R dplyr cross：动态指定函数 t.test 和 varTest 的参数

Question

我正在跨语句编写一些 dplyr。想要使用函数 t.test 和 varTest 创建一些 p 值。用于计算的 x= 列在 df_vars 中，mu= 和 sigma.squared= 参数值在 df_mu_sigma 中。

我需要的数据的硬编码版本在 df_sumry 中。如果在运行代码时变量名总是相同的，那么这样的就足够了。然而，事实并非如此。

我需要的非硬编码版本的开头是在 df_sumry2 中。但这并不能产生正确的结果，因为 mu= 和 sigma.squared= 的值不是动态指定的。 df_sumry2 中只有前两个 p 值是正确的。之后它们总是错误的，因为代码总是使用 mpg 变量的值。

我怎样才能始终如一地为 mu 和 sigma.squared 插入正确的值？

library(dplyr)
library(magrittr)
library(EnvStats)

df_vars <- mtcars %>%
  select(mpg, cyl, disp, hp)

set.seed(9302)

df_mu_sigma <- mtcars %>%
  select(mpg, cyl, disp, hp) %>%
  slice_sample(n = 12) %>%
  summarize(
    across(
      everything(),
      list(mean = mean,
           std = sd
      ))
  )

df_sumry <- df_vars %>%
  summarize(
    mpg_mean = mean(mpg),
    mpg_mean_prob = t.test(mpg, mu = df_mu_sigma$mpg_mean)$p.value,
    mpg_std = sd(mpg),
    mpg_std_prob = varTest(mpg, sigma.squared = df_mu_sigma$mpg_std^2)$p.value,
 
    cyl_mean = mean(cyl),
    cyl_mean_prob = t.test(cyl, mu = df_mu_sigma$cyl_mean)$p.value,
    cyl_std = sd(cyl),
    cyl_std_prob = varTest(cyl, sigma.squared = df_mu_sigma$cyl_std^2)$p.value,

    disp_mean = mean(disp),
    disp_mean_prob = t.test(disp, mu = df_mu_sigma$disp_mean)$p.value,
    disp_std = sd(disp),
    disp_std_prob = varTest(disp, sigma.squared = df_mu_sigma$disp_std^2)$p.value,
 
    hp_mean = mean(hp),
    hp_mean_prob = t.test(hp, mu = df_mu_sigma$hp_mean)$p.value,
    hp_std = sd(hp),
    hp_std_prob = varTest(hp, sigma.squared = df_mu_sigma$hp_std^2)$p.value
   )

vars_num <- names(df_vars)

df_sumry2 <- df_vars %>%
  summarize(
    across(
      all_of(vars_num),
      list(mean = mean,
           mean_prob = function(x) t.test(x, mu = df_mu_sigma$mpg_mean)$p.value,
           std = sd,
           std_prob = function(x) varTest(x, sigma.squared = df_mu_sigma$mpg_std^2)$p.value)
    )
  )

Answer 1

我似乎想出了解决我自己问题的方法。我很乐意看到替代解决方案，因为它们可能比我的更好。

library(dplyr)
library(magrittr)
library(EnvStats)

df_vars <- mtcars %>%
    select(mpg, cyl, disp, hp)

df_mu_sigma <- mtcars %>%
    select(mpg, cyl, disp, hp) %>%
    slice_sample(n = 12) %>%
    summarize(
        across(
            everything(),
            list(mean = mean,
                    std = sd
            ))
    )

df_sumry <- df_vars %>%
    summarize(
        mpg_mean = mean(mpg),
        mpg_mean_prob = t.test(mpg, mu = df_mu_sigma$mpg_mean)$p.value,
        mpg_std = sd(mpg),
        mpg_std_prob = varTest(mpg, sigma.squared = df_mu_sigma$mpg_std^2)$p.value,
       
        cyl_mean = mean(cyl),
        cyl_mean_prob = t.test(cyl, mu = df_mu_sigma$cyl_mean)$p.value,
        cyl_std = sd(cyl),
        cyl_std_prob = varTest(cyl, sigma.squared = df_mu_sigma$cyl_std^2)$p.value,
       
        disp_mean = mean(disp),
        disp_mean_prob = t.test(disp, mu = df_mu_sigma$disp_mean)$p.value,
        disp_std = sd(disp),
        disp_std_prob = varTest(disp, sigma.squared = df_mu_sigma$disp_std^2)$p.value,
       
        hp_mean = mean(hp),
        hp_mean_prob = t.test(hp, mu = df_mu_sigma$hp_mean)$p.value,
        hp_std = sd(hp),
        hp_std_prob = varTest(hp, sigma.squared = df_mu_sigma$hp_std^2)$p.value
    )

vars_num <- names(df_vars)

library(glue)

df_sumry2 <- df_vars %>%
    summarize(
        across(
            all_of(vars_num),
            list(mean = mean,
                    mean_prob = function(x) {
                        mu_name <- glue("{ensym(x)}_mean")
                        t.test(x, mu = df_mu_sigma[[mu_name]])$p.value
                    },
                    std = sd,
                    std_prob = function(x) {
                        sigma_name <- glue("{ensym(x)}_std")
                        varTest(x, sigma.squared = df_mu_sigma[[sigma_name]]^2)$p.value
                    }
            )
        )
    )

all.equal(df_sumry, df_sumry2)

Answer 2

这并不比您的解决方案好多少，但我会使用 cur_column() 而不是 ensym() 来避免 quosures 处理。

此外，将查询放在单独的函数中会使事情变得更整洁。

最后，为了清楚起见，我将使用 lambda 函数而不是匿名函数。

get_mu = function(suffix){
  df_mu_sigma[[paste0(cur_column(), suffix)]] #you could use glue() as well here
}

df_vars %>%
  summarize(
    across(
      all_of(vars_num),
      list(
        mean = mean,
        mean_prob = ~t.test(.x, mu = get_mu("_mean"))$p.value,
        std = sd,
        std_prob = ~varTest(.x, sigma.squared = get_mu("_std")^2)$p.value
      )
    )
  ) %>% t() #just to format the output


#                        [,1]
# mpg_mean        20.09062500
# mpg_mean_prob    0.01808550
# mpg_std          6.02694805
# mpg_std_prob     0.96094601
# cyl_mean         6.18750000
# cyl_mean_prob    0.10909740
# cyl_std          1.78592165
# cyl_std_prob     0.77092484
# disp_mean      230.72187500
# disp_mean_prob   0.17613878
# disp_std       123.93869383
# disp_std_prob    0.96381507
# hp_mean        146.68750000
# hp_mean_prob     0.03914858
# hp_std          68.56286849
# hp_std_prob      0.03459963