def __init__(self, dt_index, rdd, jtsrdd=None, sc=None):
if jtsrdd == None:
# Construct from a Python RDD object and a Python DateTimeIndex
jvm = rdd.ctx._jvm
jrdd = rdd._reserialize(_TimeSeriesSerializer())._jrdd.mapToPair( \
jvm.com.cloudera.sparkts.BytesToKeyAndSeries())
self._jtsrdd = jvm.com.cloudera.sparkts.api.java.JavaTimeSeriesRDDFactory.timeSeriesRDD( \
dt_index._jdt_index, jrdd)
RDD.__init__(self, rdd._jrdd, rdd.ctx)
else:
# Construct from a py4j.JavaObject pointing to a JavaTimeSeriesRDD and a Python SparkContext
jvm = sc._jvm
jrdd = jtsrdd.map( \
jvm.com.cloudera.sparkts.KeyAndSeriesToBytes())
RDD.__init__(self, jrdd, sc, _TimeSeriesSerializer())
self._jtsrdd = jtsrdd
def __init__(self, dt_index, rdd, jtsrdd = None, sc = None):
if jtsrdd == None:
# Construct from a Python RDD object and a Python DateTimeIndex
jvm = rdd.ctx._jvm
jrdd = rdd._reserialize(_TimeSeriesSerializer())._jrdd.map( \
jvm.com.cloudera.sparkts.BytesToKeyAndSeries())
self._jtsrdd = jvm.com.cloudera.sparkts.TimeSeriesRDD( \
dt_index._jdt_index, jrdd.rdd())
RDD.__init__(self, rdd._jrdd, rdd.ctx)
else:
# Construct from a py4j.JavaObject pointing to a TimeSeriesRDD and a Python SparkContext
jvm = sc._jvm
jrdd = jvm.org.apache.spark.api.java.JavaRDD(jtsrdd, None).map( \
jvm.com.cloudera.sparkts.KeyAndSeriesToBytes())
RDD.__init__(self, jrdd, sc, _TimeSeriesSerializer())
self._jtsrdd = jtsrdd
def __init__(self, rdd, file_type='CSV', t_rdd=None, sc=None):
if rdd is not None:
jvm = rdd.ctx._jvm
java_import(jvm, ClassNames.BYTES_TO_STRING)
java_import(jvm, ClassNames.TRANSFORMABLE_RDD)
self.__set_file_type(jvm, file_type)
self.spark_context = rdd.ctx
java_rdd = rdd._reserialize(BuddySerializer())._jrdd.map(jvm.BytesToString())
self._transformable_rdd = jvm.JavaTransformableRDD(java_rdd, self.__file_type)
RDD.__init__(self, rdd._jrdd, rdd.ctx)
else:
jvm = sc._jvm
java_import(jvm, ClassNames.STRING_TO_BYTES)
self.spark_context = sc
self.__set_file_type(jvm, file_type)
self._transformable_rdd = t_rdd
rdd = t_rdd.map(jvm.StringToBytes())
RDD.__init__(self, rdd, sc, BuddySerializer())
def __init__(self, rdd, file_type='CSV', t_rdd=None, sc=None):
if rdd is not None:
jvm = rdd.ctx._jvm
java_import(jvm, ClassNames.BYTES_TO_STRING)
java_import(jvm, ClassNames.TRANSFORMABLE_RDD)
self.__set_file_type(jvm, file_type)
self.spark_context = rdd.ctx
java_rdd = rdd._reserialize(BuddySerializer())._jrdd.map(
jvm.BytesToString())
self._transformable_rdd = jvm.JavaTransformableRDD(
java_rdd, self.__file_type)
RDD.__init__(self, rdd._jrdd, rdd.ctx)
else:
jvm = sc._jvm
java_import(jvm, ClassNames.STRING_TO_BYTES)
self.spark_context = sc
self.__set_file_type(jvm, file_type)
self._transformable_rdd = t_rdd
rdd = t_rdd.map(jvm.StringToBytes())
RDD.__init__(self, rdd, sc, BuddySerializer())
