jalpan-randeri commented on a change in pull request #26585:
URL: https://github.com/apache/spark/pull/26585#discussion_r429582019
##########
File path: python/pyspark/sql/pandas/serializers.py
##########
@@ -142,6 +142,7 @@ def _create_batch(self, series):
"""
import pandas as pd
import pyarrow as pa
+
Review comment:
Done
##########
File path: python/pyspark/sql/pandas/serializers.py
##########
@@ -154,6 +155,9 @@ def create_array(s, t):
# Ensure timestamp series are in expected form for Spark internal
representation
if t is not None and pa.types.is_timestamp(t):
s = _check_series_convert_timestamps_internal(s,
self._timezone)
+ elif type(s.dtype) == pd.CategoricalDtype:
+ # FIXME: This can be removed once minimum pyarrow version is
>= 0.16.1
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]
