SemyonSinchenko commented on code in PR #46368:
URL: https://github.com/apache/spark/pull/46368#discussion_r1592932992
##########
python/pyspark/sql/dataframe.py:
##########
@@ -657,6 +657,19 @@ def printSchema(self, level: Optional[int] = None) -> None:
"""
...
+ @dispatch_df_method
+ def sizeInBytesApproximation(self) -> int:
+ """Return approximate size in bytes of a DataFrame.
+
+ .. versionadded:: 4.0.0
+
+ Returns
+ -------
+ int
+ Size in bytes estimated from optimized plan
Review Comment:
Done
##########
python/pyspark/sql/connect/client/core.py:
##########
@@ -1157,6 +1163,20 @@ def _analyze_plan_request_with_metadata(self) ->
pb2.AnalyzePlanRequest:
req.user_context.user_id = self._user_id
return req
+ def _sizeInBytes(self, relation: pb2.Relation) -> AnalyzeResult:
Review Comment:
Done
--
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]
