Dandandan commented on code in PR #8126:
URL: https://github.com/apache/arrow-datafusion/pull/8126#discussion_r1390274643
##########
datafusion/physical-plan/src/filter.rs:
##########
@@ -194,11 +194,19 @@ impl ExecutionPlan for FilterExec {
fn statistics(&self) -> Result<Statistics> {
let predicate = self.predicate();
+ let input_stats = self.input.statistics()?;
let schema = self.schema();
if !check_support(predicate, &schema) {
- return Ok(Statistics::new_unknown(&schema));
+ // assume filter selects 20% of rows if we cannot do anything
smarter
+ // tracking issue for making this configurable:
+ // https://github.com/apache/arrow-datafusion/issues/8133
+ let selectivity = 0.2_f32;
+ let mut stats = input_stats.clone().into_inexact();
+ if let Precision::Inexact(n) = stats.num_rows {
+ stats.num_rows = Precision::Inexact((selectivity * n as f32)
as usize);
Review Comment:
I think we can/should do the same for the `total_byte_size` value
--
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]
