Class

com.soundcloud.lsh

SlidingRDD

Related Doc: package lsh

Permalink

class SlidingRDD[T] extends RDD[Array[T]]

Represents an RDD from grouping items of its parent RDD in fixed size blocks by passing a sliding window over them. The ordering is first based on the partition index and then the ordering of items within each partition. This is similar to sliding in Scala collections, except that it becomes an empty RDD if the window size is greater than the total number of items. It needs to trigger a Spark job if the parent RDD has more than one partitions. To make this operation efficient, the number of items per partition should be larger than the window size and the window size should be small, e.g., 2.

See also

Int)*

Int)*

Linear Supertypes
RDD[Array[T]], Logging, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. SlidingRDD
  2. RDD
  3. Logging
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new SlidingRDD(parent: RDD[T], windowSize: Int, step: Int)(implicit arg0: ClassTag[T])

    Permalink

    parent

    the parent RDD

    windowSize

    the window size, must be greater than 1

    step

    step size for windows

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  3. def ++(other: RDD[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  4. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  5. def aggregate[U](zeroValue: U)(seqOp: (U, Array[T]) ⇒ U, combOp: (U, U) ⇒ U)(implicit arg0: ClassTag[U]): U

    Permalink
    Definition Classes
    RDD
  6. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  7. def cache(): SlidingRDD.this.type

    Permalink
    Definition Classes
    RDD
  8. def cartesian[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(Array[T], U)]

    Permalink
    Definition Classes
    RDD
  9. def checkpoint(): Unit

    Permalink
    Definition Classes
    RDD
  10. def clearDependencies(): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    RDD
  11. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  12. def coalesce(numPartitions: Int, shuffle: Boolean, partitionCoalescer: Option[PartitionCoalescer])(implicit ord: Ordering[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  13. def collect[U](f: PartialFunction[Array[T], U])(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD
  14. def collect(): Array[Array[T]]

    Permalink
    Definition Classes
    RDD
  15. def compute(split: Partition, context: TaskContext): Iterator[Array[T]]

    Permalink
    Definition Classes
    SlidingRDD → RDD
  16. def context: SparkContext

    Permalink
    Definition Classes
    RDD
  17. def count(): Long

    Permalink
    Definition Classes
    RDD
  18. def countApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble]

    Permalink
    Definition Classes
    RDD
  19. def countApproxDistinct(relativeSD: Double): Long

    Permalink
    Definition Classes
    RDD
  20. def countApproxDistinct(p: Int, sp: Int): Long

    Permalink
    Definition Classes
    RDD
  21. def countByValue()(implicit ord: Ordering[Array[T]]): Map[Array[T], Long]

    Permalink
    Definition Classes
    RDD
  22. def countByValueApprox(timeout: Long, confidence: Double)(implicit ord: Ordering[Array[T]]): PartialResult[Map[Array[T], BoundedDouble]]

    Permalink
    Definition Classes
    RDD
  23. final def dependencies: Seq[Dependency[_]]

    Permalink
    Definition Classes
    RDD
  24. def distinct(): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  25. def distinct(numPartitions: Int)(implicit ord: Ordering[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  26. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  27. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  28. def filter(f: (Array[T]) ⇒ Boolean): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  29. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  30. def first(): Array[T]

    Permalink
    Definition Classes
    RDD
  31. def firstParent[U](implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Attributes
    protected[org.apache.spark]
    Definition Classes
    RDD
  32. def flatMap[U](f: (Array[T]) ⇒ TraversableOnce[U])(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD
  33. def fold(zeroValue: Array[T])(op: (Array[T], Array[T]) ⇒ Array[T]): Array[T]

    Permalink
    Definition Classes
    RDD
  34. def foreach(f: (Array[T]) ⇒ Unit): Unit

    Permalink
    Definition Classes
    RDD
  35. def foreachPartition(f: (Iterator[Array[T]]) ⇒ Unit): Unit

    Permalink
    Definition Classes
    RDD
  36. def getCheckpointFile: Option[String]

    Permalink
    Definition Classes
    RDD
  37. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  38. def getDependencies: Seq[Dependency[_]]

