BryanCutler 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_r319211690
##########
File path: python/pyspark/serializers.py
##########
@@ -401,6 +401,35 @@ def __repr__(self):
return "ArrowStreamPandasUDFSerializer"
+class CogroupUDFSerializer(ArrowStreamPandasUDFSerializer):
+
+ def __init__(self, timezone, safecheck, assign_cols_by_name):
+ super(CogroupUDFSerializer, self).__init__(timezone, safecheck,
assign_cols_by_name)
+
+ def load_stream(self, stream):
+ """
+ Deserialize Cogrouped ArrowRecordBatches to a tuple of Arrow tables
and return as a two
+ lists of pandas.Series.
+ """
+ import pyarrow as pa
+ dataframes_in_group = None
+
+ while dataframes_in_group is None or dataframes_in_group > 0:
+ dataframes_in_group = read_int(stream)
+
+ if dataframes_in_group == 2:
+ batch1 = [batch for batch in
ArrowStreamSerializer.load_stream(self, stream)]
+ batch2 = [batch for batch in
ArrowStreamSerializer.load_stream(self, stream)]
+ yield (
+ [self.arrow_to_pandas(c) for c in
pa.Table.from_batches(batch1).itercolumns()],
+ [self.arrow_to_pandas(c) for c in
pa.Table.from_batches(batch2).itercolumns()]
+ )
+
+ elif dataframes_in_group != 0:
+ raise ValueError(
+ 'Invalid number of dataframes in group
{0}'.format(dataframes_in_group))
Review comment:
nit: dataframes -> pandas.DataFrames
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
