aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/context.py
diff options
context:
space:
mode:
authorJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-20 13:59:45 -0800
committerJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-20 13:59:45 -0800
commitd0ba80dc727d00b2b7627dcefd2c77009af55f7d (patch)
treeeadf5f88feb468179527459a1f7316b3ca5ac2cf /python/pyspark/context.py
parent7ed1bf4b485131d58ea6728e7247b79320aca9e6 (diff)
downloadspark-d0ba80dc727d00b2b7627dcefd2c77009af55f7d.tar.gz
spark-d0ba80dc727d00b2b7627dcefd2c77009af55f7d.tar.bz2
spark-d0ba80dc727d00b2b7627dcefd2c77009af55f7d.zip
Add checkpointFile() and more tests to PySpark.
Diffstat (limited to 'python/pyspark/context.py')
-rw-r--r--python/pyspark/context.py6
1 files changed, 5 insertions, 1 deletions
diff --git a/python/pyspark/context.py b/python/pyspark/context.py
index a438b43fdc..8beb8e2ae9 100644
--- a/python/pyspark/context.py
+++ b/python/pyspark/context.py
@@ -123,6 +123,10 @@ class SparkContext(object):
jrdd = self._jsc.textFile(name, minSplits)
return RDD(jrdd, self)
+ def _checkpointFile(self, name):
+ jrdd = self._jsc.checkpointFile(name)
+ return RDD(jrdd, self)
+
def union(self, rdds):
"""
Build the union of a list of RDDs.
@@ -145,7 +149,7 @@ class SparkContext(object):
def accumulator(self, value, accum_param=None):
"""
Create an C{Accumulator} with the given initial value, using a given
- AccumulatorParam helper object to define how to add values of the data
+ AccumulatorParam helper object to define how to add values of the data
type if provided. Default AccumulatorParams are used for integers and
floating-point numbers if you do not provide one. For other types, the
AccumulatorParam must implement two methods: