Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/14517#discussion_r73884828 --- Diff: python/pyspark/sql/readwriter.py --- @@ -500,6 +500,41 @@ def partitionBy(self, *cols): self._jwrite = self._jwrite.partitionBy(_to_seq(self._spark._sc, cols)) return self + @since(2.0) + def bucketBy(self, numBuckets, *cols): + """Buckets the output by the given columns on the file system. + + :param numBuckets: the number of buckets to save + :param cols: name of columns + + >>> df.write.format('parquet').bucketBy('year', 'month').saveAsTable('bucketed_table') + """ + if len(cols) == 1 and isinstance(cols[0], (list, tuple)): + cols = cols[0] + + col = cols[0] + cols = cols[1:] + + self._jwrite = self._jwrite.bucketBy(numBuckets, col, _to_seq(self._spark._sc, cols)) + return self + + @since(2.0) + def sortBy(self, *cols): + """Sorts the output in each bucket by the given columns on the file system. + + :param cols: name of columns + + >>> df.write.format('parquet').bucketBy('year', 'month').sortBy('day').saveAsTable('sorted_bucketed_table') --- End diff -- similarly here no `numBuckets` arg
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org