library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
Auto <- read.table("http://faculty.marshall.usc.edu/gareth-james/ISL/Auto.data",
header=TRUE,
na.strings = "?")
head(Auto)
## mpg cylinders displacement horsepower weight acceleration year origin
## 1 18 8 307 130 3504 12.0 70 1
## 2 15 8 350 165 3693 11.5 70 1
## 3 18 8 318 150 3436 11.0 70 1
## 4 16 8 304 150 3433 12.0 70 1
## 5 17 8 302 140 3449 10.5 70 1
## 6 15 8 429 198 4341 10.0 70 1
## name
## 1 chevrolet chevelle malibu
## 2 buick skylark 320
## 3 plymouth satellite
## 4 amc rebel sst
## 5 ford torino
## 6 ford galaxie 500
#problem 1
str(Auto)
## 'data.frame': 397 obs. of 9 variables:
## $ mpg : num 18 15 18 16 17 15 14 14 14 15 ...
## $ cylinders : int 8 8 8 8 8 8 8 8 8 8 ...
## $ displacement: num 307 350 318 304 302 429 454 440 455 390 ...
## $ horsepower : num 130 165 150 150 140 198 220 215 225 190 ...
## $ weight : num 3504 3693 3436 3433 3449 ...
## $ acceleration: num 12 11.5 11 12 10.5 10 9 8.5 10 8.5 ...
## $ year : int 70 70 70 70 70 70 70 70 70 70 ...
## $ origin : int 1 1 1 1 1 1 1 1 1 1 ...
## $ name : chr "chevrolet chevelle malibu" "buick skylark 320" "plymouth satellite" "amc rebel sst" ...
#every thing is quantitative except for the name of the product
#problem 2
#mpg
range(Auto[,1])
## [1] 9.0 46.6
#cylinders
range(Auto[,2])
## [1] 3 8
#displacement
range(Auto[,3])
## [1] 68 455
#horsepower
range(Auto[,4])
## [1] NA NA
#weight
range(Auto[,5])
## [1] 1613 5140
#acceleration
range(Auto[,6])
## [1] 8.0 24.8
#year
range(Auto[,7])
## [1] 70 82
#origin
range(Auto[,8])
## [1] 1 3
#problem 3
#mpg
mean(Auto[,1])
## [1] 23.51587
sd(Auto[,1])
## [1] 7.825804
#cylinders
mean(Auto[,2])
## [1] 5.458438
sd(Auto[,2])
## [1] 1.701577
#displacement
mean(Auto[,3])
## [1] 193.5327
sd(Auto[,3])
## [1] 104.3796
#horsepower
mean(Auto[,4])
## [1] NA
sd(Auto[,4])
## [1] NA
#weight
mean(Auto[,5])
## [1] 2970.262
sd(Auto[,5])
## [1] 847.9041
#acceleration
mean(Auto[,6])
## [1] 15.55567
sd(Auto[,6])
## [1] 2.749995
#year
mean(Auto[,7])
## [1] 75.99496
sd(Auto[,7])
## [1] 3.690005
#origin
mean(Auto[,8])
## [1] 1.574307
sd(Auto[,8])
## [1] 0.8025495
#problem $
ten85= rbind(Auto[1:9,],Auto[86:397,])
#problem 3
#mpg
mean(ten85[,1])
## [1] 24.43863
sd(ten85[,1])
## [1] 7.908184
#cylinders
mean(ten85[,2])
## [1] 5.370717
sd(ten85[,2])
## [1] 1.653486
#displacement
mean(ten85[,3])
## [1] 187.0498
sd(ten85[,3])
## [1] 99.63539
#horsepower
mean(ten85[,4])
## [1] NA
sd(ten85[,4])
## [1] NA
#weight
mean(ten85[,5])
## [1] 2933.963
sd(ten85[,5])
## [1] 810.6429
#acceleration
mean(ten85[,6])
## [1] 15.72305
sd(ten85[,6])
## [1] 2.680514
#year
mean(ten85[,7])
## [1] 77.15265
sd(ten85[,7])
## [1] 3.11123
#origin
mean(ten85[,8])
## [1] 1.598131
sd(ten85[,8])
## [1] 0.8161627
#Ranges
#mpg
range(ten85[,1])
## [1] 11.0 46.6
#cylinders
range(ten85[,2])
## [1] 3 8
#displacement
range(ten85[,3])
## [1] 68 455
#horsepower
range(ten85[,4])
## [1] NA NA
#weight
range(ten85[,5])
## [1] 1649 4997
#acceleration
range(ten85[,6])
## [1] 8.5 24.8
#year
range(ten85[,7])
## [1] 70 82
#origin
range(ten85[,8])
## [1] 1 3
#problem 4
pairs(Auto[,1:8])
# from this i've gathered there is a correlation between the following variables mpg, displacement, horsepower,weight, and acceleration.