    Permalink
    Attributes
    protected
    Definition Classes
    RDD
  39. final def getNumPartitions: Int

    Permalink
    Definition Classes
    RDD
    Annotations
    @Since( "1.6.0" )
  40. def getPartitions: Array[Partition]

    Permalink
    Definition Classes
    SlidingRDD → RDD
  41. def getPreferredLocations(split: Partition): Seq[String]

    Permalink
    Definition Classes
    SlidingRDD → RDD
  42. def getStorageLevel: StorageLevel

    Permalink
    Definition Classes
    RDD
  43. def glom(): RDD[Array[Array[T]]]

    Permalink
    Definition Classes
    RDD
  44. def groupBy[K](f: (Array[T]) ⇒ K, p: Partitioner)(implicit kt: ClassTag[K], ord: Ordering[K]): RDD[(K, Iterable[Array[T]])]

    Permalink
    Definition Classes
    RDD
  45. def groupBy[K](f: (Array[T]) ⇒ K, numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[Array[T]])]

    Permalink
    Definition Classes
    RDD
  46. def groupBy[K](f: (Array[T]) ⇒ K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[Array[T]])]

    Permalink
    Definition Classes
    RDD
  47. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  48. val id: Int

    Permalink
    Definition Classes
    RDD
  49. def initializeLogIfNecessary(isInterpreter: Boolean): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  50. def intersection(other: RDD[Array[T]], numPartitions: Int): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  51. def intersection(other: RDD[Array[T]], partitioner: Partitioner)(implicit ord: Ordering[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  52. def intersection(other: RDD[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  53. def isCheckpointed: Boolean

    Permalink
    Definition Classes
    RDD
  54. def isEmpty(): Boolean

    Permalink
    Definition Classes
    RDD
  55. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  56. def isTraceEnabled(): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  57. final def iterator(split: Partition, context: TaskContext): Iterator[Array[T]]

    Permalink
    Definition Classes
    RDD
  58. def keyBy[K](f: (Array[T]) ⇒ K): RDD[(K, Array[T])]

    Permalink
    Definition Classes
    RDD
  59. def localCheckpoint(): SlidingRDD.this.type

    Permalink
    Definition Classes
    RDD
  60. def log: Logger

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  61. def logDebug(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  62. def logDebug(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  63. def logError(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  64. def logError(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  65. def logInfo(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  66. def logInfo(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  67. def logName: String

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  68. def logTrace(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  69. def logTrace(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  70. def logWarning(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  71. def logWarning(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  72. def map[U](f: (Array[T]) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD
  73. def mapPartitions[U](f: (Iterator[Array[T]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD
  74. def mapPartitionsWithIndex[U](f: (Int, Iterator[Array[T]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD
  75. def max()(implicit ord: Ordering[Array[T]]): Array[T]

    Permalink
    Definition Classes
    RDD
  76. def min()(implicit ord: Ordering[Array[T]]): Array[T]

    Permalink
    Definition Classes
    RDD
  77. var name: String

    Permalink
    Definition Classes
    RDD
  78. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  79. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  80. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  81. def parent[U](j: Int)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Attributes
    protected[org.apache.spark]
    Definition Classes
    RDD
  82. val parent: RDD[T]

    Permalink

    the parent RDD

  83. val partitioner: Option[Partitioner]

    Permalink
    Definition Classes
    RDD
  84. final def partitions: Array[Partition]

    Permalink
    Definition Classes
    RDD
  85. def persist(): SlidingRDD.this.type

    Permalink
    Definition Classes
    RDD
  86. def persist(newLevel: StorageLevel): SlidingRDD.this.type

    Permalink
    Definition Classes
    RDD
  87. def pipe(command: Seq[String], env: Map[String, String], printPipeContext: ((String) ⇒ Unit) ⇒ Unit, printRDDElement: (Array[T], (String) ⇒ Unit) ⇒ Unit, separateWorkingDir: Boolean, bufferSize: Int, encoding: String): RDD[String]

    Permalink
    Definition Classes
    RDD
  88. def pipe(command: String, env: Map[String, String]): RDD[String]

    Permalink
    Definition Classes
    RDD
  89. def pipe(command: String): RDD[String]

