Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/21383#discussion_r191437141 --- Diff: python/pyspark/sql/udf.py --- @@ -157,7 +157,17 @@ def _create_judf(self): spark = SparkSession.builder.getOrCreate() sc = spark.sparkContext - wrapped_func = _wrap_function(sc, self.func, self.returnType) + func = fail_on_stopiteration(self.func) + + # prevent inspect to fail + # e.g. inspect.getargspec(sum) raises + # TypeError: <built-in function sum> is not a Python function + try: + func._argspec = _get_argspec(self.func) + except TypeError: --- End diff -- Let's use all of Pandas UDFs: https://github.com/apache/spark/blob/a9350d7095b79c8374fb4a06fd3f1a1a67615f6f/python/pyspark/sql/udf.py#L40-L67
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org