DistributedDataSet

abstract def data(train: Boolean): RDD[T]

Get a sequence of data

abstract def originRDD(): RDD[_]

Get the 'origin' RDD of the dataset.

abstract def shuffle(): Unit

Change the order of the data sequence from the data set

abstract def size(): Long

Total size of the data set

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

def ->[C](transformer: Transformer[T, C])(implicit arg0: ClassTag[C]): DataSet[C]

Helper function to transform the data type in the data set.

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def cache(): Unit

Trigger the computation of this dataset and cache it in memory.

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

var isCached: Boolean

Check if rdd is cached.

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

final def synchronized[T0](arg0: ⇒ T0): T0

def toDistributed(): DistributedDataSet[T]

Convert current DataSet to a distributed DataSet, in which we use a RDD to represent the data sequence.

def toLocal(): LocalDataSet[T]

Convert current DataSet to a local DataSet, in which we use an iterator to represent the data sequence.

def toString(): String

def transform[C](transformer: Transformer[T, C])(implicit arg0: ClassTag[C]): DataSet[C]

Helper function to transform the data type in the data set.

def unpersist(): Unit

Unpersist rdd.

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit