5年后添加必要的数据。表解决方案

library(data.table) ## v 1.9.6+ 
setDT(before)[, paste0("type", 1:2) := tstrsplit(type, "_and_")]
before
#    attr          type type1 type2
# 1:    1   foo_and_bar   foo   bar
# 2:   30 foo_and_bar_2   foo bar_2
# 3:    4   foo_and_bar   foo   bar
# 4:    6 foo_and_bar_2   foo bar_2

我们还可以通过添加类型来确保结果列具有正确的类型并提高性能。转换和固定参数(因为"_and_"不是一个真正的正则表达式)

setDT(before)[, paste0("type", 1:2) := tstrsplit(type, "_and_", type.convert = TRUE, fixed = TRUE)]

要添加选项，你也可以使用我的splitstackshape::cSplit函数，像这样:

library(splitstackshape)
cSplit(before, "type", "_and_")
#    attr type_1 type_2
# 1:    1    foo    bar
# 2:   30    foo  bar_2
# 3:    4    foo    bar
# 4:    6    foo  bar_2

注意，带“[”的spapply可以用来提取这些列表中的第一项或第二项，如下所示:

before$type_1 <- sapply(strsplit(as.character(before$type),'_and_'), "[", 1)
before$type_2 <- sapply(strsplit(as.character(before$type),'_and_'), "[", 2)
before$type <- NULL

这是一个gsub方法:

before$type_1 <- gsub("_and_.+$", "", before$type)
before$type_2 <- gsub("^.+_and_", "", before$type)
before$type <- NULL

令人惊讶的是，另一个tidyverse解决方案仍然缺失——您也可以使用带有正则表达式的tidyr::extract。

library(tidyr)
before <- data.frame(attr = c(1, 30, 4, 6), type = c("foo_and_bar", "foo_and_bar_2"))

## regex - getting all characters except an underscore till the first underscore, 
## inspired by Akrun https://stackoverflow.com/a/49752920/7941188 

extract(before, col = type, into = paste0("type", 1:2), regex = "(^[^_]*)_(.*)")
#>   attr type1     type2
#> 1    1   foo   and_bar
#> 2   30   foo and_bar_2
#> 3    4   foo   and_bar
#> 4    6   foo and_bar_2

还有另一种方法:使用rbind on out:

before <- data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2'))  
out <- strsplit(as.character(before$type),'_and_') 
do.call(rbind, out)

     [,1]  [,2]   
[1,] "foo" "bar"  
[2,] "foo" "bar_2"
[3,] "foo" "bar"  
[4,] "foo" "bar_2"

并结合:

data.frame(before$attr, do.call(rbind, out))

这个主题几乎耗尽了，但我想提供一个稍微更一般的版本，你不知道输出列的数量，一个先验的解决方案。举个例子

before = data.frame(attr = c(1,30,4,6), type=c('foo_and_bar','foo_and_bar_2', 'foo_and_bar_2_and_bar_3', 'foo_and_bar'))
  attr                    type
1    1             foo_and_bar
2   30           foo_and_bar_2
3    4 foo_and_bar_2_and_bar_3
4    6             foo_and_bar

我们不能使用dplyr separate()，因为在分割之前我们不知道结果列的数量，所以我随后创建了一个使用stringr分割列的函数，并给出了所生成列的模式和名称前缀。我希望使用的编码模式是正确的。

split_into_multiple <- function(column, pattern = ", ", into_prefix){
  cols <- str_split_fixed(column, pattern, n = Inf)
  # Sub out the ""'s returned by filling the matrix to the right, with NAs which are useful
  cols[which(cols == "")] <- NA
  cols <- as.tibble(cols)
  # name the 'cols' tibble as 'into_prefix_1', 'into_prefix_2', ..., 'into_prefix_m' 
  # where m = # columns of 'cols'
  m <- dim(cols)[2]

  names(cols) <- paste(into_prefix, 1:m, sep = "_")
  return(cols)
}

然后我们可以在dplyr管道中使用split_into_multiple，如下所示:

after <- before %>% 
  bind_cols(split_into_multiple(.$type, "_and_", "type")) %>% 
  # selecting those that start with 'type_' will remove the original 'type' column
  select(attr, starts_with("type_"))

>after
  attr type_1 type_2 type_3
1    1    foo    bar   <NA>
2   30    foo  bar_2   <NA>
3    4    foo  bar_2  bar_3
4    6    foo    bar   <NA>

然后我们可以用gather来整理…

after %>% 
  gather(key, val, -attr, na.rm = T)

   attr    key   val
1     1 type_1   foo
2    30 type_1   foo
3     4 type_1   foo
4     6 type_1   foo
5     1 type_2   bar
6    30 type_2 bar_2
7     4 type_2 bar_2
8     6 type_2   bar
11    4 type_3 bar_3