aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/rdd.py
diff options
context:
space:
mode:
authorPrashant Sharma <scrapcodes@gmail.com>2013-09-15 10:55:12 +0530
committerPrashant Sharma <scrapcodes@gmail.com>2013-09-15 10:55:12 +0530
commit383e151fd7138cc6a143b3a38037cc3038c2a8b9 (patch)
tree0dbb2c0d8fdeff4c37a577eb96acb87ee7838a16 /python/pyspark/rdd.py
parent20c65bc334091d8d05fb680551155aa182d98f7d (diff)
parentc4c1db2dd5b2ec0a8182369ecdb0e14f4e199822 (diff)
downloadspark-383e151fd7138cc6a143b3a38037cc3038c2a8b9.tar.gz
spark-383e151fd7138cc6a143b3a38037cc3038c2a8b9.tar.bz2
spark-383e151fd7138cc6a143b3a38037cc3038c2a8b9.zip
Merge branch 'master' of git://github.com/mesos/spark into scala-2.10
Conflicts: core/src/main/scala/org/apache/spark/SparkContext.scala project/SparkBuild.scala
Diffstat (limited to 'python/pyspark/rdd.py')
-rw-r--r--python/pyspark/rdd.py19
1 files changed, 19 insertions, 0 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
index 1831435b33..7611b13e82 100644
--- a/python/pyspark/rdd.py
+++ b/python/pyspark/rdd.py
@@ -70,6 +70,25 @@ class RDD(object):
self._jrdd.cache()
return self
+ def persist(self, storageLevel):
+ """
+ Set this RDD's storage level to persist its values across operations after the first time
+ it is computed. This can only be used to assign a new storage level if the RDD does not
+ have a storage level set yet.
+ """
+ self.is_cached = True
+ javaStorageLevel = self.ctx._getJavaStorageLevel(storageLevel)
+ self._jrdd.persist(javaStorageLevel)
+ return self
+
+ def unpersist(self):
+ """
+ Mark the RDD as non-persistent, and remove all blocks for it from memory and disk.
+ """
+ self.is_cached = False
+ self._jrdd.unpersist()
+ return self
+
def checkpoint(self):
"""
Mark this RDD for checkpointing. It will be saved to a file inside the