class
CappedGroupByKeyRDD[K, V] extends AnyRef
Instance Constructors
-
new
CappedGroupByKeyRDD(rdd: RDD[(K, V)])(implicit arg0: ClassTag[K], arg1: ClassTag[V])
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
cappedGroupByKey(maxPerKey: Int): RDD[(K, Vector[V])]
-
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
-
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 AnyRef
Inherited from Any
Wrap an RDD and expose a
cappedGroupByKeymethod, which behaves like org.apache.spark.rdd.PairRDDFunctions.groupByKey but with a cap on the number of values that will be accumulated for each key.Takes the first values for each key, discarding the rest; to obtain a random sampling of the elements for each key, see SampleByKeyRDD.