Ridge and Lasso
Packages
library(ISLR)
library(tidyverse)
library(glmnet)
sampling
Hitters <- na.omit(Hitters)
x <- model.matrix(Salary ~ ., Hitters)[, -1]
y <- Hitters$Salary
set.seed(1)
train <- sample(1:nrow(x), nrow(x) / 2)
test <- (-train)
y.test <- y[test]
ridge regression
grid <- 10 ^ seq(10, -2, length = 100)
ridge.mod <- glmnet(x, y, alpha = 0, lambda = grid)
plot(ridge.mod, main = "The ridge")
the lasso
lasso.mod <- glmnet(x[train, ], y[train], alpha = 1, lambda = grid)
plot(lasso.mod, main = "The lasso")
cross-validation
set.seed(1)
cv.out <- cv.glmnet(x[train, ], y[train], alpha = 1)
plot(cv.out)
bestlam <- cv.out$lambda.min
lasso.pred <- predict(lasso.mod, s = bestlam, newx = x[test, ])
mean((lasso.pred - y.test) ^ 2)
## [1] 100743.4