Class

com.mongodb.spark.rdd

MongoRDD

Related Doc: package rdd

Permalink

class MongoRDD[D] extends RDD[D]

MongoRDD Class

D

the type of the collection documents

Linear Supertypes
RDD[D], org.apache.spark.internal.Logging, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. MongoRDD
  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 MongoRDD(sparkSession: SparkSession, connector: Broadcast[MongoConnector], readConfig: ReadConfig)(implicit arg0: ClassTag[D])

    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[D]): RDD[D]

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

    Permalink
    Definition Classes
    AnyRef → Any
  5. def aggregate[U](zeroValue: U)(seqOp: (U, D) ⇒ 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(): MongoRDD.this.type

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

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

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

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

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

    Permalink
    Definition Classes
    RDD
  17. def copy(connector: Broadcast[MongoConnector] = connector, readConfig: ReadConfig = readConfig): MongoRDD[D]

    Permalink

    Allows to copying of this RDD with changing some of the properties

  18. def count(): Long

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

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

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

    Permalink
    Definition Classes
    RDD
  22. def countByValue()(implicit ord: Ordering[D]): Map[D, Long]

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

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

    Permalink
    Definition Classes
    RDD
  25. def distinct(): RDD[D]

    Permalink
    Definition Classes
    RDD
  26. def distinct(numPartitions: Int)(implicit ord: Ordering[D]): RDD[D]

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

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

    Permalink
    Definition Classes
    AnyRef → Any
  29. def filter(f: (D) ⇒ Boolean): RDD[D]

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

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

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

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

    Permalink
    Definition Classes
    RDD
  34. def fold(zeroValue: D)(op: (D, D) ⇒ D): D

    Permalink
    Definition Classes
    RDD
  35. def foreach(f: (D) ⇒ Unit): Unit

    Permalink
    Definition Classes
    RDD
  36. def foreachPartition(f: (Iterator[D]) ⇒ Unit): Unit

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

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

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

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

    Permalink
    Definition Classes
    RDD
    Annotations
    @Since( "1.6.0" )
  41. def getOutputDeterministicLevel: org.apache.spark.rdd.DeterministicLevel.Value

    Permalink
    Attributes
    protected
    Definition Classes
    RDD
    Annotations
    @DeveloperApi()
  42. def getPartitions: Array[Partition]

    Permalink
    Attributes
    protected
    Definition Classes
    MongoRDD → RDD
  43. def getPreferredLocations(split: Partition): Seq[String]

    Permalink
    Definition Classes
    MongoRDD → RDD
  44. def getStorageLevel: StorageLevel

    Permalink
    Definition Classes
    RDD
  45. def glom(): RDD[Array[D]]

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

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

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

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

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

    Permalink
    Definition Classes
    RDD
  51. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  52. def initializeLogIfNecessary(isInterpreter: Boolean): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  53. def intersection(other: RDD[D], numPartitions: Int): RDD[D]

    Permalink
    Definition Classes
    RDD
  54. def intersection(other: RDD[D], partitioner: Partitioner)(implicit ord: Ordering[D]): RDD[D]

    Permalink
    Definition Classes
    RDD
  55. def intersection(other: RDD[D]): RDD[D]

    Permalink
    Definition Classes
    RDD
  56. def isCheckpointed: Boolean

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

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

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

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

    Permalink
    Definition Classes
    RDD
  61. def keyBy[K](f: (D) ⇒ K): RDD[(K, D)]

    Permalink
    Definition Classes
    RDD
  62. def localCheckpoint(): MongoRDD.this.type

    Permalink
    Definition Classes
    RDD
  63. def log: Logger

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Permalink
    Definition Classes
    RDD
  78. def max()(implicit ord: Ordering[D]): D

    Permalink
    Definition Classes
    RDD
  79. def min()(implicit ord: Ordering[D]): D

    Permalink
    Definition Classes
    RDD
  80. var name: String

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

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

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

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

    Permalink
    Attributes
    protected[org.apache.spark]
    Definition Classes
    RDD
  85. val partitioner: Option[Partitioner]

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

    Permalink
    Definition Classes
    RDD
  87. def persist(): MongoRDD.this.type

    Permalink
    Definition Classes
    RDD
  88. def persist(newLevel: StorageLevel): MongoRDD.this.type

