AlSchlo commented on code in PR #54134:
URL: https://github.com/apache/spark/pull/54134#discussion_r2825016390
##########
sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala:
##########
@@ -1134,6 +1134,277 @@ class DataFrameAggregateSuite extends QueryTest
}
}
+ test("max_by and min_by with k") {
+ // Basic: string values, integer ordering
+ checkAnswer(
+ sql(
+ """
+ |SELECT max_by(x, y, 2), min_by(x, y, 2)
+ |FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS tab(x, y)
+ """.stripMargin),
+ Row(Seq("b", "c"), Seq("a", "c")) :: Nil
+ )
+
+ // DataFrame API
+ checkAnswer(
+ spark.sql("SELECT * FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS
tab(x, y)")
+ .agg(max_by(col("x"), col("y"), 2), min_by(col("x"), col("y"), 2)),
+ Row(Seq("b", "c"), Seq("a", "c")) :: Nil
+ )
+
+ // k larger than available rows
+ checkAnswer(
+ sql(
+ """
+ |SELECT max_by(x, y, 5), min_by(x, y, 5)
+ |FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS tab(x, y)
+ """.stripMargin),
+ Row(Seq("b", "c", "a"), Seq("a", "c", "b")) :: Nil
+ )
+
+ // k = 1
+ checkAnswer(
+ sql(
+ """
+ |SELECT max_by(x, y, 1), min_by(x, y, 1)
+ |FROM VALUES (('a', 10)), (('b', 50)), (('c', 20)) AS tab(x, y)
+ """.stripMargin),
+ Row(Seq("b"), Seq("a")) :: Nil
+ )
+
+ // NULL orderings are skipped
+ checkAnswer(
+ sql(
+ """
+ |SELECT max_by(x, y, 2), min_by(x, y, 2)
+ |FROM VALUES (('a', 10)), (('b', null)), (('c', 20)) AS tab(x, y)
+ """.stripMargin),
+ Row(Seq("c", "a"), Seq("a", "c")) :: Nil
+ )
+
+ // All NULL orderings yields empty array
+ checkAnswer(
+ sql(
+ """
+ |SELECT max_by(x, y, 2), min_by(x, y, 2)
+ |FROM VALUES (('a', null)), (('b', null)) AS tab(x, y)
+ """.stripMargin),
+ Row(Seq(), Seq()) :: Nil
+ )
Review Comment:
Yup thanks for bringing this up.
--
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]
