library(e1071)
library(ggplot2)
data('thyroid',package = 'mclust')
plot(thyroid$Diagnosis)
data<-thyroid
set.seed(2016)
N<-nrow(thyroid)
train<-sample(1:N,150,FALSE)#在1到N抽样，抽150次，采样不更换
head(train)
fit<-naiveBayes(Diagnosis ~.,data=data[train,])
attributes(fit)#查看属性
#$names
#[1] "apriori"   "tables"    "levels"    "isnumeric"
#[5] "call"     

#$class
#[1] "naiveBayes"
fit$apriori#参数aprioori包含类别分布
fit$table$RT3U
> fit$table$RT3U
        RT3U
Y            [,1]      [,2]
  Hypo   121.2632 10.943502
  Normal 111.3585  7.950069
  Hyper   93.5200 19.977320
#分别为均值和标准差
pred<-predict(fit,data[-train,-1],type='class')#给出分类
head(pred,4)
pred<-predict(fit,data[-train,-1],type='raw')#给出概率
table(pred,data$Diagnosis[-train])
#pred     Hypo Normal Hyper
  #Hypo     11      1     0
  #Normal    0     43     0
  #Hyper     0      0    10

混淆矩阵显示学习效果良好