean : 549 Mean :1341 Mean : 72.7
## 3rd Qu.:5050 3rd Qu.: 600 3rd Qu.:1700 3rd Qu.: 85.0
## Max. :8124 Max. :2340 Max. :6800 Max. :103.0
## Terminal S.F.Ratio perc.alumni Expend
## Min. : 24.0 Min. : 2.5 Min. : 0.0 Min. : 3186
## 1st Qu.: 71.0 1st Qu.:11.5 1st Qu.:13.0 1st Qu.: 6751
## Median : 82.0 Median :13.6 Median :21.0 Median : 8377
## Mean : 79.7 Mean :14.1 Mean :22.7 Mean : 9660
## 3rd Qu.: 92.0 3rd Qu.:16.5 3rd Qu.:31.0 3rd Qu.:10830
## Max. :100.0 Max. :39.8 Max. :64.0 Max. :56233
## Grad.Rate elite
## Min. : 10.0 No :699
## 1st Qu.: 53.0 Yes: 78
## Median : 65.0
## Mean : 65.5
## 3rd Qu.: 78.0
## Max. :118.0
attach(college)
## The following object is masked _by_ .GlobalEnv:
##
## elite
## The following objects are masked from college (position 3):
##
## Accept, Apps, Books, Enroll, Expend, F.Undergrad, Grad.Rate,
## Outstate, P.Undergrad, perc.alumni, Personal, PhD, Private,
## Room.Board, S.F.Ratio, Terminal, Top10perc, Top25perc
plot(elite, Outstate, main = "HW-1 Prob 4(c) (iv)", xlab = "Elite (More then 50% Top10)",
ylab = "Out of State", col = 2)
par(mfrow = c(3, 2))
hist(Accept, col = 5, breaks = 100)
hist(Top25perc, col = 2, breaks = 50)
hist(Grad.Rate, col = 3, breaks = 50)
hist(Room.Board, col = 4, breaks = 50)
hist(S.F.Ratio, col = 6, breaks = 50)
hist(Outstate, col = 7, breaks = 50)
