使用 rlang 允许参数列表，然后在自定义函数中使用它

Question

我正在编写一个自定义函数，我希望其中一个参数采用变量列表。我已经设法使用 rlang 和对 ... 的一些基本理解来正确阅读函数中的这个列表。但我不知道如何将此列表作为参数分配给另一个函数（如 dplyr::group_by）。我在下面是完全可重现的示例以及我想要的最终结果。

# loading the needed libraries
library(dplyr)
library(rlang)
library(datasets)

# defining the custom function
prac.fn <- function(data, vars = ..., measure) {
  # getting the dataframe ready
  df <-
    dplyr::select(.data = data,
                  !!rlang::enquo(vars),
                  !!rlang::enquo(measure))
  # print to see if all variables are included
  print(head(df))

  # summarize by specified grouping variables
  df %>%
    dplyr::group_by(.data = ., c(!!rlang::enquo(vars))) %>%
    dplyr::summarise(mean = mean(!!rlang::enquo(measure)))

}

# use the function (doesn't work)
prac.fn(data = mtcars,
        vars = c(cyl, am),
        measure = wt)
#>                   cyl am    wt
#> Mazda RX4           6  1 2.620
#> Mazda RX4 Wag       6  1 2.875
#> Datsun 710          4  1 2.320
#> Hornet 4 Drive      6  0 3.215
#> Hornet Sportabout   8  0 3.440
#> Valiant             6  0 3.460
#> Error in mutate_impl(.data, dots): Column `c(c(cyl, am))` must be length 32 (the number of rows) or one, not 64

# output I want
mtcars %>%
  dplyr::group_by(cyl, am) %>%
  dplyr::summarise(mean = mean(wt))
#> # A tibble: 6 x 3
#> # Groups:   cyl [?]
#>     cyl    am  mean
#>   <dbl> <dbl> <dbl>
#> 1  4.00  0     2.94
#> 2  4.00  1.00  2.04
#> 3  6.00  0     3.39
#> 4  6.00  1.00  2.76
#> 5  8.00  0     4.10
#> 6  8.00  1.00  3.37

由 reprex package (v0.2.0) 创建于 2018-02-17。

Answer 1

在group_by中，将'vars'转换为quosure(enquo)后，用quo_squash压平表达式，将其转换为list (as.list) 并删除第一个元素，即。 c，然后用!!!求值

prac.fn <- function(data,  vars, measure) {
    data %>%
        select(!!rlang::enquo(vars),
         !!rlang::enquo(measure)) %>%
        dplyr::group_by(!!! as.list(quo_squash(rlang::enquo(vars)))[-1]) %>%
        dplyr::summarise(mean = mean(!!rlang::enquo(measure)))      

 }

-测试

prac.fn(data = mtcars,
        vars = c(cyl, am),
         measure = wt)
# A tibble: 6 x 3
# Groups: cyl [?]
#    cyl    am  mean
#  <dbl> <dbl> <dbl>
#1  4.00  0     2.94
#2  4.00  1.00  2.04
#3  6.00  0     3.39
#4  6.00  1.00  2.76
#5  8.00  0     4.10
#6  8.00  1.00  3.37

检查更多组数

prac.fn(data = mtcars,
        vars = c(cyl, am, gear),
         measure = wt)
# A tibble: 10 x 4
# Groups: cyl, am [?]
#     cyl    am  gear  mean
#   <dbl> <dbl> <dbl> <dbl>
# 1  4.00  0     3.00  2.46
# 2  4.00  0     4.00  3.17
# 3  4.00  1.00  4.00  2.11
# 4  4.00  1.00  5.00  1.83
# 5  6.00  0     3.00  3.34
# 6  6.00  0     4.00  3.44
# 7  6.00  1.00  4.00  2.75
# 8  6.00  1.00  5.00  2.77
# 9  8.00  0     3.00  4.10
#10  8.00  1.00  5.00  3.37

