对于每一行，将数字大于 0 的单元格放入列列表中

Tom 发表于 Dev

汤姆

我的数据如下：

dat <- structure(list(rn = c("A", "B", "C", 
"D", "E"), `[0,25)` = c("40 (replaced)", 
"52 (replaced)", "5", "2", "5 (replaced)"), `[25,50)` = c("0 (replaced)", 
"0 (replaced)", "0 (replaced)", "0 (replaced)", "0 (replaced)"), `[25,100)` = c("5", 
"3", "38", "2", "1"), `[50,100)` = c("0 (replaced)", "0 (replaced)", 
"0 (replaced)", "0 (replaced)", "0 (replaced)")), row.names = c(NA, 
-5L), class = c("data.table", "data.frame"))

   rn        [0,25)      [25,50) [25,100)     [50,100)
1:  A 40 (replaced) 0 (replaced)        5 0 (replaced)
2:  B 52 (replaced) 0 (replaced)        3 0 (replaced)
3:  C             5 0 (replaced)       38 0 (replaced)
4:  D             2 0 (replaced)        2 0 (replaced)
5:  E  5 (replaced) 0 (replaced)        1 0 (replaced)

我可以简单地得到如下数字：

    dat <- t(apply(dat, 1, extract_numeric))
    dat <- as.data.frame(dat )
    dat <- dat %>% 
        rowwise() %>% 
        summarise(V1 = V1, freq =list(c_across(-V1))) %>% 
        rowwise() %>% 
        mutate(freq = list(freq[which(freq > 0)]))

dat_out <- structure(list(V1 = c(NA_real_, NA_real_, NA_real_, NA_real_, 
NA_real_), freq = list(c(40, 5), c(52, 3), c(5, 38), c(2, 2), 
    c(5, 1))), class = c("rowwise_df", "tbl_df", "tbl", "data.frame"
), row.names = c(NA, -5L), groups = structure(list(.rows = structure(list(
    1L, 2L, 3L, 4L, 5L), ptype = integer(0), class = c("vctrs_list_of", 
"vctrs_vctr", "list"))), row.names = c(NA, -5L), class = c("tbl_df", 
"tbl", "data.frame")))

但是，如果我也想保留文本，我应该怎么做呢？

期望的输出：

freq
c("40 (replaced)","5")
c("52 (replaced)","3")
c("5","38")
c("2","2")
c("5 (replaced)","1")

阿克伦

在使用 'value' 列中具有 '0' 值的行使用正则表达式匹配，然后按 'rn' 分组后pivot_longer，使用 'long' 格式可能会更容易，filtersummariselist

library(dplyr)
library(tidyr)
library(stringr)
out <- dat %>% 
   pivot_longer(cols = -rn) %>% 
   filter(str_detect(value, '\\b0\\b', negate = TRUE)) %>% 
   group_by(rn) %>% 
   summarise(freq = list(value), .groups = 'drop')

-输出

> out
# A tibble: 5 × 2
  rn    freq     
  <chr> <list>   
1 A     <chr [2]>
2 B     <chr [2]>
3 C     <chr [2]>
4 D     <chr [2]>
5 E     <chr [2]>
> out$freq
[[1]]
[1] "40 (replaced)" "5"            

[[2]]
[1] "52 (replaced)" "3"            

[[3]]
[1] "5"  "38"

[[4]]
[1] "2" "2"

[[5]]
[1] "5 (replaced)" "1"

或者另一种选择是replace使用 0 到的列元素NA，然后unite到单个列，指定and 如果需要，在分隔符上na.rm = TRUE拆分为listwithstrsplit,

dat %>% 
   mutate(across(-rn, ~ replace(.x,
        str_detect(.x, '\\b0\\b'), NA_character_))) %>% 
   unite(freq, -rn, na.rm = TRUE, sep=",") %>% 
   mutate(freq = strsplit(freq, ","))
       rn            freq
   <char>          <list>
1:      A 40 (replaced),5
2:      B 52 (replaced),3
3:      C            5,38
4:      D             2,2
5:      E  5 (replaced),1

本文收集自互联网，转载请注明来源。

如有侵权，请联系 [email protected] 删除。