Question

我正在尝试沿着市场篮子分析的方向，但有一定的转折。假设我有兴趣对不同预定义细分市场的客户进行市场购物篮分析，并获得市场购物篮中每个商品的相关规则。这是工作代码：

   l <- NULL
   rf <- NULL
   rf_temp <- NULL
   options(scipen=999)
   options(digits = 10)
   for (i in ori_distinct_char) #different customer segments
   {
       subset <-ori[which(ori$V3==paste(i, sep = "")),] 
       # subseting different segments
       subset_data <- as(split(as.vector(subset[,2]),as.vector(subset[,1])), "transactions")
       food<- unique(subset$V2) 
      for (j in route[1:length(food)])
      {
       rules_food <- apriori(subset_data, parameter = list(supp = 0.0000001,conf = 0.0000001, minlen = 2, target = "rules"), 
       appearance = list(lhs = paste(j, sep = "") ,default='rhs')) 
       # made minimum support and confidence as low as possible to allow more rules to be defined (due to lack of data)
       rules_food <- sort(rules_food, by=c("confidence"), decreasing=TRUE)
       rf_temp <- as(head(rules_food,50), "data.frame")
       if (nrow(rf_temp)!=0)
       {rf <- rbind(rf,cbind(rf_temp,paste(i, sep = "")))}
      } 
    }

我试图找到一种方法来运行这个脚本，以便每个排列可以以并行方式运行：即：关联规则在不同的客户群和食物上以并行方式定义，以涵盖所有可能的排列。此外，这里的工作脚本太慢，想象5段和2000种食物选择。

使用＆＃39; foreach＆＃39;进行更新。循环到目前为止：

   cl<- makeCluster(3)
   registerDoParallel(cl)

   l <- NULL
   rf <- NULL
   rf_temp <- NULL
   options(scipen=999)
   options(digits = 10)
   foreach (i = 1:length(ori_distinct_char)) %dopar% #different customer segments
   {
       subset <-ori[which(ori$V3==paste(i, sep = "")),] 
       # subseting different segments
       subset_data <- as(split(as.vector(subset[,2]),as.vector(subset[,1])), "transactions")
       food<- unique(subset$V2) 
       foreach (o = 1:length(food),.combine=rbind,.packages = 'arules') %dopar%
      {
       rules_food <- apriori(subset_data, parameter = list(supp = 0.0000001,conf = 0.0000001, minlen = 2, target = "rules"), 
       appearance = list(lhs = paste(j, sep = "") ,default='rhs')) 
       # made minimum support and confidence as low as possible to allow more rules to be defined (due to lack of data)
       rules_food <- sort(rules_food, by=c("confidence"), decreasing=TRUE)
       rf_temp <- as(head(rules_food,50), "data.frame")
       if (nrow(rf_temp)!=0)
       {rf <- rbind(rf,cbind(rf_temp,paste(i, sep = "")))}
      } 
    }

R代码中市场篮子分析的优化

0 个答案: