Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/16193#discussion_r91360137 --- Diff: python/pyspark/sql/tests.py --- @@ -360,6 +360,15 @@ def test_broadcast_in_udf(self): [res] = self.spark.sql("SELECT MYUDF('')").collect() self.assertEqual("", res[0]) + def test_udf_with_filter_function(self): + df = self.spark.createDataFrame([(1, "1"), (2, "2"), (1, "2"), (1, "2")], ["key", "value"]) + from pyspark.sql.functions import udf, col + from pyspark.sql.types import BooleanType + + my_filter = udf(lambda a: a < 2, BooleanType()) + sel = df.select(col("key"), col("value")).filter((my_filter(col("key"))) & (df.value < "2")) --- End diff -- Nope. This case works well.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org