1、特征缩放

特征缩放是为了图形可视化的方便，决策树没有用到欧式距离不需要特征缩放

2、代码

# Decision Tree Classification

# Importing the dataset
dataset = read.csv('Social_Network_Ads.csv')
dataset = dataset[3:5]

# Encoding the target feature as factor
dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))

# Splitting the dataset into the Training set and Test set
# install.packages('caTools')
library(caTools)
set.seed(123)
split = sample.split(dataset$Purchased, SplitRatio = 0.75)
training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

# Feature Scaling
training_set[-3] = scale(training_set[-3])
test_set[-3] = scale(test_set[-3])

# Fitting Decision Tree to the Training set
# install.packages('rpart')
library(rpart)
classifier = rpart(formula = Purchased ~ .,
                   data = training_set)

# Predicting the Test set results
y_pred = predict(classifier, newdata = test_set[-3], type = 'class')

# Making the Confusion Matrix
cm = table(test_set[, 3], y_pred)

# Visualising the Training set results
library(ElemStatLearn)
set = training_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.0075)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.0075)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
y_grid = predict(classifier, newdata = grid_set, type = 'class')
plot(set[, -3],
     main = 'Decision Tree (Training set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

# Visualising the Test set results
library(ElemStatLearn)
set = test_set
X1 = seq(min(set[, 1]) - 1, max(set[, 1]) + 1, by = 0.0075)
X2 = seq(min(set[, 2]) - 1, max(set[, 2]) + 1, by = 0.0075)
grid_set = expand.grid(X1, X2)
colnames(grid_set) = c('Age', 'EstimatedSalary')
y_grid = predict(classifier, newdata = grid_set, type = 'class')
plot(set[, -3], main = 'Decision Tree (Test set)',
     xlab = 'Age', ylab = 'Estimated Salary',
     xlim = range(X1), ylim = range(X2))
contour(X1, X2, matrix(as.numeric(y_grid), length(X1), length(X2)), add = TRUE)
points(grid_set, pch = '.', col = ifelse(y_grid == 1, 'springgreen3', 'tomato'))
points(set, pch = 21, bg = ifelse(set[, 3] == 1, 'green4', 'red3'))

# Plotting the decision tree
plot(classifier)
text(classifier)

关键代码：
library(rpart)
classifier = rpart(formula = Purchased ~ .,
data = training_set)

Predicting the Test set results

y_pred = predict(classifier, newdata = test_set[-3], type = 'class')
类型属性可以将概率转化为分类因子
运行结果：

混淆矩阵.PNG 训练集.PNG 测试集.PNG 加type='class'.PNG 不加type='class'.PNG
决策树.PNG

3、与python中的决策树算法不同

这里的决策树算法是经过trim的，得出来的结果可以看出剔除了噪音点（异常数据，也就是离代表平均水平的，聚集的数据点比较远的数据），并且正确预测了年龄偏大收入低，以及年龄偏低收入高的人群的收入，解决了线性分类器无法解决的问题。
并且它的预测结果是概率，就是更可能的分类可能，我们需要给预测函数添加属性，才能将结果显示为分类因子。

3、还原决策树

画决策树本身是不需要特征缩放的，我们省去特征缩放这一步。
记住清除变量、图形还有CTRL+L清除控制窗口