dplyr::mutate() -- 在tibble嵌套列表中，如何忽略NULL嵌套列表？
dplyr::mutate() -- In a tibble nesting lists, how to ignore NULL nested lists?
偶尔，我的更高级别 tibble 中的嵌套列表是 NULL。我想在使用 dplyr::mutate().
时 忽略 这些列表
示例
将值重新编码为小写和下划线
数据
library(tibble)
df <-
tibble(movies = c("The Shawshank Redemption", "The Godfather", "The Godfather: Part II", "The Dark Knight", "12 Angry Men"),
continents = c("Asia", "Australia", "America", "Africa", "Europe"),
michaels = c("Michael Jackson", "Michael Jordan", "Mike Tyson", "Michael Phelps", "Michael Schumacher"))
df <- add_column(df, ignore_me = list(NULL))
df
## # A tibble: 5 x 4
## movies continents michaels ignore_me
## <chr> <chr> <chr> <list>
## 1 The Shawshank Redemption Asia Michael Jackson <NULL>
## 2 The Godfather Australia Michael Jordan <NULL>
## 3 The Godfather: Part II America Mike Tyson <NULL>
## 4 The Dark Knight Africa Michael Phelps <NULL>
## 5 12 Angry Men Europe Michael Schumacher <NULL>
正在尝试重新编码值
library(dplyr) # version 1.0.2
library(snakecase)
df %>%
mutate(across(everything(), snakecase::to_any_case))
Error: Problem with mutate() input ..1.
x argument is not a character vector
i Input ..1 is across(everything(), snakecase::to_any_case).
显然，以下任一方法都可行：
df %>% mutate(across(c(movies, continents, michaels), snakecase::to_any_case))
# or
df %>% mutate(across(-ignore_me, snakecase::to_any_case))
## movies continents michaels ignore_me
## <chr> <chr> <chr> <list>
## 1 the_shawshank_redemption asia michael_jackson <NULL>
## 2 the_godfather australia michael_jordan <NULL>
## 3 the_godfather_part_ii america mike_tyson <NULL>
## 4 the_dark_knight africa michael_phelps <NULL>
## 5 12_angry_men europe michael_schumacher <NULL>
但实际上我无法预料哪个 column/nested 列表会是 NULL 因此我需要我的代码简单地忽略这样的 NULL 但仍适用于非 NULL 列。
编辑
上面的原文df 完全忽略list 就很容易解决问题。但数据通常也可以是：
df_2 <-
tibble(movies = c("The Shawshank Redemption", "The Godfather", "The Godfather: Part II", "The Dark Knight", "12 Angry Men"),
continents = c("Asia", "Australia", "America", "Africa", "Europe"),
michaels = c("Michael Jackson", "Michael Jordan", "Mike Tyson", "Michael Phelps", "Michael Schumacher"))
df_2 <- add_column(df_2, ignore_me = list(NULL))
set.seed(2021) ; df_2 <- mutate(df_2, across(sample(colnames(df_2), 1), as.list))
df_2
## movies continents michaels ignore_me
## <chr> <chr> <list> <list>
## 1 The Shawshank Redemption Asia <chr [1]> <NULL>
## 2 The Godfather Australia <chr [1]> <NULL>
## 3 The Godfather: Part II America <chr [1]> <NULL>
## 4 The Dark Knight Africa <chr [1]> <NULL>
## 5 12 Angry Men Europe <chr [1]> <NULL>
您可以忽略所有列表列:
library(dplyr)
df %>% mutate(across(where(Negate(is.list)), snakecase::to_any_case))
或者如果不是所有 list 列都将是 NULL，您可以通过检查它们的长度来专门找到具有 NULL 值的列并忽略具有长度的列作为 0.
df %>% mutate(across(where(~!all(lengths(.) == 0)), snakecase::to_any_case))
# movies continents michaels ignore_me
# <chr> <chr> <chr> <list>
#1 the_shawshank_redemption asia michael_jackson <NULL>
#2 the_godfather australia michael_jordan <NULL>
#3 the_godfather_part_ii america mike_tyson <NULL>
#4 the_dark_knight africa michael_phelps <NULL>
#5 12_angry_men europe michael_schumacher <NULL>
对于修改后的 df_2 我们可以使用：
df_2$michaels[[3]] <- c(df_2$michaels[[3]], df_2$michaels[[4]])
df_2 %>%
mutate(across(where(~all(lengths(.) > 0)),
~relist(to_any_case(unlist(.)), .)))
# movies continents michaels ignore_me
# <chr> <chr> <list> <list>
#1 the_shawshank_redemption asia <chr [1]> <NULL>
#2 the_godfather australia <chr [1]> <NULL>
#3 the_godfather_part_ii america <chr [2]> <NULL>
#4 the_dark_knight africa <chr [1]> <NULL>
#5 12_angry_men europe <chr [1]> <NULL>
添加 purrr 的一个选项可以是：
df %>%
mutate(across(where(~ !all(map_lgl(., is.null))), to_any_case))
movies continents michaels ignore_me
<chr> <chr> <chr> <list>
1 the_shawshank_redemption asia michael_jackson <NULL>
2 the_godfather australia michael_jordan <NULL>
3 the_godfather_part_ii america mike_tyson <NULL>
4 the_dark_knight africa michael_phelps <NULL>
5 12_angry_men europe michael_schumacher <NULL>
对于第二个数据集：
df_2 %>%
mutate(across(where(~ !all(map_lgl(., is.null))), ~ to_any_case(unlist(.))))
movies continents michaels ignore_me
<chr> <chr> <chr> <list>
1 the_shawshank_redemption asia michael_jackson <NULL>
2 the_godfather australia michael_jordan <NULL>
3 the_godfather_part_ii america mike_tyson <NULL>
4 the_dark_knight africa michael_phelps <NULL>
5 12_angry_men europe michael_schumacher <NULL>
偶尔，我的更高级别 tibble 中的嵌套列表是 NULL。我想在使用 dplyr::mutate().
