Repository: spark Updated Branches: refs/heads/master de0dd6de2 -> c1b6fa983
[SPARK-5878] fix DataFrame.repartition() in Python Also add tests for distinct() Author: Davies Liu <dav...@databricks.com> Closes #4667 from davies/repartition and squashes the following commits: 79059fd [Davies Liu] add test cb4915e [Davies Liu] fix repartition Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/c1b6fa98 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/c1b6fa98 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/c1b6fa98 Branch: refs/heads/master Commit: c1b6fa9838f9d26d60fab3b05a96649882e3dd5b Parents: de0dd6d Author: Davies Liu <dav...@databricks.com> Authored: Wed Feb 18 01:00:54 2015 -0800 Committer: Reynold Xin <r...@databricks.com> Committed: Wed Feb 18 01:00:54 2015 -0800 ---------------------------------------------------------------------- python/pyspark/sql/dataframe.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/c1b6fa98/python/pyspark/sql/dataframe.py ---------------------------------------------------------------------- diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 388033d..52bd75b 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -434,12 +434,18 @@ class DataFrame(object): def repartition(self, numPartitions): """ Return a new :class:`DataFrame` that has exactly `numPartitions` partitions. + + >>> df.repartition(10).rdd.getNumPartitions() + 10 """ - return DataFrame(self._jdf.repartition(numPartitions, None), self.sql_ctx) + return DataFrame(self._jdf.repartition(numPartitions), self.sql_ctx) def distinct(self): """ Return a new :class:`DataFrame` containing the distinct rows in this DataFrame. + + >>> df.distinct().count() + 2L """ return DataFrame(self._jdf.distinct(), self.sql_ctx) --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org