Github user wzhfy commented on a diff in the pull request:
https://github.com/apache/spark/pull/19783#discussion_r153972517
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/FilterEstimation.scala
---
@@ -332,8 +332,45 @@ case class FilterEstimation(plan: Filter) extends
Logging {
colStatsMap.update(attr, newStats)
}
- Some(1.0 / BigDecimal(ndv))
- } else {
+ // We compute filter selectivity using Histogram information
+ attr.dataType match {
+ case StringType | BinaryType =>
+ Some(1.0 / BigDecimal(ndv))
+
+ case _ =>
+ // returns 1/ndv if there is no histogram
+ if (colStat.histogram.isEmpty) return Some(1.0 / BigDecimal(ndv))
+
+ // We traverse histogram bins to locate the literal value
+ val hgmBins = colStat.histogram.get.bins
+ val datum = EstimationUtils.toDecimal(literal.value,
literal.dataType).toDouble
+ // find the interval where this datum locates
+ var lowerId, higherId = -1
+ for (i <- hgmBins.indices) {
+ // if datum > upperBound, just move to next bin
--- End diff --
please remove the comment, it does not match the logic at next line
(there's no "move" logic)
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