示例
将值重新编码为小写和下划线
数据
library(tibble)
df <-
tibble(movies = c("The Shawshank Redemption", "The Godfather", "The Godfather: Part II", "The Dark Knight", "12 Angry Men"),
continents = c("Asia", "Australia", "America", "Africa", "Europe"),
michaels = c("Michael Jackson", "Michael Jordan", "Mike Tyson", "Michael Phelps", "Michael Schumacher"))
df <- add_column(df, ignore_me = list(NULL))
df
## # A tibble: 5 x 4
## movies continents michaels ignore_me
## <chr> <chr> <chr> <list>
## 1 The Shawshank Redemption Asia Michael Jackson <NULL>
## 2 The Godfather Australia Michael Jordan <NULL>
## 3 The Godfather: Part II America Mike Tyson <NULL>
## 4 The Dark Knight Africa Michael Phelps <NULL>
## 5 12 Angry Men Europe Michael Schumacher <NULL>
正在尝试重新编码值
library(dplyr) # version 1.0.2
library(snakecase)
df %>%
mutate(across(everything(), snakecase::to_any_case))
Error: Problem with
mutate()input..1.
x argument is not a character vector
i Input..1isacross(everything(), snakecase::to_any_case).
显然，以下任一方法都可行：
df %>% mutate(across(c(movies, continents, michaels), snakecase::to_any_case))
# or
df %>% mutate(across(-ignore_me, snakecase::to_any_case))
## movies continents michaels ignore_me
## <chr> <chr> <chr> <list>
## 1 the_shawshank_redemption asia michael_jackson <NULL>
## 2 the_godfather australia michael_jordan <NULL>
## 3 the_godfather_part_ii america mike_tyson <NULL>
## 4 the_dark_knight africa michael_phelps <NULL>
## 5 12_angry_men europe michael_schumacher <NULL>
但实际上我无法预料哪个 column/nested 列表会是 NULL 因此我需要我的代码简单地忽略这样的 NULL 但仍适用于非 NULL 列。
编辑
上面的原文df 完全忽略list 就很容易解决问题。但数据通常也可以是：
df_2 <-
tibble(movies = c("The Shawshank Redemption", "The Godfather", "The Godfather: Part II", "The Dark Knight", "12 Angry Men"),
continents = c("Asia", "Australia", "America", "Africa", "Europe"),
michaels = c("Michael Jackson", "Michael Jordan", "Mike Tyson", "Michael Phelps", "Michael Schumacher"))
df_2 <- add_column(df_2, ignore_me = list(NULL))
set.seed(2021) ; df_2 <- mutate(df_2, across(sample(colnames(df_2), 1), as.list))
df_2
## movies continents michaels ignore_me
## <chr> <chr> <list> <list>
## 1 The Shawshank Redemption Asia <chr [1]> <NULL>
## 2 The Godfather Australia <chr [1]> <NULL>
## 3 The Godfather: Part II America <chr [1]> <NULL>
## 4 The Dark Knight Africa <chr [1]> <NULL>
## 5 12 Angry Men Europe <chr [1]> <NULL>
您可以忽略所有列表列:
library(dplyr)
df %>% mutate(across(where(Negate(is.list)), snakecase::to_any_case))
或者如果不是所有 list 列都将是 NULL，您可以通过检查它们的长度来专门找到具有 NULL 值的列并忽略具有长度的列作为 0.
df %>% mutate(across(where(~!all(lengths(.) == 0)), snakecase::to_any_case))
# movies continents michaels ignore_me
# <chr> <chr> <chr> <list>
#1 the_shawshank_redemption asia michael_jackson <NULL>
#2 the_godfather australia michael_jordan <NULL>
#3 the_godfather_part_ii america mike_tyson <NULL>
#4 the_dark_knight africa michael_phelps <NULL>
#5 12_angry_men europe michael_schumacher <NULL>
对于修改后的 df_2 我们可以使用：
df_2$michaels[[3]] <- c(df_2$michaels[[3]], df_2$michaels[[4]])
df_2 %>%
mutate(across(where(~all(lengths(.) > 0)),
~relist(to_any_case(unlist(.)), .)))
# movies continents michaels ignore_me
# <chr> <chr> <list> <list>
#1 the_shawshank_redemption asia <chr [1]> <NULL>
#2 the_godfather australia <chr [1]> <NULL>
#3 the_godfather_part_ii america <chr [2]> <NULL>
#4 the_dark_knight africa <chr [1]> <NULL>
#5 12_angry_men europe <chr [1]> <NULL>
添加 purrr 的一个选项可以是：
df %>%
mutate(across(where(~ !all(map_lgl(., is.null))), to_any_case))
movies continents michaels ignore_me
<chr> <chr> <chr> <list>
1 the_shawshank_redemption asia michael_jackson <NULL>
2 the_godfather australia michael_jordan <NULL>
3 the_godfather_part_ii america mike_tyson <NULL>
4 the_dark_knight africa michael_phelps <NULL>
5 12_angry_men europe michael_schumacher <NULL>
对于第二个数据集：
df_2 %>%
mutate(across(where(~ !all(map_lgl(., is.null))), ~ to_any_case(unlist(.))))
movies continents michaels ignore_me
<chr> <chr> <chr> <list>
1 the_shawshank_redemption asia michael_jackson <NULL>
2 the_godfather australia michael_jordan <NULL>
3 the_godfather_part_ii america mike_tyson <NULL>
4 the_dark_knight africa michael_phelps <NULL>
5 12_angry_men europe michael_schumacher <NULL>