d80tb7 commented on a change in pull request #24981: [SPARK-27463][PYTHON] Support Dataframe Cogroup via Pandas UDFs URL: https://github.com/apache/spark/pull/24981#discussion_r315750156
########## File path: python/pyspark/serializers.py ########## @@ -401,6 +427,22 @@ def __repr__(self): return "ArrowStreamPandasUDFSerializer" +class InterleavedArrowStreamPandasSerializer(ArrowStreamPandasUDFSerializer): + + def __init__(self, timezone, safecheck, assign_cols_by_name): + super(InterleavedArrowStreamPandasSerializer, self).__init__(timezone, safecheck, assign_cols_by_name) + + def load_stream(self, stream): + """ + Deserialize ArrowRecordBatches to an Arrow table and return as a list of pandas.Series. + """ + reader = InterleavedArrowReader(stream) Review comment: doh! yes you're quick right- this is much better. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org