代码之家 › 专栏 › 技术社区 › slhck

将参数列表传递给具有准旋转的函数

tidyeval dplyr r

slhck · 技术社区 · 6 年前

我试图在R中编写一个函数,根据分组变量总结数据帧。分组变量以列表形式给出并传递给 group_by_at ,我想参数化它们。

library(tidyverse)

d = tribble(
  ~foo, ~bar, ~baz,
  1, 2, 3,
  1, 3, 5
  4, 5, 6,
  4, 5, 1
)

sum_fun <- function(df, group_vars, sum_var) {
  sum_var = enquo(sum_var)
  return(
    df %>% 
      group_by_at(.vars = group_vars) %>% 
      summarize(sum(!! sum_var))
  )
}

d %>% sum_fun(group_vars = c("foo", "bar"), baz)

但是,我想这样调用函数:

d %>% sum_fun(group_vars = c(foo, bar), baz)

我试过使用 enquo 就像summary变量一样,然后替换 group_vars 具有 !! group_vars

Error in !group_vars : invalid argument type

使用 group_by(!!!group_vars) 产量:

Column `c(foo, bar)` must be length 2 (the number of rows) or one, not 4

重写函数的正确方法是什么?

2 回复 | 直到 6 年前

Tung 6 年前

我只想用 vars 做引用。下面是一个使用 mtcars

library(tidyverse)

sum_fun <- function(.data, .summary_var, .group_vars) {
  summary_var <- enquo(.summary_var)

  .data %>%
    group_by_at(.group_vars) %>%
    summarise(mean = mean(!!summary_var))
}

sum_fun(mtcars, disp, .group_vars = vars(cyl, am))
#> # A tibble: 6 x 3
#> # Groups:   cyl [?]
#>     cyl    am  mean
#>   <dbl> <dbl> <dbl>
#> 1     4     0 136. 
#> 2     4     1  93.6
#> 3     6     0 205. 
#> 4     6     1 155  
#> 5     8     0 358. 
#> 6     8     1 326

您也可以替换 .group_vars 具有 ... (点-点)

sum_fun2 <- function(.data, .summary_var, ...) {
  summary_var <- enquo(.summary_var)

  .data %>%
    group_by_at(...) %>%  # Forward `...`
    summarise(mean = mean(!!summary_var))
}

sum_fun2(mtcars, disp, vars(cyl, am))
#> # A tibble: 6 x 3
#> # Groups:   cyl [?]
#>     cyl    am  mean
#>   <dbl> <dbl> <dbl>
#> 1     4     0 136. 
#> 2     4     1  93.6
#> 3     6     0 205. 
#> 4     6     1 155  
#> 5     8     0 358. 
#> 6     8     1 326

enquos 对于

sum_fun3 <- function(.data, .summary_var, ...) {
  summary_var <- enquo(.summary_var)

  group_var <- enquos(...)
  print(group_var)

  .data %>%
      group_by_at(group_var) %>% 
      summarise(mean = mean(!!summary_var))
}

sum_fun3(mtcars, disp, c(cyl, am))
#> [[1]]
#> <quosure>
#>   expr: ^c(cyl, am)
#>   env:  global
#> 
#> # A tibble: 6 x 3
#> # Groups:   cyl [?]
#>     cyl    am  mean
#>   <dbl> <dbl> <dbl>
#> 1     4     0 136. 
#> 2     4     1  93.6
#> 3     6     0 205. 
#> 4     6     1 155  
#> 5     8     0 358. 
#> 6     8     1 326

.addi_var 到 ... .group_var .

sum_fun4 <- function(.data, .summary_var, .addi_var, .group_vars) {
  summary_var <- enquo(.summary_var)

  .data %>%
    group_by_at(c(.group_vars, .addi_var)) %>%
    summarise(mean = mean(!!summary_var))
}

sum_fun4(mtcars, disp, .addi_var = vars(gear), .group_vars = vars(cyl, am))
#> # A tibble: 10 x 4
#> # Groups:   cyl, am [?]
#>      cyl    am  gear  mean
#>    <dbl> <dbl> <dbl> <dbl>
#>  1     4     0     3 120. 
#>  2     4     0     4 144. 
#>  3     4     1     4  88.9
#>  4     4     1     5 108. 
#>  5     6     0     3 242. 
#>  6     6     0     4 168. 
#>  7     6     1     4 160  
#>  8     6     1     5 145  
#>  9     8     0     3 358. 
#> 10     8     1     5 326

group_by_at()

sum_fun5 <- function(.data, .summary_var, .addi_var, ...) {

  summary_var <- enquo(.summary_var)
  addi_var    <- enquo(.addi_var)
  group_var   <- enquos(...)

  ### convert quosures to strings for `group_by_at`
  all_group <- purrr::map_chr(c(addi_var, group_var), quo_name)

  .data %>%
    group_by_at(all_group) %>% 
    summarise(mean = mean(!!summary_var))
}

sum_fun5(mtcars, disp, gear, cyl, am)
#> # A tibble: 10 x 4
#> # Groups:   gear, cyl [?]
#>     gear   cyl    am  mean
#>    <dbl> <dbl> <dbl> <dbl>
#>  1     3     4     0 120. 
#>  2     3     6     0 242. 
#>  3     3     8     0 358. 
#>  4     4     4     0 144. 
#>  5     4     4     1  88.9
#>  6     4     6     0 168. 
#>  7     4     6     1 160  
#>  8     5     4     1 108. 
#>  9     5     6     1 145  
#> 10     5     8     1 326

^{创建日期:2018-10-09

reprex package

(v0.2.1.9000)}

Martin Schmelzer 6 年前

你可以利用椭圆 ...

sum_fun <- function(df, sum_var, ...) {
  sum_var <- substitute(sum_var)
  grps    <- substitute(list(...))[-1L]
  return(
    df %>% 
      group_by_at(.vars = as.character(grps)) %>% 
      summarize(sum(!! sum_var))
  )
}

d %>% sum_fun(baz, foo, bar)

我们获取附加参数并从中创建一个列表。然后采用非标准评价法( substitute )获取变量名并阻止R对其求值。自 group_by_at 需要character或numeric类型的对象,我们只需将名称向量转换为字符向量,函数将按预期进行求值。

> d %>% sum_fun(baz, foo, bar)
# A tibble: 3 x 3
# Groups:   foo [?]
    foo   bar `sum(baz)`
  <dbl> <dbl>      <dbl>
1     1     2          3
2     1     3          5
3     4     5          7

如果不想将分组变量作为任意数量的附加参数提供,则当然可以使用命名参数:

sum_fun <- function(df, sum_var, grps) {
  sum_var <- enquo(sum_var)
  grps    <- as.list(substitute(grps))[-1L]
  return(
    df %>% 
      group_by_at(.vars = as.character(grps)) %>% 
      summarize(sum(!! sum_var))
  )
}

sum_fun(mtcars, sum_var = hp, grps = c(cyl, gear))

list(cyl, gear) 在它的组成部分。也许有办法 rlang 但到目前为止,我还没有深入研究这个包裹。