berkaysynnada commented on code in PR #7793:
URL: https://github.com/apache/arrow-datafusion/pull/7793#discussion_r1361584503
##########
datafusion/physical-plan/src/aggregates/mod.rs:
##########
@@ -1005,28 +1005,50 @@ impl ExecutionPlan for AggregateExec {
Some(self.metrics.clone_inner())
}
- fn statistics(&self) -> Statistics {
+ fn statistics(&self) -> Result<Statistics> {
// TODO stats: group expressions:
// - once expressions will be able to compute their own stats, use it
here
// - case where we group by on a column for which with have the
`distinct` stat
// TODO stats: aggr expression:
// - aggregations somtimes also preserve invariants such as min, max...
+ let column_statistics = Statistics::unknown_column(&self.schema());
match self.mode {
AggregateMode::Final | AggregateMode::FinalPartitioned
if self.group_by.expr.is_empty() =>
{
- Statistics {
- num_rows: Some(1),
- is_exact: true,
- ..Default::default()
- }
+ Ok(Statistics {
+ num_rows: Precision::Exact(1),
+ column_statistics,
+ total_byte_size: Precision::Absent,
+ })
+ }
+ _ => {
+ // When the input row count is 0 or 1, we can adopt that
statistic keeping its reliability.
Review Comment:
We have discussed that with @mustafasrepo, and his solution is temporary.
This change should serve as the final version after merging the PRs.
--
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]
