表示基于r中单个列的所有其他列

我有一个超过40000列的大型数据帧，我遇到了类似的问题

我目前正在使用嵌套for循环，如下所示： 尽管R是多功能的，但我相信应该有一种更快的方法来实现这一点

idx <- split(1:nrow(shop), shop$shop_id)

newdata <- data.frame()

for( i in 1:length(idx)){
    newdata[i,1]<-c(names(idx)[i] )
    for (j in 2:ncol(shop)){
        newdata[i,j]<-mean(shop[unlist(idx[i]),j])
    }
}

---

idx使用
plyr
软件包中的
ddply
功能：

> require("plyr")
> ddply(shop, ~shop_id, summarise, Assets=mean(Assets),
        Liabilities=mean(Liabilities), sale=mean(sale), profit=mean(profit))

  shop_id Assets Liabilities      sale   profit
1  Shop A    8.0    5.333333  8.666667 2.333333
2  Shop B    5.0    9.000000 15.000000 6.000000
3  Shop C    5.5   10.000000 14.000000 7.000000

尝试
data.table

library(data.table)
setDT(shop)[, lapply(.SD, mean), shop_id]
#  shop_id Assets Liabilities      sale   profit
#1:  Shop A    8.0    5.333333  8.666667 2.333333
#2:  Shop B    5.0    9.000000 15.000000 6.000000
#3:  Shop C    5.5   10.000000 14.000000 7.000000

或

或

对于40000列，我将使用
data.table
或可能是
dplyr
尝试使用
dplyr
：

library("dplyr")
shop %>% group_by(shop_id) %>% summarise_each(funs(mean))

#   shop_id Assets Liabilities      sale   profit
# 1  Shop A    8.0    5.333333  8.666667 2.333333
# 2  Shop B    5.0    9.000000 15.000000 6.000000
# 3  Shop C    5.5   10.000000 14.000000 7.000000

rowsum
可能会有所帮助，这里：

rowsum(shop[-1], shop[[1]]) / table(shop[[1]])
#       Assets Liabilities      sale   profit
#Shop A    8.0    5.333333  8.666667 2.333333
#Shop B    5.0    9.000000 15.000000 6.000000
#Shop C    5.5   10.000000 14.000000 7.000000

这是一个创新的想法
library(dplyr)
shop %>% 
    group_by(shop_id)%>%
    summarise_each(funs(mean))
# shop_id Assets Liabilities      sale   profit
#1  Shop A    8.0    5.333333  8.666667 2.333333
#2  Shop B    5.0    9.000000 15.000000 6.000000
#3  Shop C    5.5   10.000000 14.000000 7.000000

aggregate(.~shop_id, shop, FUN=mean)
#   shop_id Assets Liabilities      sale   profit
#1  Shop A    8.0    5.333333  8.666667 2.333333
#2  Shop B    5.0    9.000000 15.000000 6.000000
#3  Shop C    5.5   10.000000 14.000000 7.000000

library("dplyr")
shop %>% group_by(shop_id) %>% summarise_each(funs(mean))

#   shop_id Assets Liabilities      sale   profit
# 1  Shop A    8.0    5.333333  8.666667 2.333333
# 2  Shop B    5.0    9.000000 15.000000 6.000000
# 3  Shop C    5.5   10.000000 14.000000 7.000000

rowsum(shop[-1], shop[[1]]) / table(shop[[1]])
#       Assets Liabilities      sale   profit
#Shop A    8.0    5.333333  8.666667 2.333333
#Shop B    5.0    9.000000 15.000000 6.000000
#Shop C    5.5   10.000000 14.000000 7.000000