Class/Object

com.datastax.spark.connector.rdd

CassandraCoGroupedRDD

Related Docs: object CassandraCoGroupedRDD | package rdd

Permalink

class CassandraCoGroupedRDD[T] extends RDD[Seq[Seq[T]]]

A RDD which pulls from provided separate CassandraTableScanRDDs which share partition keys type and keyspaces. These tables will be joined on READ using a merge iterator. As long as we join on the token of the partition key the two iterators should be read in order. Note: this implementation do not restrict partition keys has the same names, but they should have the same types

Linear Supertypes
RDD[Seq[Seq[T]]], Logging, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. CassandraCoGroupedRDD
  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 CassandraCoGroupedRDD(sc: SparkContext, scanRDDs: Seq[CassandraTableScanRDD[T]])(implicit classTag: ClassTag[T])

    Permalink

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[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  4. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  5. def aggregate[U](zeroValue: U)(seqOp: (U, Seq[Seq[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 barrier(): RDDBarrier[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD
    Annotations
    @Experimental() @Since( "2.4.0" )

  8. def cache(): CassandraCoGroupedRDD.this.type

    Permalink
    Definition Classes
    RDD

  9. def cartesian[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(Seq[Seq[T]], U)]

    Permalink
    Definition Classes
    RDD

  10. def checkValidMergeJoin(): Unit

    Permalink
    Attributes
    protected

  11. def checkpoint(): Unit

    Permalink
    Definition Classes
    RDD

  12. def clearDependencies(): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    RDD

  13. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  14. def coalesce(numPartitions: Int, shuffle: Boolean, partitionCoalescer: Option[PartitionCoalescer])(implicit ord: Ordering[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  15. def collect[U](f: PartialFunction[Seq[Seq[T]], U])(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD

  16. def collect(): Array[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  17. def compute(split: Partition, context: TaskContext): Iterator[Seq[Seq[T]]]

    Permalink
    Definition Classes
    CassandraCoGroupedRDD → RDD
    Annotations
    @DeveloperApi()

  18. lazy val connector: CassandraConnector

    Permalink

  19. def context: SparkContext

    Permalink
    Definition Classes
    RDD

  20. def count(): Long

    Permalink
    Definition Classes
    RDD

  21. def countApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble]

    Permalink
    Definition Classes
    RDD

  22. def countApproxDistinct(relativeSD: Double): Long

    Permalink
    Definition Classes
    RDD

  23. def countApproxDistinct(p: Int, sp: Int): Long

    Permalink
    Definition Classes
    RDD

  24. def countByValue()(implicit ord: Ordering[Seq[Seq[T]]]): Map[Seq[Seq[T]], Long]

    Permalink
    Definition Classes
    RDD

  25. def countByValueApprox(timeout: Long, confidence: Double)(implicit ord: Ordering[Seq[Seq[T]]]): PartialResult[Map[Seq[Seq[T]], BoundedDouble]]

    Permalink
    Definition Classes
    RDD

  26. final def dependencies: Seq[Dependency[_]]

    Permalink
    Definition Classes
    RDD

  27. def distinct(): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  28. def distinct(numPartitions: Int)(implicit ord: Ordering[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  29. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  30. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  31. def filter(f: (Seq[Seq[T]]) ⇒ Boolean): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  32. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  33. def first(): Seq[Seq[T]]

    Permalink
    Definition Classes
    RDD

  34. def firstParent[U](implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Attributes
    protected[org.apache.spark]
    Definition Classes
    RDD

  35. def flatMap[U](f: (Seq[Seq[T]]) ⇒ TraversableOnce[U])(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD

  36. def fold(zeroValue: Seq[Seq[T]])(op: (Seq[Seq[T]], Seq[Seq[T]]) ⇒ Seq[Seq[T]]): Seq[Seq[T]]

    Permalink
    Definition Classes
    RDD

  37. def foreach(f: (Seq[Seq[T]]) ⇒ Unit): Unit

    Permalink
    Definition Classes
    RDD

  38. def foreachPartition(f: (Iterator[Seq[Seq[T]]]) ⇒ Unit): Unit

    Permalink
    Definition Classes
    RDD

  39. def getCheckpointFile: Option[String]

    Permalink
    Definition Classes
    RDD

  40. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any

  41. def getDependencies: Seq[Dependency[_]]

