数据挖掘实验（五）：朴素贝叶斯分类方法 R语言

59 阅读 0 评论 39 点赞

我是靠谱客的博主孝顺小鸭子，最近开发中收集的这篇文章主要介绍数据挖掘实验（五）：朴素贝叶斯分类方法 R语言，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

一、实验目的：

了解朴素贝叶斯算法基本原理；
能够使用朴素贝叶斯算法对数据进行分类
编写函数实现示例数据集输出结果。

二、实验软件：

Rstudio

三、实验思路

准备数据data，希望分类的元组X为test
主函数 NaiveBayes = function(){}
公式 P(Ci|X) = P(X|Ci) P(Ci) / P(X)

1.划分C1,C2类，“yes",“no”

求P(C1),P(C2)

2.求P(Xi|Ci)

PXi_Ci = function(data,test,class_result){}
得PXi_C1，PXi_C2

3.求PX_Ci = function(PXi_Ci)

P(X|C1) = P(X1|C1)*P(X2|C1)*P(X3|C1)…
P(X|C2) = P(X1|C2)*P(X2|C2)*P(X3|C2)…

4.比较PX_C1PC[1],PX_C2PC[2]，select函数判断预测元组X的类是yes还是No，输出final结果

测试NaiveBayes(data,test)

四、源代码：

data<-data.frame(
  
  Age=c("youth","youth","middle_aged","senior","senior","senior","middle_aged","youth","youth","senior","youth","middle_aged","middle_aged","senior"),
  income=c("high","high","high","medium","low","low","low","medium","low","medium","medium","medium","high","medium"),
  student=c("no","no","no","no","yes","yes","yes","no","yes","yes","yes","no","yes","no"),
  credit_rating=c("fair","excellent","fair","fair","fair","excellent","excellent","fair","fair","fair","excellent","excellent","fair","excellent"),
  buys_computer=c("no","no","yes","yes","yes","no","yes","no","yes","yes","yes","yes","yes","no))

#yes
test<-data.frame(Age="youth",income="medium",student="yes",credit_rating="fair")

NaiveBayes = function(data,test){

rowCount=nrow(data) #计算数据集中有几行，也即有几个样本点
colCount=ncol(data) #几列
class_result = levels(factor(data[,colCount]))  # "no""yes"

class_Count = c() #存放个数
class_Count[class_result]=rep(0,length(class_result)) 

 #pC1,pC2

for(i in 1:rowCount){ 
  if(data[i,colCount] %in%  class_result)
    temp=data[i,colCount]
  class_Count[temp]=class_Count[temp]+1
}
PC = c() 
for (i in 1:length(class_result)) {
  PC[i] = class_Count[i]/rowCount
  
}
PC[1] 
PC[2]

#####求P(Xi|Ci)


PXi_Ci = function(data,test,class_result){
 
  xCount= c()
for(k in 1:ncol(test)){
   xCount[k] = 0
   temp = 0
   for(i in 1:nrow(data)){
      if(as.vector(data[i,k]) == as.vector(test[1,k]) & data[i,ncol(data)] == class_result){
        xCount[k] <- xCount[k]+1
      }
   
  }
}
  temp = subset(data,data[,ncol(data)] == class_result)
  Pxi_Ci = xCount/nrow(temp)
  return(Pxi_Ci)
} 

PXi_C1= PXi_Ci(data,test,class_result[1]) #"no"
PXi_C2= PXi_Ci(data,test,class_result[2]) #"yes"

#####求P(X|Ci) 



PX_Ci = function(PXi_Ci){ 
result = 1
for(i in 1:length((PXi_Ci))){
    result<-result*PXi_Ci[i]
  }
  
  
  return(result)
}

PX_C1 = PX_Ci(PXi_C1)
PX_C2 = PX_Ci(PXi_C2)


#######P(Ci|X)



Ci_X = data.frame(C1_X = PX_C1*PC[1],C2_X = PX_C2*PC[2])

select = function(data){  #比较找出最大Ci_X的类，存入新的属性decide
  if(data[,1]>data[,2]){
    data$decide = "no"
  }else{
    data$decide = "yes"
  }
  return(data)
}

final = select(Ci_X)
return(final)
}
#测试
NaiveBayes(data,test)