不清楚 OP 是否总是想对 vars 参数使用 c() 即，如果有单个分组变量，如果传递参数的行为相同，则该函数有效

prac.fn(data = mtcars,
        vars = c(cyl),
         measure = wt)
#<quosure>
#  expr: ^c(cyl)
#  env:  global
# A tibble: 3 x 2
#    cyl  mean
#  <dbl> <dbl>
#1  4.00  2.29
#2  6.00  3.12
#3  8.00  4.00

但是，如果我们必须更改行为，即没有 c() 的 vars = cyl，则需要使用 if/else 语句来解决，即

prac.fnN <- function(data,  vars, measure) {
    vars <- as.list(quo_squash(enquo(vars)))
    vars <- if(length(vars) ==1) vars else vars[-1]
    data %>%
        select(!!! vars,
         !!rlang::enquo(measure)) %>%
        dplyr::group_by(!!! vars) %>%
        dplyr::summarise(mean = mean(!!rlang::enquo(measure))) 


 }

-测试

prac.fnN(data = mtcars,
        vars = cyl,
         measure = wt)
# A tibble: 3 x 2
#    cyl  mean
#  <dbl> <dbl>
#1  4.00  2.29
#2  6.00  3.12
#3  8.00  4.00


prac.fnN(data = mtcars,
       vars = c(cyl),
        measure = wt)
# A tibble: 3 x 2
#    cyl  mean
#  <dbl> <dbl>
#1  4.00  2.29
#2  6.00  3.12
#3  8.00  4.00


prac.fnN(data = mtcars,
        vars = c(cyl, am),
         measure = wt)
# A tibble: 6 x 3
# Groups: cyl [?]
#    cyl    am  mean
#  <dbl> <dbl> <dbl>
#1  4.00  0     2.94
#2  4.00  1.00  2.04
#3  6.00  0     3.39
#4  6.00  1.00  2.76
#5  8.00  0     4.10
#6  8.00  1.00  3.37

除了上述方法之外，自然的选择是将参数作为quos/quo传递，然后我们就不必考虑enquo和其他if/else

prac.fnQ <- function(data,  vars, measure) {
   stopifnot(is_quosures(vars)) 
   stopifnot(is_quosure(measure))

    data %>%
        select(!!! vars, !! measure) %>%
        dplyr::group_by(!!! vars) %>%
        dplyr::summarise(mean = mean(!! measure))   

 }

-测试

prac.fnQ(data = mtcars,
       vars = quos(cyl, am),
        measure = quo(wt))
# A tibble: 6 x 3
# Groups: cyl [?]
#    cyl    am  mean
#  <dbl> <dbl> <dbl>
#1  4.00  0     2.94
#2  4.00  1.00  2.04
#3  6.00  0     3.39
#4  6.00  1.00  2.76
#5  8.00  0     4.10
#6  8.00  1.00  3.37

如果我们还需要检查'measure'个变量（假设我们有多个'measure'个变量）是否是numeric

prac.fnQn <- function(data,  vars, measure) {
   stopifnot(is_quosures(vars)) 
   stopifnot(is_quosures(measure))

      data %>%
        select(!!! vars, !!! measure) %>%
        dplyr::group_by(!!! vars) %>%
        summarise_if(is.numeric, mean)       


 }

prac.fnQn(data = mtcars,
       vars = quos(cyl, am),
        measure = quos(wt))
# A tibble: 6 x 3
# Groups: cyl [?]
#    cyl    am    wt
#  <dbl> <dbl> <dbl>
#1  4.00  0     2.94
#2  4.00  1.00  2.04
#3  6.00  0     3.39
#4  6.00  1.00  2.76
#5  8.00  0     4.10
#6  8.00  1.00  3.37

使用 rlang 允许参数列表，然后在自定义函数中使用它

using rlang to allow a list of arguments and then use it in custom function

r

dplyr

tidyverse

rlang