group_by(across(all_of(vars, YEARS))) - 按具有固定 YEAR 变量的变量进行分组

Question

我有一些数据想总结一下。我想对所有列进行总结，并固定“年份”列。即对于一个变量我可以这样做：

\n

df %>% \n  group_by(LG1, YEAR) %>% \n  summarise(Freq = n())\n

\n

不过我想对每个变量都进行此操作。下面的内容不能按我想要的方式工作，因为它没有按YEAR变量分组。我试图包含 group_by(across(all_of(c(vars, YEAR)))) %>%返回错误的内容。

\n

vars <- c("LG1", "AA1", "FNB1", "RE1", "PE1", "LG2", "AA2", "FNB2", "RE2", "PE2", "LG3", "AA3", "FNB3", "RE3", "PE3")\ndf %>% \n  select(c(all_of(vars), "YEAR")) %>% \n  group_by(across()) %>% \n  summarise(Freq = n())\n

\n

预期输出将是一个数据框，其中包含每年每个变量的频率。

\n

数据：

\n

df <- structure(list(\xc3\xaf..N.QUESTIONAIRE = c(119L, 122L, 137L, 59L, 121L, \n19L, 50L, 40L, 124L, 108L, 26L, 193L, 94L, 27L, 49L, 82L, 149L, \n88L, 133L, 150L, 5L, 28L, 175L, 91L, 151L, 97L, 70L, 42L, 21L, \n155L), LG1 = c(4L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 3L, 4L, 5L, \n4L, 4L, 4L, 5L, 4L, 4L, 5L, 4L, 5L, 4L, 4L, 3L, 5L, 5L, 5L, 3L, \n3L, 3L), AA1 = c(1L, 3L, 2L, 2L, 2L, 2L, 2L, 3L, 4L, 3L, 3L, \n1L, 1L, 3L, 2L, 1L, 1L, 3L, 1L, 3L, 1L, 2L, 3L, 2L, 2L, 2L, 2L, \n2L, 4L, 1L), FNB1 = c(4L, 4L, 5L, 4L, 4L, 4L, 4L, 4L, 3L, 4L, \n4L, 5L, 4L, 4L, 4L, 5L, 4L, 4L, 4L, 5L, 5L, 4L, 4L, 4L, 5L, 2L, \n5L, 4L, 3L, 4L), RE1 = c(2L, 3L, 1L, 2L, 1L, 3L, 3L, 2L, 1L, \n3L, 3L, 4L, 1L, 2L, 3L, 2L, 2L, 2L, 3L, 4L, 2L, 2L, 3L, 2L, 5L, \n3L, 1L, 2L, 2L, 3L), PE1 = c(5L, 5L, 5L, 5L, 5L, 4L, 4L, 4L, \n4L, 5L, 4L, 5L, 4L, 4L, 5L, 5L, 5L, 4L, 5L, 5L, 5L, 4L, 5L, 4L, \n5L, 4L, 4L, 4L, 4L, 4L), LG2 = c(4L, 3L, 5L, 5L, 2L, 4L, 3L, \n3L, 4L, 3L, 2L, 5L, 3L, 3L, 2L, 5L, 5L, 5L, 4L, 4L, 1L, 5L, 2L, \n4L, 1L, 5L, 5L, 4L, 4L, 5L), AA2 = c(4L, 5L, 5L, 4L, 3L, 4L, \n5L, 3L, 5L, 4L, 5L, 5L, 5L, 2L, 5L, 5L, 5L, 4L, 5L, 5L, 5L, 4L, \n3L, 5L, 5L, 5L, 5L, 5L, 4L, 4L), FNB2 = c(1L, 2L, 1L, 2L, 3L, \n1L, 3L, 3L, 1L, 1L, 3L, 2L, 1L, 3L, 2L, 3L, 2L, 2L, 1L, 2L, 1L, \n2L, 2L, 3L, 5L, 1L, 3L, 3L, 2L, 1L), RE2 = c(4L, 3L, 3L, 3L, \n3L, 4L, 3L, 3L, 4L, 3L, 2L, 5L, 4L, 3L, 4L, 4L, 5L, 3L, 2L, 2L, \n4L, 2L, 4L, 1L, 5L, 5L, 4L, 1L, 3L, 4L), PE2 = c(2L, 4L, 1L, \n3L, 3L, 1L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 4L, \n1L, 1L, 2L, 2L, 4L, 1L, 1L, 2L, 4L, 1L, 1L), LG3 = c(4L, 3L, \n3L, 4L, 2L, 4L, 4L, 2L, 5L, 3L, 3L, 4L, 4L, 2L, 4L, 3L, 3L, 4L, \n4L, 3L, 5L, 4L, 4L, 2L, 5L, 5L, 3L, 4L, 5L, 4L), AA3 = c(1L, \n3L, 2L, 2L, 3L, 3L, 2L, 1L, 1L, 2L, 2L, 3L, 3L, 2L, 1L, 1L, 1L, \n3L, 2L, 3L, 1L, 1L, 4L, 2L, 4L, 4L, 1L, 1L, 3L, 2L), FNB3 = c(5L, \n5L, 5L, 5L, 5L, 2L, 4L, 4L, 5L, 4L, 5L, 5L, 4L, 4L, 5L, 5L, 5L, \n4L, 5L, 5L, 5L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), RE3 = c(2L, \n2L, 2L, 2L, 3L, 4L, 4L, 2L, 3L, 3L, 3L, 1L, 1L, 2L, 3L, 2L, 1L, \n4L, 4L, 1L, 3L, 1L, 1L, 3L, 5L, 1L, 2L, 4L, 3L, 2L), PE3 = c(5L, \n3L, 4L, 4L, 4L, 4L, 3L, 4L, 5L, 5L, 4L, 4L, 4L, 4L, 3L, 4L, 4L, \n4L, 4L, 4L, 5L, 4L, 4L, 3L, 5L, 5L, 4L, 3L, 4L, 3L), YEAR = c(2L, \n2L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, \n1L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 2L), NATIONALITY = c(2L, \n2L, 1L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 3L, 1L, 2L, 1L, 1L, \n3L, 1L, 1L, 2L, 2L, 2L, 3L, 1L, 3L, 1L, 2L, 3L, 1L), GENDER = c("F", \n"F", "M", "M", "F", "M", "M", "F", "F", "M", "F", "M", "M", "F", \n"M", "F", "F", "F", "M", "F", "M", "F", "M", "M", "F", "M", "M", \n"F", "M", "F"), AGE = c(1L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 3L, \n1L, 3L, 3L, 2L, 2L, 3L, 2L, 3L, 1L, 2L, 1L, 2L, 2L, 3L, 2L, 3L, \n2L, 2L, 1L, 2L)), class = "data.frame", row.names = c(NA, -30L\n))\n

\n

Answer 1

我们可以使用acrossingroup_by来包含所有vars列以及YEAR。

library(dplyr)

df %>%  group_by(across(c(all_of(vars), "YEAR"))) %>% summarise(Freq = n())

我们也可以在这里使用count-

df %>% count(across(c(all_of(vars), "YEAR")))

如果您想count对其中的每个值都vars可以使用map.

purrr::map(vars, ~df %>% count(YEAR, .data[[.x]]))