"""
A Resilient Distributed Dataset (RDD), the basic abstraction in Spark.
Represents an immutable, partitioned collection of elements that can be
operated on in parallel.
"""

def __init__(self, jrdd, ctx, jrdd_deserializer=AutoBatchedSerializer(PickleSerializer())):
    self._jrdd = jrdd
    self.is_cached = False
    self.is_checkpointed = False
    self.ctx = ctx
    self._jrdd_deserializer = jrdd_deserializer
    self._id = jrdd.id()
    self.partitioner = None