R语言-正规化回归预测-ridge & lasso (ridge & lasso regression in r)

废话不多说，直接附上code
影片含有程序码详细解说，若有误再烦请告知，谢谢

library(glmnet)
library(dplyr)
library(ggplot2)
data(iris)
iris <- iris[,-c(5)]
#检查离群值
par(mfrow=c(1,3))
boxplot(iris$Sepal.Width)$out
boxplot(iris$Petal.Length)$out
boxplot(iris$Petal.Width)$out
#随机抽样
n <- nrow(iris)
set.seed(1117)
subiris <- sample(seq_len(n), size = round(0.7 * n))
traindata <- iris[subiris,]%>% as.matrix()
testdata <- iris[ - subiris,]%>% as.matrix()
trainx <- traindata[,c(2:4)]
trainy <- traindata[,c(1)]
testx <- testdata[,c(2:4)]
testy <- testdata[,c(1)]

#调参 lamda
ridge <- cv.glmnet(x = trainx,y = trainy,alpha = 0)
#交叉验证 预设k=10，alpha = 0为ridge, =1为lasso
ridge
#视觉化&选自变量
coef(ridge, s = "lambda.min") %>% 
  as.matrix() %>% 
  as.data.frame() %>% 
  add_rownames(var = "var") %>% 
  `colnames<-`(c("var","coef")) %>%
  filter(var != "(Intercept)") %>%  #剔除截距项
  top_n(3, wt = coef) %>% 
  ggplot(aes(coef, reorder(var, coef))) +
  geom_bar(stat = "identity", width=0.2,
           color="blue", fill=rgb(0.1,0.4,0.5,0.7))+
  xlab("Coefficient") +
  ylab(NULL)

#预测
future <- predict(ridge,newx = testx, s = ridge$lambda.min)
future <- as.data.frame(future)
final <- cbind(future,testy) %>% data.frame()
final <- mutate(final,mape=abs(X1-testy)/testy)
mean(final$mape)