HyukjinKwon commented on a change in pull request #35410:
URL: https://github.com/apache/spark/pull/35410#discussion_r803206088
##########
File path: python/pyspark/sql/dataframe.py
##########
@@ -104,10 +105,25 @@ class DataFrame(PandasMapOpsMixin, PandasConversionMixin):
.. versionadded:: 1.3.0
"""
- def __init__(self, jdf: JavaObject, sql_ctx: "SQLContext"):
- self._jdf = jdf
- self.sql_ctx = sql_ctx
- self._sc: SparkContext = cast(SparkContext, sql_ctx and sql_ctx._sc)
+ def __init__(
+ self,
+ jdf: JavaObject,
+ sql_ctx: Optional["SQLContext"] = None,
+ session: Optional["SparkSession"] = None,
+ ):
+ assert sql_ctx is not None or session is not None
+ self._session = session
+ self._sql_ctx = sql_ctx
Review comment:
That's a good idea .. let me think and update a bit more.
--
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]
