如何在考虑R中的列组合的情况下创建循环

Question

我的数据集如下所示： 我的目标是通过组合当前变量来创建许多属性。例如，我想创建一个名为 HS_POC 的属性，当我们在数据集中拥有相同应用程序且应用程序状态为H或S并且邮政编码完全相同，否则为NO时，此属性显示Yes。这样做的代码是：

  sub <-subset(
    data,
    status  %in% c("H","S"),
    select = c(
     status,
      applications,
      postalcode))

attributes <-data.frame(setDT(sub)[, .(.N, applications) , by =
                          .(
                            status,
                            postalcode
                          )][N > 1])
attributes <- subset(attributes,
         select = c(applications, N))
attributes$N <- "Yes"
colnames(attributes)[colnames(attributes) == "N"] <- "HS_POC"
train <-
  merge(data, attributes, by = "applications", all.x =
          TRUE)
data$HS_POC <- data$HS_POC %>% replace_na("No")

结果是像这样的新列
。

我想做的是创建许多列，例如 HS_POC 和其他变量的组合，例如 HS_生日， HS_产品类型， HS_名字，然后...我为此创建了一个循环，但是它很慢，如何从速度上改善它。

    library(data.table)
data<-read.csv("test.csv")
Indep.var<-subset(data, select=-c(applications,Status))
aa<- colnames(Indep.var)
table<- t(combn(aa,2))
table<-data.frame(table)
table$Status<-c("Status")
table_status<- table
table_status<- as.matrix(table_status)
table$applications<-c("applications")
table_final<- as.matrix(table)
table_final[1,]
##paste(table_final[1,1],table_final[1,2],sep = "_")
##nrow(table_final)
N<-nrow(table_final)
for (i in 1:N)
{
  sub <- subset(data,
                Status  %in% c("H", "S"),
                select = table_final[i, ])

  attributes <- data.frame(setDT(sub)[, .(.N, applications) , by =
                                        eval(table_status[i,])][N > 1])
  attributes <- subset(attributes,
                       select = c(applications, N))

  if (nrow(attributes)== 0){
    colnames(attributes)[colnames(attributes) == "N"] <- paste("HS", table_final[i, 1], table_final[i, 2], sep = "_")
    data <- merge(data, attributes, by = "applications", all.x =
                    TRUE)

  }else{

  attributes$N <- "Yes"
  colnames(attributes)[colnames(attributes) == "N"] <- paste("HS", table_final[i, 1], table_final[i, 2], sep = "_")
  data <- merge(data, attributes, by = "applications", all.x =
            TRUE)
}
}


library(tidyr)
data %>% replace_na("No")
data[is.na(data)] <- "No"

预先感谢您的帮助。