darcy-shen commented on a change in pull request #32332: URL: https://github.com/apache/spark/pull/32332#discussion_r677110817
########## File path: python/pyspark/sql/session.py ########## @@ -697,12 +712,19 @@ def prepare(obj): verify_func(obj) return obj, else: + no_need_to_prepare = True prepare = lambda obj: obj - if isinstance(data, RDD): - rdd, schema = self._createFromRDD(data.map(prepare), schema, samplingRatio) + if isinstance(data, RDD) and no_need_to_prepare: + rdd, schema = self._createFromRDD( + data, schema, verifySchema, samplingRatio) + elif isinstance(data, RDD) and (not no_need_to_prepare): + rdd, schema = self._createFromRDD( + data.map(prepare), schema, verifySchema, samplingRatio) Review comment: Refactored, thanks! -- 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: reviews-unsubscr...@spark.apache.org 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