R dplyr across: Dynamically specifying arguments to functions t.test and varTest - r

Question

Am writing some dplyr across statements. Want to create some p-values using the functions t.test and varTest. The x= columns for calculations are in df_vars and the mu= and sigma.squared= parameter values are in df_mu_sigma.
A hard-coded version of the data I need are in df_sumry. If the variable names were always the same when code is run, something like this would suffice. That's not the case, however.
The beginnings of a non-hard-coded version of what I need are in df_sumry2. That doesn't yield a correct result yet though, because values of mu= and sigma.squared= are not dynamically specified. Only the first two p-values are correct in df_sumry2. They are always wrong after that because the code always uses values for the mpg variable.
How can I consistently get the right values inserted for mu and sigma.squared?
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

I appear to have come up with a solution to my own problem. I'd be happy to see alternative solutions though as they may be better than mine.
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

This is not much better than your solution, but I would use cur_column() instead of ensym() to avoid quosures handling.
Also, putting the query in a separate function makes things a bit tidier.
Finally, I would use lambda functions instead of anonymous functions for clarity.
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