Introduction to Statistical Learning Russ Conte Saturday, April 15, 2017 Chapter 2: Statistical Learning
Advertising=read.csv('/Users/russconte/Advertising.csv', sep=',', header=TRUE)
head(Advertising)## X TV Radio Newspaper Sales
## 1 1 230.1 37.8 69.2 22.1
## 2 2 44.5 39.3 45.1 10.4
## 3 3 17.2 45.9 69.3 9.3
## 4 4 151.5 41.3 58.5 18.5
## 5 5 180.8 10.8 58.4 12.9
## 6 6 8.7 48.9 75.0 7.2attach(Advertising)
head(Advertising)## X TV Radio Newspaper Sales
## 1 1 230.1 37.8 69.2 22.1
## 2 2 44.5 39.3 45.1 10.4
## 3 3 17.2 45.9 69.3 9.3
## 4 4 151.5 41.3 58.5 18.5
## 5 5 180.8 10.8 58.4 12.9
## 6 6 8.7 48.9 75.0 7.2plot(TV, Sales, col="red")
plot(Radio, Sales, col="red")
plot(Newspaper, Sales, col="red")
x=c(1,3,2,5)
x## [1] 1 3 2 5y=c(1,6,2)
y## [1] 1 6 2length(x)## [1] 4length(y)## [1] 3x=c(1,6,2)
x+y## [1] 2 12 4ls()## [1] "Advertising" "x" "y"rm(x,y)
ls()## [1] "Advertising"rm(list=ls()) #remove all objects at once
ls()## character(0)x=matrix(data=c(1,2,3,4), nrow=2, ncol=2)
x## [,1] [,2]
## [1,] 1 3
## [2,] 2 4matrix(c(1,2,3,4),nrow=2, ncol=2, byrow = TRUE)## [,1] [,2]
## [1,] 1 2
## [2,] 3 4sqrt(x)## [,1] [,2]
## [1,] 1.000000 1.732051
## [2,] 1.414214 2.000000x^2## [,1] [,2]
## [1,] 1 9
## [2,] 4 16x=rnorm(50)
y=x+rnorm(50, mean=50, sd = 0.1)
cor(x,y)## [1] 0.9963487set.seed(1303)
rnorm(50)## [1] -1.1439763145 1.3421293656 2.1853904757 0.5363925179 0.0631929665
## [6] 0.5022344825 -0.0004167247 0.5658198405 -0.5725226890 -1.1102250073
## [11] -0.0486871234 -0.6956562176 0.8289174803 0.2066528551 -0.2356745091
## [16] -0.5563104914 -0.3647543571 0.8623550343 -0.6307715354 0.3136021252
## [21] -0.9314953177 0.8238676185 0.5233707021 0.7069214120 0.4202043256
## [26] -0.2690521547 -1.5103172999 -0.6902124766 -0.1434719524 -1.0135274099
## [31] 1.5732737361 0.0127465055 0.8726470499 0.4220661905 -0.0188157917
## [36] 2.6157489689 -0.6931401748 -0.2663217810 -0.7206364412 1.3677342065
## [41] 0.2640073322 0.6321868074 -1.3306509858 0.0268888182 1.0406363208
## [46] 1.3120237985 -0.0300020767 -0.2500257125 0.0234144857 1.6598706557set.seed(3)
y=rnorm(100)
mean(y)## [1] 0.01103557var(y)## [1] 0.7328675sqrt(var(y))## [1] 0.8560768sd(y)## [1] 0.8560768x=rnorm(100)
y=rnorm(100)
plot(x,y)
plot(x,y, xlab="this is the x-axis", ylab="this is the y-axis", main="Plot of x vs y")
plot(x,y, col="green")
x=seq(1,10)
x## [1] 1 2 3 4 5 6 7 8 9 10x=seq(-pi, pi, length=50)
x## [1] -3.14159265 -3.01336438 -2.88513611 -2.75690784 -2.62867957
## [6] -2.50045130 -2.37222302 -2.24399475 -2.11576648 -1.98753821
## [11] -1.85930994 -1.73108167 -1.60285339 -1.47462512 -1.34639685
## [16] -1.21816858 -1.08994031 -0.96171204 -0.83348377 -0.70525549
## [21] -0.57702722 -0.44879895 -0.32057068 -0.19234241 -0.06411414
## [26] 0.06411414 0.19234241 0.32057068 0.44879895 0.57702722
## [31] 0.70525549 0.83348377 0.96171204 1.08994031 1.21816858
## [36] 1.34639685 1.47462512 1.60285339 1.73108167 1.85930994
## [41] 1.98753821 2.11576648 2.24399475 2.37222302 2.50045130
## [46] 2.62867957 2.75690784 2.88513611 3.01336438 3.14159265y=x
f=outer(x,y, function(x,y) cos(y)/(1+x^2))
