cloud-fan commented on a change in pull request #26813: [SPARK-30188][SQL][WIP]
Enable adaptive query execution by default
URL: https://github.com/apache/spark/pull/26813#discussion_r363599603
##########
File path: python/pyspark/sql/tests/test_pandas_udf_grouped_agg.py
##########
@@ -319,17 +319,17 @@ def test_complex_groupby(self):
expected4 = df.groupby(plus_one(df.id)).agg(sum(df.v))
# groupby one scalar pandas UDF
- result5 = df.groupby(plus_two(df.id)).agg(sum_udf(df.v))
- expected5 = df.groupby(plus_two(df.id)).agg(sum(df.v))
+ result5 = df.groupby(plus_two(df.id)).agg(sum_udf(df.v)).sort('sum(v)')
+ expected5 = df.groupby(plus_two(df.id)).agg(sum(df.v)).sort('sum(v)')
# groupby one expression and one python UDF
result6 = df.groupby(df.v % 2, plus_one(df.id)).agg(sum_udf(df.v))
expected6 = df.groupby(df.v % 2, plus_one(df.id)).agg(sum(df.v))
# groupby one expression and one scalar pandas UDF
- result7 = df.groupby(df.v % 2,
plus_two(df.id)).agg(sum_udf(df.v)).sort('sum(v)')
- expected7 = df.groupby(df.v % 2,
plus_two(df.id)).agg(sum(df.v)).sort('sum(v)')
-
+ result7 = df.groupby(df.v % 2,
plus_two(df.id)).agg(sum_udf(df.v)).sort(['sum(v)', 'plus_two(id)'])
+ expected7 = df.groupby(df.v % 2,
plus_two(df.id)).agg(sum(df.v)).sort(['sum(v)', 'plus_two(id)'])
+
Review comment:
extra spaces?
----------------------------------------------------------------
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]
