问题
I am trying to write a function in R that summarizes a data frame according to grouping variables. The grouping variables are given as a list and passed to group_by_at, and I would like to parametrize them.
What I am doing now is this:
library(tidyverse)
d = tribble(
~foo, ~bar, ~baz,
1, 2, 3,
1, 3, 5
4, 5, 6,
4, 5, 1
)
sum_fun <- function(df, group_vars, sum_var) {
sum_var = enquo(sum_var)
return(
df %>%
group_by_at(.vars = group_vars) %>%
summarize(sum(!! sum_var))
)
}
d %>% sum_fun(group_vars = c("foo", "bar"), baz)
However, I would like to call the function like so:
d %>% sum_fun(group_vars = c(foo, bar), baz)
Which means the grouping vars should not be evaluated in the call, but in the function. How would I go about rewriting the function to enable that?
I have tried using enquo just like for the summary variable, and then replacing group_vars with !! group_vars, but it leads to this error:
Error in !group_vars : invalid argument type
Using group_by(!!!group_vars) yields:
Column `c(foo, bar)` must be length 2 (the number of rows) or one, not 4
What would be the proper way to rewrite the function?
回答1:
I'd just use vars to do the quoting. Here is an example using mtcars dataset
library(tidyverse)
sum_fun <- function(.data, .summary_var, .group_vars) {
summary_var <- enquo(.summary_var)
.data %>%
group_by_at(.group_vars) %>%
summarise(mean = mean(!!summary_var))
}
sum_fun(mtcars, disp, .group_vars = vars(cyl, am))
#> # A tibble: 6 x 3
#> # Groups: cyl [?]
#> cyl am mean
#> <dbl> <dbl> <dbl>
#> 1 4 0 136.
#> 2 4 1 93.6
#> 3 6 0 205.
#> 4 6 1 155
#> 5 8 0 358.
#> 6 8 1 326
You can also replace .group_vars with ... (dot-dot-dot)
sum_fun2 <- function(.data, .summary_var, ...) {
summary_var <- enquo(.summary_var)
.data %>%
group_by_at(...) %>% # Forward `...`
summarise(mean = mean(!!summary_var))
}
sum_fun2(mtcars, disp, vars(cyl, am))
#> # A tibble: 6 x 3
#> # Groups: cyl [?]
#> cyl am mean
#> <dbl> <dbl> <dbl>
#> 1 4 0 136.
#> 2 4 1 93.6
#> 3 6 0 205.
#> 4 6 1 155
#> 5 8 0 358.
#> 6 8 1 326
If you prefer to supply inputs as a list of columns, you will need to use enquos for the ...
sum_fun3 <- function(.data, .summary_var, ...) {
summary_var <- enquo(.summary_var)
group_var <- enquos(...)
print(group_var)
.data %>%
group_by_at(group_var) %>%
summarise(mean = mean(!!summary_var))
}
sum_fun3(mtcars, disp, c(cyl, am))
#> [[1]]
#> <quosure>
#> expr: ^c(cyl, am)
#> env: global
#>
#> # A tibble: 6 x 3
#> # Groups: cyl [?]
#> cyl am mean
#> <dbl> <dbl> <dbl>
#> 1 4 0 136.
#> 2 4 1 93.6
#> 3 6 0 205.
#> 4 6 1 155
#> 5 8 0 358.
#> 6 8 1 326
Edit: append an .addi_var to .../.group_var.
sum_fun4 <- function(.data, .summary_var, .addi_var, .group_vars) {
summary_var <- enquo(.summary_var)
.data %>%
group_by_at(c(.group_vars, .addi_var)) %>%
summarise(mean = mean(!!summary_var))
}
sum_fun4(mtcars, disp, .addi_var = vars(gear), .group_vars = vars(cyl, am))
#> # A tibble: 10 x 4
#> # Groups: cyl, am [?]
#> cyl am gear mean
#> <dbl> <dbl> <dbl> <dbl>
#> 1 4 0 3 120.
#> 2 4 0 4 144.
#> 3 4 1 4 88.9
#> 4 4 1 5 108.
#> 5 6 0 3 242.
#> 6 6 0 4 168.
#> 7 6 1 4 160
#> 8 6 1 5 145
#> 9 8 0 3 358.
#> 10 8 1 5 326
group_by_at() can also take input as a character vector of column names
sum_fun5 <- function(.data, .summary_var, .addi_var, ...) {
summary_var <- enquo(.summary_var)
addi_var <- enquo(.addi_var)
group_var <- enquos(...)
### convert quosures to strings for `group_by_at`
all_group <- purrr::map_chr(c(addi_var, group_var), quo_name)
.data %>%
group_by_at(all_group) %>%
summarise(mean = mean(!!summary_var))
}
sum_fun5(mtcars, disp, gear, cyl, am)
#> # A tibble: 10 x 4
#> # Groups: gear, cyl [?]
#> gear cyl am mean
#> <dbl> <dbl> <dbl> <dbl>
#> 1 3 4 0 120.
#> 2 3 6 0 242.
#> 3 3 8 0 358.
#> 4 4 4 0 144.
#> 5 4 4 1 88.9
#> 6 4 6 0 168.
#> 7 4 6 1 160
#> 8 5 4 1 108.
#> 9 5 6 1 145
#> 10 5 8 1 326
Created on 2018-10-09 by the reprex package (v0.2.1.9000)
回答2:
You could make use of the ellipse .... Take the following example:
sum_fun <- function(df, sum_var, ...) {
sum_var <- substitute(sum_var)
grps <- substitute(list(...))[-1L]
return(
df %>%
group_by_at(.vars = as.character(grps)) %>%
summarize(sum(!! sum_var))
)
}
d %>% sum_fun(baz, foo, bar)
We take the additional arguments and create a list out of them. Afterwards we use non-standard evaluation (substitute) to get the variable names and prevent R from evaluating them. Since group_by_at expects an object of type character or numeric, we simply convert the vector of names into a vector of characters and the function gets evaluated as we would expect.
> d %>% sum_fun(baz, foo, bar)
# A tibble: 3 x 3
# Groups: foo [?]
foo bar `sum(baz)`
<dbl> <dbl> <dbl>
1 1 2 3
2 1 3 5
3 4 5 7
If you do not want to supply grouping variables as any number of additional arguments, then you can of course use a named argument:
sum_fun <- function(df, sum_var, grps) {
sum_var <- enquo(sum_var)
grps <- as.list(substitute(grps))[-1L]
return(
df %>%
group_by_at(.vars = as.character(grps)) %>%
summarize(sum(!! sum_var))
)
}
sum_fun(mtcars, sum_var = hp, grps = c(cyl, gear))
The reason why I use substitute is that it makes it easy to split the expression list(cyl, gear) in its components. There might be a way to use rlang but I have not digged into that package so far.
来源：https://stackoverflow.com/questions/52718604/passing-a-list-of-arguments-to-a-function-with-quasiquotation