org.apache.spark.ml.odkl.texts

HashBasedDeduplicator

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
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new HashBasedDeduplicator()

  2. new HashBasedDeduplicator(uid: String)

Value Members

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

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

    Definition Classes
    AnyRef → Any
  4. final def $[T](param: Param[T]): T

    Attributes
    protected
    Definition Classes
    Params
  5. final def ==(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  6. final def ==(arg0: Any): Boolean

    Definition Classes
    Any
  7. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  8. final def clear(param: Param[_]): HashBasedDeduplicator.this.type

    Definition Classes
    Params
  9. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  10. def copy(extra: ParamMap): Transformer

    Definition Classes
    HashBasedDeduplicator → Transformer → PipelineStage → Params
  11. def copyValues[T <: Params](to: T, extra: ParamMap): T

    Attributes
    protected
    Definition Classes
    Params
  12. final def defaultCopy[T <: Params](extra: ParamMap): T

    Attributes
    protected
    Definition Classes
    Params
  13. final def eq(arg0: AnyRef): Boolean

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

    Definition Classes
    AnyRef → Any
  15. def explainParam(param: Param[_]): String

    Definition Classes
    Params
  16. def explainParams(): String

    Definition Classes
    Params
  17. final def extractParamMap(): ParamMap

    Definition Classes
    Params
  18. final def extractParamMap(extra: ParamMap): ParamMap

    Definition Classes
    Params
  19. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  20. final def get[T](param: Param[T]): Option[T]

    Definition Classes
    Params
  21. final def getClass(): Class[_]

    Definition Classes
    AnyRef → Any
  22. final def getDefault[T](param: Param[T]): Option[T]

    Definition Classes
    Params
  23. final def getOrDefault[T](param: Param[T]): T

    Definition Classes
    Params
  24. def getParam(paramName: String): Param[Any]

    Definition Classes
    Params
  25. final def hasDefault[T](param: Param[T]): Boolean

    Definition Classes
    Params
  26. def hasParam(paramName: String): Boolean

    Definition Classes
    Params
  27. def hashCode(): Int

    Definition Classes
    AnyRef → Any
  28. val inputColHash: Param[String]

  29. val inputColVector: Param[String]

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

    Definition Classes
    Params
  31. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any
  32. final def isSet(param: Param[_]): Boolean

    Definition Classes
    Params
  33. def isTraceEnabled(): Boolean

    Attributes
    protected
    Definition Classes
    Logging
  34. def log: Logger

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

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

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

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

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

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

    Attributes
    protected
    Definition Classes
    Logging
  41. def logName: String

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

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

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

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

    Attributes
    protected
    Definition Classes
    Logging
  46. final def ne(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  47. final def notify(): Unit

    Definition Classes
    AnyRef
  48. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  49. lazy val params: Array[Param[_]]

    Definition Classes
    Params
  50. final def set(paramPair: ParamPair[_]): HashBasedDeduplicator.this.type

    Attributes
    protected
    Definition Classes
    Params
  51. final def set(param: String, value: Any): HashBasedDeduplicator.this.type

    Attributes
    protected
    Definition Classes
    Params
  52. final def set[T](param: Param[T], value: T): HashBasedDeduplicator.this.type

    Definition Classes
    Params
  53. final def setDefault(paramPairs: ParamPair[_]*): HashBasedDeduplicator.this.type

    Attributes
    protected
    Definition Classes
    Params
  54. final def setDefault[T](param: Param[T], value: T): HashBasedDeduplicator.this.type

    Attributes
    protected
    Definition Classes
    Params
  55. def setInputColHash(value: String): HashBasedDeduplicator.this.type

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

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

  58. val similarityThreshold: DoubleParam

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

    Definition Classes
    AnyRef
  60. def toString(): String

    Definition Classes
    Identifiable → AnyRef → Any
  61. def transform(dataset: DataFrame): DataFrame

    Definition Classes
    HashBasedDeduplicator → Transformer
  62. def transform(dataset: DataFrame, paramMap: ParamMap): DataFrame

    Definition Classes
    Transformer
  63. def transform(dataset: DataFrame, firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

    Definition Classes
    Transformer
    Annotations
    @varargs()
  64. def transformSchema(schema: StructType): StructType

    Definition Classes
    HashBasedDeduplicator → PipelineStage
    Annotations
    @DeveloperApi()
  65. def transformSchema(schema: StructType, logging: Boolean): StructType

    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  66. val uid: String

    Definition Classes
    HashBasedDeduplicator → Identifiable
  67. def validateParams(): Unit

    Definition Classes
    Params
  68. final def wait(): Unit

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

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

    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