    Permalink
    Attributes
    protected
    Definition Classes
    RDD

  42. final def getNumPartitions: Int

    Permalink
    Definition Classes
    RDD
    Annotations
    @Since( "1.6.0" )

  43. def getOutputDeterministicLevel: org.apache.spark.rdd.DeterministicLevel.Value

    Permalink
    Attributes
    protected
    Definition Classes
    RDD
    Annotations
    @DeveloperApi()

  44. def getPartitionKey(connector: CassandraConnector, keyspaceName: String, tableName: String): Seq[ColumnDef]

    Permalink

  45. def getPartitions: Array[Partition]

    Permalink
    Attributes
    protected
    Definition Classes
    CassandraCoGroupedRDD → RDD

  46. def getPreferredLocations(split: Partition): Seq[String]

    Permalink
    Definition Classes
    CassandraCoGroupedRDD → RDD

  47. def getStorageLevel: StorageLevel

    Permalink
    Definition Classes
    RDD

  48. def glom(): RDD[Array[Seq[Seq[T]]]]

    Permalink
    Definition Classes
    RDD

  49. def groupBy[K](f: (Seq[Seq[T]]) ⇒ K, p: Partitioner)(implicit kt: ClassTag[K], ord: Ordering[K]): RDD[(K, Iterable[Seq[Seq[T]]])]

    Permalink
    Definition Classes
    RDD

  50. def groupBy[K](f: (Seq[Seq[T]]) ⇒ K, numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[Seq[Seq[T]]])]

    Permalink
    Definition Classes
    RDD

  51. def groupBy[K](f: (Seq[Seq[T]]) ⇒ K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[Seq[Seq[T]]])]

    Permalink
    Definition Classes
    RDD

  52. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  53. val id: Int

    Permalink
    Definition Classes
    RDD

  54. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  55. def initializeLogIfNecessary(isInterpreter: Boolean): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  56. def intersection(other: RDD[Seq[Seq[T]]], numPartitions: Int): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  57. def intersection(other: RDD[Seq[Seq[T]]], partitioner: Partitioner)(implicit ord: Ordering[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  58. def intersection(other: RDD[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  59. lazy val isBarrier_: Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    RDD

  60. def isCheckpointed: Boolean

    Permalink
    Definition Classes
    RDD

  61. def isEmpty(): Boolean

    Permalink
    Definition Classes
    RDD

  62. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  63. def isTraceEnabled(): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  64. def isValidMergeJoin(): Boolean

    Permalink

  65. final def iterator(split: Partition, context: TaskContext): Iterator[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  66. def keyBy[K](f: (Seq[Seq[T]]) ⇒ K): RDD[(K, Seq[Seq[T]])]

    Permalink
    Definition Classes
    RDD

  67. def localCheckpoint(): CassandraCoGroupedRDD.this.type

    Permalink
    Definition Classes
    RDD

  68. def log: Logger

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  69. def logDebug(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  70. def logDebug(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  71. def logError(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  72. def logError(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  73. def logInfo(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  74. def logInfo(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  75. def logName: String

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  76. def logTrace(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  77. def logTrace(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  78. def logWarning(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  79. def logWarning(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  80. def map[U](f: (Seq[Seq[T]]) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD

  81. def mapPartitions[U](f: (Iterator[Seq[Seq[T]]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD

  82. def mapPartitionsWithIndex[U](f: (Int, Iterator[Seq[Seq[T]]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Definition Classes
    RDD

  83. def max()(implicit ord: Ordering[Seq[Seq[T]]]): Seq[Seq[T]]

    Permalink
    Definition Classes
    RDD

  84. def min()(implicit ord: Ordering[Seq[Seq[T]]]): Seq[Seq[T]]

    Permalink
    Definition Classes
    RDD

  85. var name: String

    Permalink
    Definition Classes
    RDD

  86. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  87. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  88. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  89. def parent[U](j: Int)(implicit arg0: ClassTag[U]): RDD[U]

    Permalink
    Attributes
    protected[org.apache.spark]
    Definition Classes
    RDD

  90. val partitioner: Option[Partitioner]

    Permalink
    Definition Classes
    RDD

  91. final def partitions: Array[Partition]

    Permalink
    Definition Classes
    RDD

  92. def persist(): CassandraCoGroupedRDD.this.type

    Permalink
    Definition Classes
    RDD

  93. def persist(newLevel: StorageLevel): CassandraCoGroupedRDD.this.type

    Permalink
    Definition Classes
    RDD

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

    Permalink
    Definition Classes
    RDD

  95. def pipe(command: String, env: Map[String, String]): RDD[String]

