使用dplyr对多个变量的所有可能组合进行分组

Question

鉴于以下情况

library(dplyr)
myData <- tbl_df(data.frame( var1 = rnorm(100), 
                             var2 = letters[1:3] %>%
                                    sample(100, replace = TRUE) %>%
                                    factor(), 
                             var3 = LETTERS[1:3] %>%
                                    sample(100, replace = TRUE) %>%
                                    factor(), 
                             var4 = month.abb[1:3] %>%
                                    sample(100, replace = TRUE) %>%
                                    factor()))

我想将"myData"分组,最终找到var2,var3和var4的所有可能组合的摘要数据分组.

我可以创建一个列表,其中包含所有可能的变量组合作为字符值

groupNames <- names(myData)[2:4]

myGroups <- Map(combn, 
              list(groupNames), 
              seq_along(groupNames),
              simplify = FALSE) %>%
              unlist(recursive = FALSE)

我的计划是使用for()循环为每个变量组合创建单独的数据集

### This Does Not Work
for (i in 1:length(myGroups)){
     assign( myGroups[i]%>%
             unlist() %>%
             paste0(collapse = "")%>%
             paste0("Data"), 
               myData %>% 
               group_by_(lapply(myGroups[[i]], as.symbol)) %>%
               summarise( n = length(var1), 
                             avgVar2 = var2 %>%
                                       mean()))
}

不可否认,我对列表不是很了解,因为dpyr更新改变了分组的工作方式,所以查找这个问题有点挑战性.

如果有更好的方法来做这个比单独的数据集我很想知道.

当我只用一个变量进行分组时,我得到了一个类似于上面的循环.

非常感谢任何和所有的帮助!谢谢!

Answer 1

这看起来很精确,并且可能有一种方法可以简化或用它来表达do它,但它有效.用你的myData和myGroups,

results = lapply(myGroups, FUN = function(x) {
    do.call(what = group_by_, args = c(list(myData), x)) %>%
        summarise( n = length(var1), 
                   avgVar1 = mean(var1))
    }
)

> results[[1]]
Source: local data frame [3 x 3]

  var2  n     avgVar1
1    a 31  0.38929738
2    b 31 -0.07451717
3    c 38 -0.22522129

> results[[4]]
Source: local data frame [9 x 4]
Groups: var2

  var2 var3  n    avgVar1
1    a    A 11 -0.1159160
2    a    B 11  0.5663312
3    a    C  9  0.7904056
4    b    A  7  0.0856384
5    b    B 13  0.1309756
6    b    C 11 -0.4192895
7    c    A 15 -0.2783099
8    c    B 10 -0.1110877
9    c    C 13 -0.2517602

> results[[7]]
# I won't paste them here, but it has all 27 rows, grouped by var2, var3 and var4.

我将您的summarise通话更改为平均值,var1因为var2它不是数字.

Answer 2

我根据 @Gregor 的答案和随后的评论创建了一个函数：

library(magrittr)
myData <- tbl_df(data.frame( var1 = rnorm(100), 
                         var2 = letters[1:3] %>%
                                sample(100, replace = TRUE) %>%
                                factor(), 
                         var3 = LETTERS[1:3] %>%
                                sample(100, replace = TRUE) %>%
                                factor(), 
                         var4 = month.abb[1:3] %>%
                                sample(100, replace = TRUE) %>%
                                factor()))

功能combSummarise

combSummarise <- function(data, variables=..., summarise=...){


  # Get all different combinations of selected variables (credit to @Michael)
    myGroups <- lapply(seq_along(variables), function(x) {
    combn(c(variables), x, simplify = FALSE)}) %>%
    unlist(recursive = FALSE)

  # Group by selected variables (credit to @konvas)
    df <- eval(parse(text=paste("lapply(myGroups, function(x){
               dplyr::group_by_(data, .dots=x) %>% 
               dplyr::summarize_( \"", paste(summarise, collapse="\",\""),"\")})"))) %>% 
          do.call(plyr::rbind.fill,.)

    groupNames <- c(myGroups[[length(myGroups)]])
    newNames <- names(df)[!(names(df) %in% groupNames)]

    df <- cbind(df[, groupNames], df[, newNames])
    names(df) <- c(groupNames, newNames)
    df

}

呼叫combSummarise

combSummarise (myData, var=c("var2", "var3", "var4"), 
               summarise=c("length(var1)", "mean(var1)", "max(var1)"))

或者

combSummarise (myData, var=c("var2", "var4"), 
               summarise=c("length(var1)", "mean(var1)", "max(var1)"))

或者

combSummarise (myData, var=c("var2", "var4"), 
           summarise=c("length(var1)"))

ETC