StratifiedSamplerReservoir

Value Members

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

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

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

   

   Definition Classes

   AnyRef → Any

4. def append[U](rows: Iterator[Row], init: U, processFlush: (U, InternalRow) ⇒ U, startBatch: (U, Int) ⇒ U, endBatch: (U) ⇒ U, rowEncoder: ExpressionEncoder[Row], partIndex: Int): Long

   

   Definition Classes

   StratifiedSamplerReservoir → StratifiedSampler

5. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

6. def clone(): StratifiedSamplerReservoir

   

   Definition Classes

   StratifiedSamplerReservoir → AnyRef

7. final def concurrency: Int

   

   Definition Classes

   StratifiedSampler

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

   

   Definition Classes

   AnyRef

9. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

10. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

11. def flushReservoir[U](init: U, process: (U, InternalRow) ⇒ U, startBatch: (U, Int) ⇒ U, endBatch: (U) ⇒ U): U

    

    Definition Classes

    StratifiedSamplerReservoir → StratifiedSampler

12. final def foldDrainSegment[U](prevReservoirSize: Int, fullReset: Boolean, process: (U, InternalRow) ⇒ U)(init: U, seg: ReservoirSegment): U

    

    Attributes

    protected

    Definition Classes

    StratifiedSampler

13. final def foldReservoir[U](prevReservoirSize: Int, doReset: Boolean, fullReset: Boolean, process: (U, InternalRow) ⇒ U)(bid: Int, sr: StratumReservoir, init: U): U

    

    Attributes

    protected

    Definition Classes

    StratifiedSampler

14. def getBucketId(partIndex: Int, primaryBucketIds: IntArrayList = null)(hashValue: Int): Int

    

    Attributes

    protected

    Definition Classes

    StratifiedSampler

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

    

    Definition Classes

    AnyRef → Any

16. def getReservoirSegment(newQcs: Array[Int], types: Array[DataType], numColumns: Int, initialCapacity: Int, loadFactor: Double, qcsColHandler: Option[ColumnHandler], segi: Int, nsegs: Int): ReservoirSegment

    

    Attributes

    protected

    Definition Classes

    StratifiedSampler

17. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

18. def initializeLogIfNecessary(): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

19. def isBucketLocal(partIndex: Int): Boolean

    

    Attributes

    protected

    Definition Classes

    StratifiedSampler

20. final def isDebugEnabled: Boolean

    

    Definition Classes

    Logging

21. final def isInfoEnabled: Boolean

    

    Definition Classes

    Logging

22. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

23. final def isTraceEnabled: Boolean

    

    Definition Classes

    Logging

24. def iterator(segmentStart: Int, segmentEnd: Int): Iterator[InternalRow]

    

    Definition Classes

    StratifiedSampler

25. def iteratorOnRegion(buckets: Set[Integer]): Iterator[InternalRow]

    

    Definition Classes

    StratifiedSampler

26. final var levelFlags: Int

    

    Attributes

    protected

    Definition Classes

    Logging

27. def log: Logger

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Definition Classes

    Logging

29. def logDebug(msg: ⇒ String): Unit

    

    Definition Classes

    Logging

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

    

    Definition Classes

    Logging

31. def logError(msg: ⇒ String): Unit

    

    Definition Classes

    Logging

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

    

    Definition Classes

    Logging

33. def logInfo(msg: ⇒ String): Unit

    

    Definition Classes

    Logging

34. def logName: String

    

    Attributes

    protected

    Definition Classes

    Logging

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

    

    Definition Classes

    Logging

36. def logTrace(msg: ⇒ String): Unit

    

    Definition Classes

    Logging

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

    

    Definition Classes

    Logging

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

    

    Definition Classes

    Logging

39. final var log_: Logger

    

    Attributes

    protected

    Definition Classes

    Logging

40. def module: String

    

    Definition Classes

    StratifiedSampler

41. final def name: String

    

    Definition Classes

    StratifiedSampler

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

    

    Definition Classes

    AnyRef

43. final def newMutableRow(row: Row, rowEncoder: ExpressionEncoder[Row]): UnsafeRow

    

    Attributes

    protected

    Definition Classes

    StratifiedSampler

44. final def notify(): Unit

    

    Definition Classes

    AnyRef

45. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

46. def onTruncate(): Unit

    

    Definition Classes

    StratifiedSamplerReservoir → StratifiedSampler

47. final val options: SampleOptions

    

    Definition Classes

    StratifiedSampler

48. final val pendingBatch: AtomicReference[ArrayBuffer[InternalRow]]

    

    Store pending values to be flushed in a separate buffer so that we do not end up creating too small ColumnBatches.

    Store pending values to be flushed in a separate buffer so that we do not end up creating too small ColumnBatches.

    Note that this mini-cache is copy-on-write (to avoid copy-on-read for readers) so the buffer inside should never be changed rather the whole buffer replaced if required. This should happen only inside flushCache.

    Attributes

    protected

    Definition Classes

    StratifiedSampler

49. final def qcs: Array[Int]

    

    Definition Classes

    StratifiedSampler

50. final def qcsSparkPlan: Option[(CodeAndComment, ArrayBuffer[Any], Int, Array[DataType])]

    

    Definition Classes

    StratifiedSampler

51. def reservoirInRegion: Boolean

    

    Definition Classes

    StratifiedSampler

52. val reservoirSize: Int

    

53. def resetLogger(): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

54. final val rng: Random

    

    Random number generator for sampling.

    Random number generator for sampling.

    Attributes

    protected

    Definition Classes

    StratifiedSampler

55. def sample(items: Iterator[InternalRow], rowEncoder: ExpressionEncoder[Row], flush: Boolean): Iterator[InternalRow]

    

    Definition Classes

    StratifiedSamplerReservoir → StratifiedSampler

56. final def schema: StructType

    

    Definition Classes

    StratifiedSampler

57. def setFlushStatus(doFlush: Boolean): Unit

    

    Definition Classes

    StratifiedSampler

58. final val strata: ConcurrentSegmentedHashMap[Row, StratumReservoir, ReservoirSegment]

    

    Map of each stratum key (i.e.

    Map of each stratum key (i.e. a unique combination of values of columns in qcs) to related metadata and reservoir

    Attributes

    protected

    Definition Classes

    StratifiedSampler

59. def strataReservoirSize: Int

    

    Attributes

    protected

    Definition Classes

    StratifiedSamplerReservoir → StratifiedSampler

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

    

    Definition Classes

    AnyRef

61. def toString(): String

    

    Definition Classes

    AnyRef → Any

62. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

65. def waitForSamplers(waitUntil: Int, maxMillis: Long): Unit

    

    Attributes

    protected

    Definition Classes

    StratifiedSampler