grundprinzip commented on code in PR #39585:
URL: https://github.com/apache/spark/pull/39585#discussion_r1072068522
##########
python/pyspark/sql/tests/connect/test_connect_function.py:
##########
@@ -2210,15 +2210,39 @@ def test_call_udf(self):
).toPandas(),
)
+ def test_udf(self):
+ from pyspark.sql import functions as SF
+ from pyspark.sql.connect import functions as CF
+
+ query = """
+ SELECT a, b, c, BINARY(c) as d FROM VALUES
+ (-1.0, float("NAN"), 'x'), (-2.1, NULL, 'y'), (1, 2.1, 'z'), (0,
0.5, NULL)
+ AS tab(a, b, c)
+ """
+
+ # +----+----+----+----+
+ # | a| b| c| d|
+ # +----+----+----+----+
+ # |-1.0| NaN| x|[78]|
+ # |-2.1|null| y|[79]|
+ # | 1.0| 2.1| z|[7A]|
+ # | 0.0| 0.5|null|null|
+ # +----+----+----+----+
+
+ cdf = self.connect.sql(query)
+ sdf = self.spark.sql(query)
+
+ self.assert_eq(
+ cdf.select(CF.udf(lambda x: x + 1)(cdf.a)).toPandas(),
+ sdf.select(SF.udf(lambda x: x + 1)(sdf.a)).toPandas(),
Review Comment:
on `pyspark.sql.function.udf` we need a similar `@try_remote_functions`.
This will help in the support.
--
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]
