nealrichardson commented on a change in pull request #10722:
URL: https://github.com/apache/arrow/pull/10722#discussion_r679284036
##########
File path: r/R/dplyr-summarize.R
##########
@@ -28,14 +28,109 @@ 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()")
+ dplyr::summarise(to_duckdb(.data), ...)
+ } 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, ...) {
+ exprs <- quos(...)
+ # Check for unnamed expressions and fix if any
+ unnamed <- !nzchar(names(exprs))
+ # Deparse and take the first element in case they're long expressions
+ names(exprs)[unnamed] <- map_chr(exprs[unnamed], as_label)
+
+ mask <- arrow_mask(.data)
+ # Add aggregation wrappers to arrow_mask somehow
Review comment:
This is done though there is some subtlety here that's not quite right.
I'll make followups to revisit this and other issues.
--
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]