    Permalink
    Definition Classes
    RDD

  96. def pipe(command: String): RDD[String]

    Permalink
    Definition Classes
    RDD

  97. final def preferredLocations(split: Partition): Seq[String]

    Permalink
    Definition Classes
    RDD

  98. def randomSplit(weights: Array[Double], seed: Long): Array[RDD[Seq[Seq[T]]]]

    Permalink
    Definition Classes
    RDD

  99. def reduce(f: (Seq[Seq[T]], Seq[Seq[T]]) ⇒ Seq[Seq[T]]): Seq[Seq[T]]

    Permalink
    Definition Classes
    RDD

  100. def repartition(numPartitions: Int)(implicit ord: Ordering[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  101. def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  102. def saveAsObjectFile(path: String): Unit

    Permalink
    Definition Classes
    RDD

  103. def saveAsTextFile(path: String, codec: Class[_ <: CompressionCodec]): Unit

    Permalink
    Definition Classes
    RDD

  104. def saveAsTextFile(path: String): Unit

    Permalink
    Definition Classes
    RDD

  105. def setName(_name: String): CassandraCoGroupedRDD.this.type

    Permalink
    Definition Classes
    RDD

  106. def sortBy[K](f: (Seq[Seq[T]]) ⇒ K, ascending: Boolean, numPartitions: Int)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  107. def sparkContext: SparkContext

    Permalink
    Definition Classes
    RDD

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

    Permalink
    Definition Classes
    RDD

  109. def subtract(other: RDD[Seq[Seq[T]]], numPartitions: Int): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  110. def subtract(other: RDD[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

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

    Permalink
    Definition Classes
    AnyRef

  112. def take(num: Int): Array[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  113. def takeOrdered(num: Int)(implicit ord: Ordering[Seq[Seq[T]]]): Array[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  114. def takeSample(withReplacement: Boolean, num: Int, seed: Long): Array[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  115. def toDebugString: String

    Permalink
    Definition Classes
    RDD

  116. def toJavaRDD(): JavaRDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  117. def toLocalIterator: Iterator[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  118. def toString(): String

    Permalink
    Definition Classes
    RDD → AnyRef → Any

  119. def tokenExtractor(row: Row): Token

    Permalink

  120. def top(num: Int)(implicit ord: Ordering[Seq[Seq[T]]]): Array[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  121. def treeAggregate[U](zeroValue: U)(seqOp: (U, Seq[Seq[T]]) ⇒ U, combOp: (U, U) ⇒ U, depth: Int)(implicit arg0: ClassTag[U]): U

    Permalink
    Definition Classes
    RDD

  122. def treeReduce(f: (Seq[Seq[T]], Seq[Seq[T]]) ⇒ Seq[Seq[T]], depth: Int): Seq[Seq[T]]

    Permalink
    Definition Classes
    RDD

  123. def union(other: RDD[Seq[Seq[T]]]): RDD[Seq[Seq[T]]]

    Permalink
    Definition Classes
    RDD

  124. def unpersist(blocking: Boolean): CassandraCoGroupedRDD.this.type

    Permalink
    Definition Classes
    RDD

  125. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  127. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Permalink
    Definition Classes
    RDD

  129. def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D])(f: (Iterator[Seq[Seq[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

  130. def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D], preservesPartitioning: Boolean)(f: (Iterator[Seq[Seq[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

  131. def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C])(f: (Iterator[Seq[Seq[T]]], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD

  132. def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C], preservesPartitioning: Boolean)(f: (Iterator[Seq[Seq[T]]], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD

  133. def zipPartitions[B, V](rdd2: RDD[B])(f: (Iterator[Seq[Seq[T]]], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD

  134. def zipPartitions[B, V](rdd2: RDD[B], preservesPartitioning: Boolean)(f: (Iterator[Seq[Seq[T]]], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

    Permalink
    Definition Classes
    RDD

  135. def zipWithIndex(): RDD[(Seq[Seq[T]], Long)]

    Permalink
    Definition Classes
    RDD

  136. def zipWithUniqueId(): RDD[(Seq[Seq[T]], Long)]

    Permalink
    Definition Classes
    RDD

Inherited from RDD[Seq[Seq[T]]]

Inherited from Logging

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped