I'm trying to write a simple wrapper to summarise() arbitrary variables by arbitrary groups and have made progress now I've got the correct library version loaded but am confused (again) about how to unquote arguments with multiple values.
I currently have the following function...
table_summary <- function(df = .,
id = individual_id,
select = c(),
group = site,
...){
## Quote all arguments (see http://dplyr.tidyverse.org/articles/programming.html)
quo_id <- enquo(id)
quo_select <- enquo(select)
quo_group <- enquo(group)
## Subset the data
df <- df %>%
dplyr::select(!!quo_id, !!quo_select, !!quo_group) %>%
unique()
## gather() data, just in case there is > 1 variable selected to be summarised
df <- df %>%
gather(key = variable, value = value, !!quo_select)
## Summarise selected variables by specified groups
results <- df %>%
group_by(!!quo_group, variable) %>%
summarise(n = n(),
mean = mean(value, na.rm = TRUE))
return(results)
}
Which gets most of the way there and works if I specify one grouping variable...
> table_summary(df = mtcars, id = model, select = c(mpg), group = gear)
# A tibble: 3 x 4
# Groups: c(gear) [?]
gear variable n mean
<dbl> <chr> <int> <dbl>
1 3 mpg 15 16.10667
2 4 mpg 12 24.53333
3 5 mpg 5 21.38000
...but fails at the group_by(!!quo_group, variable) when I specify more than one group = c(gear, hp)...
> mtcars$model <- rownames(mtcars)
> table_summary(df = mtcars, id = model, select = c(mpg), group = c(gear, hp))
Error in mutate_impl(.data, dots) :
Column `c(gear, hp)` must be length 32 (the group size) or one, not 64
I went back and re-read the programming dplyr documentation and I read that you can capture multiple variables using quos() instead of enquo() and then unquote-splice them with !!!, so tried...
table_summary <- function(df = .,
id = individual_id,
select = c(),
group = c(),
digits = 3,
...){
## Quote all arguments (see http://dplyr.tidyverse.org/articles/programming.html)
quo_id <- enquo(id)
quo_select <- enquo(select)
quo_group <- quos(group) ## Use quos() rather than enquo()
UQS(quo_group) %>% print() ## Check to see what quo_group holds
## Subset the data
df <- df %>%
dplyr::select(!!quo_id, !!quo_select, !!!quo_group)) %>%
unique()
## gather() data, just in case there is > 1 variable selected to be summarised
df <- df %>%
gather(key = variable, value = value, !!quo_select)
## Summarise selected variables by specified groups
results <- df %>%
group_by(!!!quo_group, variable) %>%
summarise(n = n(),
mean = mean(value, na.rm = TRUE))
return(results)
}
...which now fails at the first reference to !!!quo_group``withindplyr::select()regardless of how many variables are specified undergroup = `...
> table_summary(df = mtcars, id = model, select = c(mpg), group = c(gear))
[[1]]
<quosure: frame>
~group
attr(,"class")
[1] "quosures"
Error in overscope_eval_next(overscope, expr) : object 'gear' not found
> traceback()
17: .Call(rlang_eval, f_rhs(quo), overscope)
16: overscope_eval_next(overscope, expr)
15: FUN(X[[i]], ...)
14: lapply(.x, .f, ...)
13: map(.x[matches], .f, ...)
12: map_if(ind_list, !is_helper, eval_tidy, data = names_list)
11: select_vars(names(.data), !(!(!quos(...))))
10: select.data.frame(., !(!quo_id), !(!quo_select), !(!(!quo_group)))
9: dplyr::select(., !(!quo_id), !(!quo_select), !(!(!quo_group)))
8: function_list[[i]](value)
7: freduce(value, `_function_list`)
6: `_fseq`(`_lhs`)
5: eval(quote(`_fseq`(`_lhs`)), env, env)
4: eval(quote(`_fseq`(`_lhs`)), env, env)
3: withVisible(eval(quote(`_fseq`(`_lhs`)), env, env))
2: df %>% dplyr::select(!(!quo_id), !(!quo_select), !(!(!quo_group))) %>%
unique()
1: table_summary(df = mtcars, id = model, select = c(mpg), group = c(gear))
What seems strange and I think is the source of the problem is that !!!quo_group (i.e. UQS(quo_group)) prints out ~gear rather than a list of quosures as adding a print() into the worked examples shows happens...
> my_summarise <- function(df, ...) {
group_by <- quos(...)
UQS(group_by) %>% print()
df %>%
group_by(!!!group_by) %>%
summarise(a = mean(a))
}
> df <- tibble(
g1 = c(1, 1, 2, 2, 2),
g2 = c(1, 2, 1, 2, 1),
a = sample(5),
b = sample(5)
)
> my_summarise(df, g1, g2)
[[1]]
<quosure: global>
~g1
[[2]]
<quosure: global>
~g2
attr(,"class")
[1] "quosures"
# A tibble: 4 x 3
# Groups: g1 [?]
g1 g2 a
<dbl> <dbl> <dbl>
1 1 1 1.0
2 1 2 5.0
3 2 1 2.5
4 2 2 4.0
I'd like to explicitly supply the variables I wish to group by as a parameter to my argument but does it work if I specify them as ... but I decided to test if my function works when supplying the grouping variables as ...
table_summary <- function(df = .,
id = individual_id,
select = c(),
group = c(),
digits = 3,
...){
## Quote all arguments (see http://dplyr.tidyverse.org/articles/programming.html)
quo_id <- enquo(id)
quo_select <- enquo(select)
## quo_group <- quos(group)
quo_group <- quos(...)
UQS(quo_group) %>% print()
## Subset the data
df <- df %>%
dplyr::select(!!quo_id, !!quo_select, !!!quo_group) %>%
unique()
## gather() data, just in case there is > 1 variable selected to be summarised
df <- df %>%
gather(key = variable, value = value, !!quo_select)
## Summarise selected variables by specified groups
results <- df %>%
group_by(!!!quo_group, variable) %>%
summarise(n = n(),
mean = mean(value, na.rm = TRUE))
return(results)
}
...but it doesn't, quos() again unquote-splices to NULL so the variables are neither selected nor grouped by...
> table_summary(df = mtcars, id = model, select = c(mpg), gear, hp)
NULL
# A tibble: 1 x 3
variable n mean
<chr> <int> <dbl>
1 mpg 32 20.09062
> table_summary(df = mtcars, id = model, select = c(mpg), gear)
NULL
# A tibble: 1 x 3
variable n mean
<chr> <int> <dbl>
1 mpg 32 20.09062
I've gone through this cycle several times now checking each method of using enquo() and quos() but can not see where I am going wrong and despite having read the programming dplyr documentation several times.