buraksenn commented on code in PR #20926:
URL: https://github.com/apache/datafusion/pull/20926#discussion_r3046674543
##########
datafusion/physical-plan/src/aggregates/mod.rs:
##########
@@ -1113,6 +1134,82 @@ impl AggregateExec {
}
}
+ /// Estimates the output row count for grouped aggregations, combining NDV,
+ /// input row count, and TopK limit into a single [`Precision<usize>`].
+ fn estimate_num_rows(&self, child_statistics: &Statistics) ->
Precision<usize> {
+ let ndv = if !self.group_by.expr.is_empty() {
+ self.compute_group_ndv(child_statistics)
+ } else {
+ None
+ };
+ let limit = self.limit_options.as_ref().map(|lo| lo.limit);
+
+ if let Some(&value) = child_statistics.num_rows.get_value() {
+ if value > 1 {
+ let mut num_rows = child_statistics.num_rows.to_inexact();
+ if let Some(ndv) = ndv {
+ num_rows = num_rows.map(|n| n.min(ndv));
+ }
+ if let Some(limit) = limit {
+ num_rows = num_rows.map(|n| n.min(limit));
+ }
+ num_rows
+ } else if value == 0 {
+ child_statistics.num_rows
+ } else {
+ let grouping_set_num = self.group_by.groups.len();
+ child_statistics.num_rows.map(|x| x * grouping_set_num)
Review Comment:
I've missed that and applied it now thanks @xudong963
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
