分類決策樹：用于預測定性數據，給定觀測值被預測為它所屬的葉節(jié)點內訓練集中最常見的類別（多數表決）。

構造過程：特征選擇→決策樹的生成→決策樹的剪枝

分類決策樹以分類錯誤率作為確定分割點的準則

rm(list=ls())
library(tree) #加載tree包以建立分類樹和回歸樹
data("Carseats")
attach(Carseats)
High=ifelse(Sales<=8,"No","Yes")  #創(chuàng)建高銷量變量
Carseats=data.frame(Carseats,High)
dim(Carseats)  #400 12
tree.carseats=tree(High~.-Sales,data=Carseats)
summary(tree.carseats)

###生成####
set.seed(2)
train=sample(1:nrow(Carseats),200) #200個訓練集 200個測試集
Carseats.test=Carseats[-train,] #測試數據
High.test=High[-train]
tree.carseats=tree(High~.-Sales,Carseats,subset = train)
tree.carseats
par(mfrow=c(1,1))
plot(tree.carseats)
text(tree.carseats,pretty=0)
tree.pred=predict(tree.carseats,Carseats.test,type="class")
table(tree.pred,High.test)(86+57)/200 #測試集預測的準確率為(86+57)/200=0.715

###剪枝####
set.seed(3)
cv.carseats=cv.tree(tree.carseats,FUN=prune.misclass)
names(cv.carseats)
par(mfrow=c(1,2))
plot(cv.carseatssize,cv.carseatsdev,type="b") #錯誤率對樹規(guī)模size的函數
plot(cv.carseatsk,cv.carseatsdev,type="b")  #錯誤率對復雜度k的函數
par(mfrow=c(1,1))
prune.carseats=prune.misclass(tree.carseats,best=9)
plot(prune.carseats)
text(prune.carseats,pretty=0)
tree.pred=predict(prune.carseats,Carseats.test,type="class")
table(tree.pred,High.test)(96+60)/200 #測試集預測的準確率為(96+60)/200=0.78