buraksenn commented on code in PR #20926:
URL: https://github.com/apache/datafusion/pull/20926#discussion_r3040202558
##########
datafusion/physical-plan/src/aggregates/mod.rs:
##########
@@ -1113,6 +1163,34 @@ impl AggregateExec {
}
}
+ /// Computes the estimated number of distinct groups across all grouping
sets.
+ /// For each grouping set, computes `product(NDV_i + null_adj_i)` for
active columns,
+ /// then sums across all sets. Returns `None` if any active column is not
a direct
+ /// column reference or lacks `distinct_count` stats.
+ /// When `null_count` is absent or unknown, null_adjustment defaults to 0.
+ fn compute_group_ndv(&self, child_statistics: &Statistics) ->
Option<usize> {
+ let mut total: usize = 0;
+ for group_mask in &self.group_by.groups {
+ let mut set_product: usize = 1;
+ for (j, (expr, _)) in self.group_by.expr.iter().enumerate() {
+ if group_mask[j] {
+ continue;
+ }
+ let col = expr.as_any().downcast_ref::<Column>()?;
Review Comment:
added comment
--
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]
