Laboratorio 2

Fiabilidad

Brayan Ivan Cruz Corona

13001595

5.3.1 The validation set approach

library(ISLR)
set.seed(1)
train=sample(392,196)

lm.fit=lm(mpg~horsepower,data=Auto,subset = train)

attach(Auto)

The following objects are masked from Auto (pos = 3):

    acceleration, cylinders, displacement,
    horsepower, mpg, name, origin, weight, year

The following objects are masked from Auto (pos = 4):

    acceleration, cylinders, displacement,
    horsepower, mpg, name, origin, weight, year

The following objects are masked from Auto (pos = 5):

    acceleration, cylinders, displacement,
    horsepower, mpg, name, origin, weight, year

mean((mpg-predict(lm.fit,Auto))[-train]^2)

[1] 26.14142

lm.fit2=lm(mpg~poly(horsepower,2),data = Auto,subset=train)
mean((mpg-predict(lm.fit2,Auto))[-train]^2)

[1] 19.82259

lm.fit3=lm(mpg~poly(horsepower,3),data = Auto,subset=train)
mean((mpg-predict(lm.fit3,Auto))[-train]^2)

[1] 19.78252

set.seed(2)
train=sample(392,196)
lm.fit=lm(mpg~horsepower,subset = train)
mean((mpg-predict(lm.fit,Auto))[-train]^2)

[1] 23.29559

lm.fit2=lm(mpg~poly(horsepower,2),data = Auto,subset=train)
mean((mpg-predict(lm.fit2,Auto))[-train]^2)

[1] 18.90124

lm.fit3=lm(mpg~poly(horsepower,3),data = Auto,subset=train)
mean((mpg-predict(lm.fit3,Auto))[-train]^2)

[1] 19.2574

5.3.2 Leave-One-Out Cross Validation

glm.fit= glm(mpg~horsepower, data=Auto)
coef(glm.fit)

(Intercept)  horsepower 
 39.9358610  -0.1578447 

lm.fit=lm(mpg~horsepower,data=Auto)
coef(lm.fit)

(Intercept)  horsepower 
 39.9358610  -0.1578447 

library(boot)
glm.fit = glm(mpg~horsepower, data=Auto)
cv.err=cv.glm(Auto, glm.fit)
cv.err$delta

[1] 24.23151 24.23114

cv.error = rep(0,5)
for (i in 1:5) {
  glm.fit=glm(mpg~poly(horsepower,i),data=Auto)
  cv.error[i]=cv.glm(Auto,glm.fit)$delta[1]
}
cv.error

[1] 24.23151 19.24821 19.33498 19.42443 19.03321

5.3.3 k-Fold Cross Validation

set.seed(17)
cv.error.10=rep(0,10)
for(i in 1:10){
  glm.fit=glm(mpg~poly(horsepower,i),data=Auto)
  cv.error.10[i]=cv.glm(Auto,glm.fit,K=10)$delta[1]
}
cv.error.10

 [1] 24.20520 19.18924 19.30662 19.33799 18.87911
 [6] 19.02103 18.89609 19.71201 18.95140 19.50196

===========================================================

4.6.5 K-Nearest Neighbors

library(class)
attach(Smarket)

The following objects are masked from Smarket (pos = 3):

    Direction, Lag1, Lag2, Lag3, Lag4, Lag5,
    Today, Volume, Year

The following objects are masked from Smarket (pos = 4):

    Direction, Lag1, Lag2, Lag3, Lag4, Lag5,
    Today, Volume, Year

train.X=cbind(Lag1,Lag2)[train,]
test.X=cbind(Lag1,Lag2)[!train,]
train.Direction=Direction[train]

set.seed(1)
train=(Year<2005)
Direction.2005=Direction[!train]
knn.pred=knn(train.X,test.X,train.Direction,k=1)
table(knn.pred,Direction.2005)

        Direction.2005
knn.pred Down Up
    Down   43 58
    Up     68 83

(83+43)/252

[1] 0.5

knn.pred=knn(train.X,test.X,train.Direction,k=3)
table(knn.pred,Direction.2005)

        Direction.2005
knn.pred Down Up
    Down   48 54
    Up     63 87

mean(knn.pred==Direction.2005)

[1] 0.5357143