library(tidyverse)
## -- Attaching packages ---------------- tidyverse 1.2.1 --
## v ggplot2 3.2.1 v purrr 0.3.2
## v tibble 2.1.3 v dplyr 0.8.3
## v tidyr 1.0.0 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0
## -- Conflicts ------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
auto1=read.csv("Auto.csv", header=TRUE, na.strings = "?")
auto=na.omit(auto1)
dim(auto)
## [1] 392 9
A.-D.
str(auto)
## 'data.frame': 392 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 : int 130 165 150 150 140 198 220 215 225 190 ...
## $ weight : int 3504 3693 3436 3433 3449 4341 4354 4312 4425 3850 ...
## $ 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 : Factor w/ 304 levels "amc ambassador brougham",..: 49 36 231 14 161 141 54 223 241 2 ...
## - attr(*, "na.action")= 'omit' Named int 33 127 331 337 355
## ..- attr(*, "names")= chr "33" "127" "331" "337" ...
range(auto$displacement)
## [1] 68 455
range(auto$horsepower)
## [1] 46 230
range(auto$acceleration)
## [1] 8.0 24.8
mean(auto$displacement)
## [1] 194.412
sd(auto$displacement)
## [1] 104.644
mean(auto$horsepower)
## [1] 104.4694
sd(auto$horsepower)
## [1] 38.49116
mean(auto$weight)
## [1] 2977.584
sd(auto$weight)
## [1] 849.4026
mean(auto$acceleration)
## [1] 15.54133
sd(auto$acceleration)
## [1] 2.758864
subauto=auto[-c(10:85),]
dim(subauto)
## [1] 316 9
range(subauto$displacement)
## [1] 68 455
range(subauto$horsepower)
## [1] 46 230
range(subauto$weight)
## [1] 1649 4997
range(subauto$acceleration)
## [1] 8.5 24.8
mean(auto$displacement)
## [1] 194.412
sd(subauto$displacement)
## [1] 99.67837
mean(subauto$horsepower)
## [1] 100.7215
sd(subauto$horsepower)
## [1] 35.70885
mean(subauto$weight)
## [1] 2935.972
sd(subauto$weight)
## [1] 811.3002
mean(subauto$acceleration)
## [1] 15.7269
sd(subauto$acceleration)
## [1] 2.693721
hist(auto$mpg)
plot(auto$mpg, auto$horsepower,)
boxplot(mpg~cylinders, data=auto)
# F. Looking at the scatterplots, we see that cylinders, horsepower, and weight have a negative correlation because of the negative line of best fit. Horse power does not show correlation on the scatter plot.
# Box office Star Wars (in millions!)
new_hope <- c(460.998, 314.4)
empire_strikes <- c(290.475, 247.900)
return_jedi <- c(309.306, 165.8)
# Vectors region and titles, used for naming
region <- c("US", "non-US")
titles <- c("A New Hope", "The Empire Strikes Back", "Return of
the Jedi")
#A. Construct a matrix, where rows represent each movie. Name this matrix starWars and output it.
