JoshRosen commented on a change in pull request #24557: [SPARK-27653][SQL] Add
max_by() SQL aggregate function
URL: https://github.com/apache/spark/pull/24557#discussion_r282149868
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala
##########
@@ -782,4 +782,47 @@ class DataFrameAggregateSuite extends QueryTest with
SharedSQLContext {
val countAndDistinct = df.select(count("*"), countDistinct("*"))
checkAnswer(countAndDistinct, Row(100000, 100))
}
+
+ test("max_by") {
+ val yearOfMaxEarnings =
+ sql("SELECT course, max_by(year, earnings) FROM courseSales GROUP BY
course")
+ checkAnswer(yearOfMaxEarnings, Row("dotNET", 2013) :: Row("Java", 2013) ::
Nil)
+
+ checkAnswer(
+ sql("SELECT max_by(x, y) FROM VALUES (('a', 10)), (('b', 50)), (('c',
20)) AS tab(x, y)"),
+ Row("b") :: Nil
+ )
+
+ checkAnswer(
+ sql("SELECT max_by(x, y) FROM VALUES (('a', 10)), (('b', null)), (('c',
20)) AS tab(x, y)"),
+ Row("c") :: Nil
+ )
+
+ checkAnswer(
+ sql("SELECT max_by(x, y) FROM VALUES (('a', null)), (('b', null)),
(('c', 20)) AS tab(x, y)"),
+ Row("c") :: Nil
+ )
+
+ checkAnswer(
+ sql("SELECT max_by(x, y) FROM VALUES (('a', 10)), (('b', 50)), (('c',
null)) AS tab(x, y)"),
+ Row("b") :: Nil
+ )
+
+ checkAnswer(
+ sql("SELECT max_by(x, y) FROM VALUES (('a', null)), (('b', null)) AS
tab(x, y)"),
Review comment:
This makes sense if you think of this function as being semantically
equivalent to
SELECT first(x) FROM tab WHERE y = max(y)
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
