随机森林-R

这里与Python的区别在于R中有一种变量叫factor，是专门用来表示分类对象的，我们需要把分类结果转换成factor。
另外，对于随机森林来说，决策树的数量并不是越多越好，且由于是随机的，每次的结果可能稍有不同。
代码：

# Random Forest 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 Random Forest Classification to the Training set
# install.packages('randomForest')
library(randomForest)
classifier = randomForest(x = training_set[-3],
                          y = training_set$Purchased,
                          ntree=10)

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

# 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)
plot(set[, -3],
     main = 'Random Forest Classification (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)
plot(set[, -3], main = 'Random Forest Classification (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'))

关键代码：
dataset$Purchased = factor(dataset$Purchased, levels = c(0, 1))
library(randomForest)
classifier = randomForest(x = training_set[-3],
y = training_set$Purchased,
ntree=10)
运行结果：

测试集.PNG 训练集.PNG
混淆矩阵.PNG
对于这组数据，逻辑回归算法和线性SVM无法正确划分低龄高收入以及高龄低收入用户，决策树和随机森林过拟合，无法去除噪音点，只有高斯SVM以及朴素贝叶斯预测出平滑曲线，分类效果比较好