Question

我有一个R数据帧，其中3列包含值0或1。当值是1且由'＆'分隔时，我需要创建一列作为列名称的串联。以下代码使用空格''作为分隔符，但当我将其更改为'＆'时失败。

代码：

A = c(1,0,1,0,0,1)
B = c(1,1,1,0,1,0)
C = c(0,0,0,1,1,1)
data = data.frame(A, B, C)
data$New = paste(ifelse(data$A == 1, "A", ""),
                 ifelse(data$B == 1, "B", ""),
                 ifelse(data$C == 1, "C", ""), sep = '')
data

输出：

  A B C New
1 1 1 0  AB
2 0 1 0   B
3 1 1 0  AB
4 0 0 1   C
5 0 1 1  BC
6 1 0 1  AC

带有'＆'分隔符的代码和输出：

A = c(1,0,1,0,0,1)
B = c(1,1,1,0,1,0)
C = c(0,0,0,1,1,1)
data = data.frame(A, B, C)
data$New = paste(ifelse(data$A == 1, "A", ""), 
                 ifelse(data$B == 1, "B", ""),
                 ifelse(data$C == 1, "C", ""), sep = '&')
data

  A B C  New
1 1 1 0 A&B&
2 0 1 0  &B&
3 1 1 0 A&B&
4 0 0 1  &&C
5 0 1 1 &B&C
6 1 0 1 A&&C

预期输出：

  A B C New
1 1 1 0 A&B
2 0 1 0   B
3 1 1 0 A&B
4 0 0 1   C
5 0 1 1 B&C
6 1 0 1 A&C

有没有办法在R中做到这一点？
如果列数很多，是否可以在不为每列写显式ifelse条件的情况下做到这一点？

Answer 1

我们可以通过遍历行来names的子集

data$New <- apply(data[1:3], 1, function(x) paste(names(x[x!=0]), collapse="&"))
data$New
#[1] "A&B" "B"   "A&B" "C"   "B&C" "A&C"

也可以按列进行

library(tidyverse)
data[1:3] %>% 
    na_if(0) %>%
   `*`(col(.)) %>% 
   imap(~ rep(.y, length(.x))[.x]) %>%
   reduce(paste, sep= "&") %>% 
   str_remove("(NA&)+|(&NA)+") %>%
   str_remove("&NA")
#[1] "A&B" "B"   "A&B" "C"   "B&C" "A&C"

Answer 2

您可以将apply与paste一起使用。

nms <- names(data)
data$New <- apply(data, 1, function(x){
  paste(nms[as.logical(x)], collapse = "&")
})

data
#  A B C New
#1 1 1 0 A&B
#2 0 1 0   B
#3 1 1 0 A&B
#4 0 0 1   C
#5 0 1 1 B&C
#6 1 0 1 A&C

Answer 3

使用which和arr.ind = TRUE，然后使用aggregate：

cbind(data,
      new = aggregate(col ~ row, data = which(data == 1, arr.ind = TRUE),
                      function(x) paste(names(data)[x], collapse = "&"))[ , "col"])

#   A B C new
# 1 1 1 0 A&B
# 2 0 1 0   B
# 3 1 1 0 A&B
# 4 0 0 1   C
# 5 0 1 1 B&C
# 6 1 0 1 A&C

类似，使用tapply：

ix <- which(data == 1, arr.ind = TRUE)
cbind(data,
      new = tapply(ix[ , "col"], ix[ , "row"],
                   function(x) paste(names(data)[x], collapse = "&")))

根据行值连接列名

3 个答案: