Repository: spark Updated Branches: refs/heads/master 7afa912e7 -> d81c08bac
[SPARK-2130] End-user friendly String repr for StorageLevel in Python JIRA issue https://issues.apache.org/jira/browse/SPARK-2130 This PR adds an end-user friendly String representation for StorageLevel in Python, similar to ```StorageLevel.description``` in Scala. ``` >>> rdd = sc.parallelize([1,2]) >>> storage_level = rdd.getStorageLevel() >>> storage_level StorageLevel(False, False, False, False, 1) >>> print(storage_level) Serialized 1x Replicated ``` Author: Kan Zhang <kzh...@apache.org> Closes #1096 from kanzhang/SPARK-2130 and squashes the following commits: 7c8b98b [Kan Zhang] [SPARK-2130] Prettier epydoc output cc5bf45 [Kan Zhang] [SPARK-2130] End-user friendly String representation for StorageLevel in Python Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/d81c08ba Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/d81c08ba Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/d81c08ba Branch: refs/heads/master Commit: d81c08bac9756045865ed6490252fbb3f7591142 Parents: 7afa912 Author: Kan Zhang <kzh...@apache.org> Authored: Mon Jun 16 23:31:31 2014 -0700 Committer: Patrick Wendell <pwend...@gmail.com> Committed: Mon Jun 16 23:31:31 2014 -0700 ---------------------------------------------------------------------- python/pyspark/rdd.py | 3 +++ python/pyspark/storagelevel.py | 9 +++++++++ 2 files changed, 12 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/d81c08ba/python/pyspark/rdd.py ---------------------------------------------------------------------- diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index ddd2285..bb4d035 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -1448,9 +1448,12 @@ class RDD(object): def getStorageLevel(self): """ Get the RDD's current storage level. + >>> rdd1 = sc.parallelize([1,2]) >>> rdd1.getStorageLevel() StorageLevel(False, False, False, False, 1) + >>> print(rdd1.getStorageLevel()) + Serialized 1x Replicated """ java_storage_level = self._jrdd.getStorageLevel() storage_level = StorageLevel(java_storage_level.useDisk(), http://git-wip-us.apache.org/repos/asf/spark/blob/d81c08ba/python/pyspark/storagelevel.py ---------------------------------------------------------------------- diff --git a/python/pyspark/storagelevel.py b/python/pyspark/storagelevel.py index 7b6660e..3a18ea5 100644 --- a/python/pyspark/storagelevel.py +++ b/python/pyspark/storagelevel.py @@ -36,6 +36,15 @@ class StorageLevel: return "StorageLevel(%s, %s, %s, %s, %s)" % ( self.useDisk, self.useMemory, self.useOffHeap, self.deserialized, self.replication) + def __str__(self): + result = "" + result += "Disk " if self.useDisk else "" + result += "Memory " if self.useMemory else "" + result += "Tachyon " if self.useOffHeap else "" + result += "Deserialized " if self.deserialized else "Serialized " + result += "%sx Replicated" % self.replication + return result + StorageLevel.DISK_ONLY = StorageLevel(True, False, False, False) StorageLevel.DISK_ONLY_2 = StorageLevel(True, False, False, False, 2) StorageLevel.MEMORY_ONLY = StorageLevel(False, True, False, True)
