sadhen commented on a change in pull request #31735:
URL: https://github.com/apache/spark/pull/31735#discussion_r605705005
##########
File path: python/pyspark/sql/pandas/serializers.py
##########
@@ -153,14 +157,15 @@ def _create_batch(self, series):
from pyspark.sql.pandas.types import
_check_series_convert_timestamps_internal, \
_convert_dict_to_map_items
from pandas.api.types import is_categorical_dtype
- # Make input conform to [(series1, type1), (series2, type2), ...]
- if not isinstance(series, (list, tuple)) or \
- (len(series) == 2 and isinstance(series[1], pa.DataType)):
- series = [series]
- series = ((s, None) if not isinstance(s, (list, tuple)) else s for s
in series)
- def create_array(s, t):
- mask = s.isnull()
+ def create_array(s, t: pa.DataType, dt: Optional[DataType] = None):
Review comment:
Fixed, see https://github.com/apache/spark/pull/32026/files
--
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
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
