trait JavaDStreamLike[T, This <: JavaDStreamLike[T, This, R], R <: JavaRDDLike[T, R]] extends Serializable
- Source
- JavaDStreamLike.scala
- Alphabetic
- By Inheritance
- JavaDStreamLike
- Serializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Abstract Value Members
Concrete Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
checkpoint(interval: Duration): DStream[T]
Enable periodic checkpointing of RDDs of this DStream.
Enable periodic checkpointing of RDDs of this DStream.
- interval
Time interval after which generated RDD will be checkpointed
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
context(): StreamingContext
Return the org.apache.spark.streaming.StreamingContext associated with this DStream
-
def
count(): JavaDStream[Long]
Return a new DStream in which each RDD has a single element generated by counting each RDD of this DStream.
-
def
countByValue(numPartitions: Int): JavaPairDStream[T, Long]
Return a new DStream in which each RDD contains the counts of each distinct value in each RDD of this DStream.
Return a new DStream in which each RDD contains the counts of each distinct value in each RDD of this DStream. Hash partitioning is used to generate the RDDs with
numPartitions
partitions.- numPartitions
number of partitions of each RDD in the new DStream.
-
def
countByValue(): JavaPairDStream[T, Long]
Return a new DStream in which each RDD contains the counts of each distinct value in each RDD of this DStream.
Return a new DStream in which each RDD contains the counts of each distinct value in each RDD of this DStream. Hash partitioning is used to generate the RDDs with Spark's default number of partitions.
-
def
countByValueAndWindow(windowDuration: Duration, slideDuration: Duration, numPartitions: Int): JavaPairDStream[T, Long]
Return a new DStream in which each RDD contains the count of distinct elements in RDDs in a sliding window over this DStream.
Return a new DStream in which each RDD contains the count of distinct elements in RDDs in a sliding window over this DStream. Hash partitioning is used to generate the RDDs with
numPartitions
partitions.- windowDuration
width of the window; must be a multiple of this DStream's batching interval
- slideDuration
sliding interval of the window (i.e., the interval after which the new DStream will generate RDDs); must be a multiple of this DStream's batching interval
- numPartitions
number of partitions of each RDD in the new DStream.
-
def
countByValueAndWindow(windowDuration: Duration, slideDuration: Duration): JavaPairDStream[T, Long]
Return a new DStream in which each RDD contains the count of distinct elements in RDDs in a sliding window over this DStream.
Return a new DStream in which each RDD contains the count of distinct elements in RDDs in a sliding window over this DStream. Hash partitioning is used to generate the RDDs with Spark's default number of partitions.
- windowDuration
width of the window; must be a multiple of this DStream's batching interval
- slideDuration
sliding interval of the window (i.e., the interval after which the new DStream will generate RDDs); must be a multiple of this DStream's batching interval
-
def
countByWindow(windowDuration: Duration, slideDuration: Duration): JavaDStream[Long]
Return a new DStream in which each RDD has a single element generated by counting the number of elements in a window over this DStream.
Return a new DStream in which each RDD has a single element generated by counting the number of elements in a window over this DStream. windowDuration and slideDuration are as defined in the window() operation. This is equivalent to window(windowDuration, slideDuration).count()
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
def
flatMap[U](f: FlatMapFunction[T, U]): JavaDStream[U]
Return a new DStream by applying a function to all elements of this DStream, and then flattening the results
-
def
flatMapToPair[K2, V2](f: PairFlatMapFunction[T, K2, V2]): JavaPairDStream[K2, V2]
Return a new DStream by applying a function to all elements of this DStream, and then flattening the results
-
def
foreachRDD(foreachFunc: VoidFunction2[R, Time]): Unit
Apply a function to each RDD in this DStream.
Apply a function to each RDD in this DStream. This is an output operator, so 'this' DStream will be registered as an output stream and therefore materialized.
-
def
foreachRDD(foreachFunc: VoidFunction[R]): Unit
Apply a function to each RDD in this DStream.
Apply a function to each RDD in this DStream. This is an output operator, so 'this' DStream will be registered as an output stream and therefore materialized.
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
glom(): JavaDStream[List[T]]
Return a new DStream in which each RDD is generated by applying glom() to each RDD of this DStream.
Return a new DStream in which each RDD is generated by applying glom() to each RDD of this DStream. Applying glom() to an RDD coalesces all elements within each partition into an array.
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
def
map[U](f: Function[T, U]): JavaDStream[U]
Return a new DStream by applying a function to all elements of this DStream.
-
def
mapPartitions[U](f: FlatMapFunction[Iterator[T], U]): JavaDStream[U]
Return a new DStream in which each RDD is generated by applying mapPartitions() to each RDDs of this DStream.
Return a new DStream in which each RDD is generated by applying mapPartitions() to each RDDs of this DStream. Applying mapPartitions() to an RDD applies a function to each partition of the RDD.