contour(x,y,f)
contour(x,y,f, nlevels = 45, add=TRUE)
fa=(f-t(f))/2
contour(x,y,fa, nlevels = 15)
image(x,y,fa)
persp(x,y,fa)
persp(x,y,fa, theta = 30)
persp(x,y,fa, theta=30, phi = 20)
persp(x,y,fa,theta = 30, phi = 70)
persp(x,y,fa,theta = 30, phi = 40)
2.3.3 Indexing Data
A=matrix(1:16, 4,4)
A## [,1] [,2] [,3] [,4]
## [1,] 1 5 9 13
## [2,] 2 6 10 14
## [3,] 3 7 11 15
## [4,] 4 8 12 16A[2,3]## [1] 10A[c(1,3),c(2,4)]## [,1] [,2]
## [1,] 5 13
## [2,] 7 15A[1:3, 2:4]## [,1] [,2] [,3]
## [1,] 5 9 13
## [2,] 6 10 14
## [3,] 7 11 15A[1:2,]## [,1] [,2] [,3] [,4]
## [1,] 1 5 9 13
## [2,] 2 6 10 14A[,1:2]## [,1] [,2]
## [1,] 1 5
## [2,] 2 6
## [3,] 3 7
## [4,] 4 8A[1,]## [1] 1 5 9 13A[-c(1,3), -c(1,3,4)]## [1] 6 8dim(A)## [1] 4 4Auto=read.table('/Users/russconte/Auto.data', header=TRUE)
head(Auto)## mpg cylinders displacement horsepower weight acceleration year origin
## 1 18 8 307 130.0 3504 12.0 70 1
## 2 15 8 350 165.0 3693 11.5 70 1
## 3 18 8 318 150.0 3436 11.0 70 1
## 4 16 8 304 150.0 3433 12.0 70 1
## 5 17 8 302 140.0 3449 10.5 70 1
## 6 15 8 429 198.0 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 500Auto=read.table('/Users/russconte/Auto.data', header=TRUE, na.strings = "?")
dim(Auto)## [1] 397 9Auto[1:4,]## 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
## name
## 1 chevrolet chevelle malibu
## 2 buick skylark 320
## 3 plymouth satellite
## 4 amc rebel sstnames(Auto)## [1] "mpg" "cylinders" "displacement" "horsepower"
## [5] "weight" "acceleration" "year" "origin"
## [9] "name"attach(Auto)
plot(cylinders, mpg)
plot(cylinders, mpg, col="red")
plot(cylinders, mpg, col="red")
plot(cylinders, mpg, col="red", xlab="cylinders", ylab="MPG")
hist(mpg)
hist(mpg, col = 2)
hist(mpg, col=2, breaks = 15)
pairs(Auto)
pairs(~mpg+displacement+horsepower+weight+acceleration, Auto)
plot(horsepower, mpg)
identify(horsepower, mpg, name)
## integer(0)summary(Auto)## mpg cylinders displacement horsepower
## Min. : 9.00 Min. :3.000 Min. : 68.0 Min. : 46.0
## 1st Qu.:17.50 1st Qu.:4.000 1st Qu.:104.0 1st Qu.: 75.0
## Median :23.00 Median :4.000 Median :146.0 Median : 93.5
## Mean :23.52 Mean :5.458 Mean :193.5 Mean :104.5
## 3rd Qu.:29.00 3rd Qu.:8.000 3rd Qu.:262.0 3rd Qu.:126.0
## Max. :46.60 Max. :8.000 Max. :455.0 Max. :230.0
## NA's :5
## weight acceleration year origin
## Min. :1613 Min. : 8.00 Min. :70.00 Min. :1.000
## 1st Qu.:2223 1st Qu.:13.80 1st Qu.:73.00 1st Qu.:1.000
## Median :2800 Median :15.50 Median :76.00 Median :1.000
## Mean :2970 Mean :15.56 Mean :75.99 Mean :1.574
## 3rd Qu.:3609 3rd Qu.:17.10 3rd Qu.:79.00 3rd Qu.:2.000
## Max. :5140 Max. :24.80 Max. :82.00 Max. :3.000
##
## name
## ford pinto : 6
## amc matador : 5
## ford maverick : 5
## toyota corolla: 5
## amc gremlin : 4
## amc hornet : 4
## (Other) :368summary(mpg)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 9.00 17.50 23.00 23.52 29.00 46.60q## function (save = "default", status = 0, runLast = TRUE)
## .Internal(quit(save, status, runLast))
## <bytecode: 0x7fd228fd1c70>
## <environment: namespace:base>