    Permalink
    Definition Classes
    RDD
  90. final def preferredLocations(split: Partition): Seq[String]

    Permalink
    Definition Classes
    RDD
  91. def randomSplit(weights: Array[Double], seed: Long): Array[RDD[Array[T]]]

    Permalink
    Definition Classes
    RDD
  92. def reduce(f: (Array[T], Array[T]) ⇒ Array[T]): Array[T]

    Permalink
    Definition Classes
    RDD
  93. def repartition(numPartitions: Int)(implicit ord: Ordering[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  94. def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  95. def saveAsObjectFile(path: String): Unit

    Permalink
    Definition Classes
    RDD
  96. def saveAsTextFile(path: String, codec: Class[_ <: CompressionCodec]): Unit

    Permalink
    Definition Classes
    RDD
  97. def saveAsTextFile(path: String): Unit

    Permalink
    Definition Classes
    RDD
  98. def setName(_name: String): SlidingRDD.this.type

    Permalink
    Definition Classes
    RDD
  99. def sortBy[K](f: (Array[T]) ⇒ K, ascending: Boolean, numPartitions: Int)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  100. def sparkContext: SparkContext

    Permalink
    Definition Classes
    RDD
  101. val step: Int

    Permalink

    step size for windows

  102. def subtract(other: RDD[Array[T]], p: Partitioner)(implicit ord: Ordering[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  103. def subtract(other: RDD[Array[T]], numPartitions: Int): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  104. def subtract(other: RDD[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  105. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  106. def take(num: Int): Array[Array[T]]

    Permalink
    Definition Classes
    RDD
  107. def takeOrdered(num: Int)(implicit ord: Ordering[Array[T]]): Array[Array[T]]

    Permalink
    Definition Classes
    RDD
  108. def takeSample(withReplacement: Boolean, num: Int, seed: Long): Array[Array[T]]

    Permalink
    Definition Classes
    RDD
  109. def toDebugString: String

    Permalink
    Definition Classes
    RDD
  110. def toJavaRDD(): JavaRDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  111. def toLocalIterator: Iterator[Array[T]]

    Permalink
    Definition Classes
    RDD
  112. def toString(): String

    Permalink
    Definition Classes
    RDD → AnyRef → Any
  113. def top(num: Int)(implicit ord: Ordering[Array[T]]): Array[Array[T]]

    Permalink
    Definition Classes
    RDD
  114. def treeAggregate[U](zeroValue: U)(seqOp: (U, Array[T]) ⇒ U, combOp: (U, U) ⇒ U, depth: Int)(implicit arg0: ClassTag[U]): U

    Permalink
    Definition Classes
    RDD
  115. def treeReduce(f: (Array[T], Array[T]) ⇒ Array[T], depth: Int): Array[T]

    Permalink
    Definition Classes
    RDD
  116. def union(other: RDD[Array[T]]): RDD[Array[T]]

    Permalink
    Definition Classes
    RDD
  117. def unpersist(blocking: Boolean): SlidingRDD.this.type

    Permalink
    Definition Classes
    RDD
  118. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  121. val windowSize: Int

    Permalink

    the window size, must be greater than 1

  122. def zip[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(Array[T], U)]

    Permalink
    Definition Classes
    RDD
  123. def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D])(f: (Iterator[Array[T]], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD
  124. def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D], preservesPartitioning: Boolean)(f: (Iterator[Array[T]], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD
  125. def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C])(f: (Iterator[Array[T]], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD
  126. def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C], preservesPartitioning: Boolean)(f: (Iterator[Array[T]], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD
  127. def zipPartitions[B, V](rdd2: RDD[B])(f: (Iterator[Array[T]], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD
  128. def zipPartitions[B, V](rdd2: RDD[B], preservesPartitioning: Boolean)(f: (Iterator[Array[T]], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD
  129. def zipWithIndex(): RDD[(Array[T], Long)]

    Permalink
    Definition Classes
    RDD
  130. def zipWithUniqueId(): RDD[(Array[T], Long)]

    Permalink
    Definition Classes
    RDD

Inherited from RDD[Array[T]]

Inherited from Logging

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped