Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/20213#discussion_r160588222 --- Diff: python/pyspark/sql/session.py --- @@ -459,21 +459,23 @@ def _convert_from_pandas(self, pdf, schema, timezone): # TODO: handle nested timestamps, such as ArrayType(TimestampType())? if isinstance(field.dataType, TimestampType): s = _check_series_convert_timestamps_tz_local(pdf[field.name], timezone) - if not copied and s is not pdf[field.name]: - # Copy once if the series is modified to prevent the original Pandas - # DataFrame from being updated - pdf = pdf.copy() - copied = True - pdf[field.name] = s + if s is not pdf[field.name]: + if not copied: --- End diff -- BTW, what's diff between: ``` if s is not pdf[field.name]: if not copied: ``` vs ``` if not copied and s is not pdf[field.name]: ``` ?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org