这种方法使用tidyr中的separate_longer_delim来分割文本类别，然后借用recipes中一个方便的伪编码函数进行one-hot编码。

library(recipes)
#> Loading required package: dplyr
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
#> 
#> Attaching package: 'recipes'
#> The following object is masked from 'package:stats':
#> 
#>     step
library(dplyr)
library(tidyr)

df <- data.frame(id=c(1,2,3,4,5),
                 number=c("a,b,d","e,a","c","","k,t"))

df %>%
  separate_longer_delim(number, delim = ',') %>%
  recipe(~.) %>%
  step_dummy(number, one_hot = TRUE) %>%
  prep() %>%
  bake(new_data = NULL) %>%
  group_by(id) %>%
  summarize(across(everything(), max))
#> # A tibble: 5 × 9
#>      id number_X number_a number_b number_c number_d number_e number_k number_t
#>   <dbl>    <dbl>    <dbl>    <dbl>    <dbl>    <dbl>    <dbl>    <dbl>    <dbl>
#> 1     1        0        1        1        0        1        0        0        0
#> 2     2        0        1        0        0        0        1        0        0
#> 3     3        0        0        0        1        0        0        0        0
#> 4     4        1        0        0        0        0        0        0        0
#> 5     5        0        0        0        0        0        0        1        1

创建于2023年3月16日，使用reprex v2.0.2

首先使用基R的strsplit提取唯一类别，然后获得每个类别的存在，其中lapply在每行上为grepls，as.data.frame为：

df <- data.frame(id=c(1,2,3,4,5),
                     number=c("a,b,d","e,a","c","","k,t"))
    
    
    categories <- unique(unlist(strsplit(df$number, ",")))
    
    data <- as.data.frame(lapply(categories,
           function(x) as.numeric(grepl(x, df$number))))
    names(data) <- categories

#> data
#  a b d e c k t
#1 1 1 1 0 0 0 0
#2 1 0 0 1 0 0 0
#3 0 0 0 0 1 0 0
#4 0 0 0 0 0 0 0
#5 0 0 0 0 0 1 1