Class

org.apache.spark.ml.odkl.texts

HashBasedDeduplicator

Related Doc: package texts

Permalink

class HashBasedDeduplicator extends Transformer with Params with Logging

Created by eugeny.malyutin on 05.05.16.

Deduplicator based on RandomProjectionsHasher and cosine similarity.

Linear Supertypes
Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. HashBasedDeduplicator
  2. Transformer
  3. PipelineStage
  4. Logging
  5. Params
  6. Serializable
  7. Serializable
  8. Identifiable
  9. AnyRef
  10. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new HashBasedDeduplicator()

    Permalink

  2. new HashBasedDeduplicator(uid: String)

    Permalink

Value Members

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

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. final def $[T](param: Param[T]): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params

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

    Permalink
    Definition Classes
    AnyRef → Any

  5. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  6. final def clear(param: Param[_]): HashBasedDeduplicator.this.type

    Permalink
    Definition Classes
    Params

  7. def clone(): AnyRef

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

  8. def copy(extra: ParamMap): Transformer

    Permalink
    Definition Classes
    HashBasedDeduplicator → Transformer → PipelineStage → Params

  9. def copyValues[T <: Params](to: T, extra: ParamMap): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params

  10. final def defaultCopy[T <: Params](extra: ParamMap): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params

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

    Permalink
    Definition Classes
    AnyRef

  12. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  13. def explainParam(param: Param[_]): String

    Permalink
    Definition Classes
    Params

  14. def explainParams(): String

    Permalink
    Definition Classes
    Params

  15. final def extractParamMap(): ParamMap

    Permalink
    Definition Classes
    Params

  16. final def extractParamMap(extra: ParamMap): ParamMap

    Permalink
    Definition Classes
    Params

  17. def finalize(): Unit

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

  18. final def get[T](param: Param[T]): Option[T]

    Permalink
    Definition Classes
    Params

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

    Permalink
    Definition Classes
    AnyRef → Any

  20. final def getDefault[T](param: Param[T]): Option[T]

    Permalink
    Definition Classes
    Params

  21. final def getOrDefault[T](param: Param[T]): T

    Permalink
    Definition Classes
    Params

  22. def getParam(paramName: String): Param[Any]

    Permalink
    Definition Classes
    Params

  23. final def hasDefault[T](param: Param[T]): Boolean

    Permalink
    Definition Classes
    Params

  24. def hasParam(paramName: String): Boolean

    Permalink
    Definition Classes
    Params

  25. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  26. def initializeLogIfNecessary(isInterpreter: Boolean): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  27. val inputColHash: Param[String]

    Permalink

  28. val inputColVector: Param[String]

    Permalink

  29. final def isDefined(param: Param[_]): Boolean

    Permalink
    Definition Classes
    Params

  30. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  31. final def isSet(param: Param[_]): Boolean

    Permalink
    Definition Classes
    Params

  32. def isTraceEnabled(): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  33. def log: Logger

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

  40. def logName: String

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging

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

    Permalink
    Definition Classes
    AnyRef

  46. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  47. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  48. lazy val params: Array[Param[_]]

    Permalink
    Definition Classes
    Params

  49. final def set(paramPair: ParamPair[_]): HashBasedDeduplicator.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params

  50. final def set(param: String, value: Any): HashBasedDeduplicator.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params

  51. final def set[T](param: Param[T], value: T): HashBasedDeduplicator.this.type

    Permalink
    Definition Classes
    Params

  52. final def setDefault(paramPairs: ParamPair[_]*): HashBasedDeduplicator.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params

  53. final def setDefault[T](param: Param[T], value: T): HashBasedDeduplicator.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params

  54. def setInputColHash(value: String): HashBasedDeduplicator.this.type

    Permalink

  55. def setInputColVector(value: String): HashBasedDeduplicator.this.type

    Permalink

  56. def setSimilarityTreshold(value: Double): HashBasedDeduplicator.this.type

    Permalink

  57. val similarityThreshold: DoubleParam

    Permalink

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

    Permalink
    Definition Classes
    AnyRef

  59. def toString(): String

    Permalink
    Definition Classes
    Identifiable → AnyRef → Any

  60. def transform(dataset: Dataset[_]): DataFrame

    Permalink
    Definition Classes
    HashBasedDeduplicator → Transformer

  61. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

    Permalink
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )

  62. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

    Permalink
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()

  63. def transformSchema(schema: StructType): StructType

    Permalink
    Definition Classes
    HashBasedDeduplicator → PipelineStage
    Annotations
    @DeveloperApi()

  64. def transformSchema(schema: StructType, logging: Boolean): StructType

    Permalink
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()

  65. val uid: String

    Permalink
    Definition Classes
    HashBasedDeduplicator → Identifiable

  66. final def wait(): Unit

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

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

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

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

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

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

setParam

Ungrouped