xinrong-databricks commented on a change in pull request #35868:
URL: https://github.com/apache/spark/pull/35868#discussion_r828546723
##########
File path: python/pyspark/pandas/series.py
##########
@@ -3618,8 +3622,25 @@ def rank(self, method: str = "average", ascending: bool
= True) -> "Series":
2 2.0
3 3.0
Name: A, dtype: float64
+
+ If numeric_only is set to 'True', rank only numeric Series,
+ return an empty Series otherwise.
+
+ >>> s = ps.Series(['a', 'b', 'c'], name='A', index=['x', 'y', 'z'])
+ >>> s
+ x a
+ y b
+ z c
+ Name: A, dtype: object
+
+ >>> s.rank(numeric_only=True)
+ Series([], Name: A, dtype: float64)
"""
- return self._rank(method, ascending).spark.analyzed
+ is_numeric = isinstance(self.spark.data_type, (NumericType,
BooleanType))
+ if numeric_only and not is_numeric:
+ return ps.Series([], dtype="float64", name=self.name)
Review comment:
Following pandas' behavior.
--
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]
