HyukjinKwon commented on code in PR #39469:
URL: https://github.com/apache/spark/pull/39469#discussion_r1066532044
##########
python/pyspark/sql/connect/session.py:
##########
@@ -215,7 +215,38 @@ def createDataFrame(
_inferred_schema: Optional[StructType] = None
if isinstance(data, pd.DataFrame):
- _table = pa.Table.from_pandas(data)
+ from pandas.api.types import ( # type: ignore[attr-defined]
+ is_datetime64_dtype,
+ is_datetime64tz_dtype,
+ )
+ from pyspark.sql.pandas.types import (
+ _check_series_convert_timestamps_internal,
+ _get_local_timezone,
+ )
+
+ # Copying the frame to avoid modifying it.
+ data_copy = data.copy()
Review Comment:
Or would be nicer if we can avoid copying here at all if possible
--
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]
