xinrong-databricks commented on code in PR #36148:
URL: https://github.com/apache/spark/pull/36148#discussion_r850624426
##########
python/pyspark/pandas/groupby.py:
##########
@@ -2573,15 +2631,30 @@ def stat_function(col: Column) -> Column:
return self._reduce_for_stat_function(stat_function,
only_numeric=numeric_only)
def _reduce_for_stat_function(
- self, sfun: Callable[[Column], Column], only_numeric: bool
+ self,
+ sfun: Callable[[Column], Column],
+ only_numeric: Optional[bool] = None,
+ bool_as_numeric: bool = False,
) -> FrameLike:
+ """Apply an aggregate function `sfun` per column and reduce to a
FrameLike.
+
+ Parameters
+ ----------
+ sfun : The aggregate function to apply per column
+ only_numeric: If True, only numeric columns are involved
+ bool_as_numeric: If True, boolean columns are seen as numeric columns
(following pandas)
+ """
groupkey_names = [SPARK_INDEX_NAME_FORMAT(i) for i in
range(len(self._groupkeys))]
groupkey_scols = [s.alias(name) for s, name in
zip(self._groupkeys_scols, groupkey_names)]
agg_columns = [
psser
for psser in self._agg_columns
- if isinstance(psser.spark.data_type, NumericType) or not
only_numeric
+ if (
+ isinstance(psser.spark.data_type, NumericType)
+ or (isinstance(psser.spark.data_type, BooleanType) and
bool_as_numeric)
Review Comment:
Actually, that's a pretty good idea. Adjusted.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
