机器学习与R之回归树CART与模型树M5

根据SDR标准偏差减少-来选择特征
sdr_a <- sd(tee) - (length(at1) / length(tee) * sd(at1) + length(at2) / length(tee) * sd(at2))
回归树CART-叶子节点利用的是均值
rpart(formula, data, weights, subset, na.action = na.rpart, method,
      model = FALSE, x = FALSE, y = TRUE, parms, control, cost, ...)
control算法细节  
rpart(Kyphosis ~ Age + Number + Start, data = kyphosis,
              control = rpart.control(cp = 0.05))
library(rpart)
m.rpart <- rpart(quality ~ ., data = wine_train)
p.rpart <- predict(m.rpart, wine_test,type="vector") #vector预测数值class预测类别prob预测类别的概率
可视化决策树
library(rpart.plot)
rpart.plot(m.rpart, digits = 3) #digits图中数字位置
#fallen.leaves叶节点与图底部对齐, type决策被标记的方式, extra节点被标记的方式
rpart.plot(m.rpart, digits = 4, fallen.leaves = TRUE, type = 3, extra = 101)
模型树M5-叶子节点利用的是回归模型
library(RWeka)
m.m5p <- M5P(quality ~ ., data = wine_train)

p.m5p <- predict(m.m5p, wine_test)

wine <- read.csv("whitewines.csv")

# examine the wine data
str(wine)

# the distribution of quality ratings
hist(wine$quality)

# summary statistics of the wine data
summary(wine)

wine_train <- wine[1:3750, ]
wine_test <- wine[3751:4898, ]

## Step 3: Training a model on the data ----
# regression tree using rpart
library(rpart)
m.rpart <- rpart(quality ~ ., data = wine_train)

# get basic information about the tree
m.rpart

# get more detailed information about the tree
summary(m.rpart)

# use the rpart.plot package to create a visualization
library(rpart.plot)

# a basic decision tree diagram
rpart.plot(m.rpart, digits = 3)

# a few adjustments to the diagram
rpart.plot(m.rpart, digits = 4, fallen.leaves = TRUE, type = 3, extra = 101)

## Step 4: Evaluate model performance ----

# generate predictions for the testing dataset
p.rpart <- predict(m.rpart, wine_test)

# compare the distribution of predicted values vs. actual values
summary(p.rpart)
summary(wine_test$quality)

# compare the correlation
cor(p.rpart, wine_test$quality)

# function to calculate the mean absolute error
MAE <- function(actual, predicted) {
  mean(abs(actual - predicted))  
}

# mean absolute error between predicted and actual values
MAE(p.rpart, wine_test$quality)

# mean absolute error between actual values and mean value
mean(wine_train$quality) # result = 5.87
MAE(5.87, wine_test$quality)

## Step 5: Improving model performance ----
# train a M5' Model Tree
library(RWeka)
m.m5p <- M5P(quality ~ ., data = wine_train)

# display the tree
m.m5p

# get a summary of the model's performance
summary(m.m5p)

# generate predictions for the model
p.m5p <- predict(m.m5p, wine_test)

# summary statistics about the predictions
summary(p.m5p)

# correlation between the predicted and true values
cor(p.m5p, wine_test$quality)

# mean absolute error of predicted and true values
# (uses a custom function defined above)
MAE(wine_test$quality, p.m5p)