#Starwars
movies=c(new_hope, empire_strikes, return_jedi)
starwars=matrix(movies, nrow=3, ncol=2, byrow = TRUE)
starwars
## [,1] [,2]
## [1,] 460.998 314.4
## [2,] 290.475 247.9
## [3,] 309.306 165.8
rownames(starwars)=titles
colnames(starwars)=region
starwars
## US non-US
## A New Hope 460.998 314.4
## The Empire Strikes Back 290.475 247.9
## Return of\nthe Jedi 309.306 165.8
wwboxoffice=rowSums(starwars)
wwboxoffice
## A New Hope The Empire Strikes Back Return of\nthe Jedi
## 775.398 538.375 475.106
cbind(starwars,wwboxoffice)
## US non-US wwboxoffice
## A New Hope 460.998 314.4 775.398
## The Empire Strikes Back 290.475 247.9 538.375
## Return of\nthe Jedi 309.306 165.8 475.106
# Prequels
phantom_menace <- c(474.5, 552.5)
attack_clones <- c(310.7, 338.7)
revenge_sith <- c(380.3, 468.5)
titles2<-c("The Phantom Menace", "Attack of the Clones",
"Revenge of the Sith")
movies2=c(phantom_menace, attack_clones, revenge_sith)
starWars2=matrix(movies2, nrow=3, byrow = TRUE)
rownames(starWars2)=titles2
colnames(starWars2)=region
starWars2
## US non-US
## The Phantom Menace 474.5 552.5
## Attack of the Clones 310.7 338.7
## Revenge of the Sith 380.3 468.5
allstarwars=rbind(starwars, starWars2)
colSums(allstarwars)
## US non-US
## 2226.279 2087.800
college<-read.csv("http://faculty.marshall.usc.edu/gareth-james/ISL/
College.csv",header=TRUE)
view(college)
rownames(college)=college[,1]
view(college)
college = college[,-1]
view(college)
summary(college)
## Private Apps Accept Enroll Top10perc
## No :212 Min. : 81 Min. : 72 Min. : 35 Min. : 1.00
## Yes:565 1st Qu.: 776 1st Qu.: 604 1st Qu.: 242 1st Qu.:15.00
## Median : 1558 Median : 1110 Median : 434 Median :23.00
## Mean : 3002 Mean : 2019 Mean : 780 Mean :27.56
## 3rd Qu.: 3624 3rd Qu.: 2424 3rd Qu.: 902 3rd Qu.:35.00
## Max. :48094 Max. :26330 Max. :6392 Max. :96.00
## Top25perc F.Undergrad P.Undergrad Outstate
## Min. : 9.0 Min. : 139 Min. : 1.0 Min. : 2340
## 1st Qu.: 41.0 1st Qu.: 992 1st Qu.: 95.0 1st Qu.: 7320
## Median : 54.0 Median : 1707 Median : 353.0 Median : 9990
## Mean : 55.8 Mean : 3700 Mean : 855.3 Mean :10441
## 3rd Qu.: 69.0 3rd Qu.: 4005 3rd Qu.: 967.0 3rd Qu.:12925
## Max. :100.0 Max. :31643 Max. :21836.0 Max. :21700
## Room.Board Books Personal PhD
## Min. :1780 Min. : 96.0 Min. : 250 Min. : 8.00
## 1st Qu.:3597 1st Qu.: 470.0 1st Qu.: 850 1st Qu.: 62.00
## Median :4200 Median : 500.0 Median :1200 Median : 75.00
## Mean :4358 Mean : 549.4 Mean :1341 Mean : 72.66
## 3rd Qu.:5050 3rd Qu.: 600.0 3rd Qu.:1700 3rd Qu.: 85.00
## Max. :8124 Max. :2340.0 Max. :6800 Max. :103.00
## Terminal S.F.Ratio perc.alumni Expend
## Min. : 24.0 Min. : 2.50 Min. : 0.00 Min. : 3186
## 1st Qu.: 71.0 1st Qu.:11.50 1st Qu.:13.00 1st Qu.: 6751
## Median : 82.0 Median :13.60 Median :21.00 Median : 8377
## Mean : 79.7 Mean :14.09 Mean :22.74 Mean : 9660
## 3rd Qu.: 92.0 3rd Qu.:16.50 3rd Qu.:31.00 3rd Qu.:10830
## Max. :100.0 Max. :39.80 Max. :64.00 Max. :56233
## Grad.Rate
## Min. : 10.00
## 1st Qu.: 53.00
## Median : 65.00
## Mean : 65.46
## 3rd Qu.: 78.00
## Max. :118.00
pairs(college[,1:10])
plot(college$Outstate, college$Private)
Elite <- rep("No", nrow(college))
Elite[college$Top10perc > 50] = "Yes"
Elite <- as.factor(Elite)
college <- data.frame(college, Elite)
summary(Elite)
## No Yes
## 699 78
plot(college$Outstate, Elite)