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。
我可以使用
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，例如
### 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。
如果有更好的方法来做这个而不是单独的数据集，我很想知道。
当我只使用单个变量进行分组时，我得到了一个与上述类似的循环。
非常感谢任何和所有帮助！谢谢！
答案 0 :(得分：8)
这看起来很有意思，并且可能有一种方法可以使用do来简化或理解它，但它有效。使用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summarise来电更改为平均var1，因为var2不是数字。
答案 1 :(得分：3)
我根据@Gregor的答案和后面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()))
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
}
combSummarise combSummarise (myData, var=c("var2", "var3", "var4"),
summarise=c("length(var1)", "mean(var1)", "max(var1)"))
或
combSummarise (myData, var=c("var2", "var4"),
summarise=c("length(var1)", "mean(var1)", "max(var1)"))
或
combSummarise (myData, var=c("var2", "var4"),
summarise=c("length(var1)"))
等
答案 2 :(得分：2)
受到Gregor和dimitris_ps的回答的启发，我编写了一个dplyr样式函数，该函数对所有组变量组合进行汇总。
summarise_combo <- function(data, ...) {
groupVars <- group_vars(data) %>% map(as.name)
groupCombos <- map( 0:length(groupVars), ~combn(groupVars, ., simplify=FALSE) ) %>%
unlist(recursive = FALSE)
results <- groupCombos %>%
map(function(x) {data %>% group_by(!!! x) %>% summarise(...)} ) %>%
bind_rows()
results %>% select(!!! groupVars, everything())
}
实施例
library(tidyverse)
mtcars %>% group_by(cyl, vs) %>% summarise_combo(cyl_n = n(), mean(mpg))
答案 3 :(得分：0)
使用unite创建新列是最简单的方法
library(tidyverse)
df = tibble(
a = c(1,1,2,2,1,1,2,2),
b = c(3,4,3,4,3,4,3,4),
val = c(1,2,3,4,5,6,7,8)
)
print(df)#output1
df_2 = unite(df, 'combined_header', a, b, sep='_', remove=FALSE) #remove=F doesn't remove existing columns
print(df_2)#output2
df_2 %>% group_by(combined_header) %>%
summarize(avg_val=mean(val)) %>% print()#output3
#avg 1_3 = mean(1,5)=3 avg 1_4 = mean(2, 6) = 4
结果
Output:
output1
a b val
<dbl> <dbl> <dbl>
1 1 3 1
2 1 4 2
3 2 3 3
4 2 4 4
5 1 3 5
6 1 4 6
7 2 3 7
8 2 4 8
output2
combined_header a b val
<chr> <dbl> <dbl> <dbl>
1 1_3 1 3 1
2 1_4 1 4 2
3 2_3 2 3 3
4 2_4 2 4 4
5 1_3 1 3 5
6 1_4 1 4 6
7 2_3 2 3 7
8 2_4 2 4 8
output3
combined_header avg_val
<chr> <dbl>
1 1_3 3
2 1_4 4
3 2_3 5
4 2_4 6