R中有一类数据类型叫Categorical Varieble，我们用factor来存储它
CTRL+L用来清除控制区域，小扫帚用来清除已生成变量
代码：

# Naive Bayes

# 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 Naive Bayes to the Training set
# install.packages('e1071')
library(e1071)
classifier = naiveBayes(x = training_set[-3],
                        y = training_set$Purchased)

# 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 = 'Naive Bayes (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 = 'Naive Bayes (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：

Encoding the target feature as factor

dataset$Purchased = factor(dataset$Purchased, levels = c(0,1))
没有这部分代码，就无法显示预测结果，我们要将数值转换成因子，也就是分类变量，否则在显示预测结果时就会出现factor(0)，在显示混淆矩阵时，就会出现数值大小不一致，因为一个是数字，一个是分类变量为空。这里的第二行代码表示分类变量有两个取值，0和1，它们此时代表的是因子，而不是数值
library(e1071)
classifier = naiveBayes(x = training_set[-3],
y = training_set$Purchased)
运行结果：

混淆矩阵.PNG 训练集.PNG 测试集.PNG

朴素贝叶斯要求特征点是独立的