ianmcook commented on a change in pull request #9521:
URL: https://github.com/apache/arrow/pull/9521#discussion_r581437454
##########
File path: r/R/dplyr.R
##########
@@ -423,26 +482,115 @@ ungroup.arrow_dplyr_query <- function(x, ...) {
}
ungroup.Dataset <- ungroup.ArrowTabular <- force
-mutate.arrow_dplyr_query <- function(.data, ...) {
+mutate.arrow_dplyr_query <- function(.data,
+ ...,
+ .keep = c("all", "used", "unused",
"none"),
+ .before = NULL,
+ .after = NULL) {
+ call <- match.call()
+ exprs <- quos(...)
+ if (length(exprs) == 0) {
+ # Nothing to do
+ return(.data)
+ }
+
.data <- arrow_dplyr_query(.data)
if (query_on_dataset(.data)) {
not_implemented_for_dataset("mutate()")
}
- # TODO: see if we can defer evaluating the expressions and not collect here.
- # It's different from filters (as currently implemented) because the basic
- # vector transformation functions aren't yet implemented in Arrow C++.
- dplyr::mutate(dplyr::collect(.data), ...)
+
+ .keep <- match.arg(.keep)
+ .before <- enquo(.before)
+ .after <- enquo(.after)
+ # Restrict the cases we support for now
+ if (!quo_is_null(.before) || !quo_is_null(.after)) {
+ # TODO(ARROW-11701)
+ return(abandon_ship(call, .data, '.before and .after arguments are not
supported in Arrow'))
+ } else if (length(group_vars(.data)) > 0) {
+ # mutate() on a grouped dataset does calculations within groups
+ # This doesn't matter on scalar ops (arithmetic etc.) but it does
+ # for things with aggregations (e.g. subtracting the mean)
+ return(abandon_ship(call, .data, 'mutate() on grouped data not supported
in Arrow'))
+ } else if (!all(nzchar(names(exprs)))) {
+ # This is either user error or a function that returns a data.frame
+ # e.g. across() that dplyr::mutate() will autosplice
+ # TODO(ARROW-16999)
+ msg <- 'all ... expressions must be named: autosplicing multi-column
results not supported in Arrow'
+ return(abandon_ship(call, .data, msg))
Review comment:
I think this warning message will bewilder folks. Can we separate these
two cases and give different error messages? Something like this would work
```r
if (length(exprs[[1]]) > 1 && identical(typeof(exprs[[1]][[2]]), "language")
{
msg <- "Autosplicing functions in mutate() are not yet supported in Arrow"
} else {
msg <- "Unnamed expressions in mutate() are not yet 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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