-
def
mapPartitionsToPair[K2, V2](f: PairFlatMapFunction[Iterator[T], K2, V2]): JavaPairDStream[K2, V2]
Return a new DStream in which each RDD is generated by applying mapPartitions() to each RDDs of this DStream.
Return a new DStream in which each RDD is generated by applying mapPartitions() to each RDDs of this DStream. Applying mapPartitions() to an RDD applies a function to each partition of the RDD.
-
def
mapToPair[K2, V2](f: PairFunction[T, K2, V2]): JavaPairDStream[K2, V2]
Return a new DStream by applying a function to all elements of this DStream.
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
print(num: Int): Unit
Print the first num elements of each RDD generated in this DStream.
Print the first num elements of each RDD generated in this DStream. This is an output operator, so this DStream will be registered as an output stream and there materialized.
-
def
print(): Unit
Print the first ten elements of each RDD generated in this DStream.
Print the first ten elements of each RDD generated in this DStream. This is an output operator, so this DStream will be registered as an output stream and there materialized.
-
def
reduce(f: Function2[T, T, T]): JavaDStream[T]
Return a new DStream in which each RDD has a single element generated by reducing each RDD of this DStream.
-
def
reduceByWindow(reduceFunc: Function2[T, T, T], invReduceFunc: Function2[T, T, T], windowDuration: Duration, slideDuration: Duration): JavaDStream[T]
Return a new DStream in which each RDD has a single element generated by reducing all elements in a sliding window over this DStream.
Return a new DStream in which each RDD has a single element generated by reducing all elements in a sliding window over this DStream. However, the reduction is done incrementally using the old window's reduced value :
- reduce the new values that entered the window (e.g., adding new counts) 2. "inverse reduce" the old values that left the window (e.g., subtracting old counts) This is more efficient than reduceByWindow without "inverse reduce" function. However, it is applicable to only "invertible reduce functions".
- reduceFunc
associative and commutative reduce function
- invReduceFunc
inverse reduce function; such that for all y, invertible x:
invReduceFunc(reduceFunc(x, y), x) = y
- windowDuration
width of the window; must be a multiple of this DStream's batching interval
- slideDuration
sliding interval of the window (i.e., the interval after which the new DStream will generate RDDs); must be a multiple of this DStream's batching interval
-
def
reduceByWindow(reduceFunc: Function2[T, T, T], windowDuration: Duration, slideDuration: Duration): JavaDStream[T]
Return a new DStream in which each RDD has a single element generated by reducing all elements in a sliding window over this DStream.
Return a new DStream in which each RDD has a single element generated by reducing all elements in a sliding window over this DStream.
- reduceFunc
associative and commutative reduce function
- windowDuration
width of the window; must be a multiple of this DStream's batching interval
- slideDuration
sliding interval of the window (i.e., the interval after which the new DStream will generate RDDs); must be a multiple of this DStream's batching interval
- implicit def scalaIntToJavaLong(in: DStream[Long]): JavaDStream[Long]
-
def
slice(fromTime: Time, toTime: Time): List[R]
Return all the RDDs between 'fromDuration' to 'toDuration' (both included)
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
def
transform[U](transformFunc: Function2[R, Time, JavaRDD[U]]): JavaDStream[U]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream.
-
def
transform[U](transformFunc: Function[R, JavaRDD[U]]): JavaDStream[U]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream.
-
def
transformToPair[K2, V2](transformFunc: Function2[R, Time, JavaPairRDD[K2, V2]]): JavaPairDStream[K2, V2]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream.
-
def
transformToPair[K2, V2](transformFunc: Function[R, JavaPairRDD[K2, V2]]): JavaPairDStream[K2, V2]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream.
-
def
transformWith[K2, V2, W](other: JavaPairDStream[K2, V2], transformFunc: Function3[R, JavaPairRDD[K2, V2], Time, JavaRDD[W]]): JavaDStream[W]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream and 'other' DStream.
-
def
transformWith[U, W](other: JavaDStream[U], transformFunc: Function3[R, JavaRDD[U], Time, JavaRDD[W]]): JavaDStream[W]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream and 'other' DStream.
-
def
transformWithToPair[K2, V2, K3, V3](other: JavaPairDStream[K2, V2], transformFunc: Function3[R, JavaPairRDD[K2, V2], Time, JavaPairRDD[K3, V3]]): JavaPairDStream[K3, V3]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream and 'other' DStream.
-
def
transformWithToPair[U, K2, V2](other: JavaDStream[U], transformFunc: Function3[R, JavaRDD[U], Time, JavaPairRDD[K2, V2]]): JavaPairDStream[K2, V2]
Return a new DStream in which each RDD is generated by applying a function on each RDD of 'this' DStream and 'other' DStream.
-
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( ... ) @native()