lidavidm commented on a change in pull request #29818:
URL: https://github.com/apache/spark/pull/29818#discussion_r505044467
##########
File path: python/pyspark/sql/pandas/serializers.py
##########
@@ -90,7 +90,10 @@ def load_stream(self, stream):
import pyarrow as pa
reader = pa.ipc.open_stream(stream)
for batch in reader:
- yield batch
+ split_batch = pa.RecordBatch.from_arrays([
+ pa.concat_arrays([array]) for array in batch
+ ], schema=batch.schema)
Review comment:
I added a comment, but please let me know if it's unclear.
##########
File path: python/pyspark/sql/pandas/conversion.py
##########
@@ -103,10 +103,18 @@ def toPandas(self):
batches = self.toDF(*tmp_column_names)._collect_as_arrow()
if len(batches) > 0:
table = pyarrow.Table.from_batches(batches)
+ del batches
# Pandas DataFrame created from PyArrow uses
datetime64[ns] for date type
# values, but we should use datetime.date to match the
behavior with when
# Arrow optimization is disabled.
- pdf = table.to_pandas(date_as_object=True)
+ pandas_options = {'date_as_object': True}
+ if self_destruct:
+ pandas_options.update({
+ 'self_destruct': True,
Review comment:
Done.
##########
File path: python/pyspark/sql/pandas/conversion.py
##########
@@ -34,7 +34,7 @@ class PandasConversionMixin(object):
"""
@since(1.3)
- def toPandas(self):
+ def toPandas(self, self_destruct=False):
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
