Module broadcast

source code

>>> from pyspark.context import SparkContext
>>> sc = SparkContext('local', 'test')
>>> b = sc.broadcast([1, 2, 3, 4, 5])
>>> b.value
[1, 2, 3, 4, 5]

>>> from pyspark.broadcast import _broadcastRegistry
>>> _broadcastRegistry[b.bid] = b
>>> from cPickle import dumps, loads
>>> loads(dumps(b)).value
[1, 2, 3, 4, 5]

>>> sc.parallelize([0, 0]).flatMap(lambda x: b.value).collect()
[1, 2, 3, 4, 5, 1, 2, 3, 4, 5]

>>> large_broadcast = sc.broadcast(list(range(10000)))