#Problem 1A

The name and origin is the qualitative data. The rest is quantitative,

#1B

range(auto2$cylinders)
## [1] 3 8
range(auto2$displacement)
## [1]  68 455
range(auto2$horsepower)
## [1]  46 230
range(auto2$mpg)
## [1]  9.0 46.6
range(auto2$weight)
## [1] 1613 5140
range(auto2$acceleration)
## [1]  8.0 24.8
range(auto2$year)
## [1] 70 82

cyl:3-8 disp: 68-455 hp: 46-230 mpg:9.0-46.6 weight:1613-5140 acc:8.0-24.8 year:70-82

#1C mean

mean(auto2$cylinders)
## [1] 5.471939
mean(auto2$displacement)
## [1] 194.412
mean(auto2$horsepower)
## [1] 104.4694
mean(auto2$mpg)
## [1] 23.44592
mean(auto2$weight)
## [1] 2977.584
mean(auto2$acceleration)
## [1] 15.54133
mean(auto2$year)
## [1] 75.97959

cyl:5.4719 disp: 194.412 hp: 104.4694 mpg:23.44592 weight:2977.584 acc:15.54133 year:75.97959

SD

sd(auto2$cylinders)
## [1] 1.705783
sd(auto2$displacement)
## [1] 104.644
sd(auto2$horsepower)
## [1] 38.49116
sd(auto2$mpg)
## [1] 7.805007
sd(auto2$weight)
## [1] 849.4026
sd(auto2$acceleration)
## [1] 2.758864
sd(auto2$year)
## [1] 3.683737

cyl:1.705 disp:104.644 hp: 38.49166 mpg:7.805007 weight:849.4026 acc:15.2.758864 year:3.683737

#1D

auto3=auto2[-c(10:85),]

range

range(auto3$cylinders)
## [1] 3 8
range(auto3$displacement)
## [1]  68 455
range(auto3$horsepower)
## [1]  46 230
range(auto3$mpg)
## [1] 11.0 46.6
range(auto3$weight)
## [1] 1649 4997
range(auto3$acceleration)
## [1]  8.5 24.8
range(auto3$year)
## [1] 70 82

cyl:3-8 disp:68-455 hp:46-230 mpg:11.0-46.6 weight:1649-4997 acc:8.5-24.8 year:70-82

mean

mean(auto3$cylinders)
## [1] 5.373418
mean(auto3$displacement)
## [1] 187.2405
mean(auto3$horsepower)
## [1] 100.7215
mean(auto3$mpg)
## [1] 24.40443
mean(auto3$weight)
## [1] 2935.972
mean(auto3$acceleration)
## [1] 15.7269
mean(auto3$year)
## [1] 77.14557

cyl:5.37341 disp:187.2405 hp:100.7215 mpg:24.40443 weight:2945.972 acc:15.7269 year:77.14557

SD

sd(auto3$cylinders)
## [1] 1.654179
sd(auto3$displacement)
## [1] 99.67837
sd(auto3$horsepower)
## [1] 35.70885
sd(auto3$mpg)
## [1] 7.867283
sd(auto3$weight)
## [1] 811.3002
sd(auto3$acceleration)
## [1] 2.693721
sd(auto3$year)
## [1] 3.106217

cyl:1.654179 disp:99.67837 hp:35.70885 mpg:7.86 weight:811.3002 acc:2.693721 year:3.106217

1E

plot(auto$weight, auto$mpg, col="red")

plot(auto$year, auto$mpg, col="blue")

plot(auto$displacement, auto$horsepower, col="orange")

We can see a relationship between differenct varibales, such as how the weight affects mpg, or how more displacment is correleated to more horsepower.

1F

Mpg seems cloely related to the weight of the car, as it decreases when the car is heaver. Ther is also a nticble relationship between the newer cars having bettter mpg than the older ones. Plotting a best fit line can show these relationships.

#2A

new_hope <- c(460.998, 314.4)
empire_strikes <- c(290.475, 247.900)
return_jedi <- c(309.306, 165.8)


starWars=matrix(data=c(new_hope, empire_strikes, return_jedi),nrow=3, ncol=2)
starWars
##         [,1]    [,2]
## [1,] 460.998 247.900
## [2,] 314.400 309.306
## [3,] 290.475 165.800

#2B

region <- c("US", "non-US")
titles <- c("A New Hope", "The Empire Strikes Back", "Return of the Jedi")


colnames(starWars)=region
rownames(starWars)=titles


starWars
##                              US  non-US
## A New Hope              460.998 247.900
## The Empire Strikes Back 314.400 309.306
## Return of the Jedi      290.475 165.800

#2C

sales=rowSums(starWars)
sales
##              A New Hope The Empire Strikes Back      Return of the Jedi 
##                 708.898                 623.706                 456.275

#2D

cbind(starWars, sales)
##                              US  non-US   sales
## A New Hope              460.998 247.900 708.898
## The Empire Strikes Back 314.400 309.306 623.706
## Return of the Jedi      290.475 165.800 456.275

#2E

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")

starWars2=matrix(data=c(phantom_menace, attack_clones, revenge_sith), nrow=3, ncol=2)

colnames(starWars2)=region
rownames(starWars2)=titles2
starWars2
##                         US non-US
## The Phantom Menace   474.5  338.7
## Attack of the Clones 552.5  380.3
## Revenge of the Sith  310.7  468.5

#2F

allstarWars=rbind(starWars,starWars2)
allstarWars
##                              US  non-US
## A New Hope              460.998 247.900
## The Empire Strikes Back 314.400 309.306
## Return of the Jedi      290.475 165.800
## The Phantom Menace      474.500 338.700
## Attack of the Clones    552.500 380.300
## Revenge of the Sith     310.700 468.500

#2G

colSums(allstarWars)
##       US   non-US 
## 2403.573 1910.506

#3A

college=read.csv("http://faculty.marshall.usc.edu/gareth-james/ISL/College.csv",header=TRUE)
View(college)

#3B

rownames(college) = college[,1]


college <- college[,-1]
View(college)

#3Ca

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

#3Cb

pairs(college[,1:10])

#3Cc

plot(college$Private, college$Outstate, col="blue")

#3Cd

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$Elite, college$Outstate, col="purple")