aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/context.py
diff options
context:
space:
mode:
authorJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-16 19:15:14 -0800
committerJosh Rosen <joshrosen@eecs.berkeley.edu>2013-01-20 13:19:19 -0800
commit7ed1bf4b485131d58ea6728e7247b79320aca9e6 (patch)
tree4c9e91c1c997d328bed7c939fdb69f6e8eed516f /python/pyspark/context.py
parentfe85a075117a79675971aff0cd020bba446c0233 (diff)
downloadspark-7ed1bf4b485131d58ea6728e7247b79320aca9e6.tar.gz
spark-7ed1bf4b485131d58ea6728e7247b79320aca9e6.tar.bz2
spark-7ed1bf4b485131d58ea6728e7247b79320aca9e6.zip
Add RDD checkpointing to Python API.
Diffstat (limited to 'python/pyspark/context.py')
-rw-r--r--python/pyspark/context.py9
1 files changed, 9 insertions, 0 deletions
diff --git a/python/pyspark/context.py b/python/pyspark/context.py
index 1e2f845f9c..a438b43fdc 100644
--- a/python/pyspark/context.py
+++ b/python/pyspark/context.py
@@ -195,3 +195,12 @@ class SparkContext(object):
filename = path.split("/")[-1]
os.environ["PYTHONPATH"] = \
"%s:%s" % (filename, os.environ["PYTHONPATH"])
+
+ def setCheckpointDir(self, dirName, useExisting=False):
+ """
+ Set the directory under which RDDs are going to be checkpointed. This
+ method will create this directory and will throw an exception of the
+ path already exists (to avoid overwriting existing files may be
+ overwritten). The directory will be deleted on exit if indicated.
+ """
+ self._jsc.sc().setCheckpointDir(dirName, useExisting)