diff options
-rw-r--r-- | python/pyspark/conf.py | 6 | ||||
-rw-r--r-- | python/pyspark/context.py | 2 | ||||
-rw-r--r-- | python/pyspark/rdd.py | 4 |
3 files changed, 9 insertions, 3 deletions
diff --git a/python/pyspark/conf.py b/python/pyspark/conf.py index b50590ab3b..b4c82f519b 100644 --- a/python/pyspark/conf.py +++ b/python/pyspark/conf.py @@ -100,6 +100,12 @@ class SparkConf(object): self._jconf.set(key, unicode(value)) return self + def setIfMissing(self, key, value): + """Set a configuration property, if not already set.""" + if self.get(key) is None: + self.set(key, value) + return self + def setMaster(self, value): """Set master URL to connect to.""" self._jconf.setMaster(value) diff --git a/python/pyspark/context.py b/python/pyspark/context.py index e21be0e10a..024fb88187 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -101,7 +101,7 @@ class SparkContext(object): else: self.serializer = BatchedSerializer(self._unbatched_serializer, batchSize) - + self._conf.setIfMissing("spark.rdd.compress", "true") # Set any parameters passed directly to us on the conf if master: self._conf.setMaster(master) diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 94ba22306a..a38dd0b923 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -231,10 +231,10 @@ class RDD(object): def cache(self): """ - Persist this RDD with the default storage level (C{MEMORY_ONLY}). + Persist this RDD with the default storage level (C{MEMORY_ONLY_SER}). """ self.is_cached = True - self._jrdd.cache() + self.persist(StorageLevel.MEMORY_ONLY_SER) return self def persist(self, storageLevel): |