Class

com.johnsnowlabs.nlp.annotators

Chunk2Token

Related Doc: package annotators

Permalink

class Chunk2Token extends AnnotatorModel[Chunk2Token]

A feature transformer that converts the input array of strings (annotatorType CHUNK) into an array of chunk-based tokens (annotatorType TOKEN).

When the input is empty, an empty array is returned.

This Annotator is specially convenient when using NGramGenerator annotations as inputs to WordEmbeddingsModels

Linear Supertypes
AnnotatorModel[Chunk2Token], CanBeLazy, RawAnnotator[Chunk2Token], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[Chunk2Token], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Chunk2Token
  2. AnnotatorModel
  3. CanBeLazy
  4. RawAnnotator
  5. HasOutputAnnotationCol
  6. HasInputAnnotationCols
  7. HasOutputAnnotatorType
  8. ParamsAndFeaturesWritable
  9. HasFeatures
  10. DefaultParamsWritable
  11. MLWritable
  12. Model
  13. Transformer
  14. PipelineStage
  15. Logging
  16. Params
  17. Serializable
  18. Serializable
  19. Identifiable
  20. AnyRef
  21. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Chunk2Token()

    Permalink
  2. new Chunk2Token(uid: String)

    Permalink

Type Members

  1. type AnnotationContent = Seq[Row]

    Permalink
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String

    Permalink
    Definition Classes
    HasOutputAnnotatorType

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. def $$[T](feature: StructFeature[T]): T

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  9. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame

    Permalink
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame

    Permalink
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]

    Permalink
    Definition Classes
    Chunk2Token → AnnotatorModel
  12. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  13. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]

    Permalink
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  14. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  15. final def clear(param: Param[_]): Chunk2Token.this.type

    Permalink
    Definition Classes
    Params
  16. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  17. def copy(extra: ParamMap): Chunk2Token

    Permalink
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  18. def copyValues[T <: Params](to: T, extra: ParamMap): T

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

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  20. def dfAnnotate: UserDefinedFunction

    Permalink
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  21. final def eq(arg0: AnyRef): Boolean

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

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

    Permalink
    Definition Classes
    Params
  24. def explainParams(): String

    Permalink
    Definition Classes
    Params
  25. def extraValidate(structType: StructType): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    RawAnnotator
  26. def extraValidateMsg: String

    Permalink
    Attributes
    protected
    Definition Classes
    RawAnnotator
  27. final def extractParamMap(): ParamMap

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

    Permalink
    Definition Classes
    Params
  29. val features: ArrayBuffer[Feature[_, _, _]]

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

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  31. def get[T](feature: StructFeature[T]): Option[T]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  32. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  33. def get[T](feature: SetFeature[T]): Option[Set[T]]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  34. def get[T](feature: ArrayFeature[T]): Option[Array[T]]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. final def get[T](param: Param[T]): Option[T]

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

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

    Permalink
    Definition Classes
    Params
  38. def getInputCols: Array[String]

    Permalink
    Definition Classes
    HasInputAnnotationCols
  39. def getLazyAnnotator: Boolean

    Permalink
    Definition Classes
    CanBeLazy
  40. final def getOrDefault[T](param: Param[T]): T

    Permalink
    Definition Classes
    Params
  41. final def getOutputCol: String

    Permalink
    Definition Classes
    HasOutputAnnotationCol
  42. def getParam(paramName: String): Param[Any]

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

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

    Permalink
    Definition Classes
    Params
  45. def hasParent: Boolean

    Permalink
    Definition Classes
    Model
  46. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  47. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  49. val inputAnnotatorTypes: Array[AnnotatorType]

    Permalink

    inputAnnotatorTypes is CHUNK

    inputAnnotatorTypes is CHUNK

    Definition Classes
    Chunk2Token → HasInputAnnotationCols
  50. final val inputCols: StringArrayParam

    Permalink
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  51. final def isDefined(param: Param[_]): Boolean

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

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

    Permalink
    Definition Classes
    Params
  54. def isTraceEnabled(): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  55. val lazyAnnotator: BooleanParam

    Permalink
    Definition Classes
    CanBeLazy
  56. def log: Logger

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

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

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

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

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

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

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

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

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

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  68. def msgHelper(schema: StructType): String

    Permalink
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  69. final def ne(arg0: AnyRef): Boolean

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

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

    Permalink
    Definition Classes
    AnyRef
  72. def onWrite(path: String, spark: SparkSession): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  73. val outputAnnotatorType: AnnotatorType

    Permalink

    outputAnnotatorType is TOKEN

    outputAnnotatorType is TOKEN

    Definition Classes
    Chunk2Token → HasOutputAnnotatorType
  74. final val outputCol: Param[String]

    Permalink
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  75. lazy val params: Array[Param[_]]

    Permalink
    Definition Classes
    Params
  76. var parent: Estimator[Chunk2Token]

    Permalink
    Definition Classes
    Model
  77. def save(path: String): Unit

    Permalink
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  78. def set[T](feature: StructFeature[T], value: T): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  79. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  80. def set[T](feature: SetFeature[T], value: Set[T]): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  81. def set[T](feature: ArrayFeature[T], value: Array[T]): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  82. final def set(paramPair: ParamPair[_]): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  83. final def set(param: String, value: Any): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  84. final def set[T](param: Param[T], value: T): Chunk2Token.this.type

    Permalink
    Definition Classes
    Params
  85. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  86. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  87. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  88. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  89. final def setDefault(paramPairs: ParamPair[_]*): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  90. final def setDefault[T](param: Param[T], value: T): Chunk2Token.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  91. final def setInputCols(value: String*): Chunk2Token.this.type

    Permalink
    Definition Classes
    HasInputAnnotationCols
  92. final def setInputCols(value: Array[String]): Chunk2Token.this.type

    Permalink
    Definition Classes
    HasInputAnnotationCols
  93. def setLazyAnnotator(value: Boolean): Chunk2Token.this.type

    Permalink
    Definition Classes
    CanBeLazy
  94. final def setOutputCol(value: String): Chunk2Token.this.type

    Permalink
    Definition Classes
    HasOutputAnnotationCol
  95. def setParent(parent: Estimator[Chunk2Token]): Chunk2Token

    Permalink
    Definition Classes
    Model
  96. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  97. def toString(): String

    Permalink
    Definition Classes
    Identifiable → AnyRef → Any
  98. final def transform(dataset: Dataset[_]): DataFrame

    Permalink
    Definition Classes
    AnnotatorModel → Transformer
  99. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

    Permalink
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  100. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

    Permalink
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  101. final def transformSchema(schema: StructType): StructType

    Permalink
    Definition Classes
    RawAnnotator → PipelineStage
  102. def transformSchema(schema: StructType, logging: Boolean): StructType

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

    Permalink
    Definition Classes
    Chunk2Token → Identifiable
  104. def validate(schema: StructType): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    RawAnnotator
  105. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  108. def wrapColumnMetadata(col: Column): Column

    Permalink
    Attributes
    protected
    Definition Classes
    RawAnnotator
  109. def write: MLWriter

    Permalink
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from AnnotatorModel[Chunk2Token]

Inherited from CanBeLazy

Inherited from RawAnnotator[Chunk2Token]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[Chunk2Token]

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

Ungrouped