You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by rx...@apache.org on 2015/06/05 22:49:52 UTC
spark git commit: [SPARK-7991] [PySpark] Adding support for passing
lists to describe.
Repository: spark
Updated Branches:
refs/heads/master 4060526cd -> 356a4a9b9
[SPARK-7991] [PySpark] Adding support for passing lists to describe.
This is a minor change.
Author: amey <am...@skytree.net>
Closes #6655 from ameyc/JIRA-7991/support-passing-list-to-describe and squashes the following commits:
e8a1dff [amey] Adding support for passing lists to describe.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/356a4a9b
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/356a4a9b
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/356a4a9b
Branch: refs/heads/master
Commit: 356a4a9b93a1eeedb910c6bccc0abadf59e4877f
Parents: 4060526
Author: amey <am...@skytree.net>
Authored: Fri Jun 5 13:49:33 2015 -0700
Committer: Reynold Xin <rx...@databricks.com>
Committed: Fri Jun 5 13:49:33 2015 -0700
----------------------------------------------------------------------
python/pyspark/sql/dataframe.py | 12 ++++++++++++
1 file changed, 12 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/356a4a9b/python/pyspark/sql/dataframe.py
----------------------------------------------------------------------
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index 03b01a1..902504d 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -616,7 +616,19 @@ class DataFrame(object):
| min| 2|
| max| 5|
+-------+---+
+ >>> df.describe(['age', 'name']).show()
+ +-------+---+-----+
+ |summary|age| name|
+ +-------+---+-----+
+ | count| 2| 2|
+ | mean|3.5| null|
+ | stddev|1.5| null|
+ | min| 2|Alice|
+ | max| 5| Bob|
+ +-------+---+-----+
"""
+ if len(cols) == 1 and isinstance(cols[0], list):
+ cols = cols[0]
jdf = self._jdf.describe(self._jseq(cols))
return DataFrame(jdf, self.sql_ctx)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org