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

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

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

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

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

    Permalink
    Definition Classes
    RDD
  94. def reduce(f: (D, D) ⇒ D): D

    Permalink
    Definition Classes
    RDD
  95. def repartition(numPartitions: Int)(implicit ord: Ordering[D]): RDD[D]

    Permalink
    Definition Classes
    RDD
  96. def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[D]

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

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

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

    Permalink
    Definition Classes
    RDD
  100. val sc: SparkContext

    Permalink
  101. def setName(_name: String): MongoRDD.this.type

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

    Permalink
    Definition Classes
    RDD
  103. def sparkContext: SparkContext

    Permalink
    Definition Classes
    RDD
  104. val sparkSession: SparkSession

    Permalink
  105. def subtract(other: RDD[D], p: Partitioner)(implicit ord: Ordering[D]): RDD[D]

    Permalink
    Definition Classes
    RDD
  106. def subtract(other: RDD[D], numPartitions: Int): RDD[D]

    Permalink
    Definition Classes
    RDD
  107. def subtract(other: RDD[D]): RDD[D]

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

    Permalink
    Definition Classes
    AnyRef
  109. def take(num: Int): Array[D]

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

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

    Permalink
    Definition Classes
    RDD
  112. def toDF(schema: StructType): DataFrame

    Permalink

    Creates a DataFrame based on the provided schema.

    Creates a DataFrame based on the provided schema.

    schema

    the schema representing the DataFrame.

    returns

    a DataFrame.

  113. def toDF[T](beanClass: Class[T]): DataFrame

    Permalink

    Creates a DataFrame based on the schema derived from the bean class.

    Creates a DataFrame based on the schema derived from the bean class.

    Note: Prefer toDS[T](beanClass:Class[T])* as computations will be more efficient.

    T

    The bean class type to shape the data from MongoDB into

    beanClass

    encapsulating the data from MongoDB

    returns

    a DataFrame

  114. def toDF[T <: Product]()(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T]): DataFrame

    Permalink

    Creates a DataFrame based on the schema derived from the optional type.

    Creates a DataFrame based on the schema derived from the optional type.

    Note: Prefer toDS[T<:Product]()* as computations will be more efficient. The rdd must contain an _id for MongoDB versions < 3.2.

    T

    The optional type of the data from MongoDB, if not provided the schema will be inferred from the collection

    returns

    a DataFrame

  115. def toDS[T](beanClass: Class[T]): Dataset[T]

    Permalink

    Creates a Dataset from the RDD strongly typed to the provided java bean.

    Creates a Dataset from the RDD strongly typed to the provided java bean.

    T

    The type of the data from MongoDB

  116. def toDS[T <: Product]()(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T], arg1: NotNothing[T]): Dataset[T]

    Permalink

    Creates a Dataset from the collection strongly typed to the provided case class.

    Creates a Dataset from the collection strongly typed to the provided case class.

    T

    The type of the data from MongoDB

  117. def toDebugString: String

    Permalink
    Definition Classes
    RDD
  118. def toJavaRDD(): JavaMongoRDD[D]

    Permalink
    Definition Classes
    MongoRDD → RDD
  119. def toLocalIterator: Iterator[D]

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

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

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

    Permalink
    Definition Classes
    RDD
  123. def treeReduce(f: (D, D) ⇒ D, depth: Int): D

    Permalink
    Definition Classes
    RDD
  124. def union(other: RDD[D]): RDD[D]

    Permalink
    Definition Classes
    RDD
  125. def unpersist(blocking: Boolean): MongoRDD.this.type

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

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  129. def withPipeline[B <: Bson](pipeline: Seq[B]): MongoRDD[D]

    Permalink

    Returns a copy with the specified aggregation pipeline

    Returns a copy with the specified aggregation pipeline

    pipeline

    the aggregation pipeline to use

    returns

    the updated MongoRDD

  130. def zip[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(D, U)]

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

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

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

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

    Permalink
    Definition Classes
    RDD
  137. def zipWithIndex(): RDD[(D, Long)]

    Permalink
    Definition Classes
    RDD
  138. def zipWithUniqueId(): RDD[(D, Long)]

    Permalink
    Definition Classes
    RDD

Inherited from RDD[D]

Inherited from org.apache.spark.internal.Logging

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped