决策树

library(tree)
tree.car <- tree(High ~ . - Sales, data = Carseats) #去除scales然后构造决策树

Logistic回归

require(MASS)
glm.fit <- glm(Direction ~ Lag1 + Lag2 + Lag3 + Lag4 + Lag5 + Volume, 
			   data = Smarket,
			   family = binomial)
# binomial表示要用Logitsti回归

LDA

require(MASS)
lda.fit <- lda(Direction ~ Lag1 + Lag2, data = Smarket_2001TO2004)

QDA

require(MASS)
qda.fit <- qda(Direction ~ Lag1 + Lag2, data = Smarket_2001TO2004)

SVM

library(e1071)
svmfit <- svm(y~., data=dat[train,], 
			  kernel="linear", 
			  cost=10, 
			  scale=FALSE)
# kernel="linear"表明用线性核
# scale=FALSE说明不需要对每个特征进行均值为零标准差为1的缩放
# 参数cost指出违背边界的代价权重, 越大则边界较窄

核函数使用径向基函数, 径向基函数的公式为：\(exp\{−γ|u−v|2\}\).

svmfit <- svm(y~., data=dat[train,], 
			  kernel="radial", 
			  gamma=1, 
			  cost=1)

核函数使用多项式核, 公式为: \((gamma∗u′∗v+coef0)^{degree}\)

svmfit <- svm(y~., data=dat[train,], 
			  kernel="polynomial", 
			  degree=3, 
			  gamma=1,
			  coef0=1, 
			  cost=1)