R语言中的Apriori关联规则的使用

OGeek|极客世界-中国程序员成长平台 › 门户 › 编程› R语言›R语言教程

原作者: [db:作者] 来自: [db:来源] 收藏邀请

1.下载Matrix和arules包

install.packages(c("Matrix","arules"))

2.载入引入Matrix和arules包

# 引入Matrix和arules包
library(Matrix)
library(arules)

3.读取数据

# 读入数据 
dataset <- mysql_find(sql)

4.数据转换

# 将数据框转为矩阵
dataset2 <- as.matrix(dataset)  
# 转换为交易流数据transactions
dataset2.class<-as(dataset2,"transactions")

5.调用apriori算法

rules<-apriori(dataset2.class,parameter=list(supp=0.7,conf=0.8,target="rules"))
# 指定前导为item1
rules<-apriori(dataset2.class,parameter=list(supp=supp,conf=conf,target="rules"),appearance= list(rhs="item1",default="lhs"))

6.将结果保存

# 写入
write.table(inspect(rules), file = paste("app/save/aprio/",filename,".txt",sep =""), col.names = F, row.names = F, quote=F)

封装AprioriHelper.R类

# 引入Matrix和arules库
library(Matrix)
library(arules)

# 引入脚本文件
source('Helper/mysql_helper.R', encoding = 'UTF-8')

# 构建aprio函数
aprio <- function(sql,supp,conf,filename){
  
  # 读入数据
  dataset <- mysql_find(sql)[,3:17] 
  
  # 修改列名
  names(dataset) <- c("item1", "item2", "item3", "item4", "item5", "item6", "item7", "item8", "item9", "item10", "item11", "item12", "item13", "item14", "item15")
  
  # 将数据框转为矩阵
  dataset2 <- as.matrix(dataset)
  
  # 转换为交易流数据transactions
  dataset2.class<-as(dataset2,"transactions")
  
  # 调用apriori算法
  if(filename=="all"){
    rules<-apriori(dataset2.class,parameter=list(supp=supp,conf=conf,target="rules"))    
  }else{
    rules<-apriori(dataset2.class,parameter=list(supp=supp,conf=conf,target="rules"),appearance= list(rhs="item1",default="lhs"))
  }
  
  # 写入
  write.table(inspect(rules), file = paste("app/save/aprio/",filename,".txt",sep =""), col.names = F, row.names = F, quote=F)
  
}