[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 <[email protected]> Closes apache#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
vrilleup · Jun 17, 2014 · d81c08b · d81c08b
1 parent 7afa912
commit d81c08b
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 0 deletions.
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py
@@ -1448,9 +1448,12 @@ def toDebugString(self):
     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(),

diff --git a/python/pyspark/storagelevel.py b/python/pyspark/storagelevel.py
@@ -36,6 +36,15 @@ def __repr__(self):
         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)