Github user icexelloss commented on a diff in the pull request: https://github.com/apache/spark/pull/18732#discussion_r143033289 --- Diff: python/pyspark/worker.py --- @@ -74,17 +74,35 @@ def wrap_udf(f, return_type): def wrap_pandas_udf(f, return_type): - arrow_return_type = toArrowType(return_type) - - def verify_result_length(*a): - result = f(*a) - if not hasattr(result, "__len__"): - raise TypeError("Return type of pandas_udf should be a Pandas.Series") - if len(result) != len(a[0]): - raise RuntimeError("Result vector from pandas_udf was not the required length: " - "expected %d, got %d" % (len(a[0]), len(result))) - return result - return lambda *a: (verify_result_length(*a), arrow_return_type) + if isinstance(return_type, StructType): --- End diff -- Added doc. Check for `returnType == StructType `is done earlier: https://github.com/icexelloss/spark/blob/groupby-apply-SPARK-20396/python/pyspark/sql/group.py#L238
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org