使用 dplyr 将列名作为函数输入包含在内

Question

我经常需要将长而整齐的数据帧转换为宽格式。为此，我使用以下标准程序：

# Example data frame
df <- data.frame("ID" = rep(1:5, each = 4), "score" = runif(20, 0, 100), "location" = rep(c("a", "b", "c", "d"), 5))

# Transform into wide format
df_wide <- df %>%
  group_by_at(vars(-score)) %>%  # group by everything other than the value column. 
  mutate(row_id=1:n()) %>% ungroup() %>%  # build group index
  spread(key=location, value=score) %>%    # spread
  dplyr::select(-row_id)

我不想一遍又一遍地输入这个小脚本，而是想定义一个函数来自动完成。我发现了许多关于如何将列名包含为函数输入的有用帖子，但不知何故它不起作用或我收到错误消息。我做错了什么？

根据these 和this 的建议，以下是我的一些尝试（它们都不起作用）：

wide_fun <- function(dat, key_name, value_name) {
  group_by_at(vars(- !! sym(value_name))) %>%  # group by everything other than the value column. 
    mutate(row_id=1:n()) %>% ungroup() %>%  # build group index
    spread(key=!! sym(key_name), value=!! sym(value_name)) %>%    # spread
    dplyr::select(-row_id)
}

wide_fun2 <- function(dat,  key_name, value_name) {
  key_col <- enquo(key_name)
  value_col <- enquo(value_name)
  group_by_at(vars(- !!value_col)) %>%  # group by everything other than the value column. 
    mutate(row_id=1:n()) %>% ungroup() %>%  # build group index
    spread(key= !!key_col, value= !!value_col) %>%    # spread
    dplyr::select(-row_id)
}

wide_fun3 <- function(dat, key_name, value_name) {
  group_by_at(vars(- value_name)) %>%  # group by everything other than the value column. 
    mutate(row_id=1:n()) %>% ungroup() %>%  # build group index
    spread(key=key_name, value=value_name) %>%    # spread
    dplyr::select(-row_id)
}

wide_fun3(df, quote(location), quote(score))

感谢您的帮助！

Answer 1

我已将您的代码稍微更新为dplyr 1.0.0 和tidyr。然后您可以使用new dplyr programming feature {{}} 来指定作为函数参数的变量。

# Example data frame
df <- data.frame("ID" = rep(1:5, each = 4), "score" = runif(20, 0, 100), "location" = rep(c("a", "b", "c", "d"), 5))
library(dplyr)
wide_fun <- function(.data, key_name, value_name) {
  .data %>% 
  group_by(across(-{{value_name}})) %>%  # group by everything other than the value column. 
    mutate(row_id = 1:n()) %>% ungroup() %>%  # build group index
    tidyr::pivot_wider(
      names_from = {{key_name}},
      values_from = {{value_name}}) %>%    # spread
    select(-row_id)
}

wide_fun(df, location, score)
#> # A tibble: 5 x 5
#>      ID     a     b     c     d
#>   <int> <dbl> <dbl> <dbl> <dbl>
#> 1     1  90.8  38.9  28.7  39.0
#> 2     2  94.5  24.9  84.6  54.6
#> 3     3  61.1  97.2  12.2  57.7
#> 4     4  52.7  85.6  41.4 100. 
#> 5     5  17.8  86.1  92.3  33.7

^{由reprex package (v0.3.0) 于 2020 年 9 月 11 日创建}

编辑

这个函数也应该适用于旧版本的dplyr：

library(dplyr)
wide_fun_2 <- function(.data, key_name, value_name) {
  .data %>% 
    group_by_at(vars(-!!ensym(value_name))) %>%  # group by everything other than the value column. 
    mutate(row_id = 1:n()) %>% ungroup() %>%  # build group index
    tidyr::pivot_wider(
      names_from = !!ensym(key_name),
      values_from = !!ensym(value_name)) %>%    # spread
    select(-row_id)
}

df %>% 
  wide_fun_2(location, score)
 A tibble: 5 x 5
     ID      a     b     c     d
  <int>  <dbl> <dbl> <dbl> <dbl>
1     1 72.2    81.4  52.5  48.8
2     2 36.1    27.5  82.2  73.0
3     3 83.9    68.2  80.9  15.7
4     4  0.451  70.0  18.5  43.2
5     5 82.6    68.2  22.8  63.0

如果你只提供指定列的参数，你只需要处理符号而不是quosures，因此你需要使用ensym。