PDataSource

Base class of a parallel data source.

A parallel data source runs locally within a single machine, or in parallel on a cluster, to return data that is distributed across a cluster.

TD: Training data class.
EI: Evalution Info class.
Q: Input query class.
A: Actual value class.

Linear Supertypes

BaseDataSource[TD, EI, Q, A], AbstractDoer, Serializable, Serializable, AnyRef, Any

Instance Constructors

new PDataSource()

Value Members

final def !=(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def !=(arg0: Any): Boolean

Definition Classes
Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def ==(arg0: Any): Boolean

Definition Classes
Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def read(sc: SparkContext): Seq[(TD, EI, RDD[(Q, A)])]

Implement this method to return data from a data source.
Implement this method to return data from a data source. Returned data can optionally include a sequence of query and actual value pairs for evaluation purpose.
def readBase(sc: SparkContext): Seq[(TD, EI, RDD[(Q, A)])]

Definition Classes
PDataSource → BaseDataSource
def readTest(sc: SparkContext): (EI, RDD[(Q, A)])

Implement this method to return one set of test data ( a sequence of query and actual value pairs) from a data source.
Implement this method to return one set of test data ( a sequence of query and actual value pairs) from a data source. Should also implement readTraining to return correponding training data.
def readTraining(sc: SparkContext): TD

Implement this method to only return training data from a data source.
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

abstract class PDataSource[TD, EI, Q, A] extends BaseDataSource[TD, EI, Q, A]

Instance Constructors

new PDataSource()

Value Members

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def read(sc: SparkContext): Seq[(TD, EI, RDD[(Q, A)])]

def readBase(sc: SparkContext): Seq[(TD, EI, RDD[(Q, A)])]

def readTest(sc: SparkContext): (EI, RDD[(Q, A)])

def readTraining(sc: SparkContext): TD

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

def toString(): String

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from BaseDataSource[TD, EI, Q, A]

Inherited from AbstractDoer

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped