如何在只有 ID 但没有其他内容的列表中识别 df

Question

我有如下列表：

lst<- list(`101-01-101` = list(Demographics = structure(list(SubjectID = c("SubjectID", 
"101-01-101"), BRTHDTC = c("BRTHDTC", "1953-07-07"), SEX = c("SEX", 
"Female")), row.names = c(NA, -2L), class = c("tbl_df", "tbl", 
"data.frame")), DiseaseStatus = structure(list(SubjectID = c("SubjectID", 
"101-01-101"), DSDT = c("DSDT", "2016-03-14"), DSDT_P = c("DSDT_P", 
NA)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"
)), Visits = structure(list(SubjectID = c("SubjectID", "101-01-101"
), Visit = c("Visit", "Screening: -28 Days to Day 1"), VISND = c("VISND", 
NA)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"
))), `101-02-102` = list(Demographics = structure(list(SubjectID = c("SubjectID", 
"101-02-102"), BRTHDTC = c("BRTHDTC", "1963-07-02"), SEX = c("SEX", 
"Female")), row.names = c(NA, -2L), class = c("tbl_df", "tbl", 
"data.frame")), DiseaseStatus = structure(list(SubjectID = c("SubjectID", 
"101-02-102"), DSDT = c("DSDT", "2017-04-04"), DSDT_P = c("DSDT_P", 
NA)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"
)), Visits = structure(list(SubjectID = c("SubjectID", "101-02-102"
), Visit = c("Visit", NA), VISND = c("VISND", NA)), row.names = c(NA, 
-2L), class = c("tbl_df", "tbl", "data.frame"))), `101-03-103` = list(
    Demographics = structure(list(SubjectID = c("SubjectID", 
    "101-03-103"), BRTHDTC = c("BRTHDTC", "1940-09-11"), SEX = c("SEX", 
    "Male")), row.names = c(NA, -2L), class = c("tbl_df", "tbl", 
    "data.frame")), DiseaseStatus = structure(list(SubjectID = c("SubjectID", 
    "101-03-103"), DSDT = c("DSDT", NA), DSDT_P = c("DSDT_P", 
    NA)), row.names = c(NA, -2L), class = c("tbl_df", "tbl", 
    "data.frame")), Visits = structure(list(SubjectID = c("SubjectID", 
    "101-03-103"), Visit = c("Visit", "Screening: -28 Days to Day 1"
    ), VISND = c("VISND", NA)), row.names = c(NA, -2L), class = c("tbl_df", 
    "tbl", "data.frame"))))

我想将 subjectID 输入更改为 NA 如果列表中的 df 仅具有 SubjectID 中的值，但所有 NA其他变量。我该怎么办？

我正在考虑为每个 df 计算 none NA 个输入，如果值等于 1，则删除所有记录或将 SubjectID 更改为 [=12] =].我想仍然保留列名，但是该怎么做？

在我的示例文件中，101-02-102 应该将 Visits 设为空 df，并且 101-03-103 应该将 DiseaseStatus 设为空 df。

Answer 1

因为是嵌套列表，所以用double lapply，在里面的list，元素上，取NA上逻辑矩阵的colSums，判断是否相等到行数 (nrow)，然后将 SubjectID 分配给 NA，return 数据

lst2 <- lapply(lst1, function(x) {x <- lapply(x, function(y) 
    {if(all(colSums(is.na(y[-1])) == nrow(y))) y$SubjectID <- NA_character_
          y}); x})

-输出

lst2
$`101-01-101`
$`101-01-101`$Demographics
# A tibble: 1 x 3
  SubjectID  BRTHDTC    SEX   
  <chr>      <chr>      <chr> 
1 101-01-101 1953-07-07 Female

$`101-01-101`$DiseaseStatus
# A tibble: 1 x 3
  SubjectID  DSDT       DSDT_P
  <chr>      <chr>      <chr> 
1 101-01-101 2016-03-14 <NA>  

$`101-01-101`$Visits
# A tibble: 1 x 3
  SubjectID  Visit                        VISND
  <chr>      <chr>                        <chr>
1 101-01-101 Screening: -28 Days to Day 1 <NA> 


$`101-02-102`
$`101-02-102`$Demographics
# A tibble: 1 x 3
  SubjectID  BRTHDTC    SEX   
  <chr>      <chr>      <chr> 
1 101-02-102 1963-07-02 Female

$`101-02-102`$DiseaseStatus
# A tibble: 1 x 3
  SubjectID  DSDT       DSDT_P
  <chr>      <chr>      <chr> 
1 101-02-102 2017-04-04 <NA>  

$`101-02-102`$Visits
# A tibble: 1 x 3
  SubjectID Visit VISND
  <chr>     <chr> <chr>
1 <NA>      <NA>  <NA> 


$`101-03-103`
$`101-03-103`$Demographics
# A tibble: 1 x 3
  SubjectID  BRTHDTC    SEX  
  <chr>      <chr>      <chr>
1 101-03-103 1940-09-11 Male 

$`101-03-103`$DiseaseStatus
# A tibble: 1 x 3
  SubjectID DSDT  DSDT_P
  <chr>     <chr> <chr> 
1 <NA>      <NA>  <NA>  

$`101-03-103`$Visits
# A tibble: 1 x 3
  SubjectID  Visit                        VISND
  <chr>      <chr>                        <chr>
1 101-03-103 Screening: -28 Days to Day 1 <NA>

更新案例

lapply(lst, function(x) {x <- lapply(x, function(y)     
       {if(all(colSums(is.na(y[-1, -1])) == nrow(y[-1, ]))) 
        y$SubjectID <- NA_character_    
             y[-1,]})
 x})

Answer 2

更新解决方案

我已经根据 OP 的新要求更新了我的解决方案，因此第二行的 SubjectID 将是 NA，前提是所有其他变量也是 NA。

library(purrr)

lst %>%
  map(~ .x %>% 
        map(~ if(all(is.na(.x[2, -1]))) {
          .x %>%
            mutate(SubjectID = if_else(row_number() == 1, SubjectID, NA_character_))
        } else {
          .x
        }))

$`101-01-101`
$`101-01-101`$Demographics
# A tibble: 2 x 3
  SubjectID  BRTHDTC    SEX   
  <chr>      <chr>      <chr> 
1 SubjectID  BRTHDTC    SEX   
2 101-01-101 1953-07-07 Female

$`101-01-101`$DiseaseStatus
# A tibble: 2 x 3
  SubjectID  DSDT       DSDT_P
  <chr>      <chr>      <chr> 
1 SubjectID  DSDT       DSDT_P
2 101-01-101 2016-03-14 NA    

$`101-01-101`$Visits
# A tibble: 2 x 3
  SubjectID  Visit                        VISND
  <chr>      <chr>                        <chr>
1 SubjectID  Visit                        VISND
2 101-01-101 Screening: -28 Days to Day 1 NA   


$`101-02-102`
$`101-02-102`$Demographics
# A tibble: 2 x 3
  SubjectID  BRTHDTC    SEX   
  <chr>      <chr>      <chr> 
1 SubjectID  BRTHDTC    SEX   
2 101-02-102 1963-07-02 Female

$`101-02-102`$DiseaseStatus
# A tibble: 2 x 3
  SubjectID  DSDT       DSDT_P
  <chr>      <chr>      <chr> 
1 SubjectID  DSDT       DSDT_P
2 101-02-102 2017-04-04 NA    

$`101-02-102`$Visits
# A tibble: 2 x 3
  SubjectID Visit VISND
  <chr>     <chr> <chr>
1 SubjectID Visit VISND
2 NA        NA    NA   


$`101-03-103`
$`101-03-103`$Demographics
# A tibble: 2 x 3
  SubjectID  BRTHDTC    SEX  
  <chr>      <chr>      <chr>
1 SubjectID  BRTHDTC    SEX  
2 101-03-103 1940-09-11 Male 

$`101-03-103`$DiseaseStatus
# A tibble: 2 x 3
  SubjectID DSDT  DSDT_P
  <chr>     <chr> <chr> 
1 SubjectID DSDT  DSDT_P
2 NA        NA    NA    

$`101-03-103`$Visits
# A tibble: 2 x 3
  SubjectID  Visit                        VISND
  <chr>      <chr>                        <chr>
1 SubjectID  Visit                        VISND
2 101-03-103 Screening: -28 Days to Day 1 NA

如何在只有 ID 但没有其他内容的列表中识别 df

How to identify df in a list that only have ID but nothing else in it

r

lapply

purrr