HyukjinKwon commented on code in PR #46817:
URL: https://github.com/apache/spark/pull/46817#discussion_r1621777318
##########
python/pyspark/sql/classic/dataframe.py:
##########
@@ -1220,28 +1220,20 @@ def intersectAll(self, other: ParentDataFrame) ->
ParentDataFrame:
def subtract(self, other: ParentDataFrame) -> ParentDataFrame:
return DataFrame(getattr(self._jdf, "except")(other._jdf),
self.sparkSession)
- def dropDuplicates(self, subset: Optional[List[str]] = None) ->
ParentDataFrame:
- if subset is not None and (not isinstance(subset, Iterable) or
isinstance(subset, str)):
- raise PySparkTypeError(
- error_class="NOT_LIST_OR_TUPLE",
- message_parameters={"arg_name": "subset", "arg_type":
type(subset).__name__},
- )
-
- if subset is None:
+ def dropDuplicates(self, *subset: Union[str, List[str]]) ->
ParentDataFrame:
Review Comment:
Let's also fix `docs/structured-streaming-programming-guide.md` together :-)
--
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]
