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 07:21:13 UTC
spark git commit: [SPARK-8116][PYSPARK] Allow sc.range() to take a
single argument.
Repository: spark
Updated Branches:
refs/heads/branch-1.4 3ba6fc515 -> f02af7c8f
[SPARK-8116][PYSPARK] Allow sc.range() to take a single argument.
Author: Ted Blackman <te...@gmail.com>
Closes #6656 from belisarius222/branch-1.4 and squashes the following commits:
747cbc2 [Ted Blackman] [SPARK-8116][PYSPARK] Allow sc.range() to take a single argument.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f02af7c8
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f02af7c8
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f02af7c8
Branch: refs/heads/branch-1.4
Commit: f02af7c8f7f43e4cfe3c412d2b5ea4128669ce22
Parents: 3ba6fc5
Author: Ted Blackman <te...@gmail.com>
Authored: Thu Jun 4 22:21:11 2015 -0700
Committer: Reynold Xin <rx...@databricks.com>
Committed: Thu Jun 4 22:21:11 2015 -0700
----------------------------------------------------------------------
python/pyspark/context.py | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/f02af7c8/python/pyspark/context.py
----------------------------------------------------------------------
diff --git a/python/pyspark/context.py b/python/pyspark/context.py
index aeb7ad4..44d90f1 100644
--- a/python/pyspark/context.py
+++ b/python/pyspark/context.py
@@ -324,10 +324,12 @@ class SparkContext(object):
with SparkContext._lock:
SparkContext._active_spark_context = None
- def range(self, start, end, step=1, numSlices=None):
+ def range(self, start, end=None, step=1, numSlices=None):
"""
Create a new RDD of int containing elements from `start` to `end`
- (exclusive), increased by `step` every element.
+ (exclusive), increased by `step` every element. Can be called the same
+ way as python's built-in range() function. If called with a single argument,
+ the argument is interpreted as `end`, and `start` is set to 0.
:param start: the start value
:param end: the end value (exclusive)
@@ -335,9 +337,17 @@ class SparkContext(object):
:param numSlices: the number of partitions of the new RDD
:return: An RDD of int
+ >>> sc.range(5).collect()
+ [0, 1, 2, 3, 4]
+ >>> sc.range(2, 4).collect()
+ [2, 3]
>>> sc.range(1, 7, 2).collect()
[1, 3, 5]
"""
+ if end is None:
+ end = start
+ start = 0
+
return self.parallelize(xrange(start, end, step), numSlices)
def parallelize(self, c, numSlices=None):
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org