beliefer commented on code in PR #43910:
URL: https://github.com/apache/spark/pull/43910#discussion_r1400585209
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/percentiles.scala:
##########
@@ -444,3 +444,81 @@ case class PercentileDisc(
}
}
}
+
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+ usage = "_FUNC_(percentage) WITHIN GROUP (ORDER BY col) - Return a
percentile value based on " +
+ "a continuous distribution of numeric or ANSI interval column `col` at the
given " +
+ "`percentage` (specified in ORDER BY clause).",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(0.25) WITHIN GROUP (ORDER BY col) FROM VALUES (0), (10)
AS tab(col);
+ 2.5
+ > SELECT _FUNC_(0.25) WITHIN GROUP (ORDER BY col) FROM VALUES (INTERVAL
'0' MONTH), (INTERVAL '10' MONTH) AS tab(col);
+ 0-2
+ """,
+ group = "agg_funcs",
+ since = "4.0.0")
+// scalastyle:on line.size.limit
+object PercentileContBuilder extends ExpressionBuilder {
+ override def build(funcName: String, expressions: Seq[Expression]):
Expression = {
+ val numArgs = expressions.length
+ if (numArgs == 2) {
Review Comment:
Because the two percentile expressions have a lot of complexity. I recommend
the factory mode for inverse distribution function.
```
trait InverseDistributionFactory extends AggregateFunction {
def createInverseDistributionFunction(sortOrder: SortOrder):
AggregateFunction
}
```
--
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]
