Github user icexelloss commented on a diff in the pull request: https://github.com/apache/spark/pull/18732#discussion_r143810539 --- Diff: python/pyspark/sql/group.py --- @@ -192,7 +193,84 @@ def pivot(self, pivot_col, values=None): jgd = self._jgd.pivot(pivot_col) else: jgd = self._jgd.pivot(pivot_col, values) - return GroupedData(jgd, self.sql_ctx) + return GroupedData(jgd, self._df) + + @since(2.3) + def apply(self, udf): + """ + Maps each group of the current :class:`DataFrame` using a pandas udf and returns the result + as a `DataFrame`. + + The user-defined function should take a `pandas.DataFrame` and return another + `pandas.DataFrame`. For each group, all columns are passed together as a `pandas.DataFrame` + to the user-function and the returned `pandas.DataFrame` are combined as a `DataFrame`. --- End diff -- Fixed.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org