ianmcook commented on a change in pull request #10722:
URL: https://github.com/apache/arrow/pull/10722#discussion_r682256920
##########
File path: r/R/dplyr-summarize.R
##########
@@ -28,14 +28,107 @@ summarise.arrow_dplyr_query <- function(.data, ...,
.engine = c("arrow", "duckdb
dplyr::group_vars(.data) # vars needed for grouping
))
.data <- dplyr::select(.data, vars_to_keep)
-
if (match.arg(.engine) == "duckdb") {
dplyr::summarise(to_duckdb(.data), ...)
- } else {
- if (query_on_dataset(.data)) {
- not_implemented_for_dataset("summarize()")
+ } else if (isTRUE(getOption("arrow.summarize", FALSE))) {
+ # Try stuff, if successful return()
+ out <- try(do_arrow_summarize(.data, ...), silent = TRUE)
+ if (inherits(out, "try-error")) {
+ return(abandon_ship(call, .data, format(out)))
+ } else {
+ return(out)
}
+ } else {
+ # If unsuccessful or if option not set, do the work in R
dplyr::summarise(dplyr::collect(.data), ...)
}
}
summarise.Dataset <- summarise.ArrowTabular <- summarise.arrow_dplyr_query
+
+do_arrow_summarize <- function(.data, ...) {
Review comment:
Handle the `.groups` argument to `dplyr::summarise()`:
```suggestion
do_arrow_summarize <- function(.data, ..., .groups = NULL) {
if (!is.null(.groups)) {
# ARROW-13550
abort("`summarize()` with `.groups` argument not supported in Arrow")
}
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