#problem 5
college<-read.csv("http://faculty.marshall.usc.edu/gareth-james/ISL/College.csv",header=TRUE)
rownames(college) <- college[,1]
View(college)
college <- college[,-1]
View(college)
#part C.A
summary(college)
## Private Apps Accept Enroll
## Length:777 Min. : 81 Min. : 72 Min. : 35
## Class :character 1st Qu.: 776 1st Qu.: 604 1st Qu.: 242
## Mode :character Median : 1558 Median : 1110 Median : 434
## Mean : 3002 Mean : 2019 Mean : 780
## 3rd Qu.: 3624 3rd Qu.: 2424 3rd Qu.: 902
## Max. :48094 Max. :26330 Max. :6392
## Top10perc Top25perc F.Undergrad P.Undergrad
## Min. : 1.00 Min. : 9.0 Min. : 139 Min. : 1.0
## 1st Qu.:15.00 1st Qu.: 41.0 1st Qu.: 992 1st Qu.: 95.0
## Median :23.00 Median : 54.0 Median : 1707 Median : 353.0
## Mean :27.56 Mean : 55.8 Mean : 3700 Mean : 855.3
## 3rd Qu.:35.00 3rd Qu.: 69.0 3rd Qu.: 4005 3rd Qu.: 967.0
## Max. :96.00 Max. :100.0 Max. :31643 Max. :21836.0
## Outstate Room.Board Books Personal
## Min. : 2340 Min. :1780 Min. : 96.0 Min. : 250
## 1st Qu.: 7320 1st Qu.:3597 1st Qu.: 470.0 1st Qu.: 850
## Median : 9990 Median :4200 Median : 500.0 Median :1200
## Mean :10441 Mean :4358 Mean : 549.4 Mean :1341
## 3rd Qu.:12925 3rd Qu.:5050 3rd Qu.: 600.0 3rd Qu.:1700
## Max. :21700 Max. :8124 Max. :2340.0 Max. :6800
## PhD Terminal S.F.Ratio perc.alumni
## Min. : 8.00 Min. : 24.0 Min. : 2.50 Min. : 0.00
## 1st Qu.: 62.00 1st Qu.: 71.0 1st Qu.:11.50 1st Qu.:13.00
## Median : 75.00 Median : 82.0 Median :13.60 Median :21.00
## Mean : 72.66 Mean : 79.7 Mean :14.09 Mean :22.74
## 3rd Qu.: 85.00 3rd Qu.: 92.0 3rd Qu.:16.50 3rd Qu.:31.00
## Max. :103.00 Max. :100.0 Max. :39.80 Max. :64.00
## Expend Grad.Rate
## Min. : 3186 Min. : 10.00
## 1st Qu.: 6751 1st Qu.: 53.00
## Median : 8377 Median : 65.00
## Mean : 9660 Mean : 65.46
## 3rd Qu.:10830 3rd Qu.: 78.00
## Max. :56233 Max. :118.00
#part C.b
pairs(college[,2:10])
