代码之家 › 专栏 › 技术社区 › a_todd12

如何使用R中foreach循环的Stata等价物与mutate()[复制]

stata dplyr r

a_todd12 · 技术社区 · 6 月前

我的原始数据中有4个不同的变量(都以前缀开头 生的_ ),其次是时间/金钱和学校/社交的组合。在我的真实数据中,我对变量的每个值都有更多的选择,所以最终需要迭代4次,这是一段相当长的代码。

在R中,必须有一种简单的方法来执行Stata中的foreach循环(我更经常使用它进行数据清理)的等效操作,将4次迭代压缩为1次。

在Stata中,循环看起来像:

foreach suffix in hours_school hours_social money_school money_social {
   gen olderch_`suffix' = .
   replace olderch_`suffix' = 90 if raw_`suffix' == "90% or more 10% or less"
   replace olderch_`suffix' = 10 if raw_`suffix' == "10% or less 90% or more"
}

这是我目前的R代码版本,我想用类似的方式进行压缩:

d <- d %>% 
  mutate(olderch_hours_school = case_when (
    raw_hours_school == "90% or more 10% or less" ~ 90,
    raw_hours_school == "10% or less 90% or more" ~ 10
  ))

d <- d %>% 
  mutate(olderch_hours_social = case_when (
    raw_hours_social == "90% or more 10% or less" ~ 90,
    raw_hours_social == "10% or less 90% or more" ~ 10
  ))

d <- d %>% 
  mutate(olderch_money_school = case_when (
    raw_money_school == "90% or more 10% or less" ~ 90,
    raw_money_school == "10% or less 90% or more" ~ 10
  ))

d <- d %>% 
  mutate(olderch_money_social = case_when (
    raw_money_social == "90% or more 10% or less" ~ 90,
    raw_money_social == "10% or less 90% or more" ~ 10
  ))

1 回复 | 直到 6 月前

Seth 6 月前

编辑:根据评论中的要求,答案示例会根据原始内容创建新列。

dplyr::across() ( docs )允许您在数据帧中的多列之间应用函数。你可以调整你的 case_when 通过添加语句 ~ 创建一个lambda函数并使用 . 代表每一列。

您可以提供正在转换的所有列的向量,或使用 selection helper ,例如 everything() 或 starts_with() .

测试数据遵循示例。

library(dplyr)

glimpse(df)
#> Rows: 10
#> Columns: 4
#> $ raw_hours_school <chr> "90% or more 10% or less", "90% or more 10% or less",â¦
#> $ raw_hours_social <chr> "10% or less 90% or more", "10% or less 90% or more",â¦
#> $ raw_money_school <chr> "90% or more 10% or less", "10% or less 90% or more",â¦
#> $ raw_money_social <chr> "90% or more 10% or less", "10% or less 90% or more",â¦

df |>
  mutate(across(
    c(raw_hours_school, raw_hours_social,
      raw_money_school, raw_money_social),
    ~ case_when(. ==  "90% or more 10% or less" ~ 90,
                . == "10% or less 90% or more" ~ 10),
    .names = "new_{.col}")) %>%
  setNames(gsub('_raw', '', names(.)))
#>           raw_hours_school        raw_hours_social        raw_money_school
#> 1  90% or more 10% or less 10% or less 90% or more 90% or more 10% or less
#> 2  90% or more 10% or less 10% or less 90% or more 10% or less 90% or more
#> 3  90% or more 10% or less 10% or less 90% or more 90% or more 10% or less
#> 4  10% or less 90% or more 90% or more 10% or less 90% or more 10% or less
#> 5  90% or more 10% or less 10% or less 90% or more 90% or more 10% or less
#> 6  10% or less 90% or more 90% or more 10% or less 90% or more 10% or less
#> 7  10% or less 90% or more 10% or less 90% or more 10% or less 90% or more
#> 8  10% or less 90% or more 90% or more 10% or less 10% or less 90% or more
#> 9  90% or more 10% or less 90% or more 10% or less 90% or more 10% or less
#> 10 90% or more 10% or less 90% or more 10% or less 10% or less 90% or more
#>           raw_money_social new_hours_school new_hours_social new_money_school
#> 1  90% or more 10% or less               90               10               90
#> 2  10% or less 90% or more               90               10               10
#> 3  90% or more 10% or less               90               10               90
#> 4  10% or less 90% or more               10               90               90
#> 5  10% or less 90% or more               90               10               90
#> 6  90% or more 10% or less               10               90               90
#> 7  90% or more 10% or less               10               10               10
#> 8  90% or more 10% or less               10               90               10
#> 9  90% or more 10% or less               90               90               90
#> 10 10% or less 90% or more               90               90               10
#>    new_money_social
#> 1                90
#> 2                10
#> 3                90
#> 4                10
#> 5                10
#> 6                90
#> 7                90
#> 8                90
#> 9                90
#> 10               10

df |>
  mutate(across(
   starts_with("raw"),
    ~ case_when(. ==  "90% or more 10% or less" ~ 90,
                . == "10% or less 90% or more" ~ 10),
   .names = "new_{.col}")) %>%
  setNames(gsub('_raw', '', names(.)))
#>           raw_hours_school        raw_hours_social        raw_money_school
#> 1  90% or more 10% or less 10% or less 90% or more 90% or more 10% or less
#> 2  90% or more 10% or less 10% or less 90% or more 10% or less 90% or more
#> 3  90% or more 10% or less 10% or less 90% or more 90% or more 10% or less
#> 4  10% or less 90% or more 90% or more 10% or less 90% or more 10% or less
#> 5  90% or more 10% or less 10% or less 90% or more 90% or more 10% or less
#> 6  10% or less 90% or more 90% or more 10% or less 90% or more 10% or less
#> 7  10% or less 90% or more 10% or less 90% or more 10% or less 90% or more
#> 8  10% or less 90% or more 90% or more 10% or less 10% or less 90% or more
#> 9  90% or more 10% or less 90% or more 10% or less 90% or more 10% or less
#> 10 90% or more 10% or less 90% or more 10% or less 10% or less 90% or more
#>           raw_money_social new_hours_school new_hours_social new_money_school
#> 1  90% or more 10% or less               90               10               90
#> 2  10% or less 90% or more               90               10               10
#> 3  90% or more 10% or less               90               10               90
#> 4  10% or less 90% or more               10               90               90
#> 5  10% or less 90% or more               90               10               90
#> 6  90% or more 10% or less               10               90               90
#> 7  90% or more 10% or less               10               10               10
#> 8  90% or more 10% or less               10               90               10
#> 9  90% or more 10% or less               90               90               90
#> 10 10% or less 90% or more               90               90               10
#>    new_money_social
#> 1                90
#> 2                10
#> 3                90
#> 4                10
#> 5                10
#> 6                90
#> 7                90
#> 8                90
#> 9                90
#> 10               10

set.seed(123)

df <- data.frame(
  raw_hours_school = sample(c("90% or more 10% or less",
                          "10% or less 90% or more"),
                        10, replace = TRUE),
  raw_hours_social = sample(c("90% or more 10% or less",
                          "10% or less 90% or more"),
                        10, replace = TRUE),
  raw_money_school = sample(c("90% or more 10% or less",
                          "10% or less 90% or more"),
                        10, replace = TRUE),
  raw_money_social = sample(c("90% or more 10% or less",
                          "10% or less 90% or more"),
                        10, replace = TRUE)
)