EnricoMi commented on code in PR #38624:
URL: https://github.com/apache/spark/pull/38624#discussion_r1202124485
##########
python/pyspark/sql/pandas/serializers.py:
##########
@@ -147,6 +147,49 @@ def wrap_and_init_stream():
return super(ArrowStreamUDFSerializer,
self).dump_stream(wrap_and_init_stream(), stream)
+class ArrowStreamGroupUDFSerializer(ArrowStreamUDFSerializer):
+ """
+ Serializes pyarrow.RecordBatch data with Arrow streaming format.
+
+ Loads Arrow record batches as `[[pa.RecordBatch]]` (one `[pa.RecordBatch]`
per group)
+ and serializes `[([pa.RecordBatch], arrow_type)]`.
+
+ Parameters
+ ----------
+ assign_cols_by_name : bool
+ If True, then DataFrames will get columns by name
+ """
+
+ def __init__(self, assign_cols_by_name):
+ super(ArrowStreamGroupUDFSerializer, self).__init__()
+ self._assign_cols_by_name = assign_cols_by_name
+
+ def dump_stream(self, iterator, stream):
+ import pyarrow as pa
+
+ # flatten inner list [([pa.RecordBatch], arrow_type)] into
[(pa.RecordBatch, arrow_type)]
+ # so strip off inner iterator induced by
ArrowStreamUDFSerializer.load_stream
+ batch_iter = [
+ (batch, arrow_type)
+ for batches, arrow_type in iterator # tuple constructed in
wrap_grouped_map_arrow_udf
+ for batch in batches
+ ]
+
+ if self._assign_cols_by_name:
+ batch_iter = [
+ (
+ pa.RecordBatch.from_arrays(
+ [batch.column(field.name) for field in arrow_type],
+ names=[field.name for field in arrow_type],
+ ),
+ arrow_type,
+ )
+ for batch, arrow_type in batch_iter
+ ]
Review Comment:
Thanks for highlighting this, I have changed this to a generator.
--
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]
