Github user BryanCutler commented on a diff in the pull request:
https://github.com/apache/spark/pull/18732#discussion_r142244544
--- Diff: python/pyspark/sql/group.py ---
@@ -194,6 +194,37 @@ def pivot(self, pivot_col, values=None):
jgd = self._jgd.pivot(pivot_col, values)
return GroupedData(jgd, self.sql_ctx)
+ def apply(self, udf_obj):
+ """
+ Maps each group of the current [[DataFrame]] using a pandas udf
and returns the result
+ as a :class:`DataFrame`.
+
+ """
+ from pyspark.sql.functions import pandas_udf
+
+ if not udf_obj._vectorized:
+ raise ValueError("Must pass a pandas_udf")
--- End diff --
Maybe reword to "The argument to apply() must be a pandas_udf"
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
