Packages

class AnnotationMerger extends AnnotatorModel[AnnotationMerger] with CheckLicense with HasMultipleInputAnnotationCols with HasSimpleAnnotate[AnnotationMerger]

Merges Annotations from multiple columns.

Example

val empty_data = Seq([[""]]).toDF("text")
val document1 = DocumentAssembler().setInputCol("text").setOutputCol("document1")
val document2 = DocumentAssembler().setInputCol("text").setOutputCol("document2")
val annotation_merger = AnnotationMerger()
    .setInputCols("document1", "document2")
    .setInputType("document")
    .setOutputCol("all_docs")

val pipelineModel = new Pipeline().setStages(Array(
    document1, document2, annotation_merger)).fit(empty_data)
val lp = LightPipeline(pipelineModel)
lp.fullAnnotate("one doc to be replicated")
[{'document1': [Annotation(document, 0, 23, one doc to be replicated, {})], 'document2': [Annotation(document, 0, 23, one doc to be replicated, {})], 'all_docs': [Annotation(document, 0, 23, one doc to be replicated, {}), Annotation(document, 0, 23, one doc to be replicated, {})]}]
Linear Supertypes
HasSimpleAnnotate[AnnotationMerger], HasMultipleInputAnnotationCols, CheckLicense, AnnotatorModel[AnnotationMerger], CanBeLazy, RawAnnotator[AnnotationMerger], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[AnnotationMerger], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. AnnotationMerger
  2. HasSimpleAnnotate
  3. HasMultipleInputAnnotationCols
  4. CheckLicense
  5. AnnotatorModel
  6. CanBeLazy
  7. RawAnnotator
  8. HasOutputAnnotationCol
  9. HasInputAnnotationCols
  10. HasOutputAnnotatorType
  11. ParamsAndFeaturesWritable
  12. HasFeatures
  13. DefaultParamsWritable
  14. MLWritable
  15. Model
  16. Transformer
  17. PipelineStage
  18. Logging
  19. Params
  20. Serializable
  21. Serializable
  22. Identifiable
  23. AnyRef
  24. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new AnnotationMerger()
  2. new AnnotationMerger(uid: String)

    uid

    a unique identifier for the instantiated AnnotatorModel

Type Members

  1. type AnnotationContent = Seq[Row]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]
    Definition Classes
    AnnotationMerger → HasSimpleAnnotate
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  14. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  15. def checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String]): Unit
    Definition Classes
    CheckLicense
  16. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  17. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  18. def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  19. final def clear(param: Param[_]): AnnotationMerger.this.type
    Definition Classes
    Params
  20. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  21. def copy(extra: ParamMap): AnnotationMerger
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  22. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  24. def dfAnnotate: UserDefinedFunction
    Definition Classes
    HasSimpleAnnotate
  25. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  26. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  27. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  28. def explainParams(): String
    Definition Classes
    Params
  29. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  30. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  31. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  32. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  33. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  34. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  35. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  40. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  41. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  42. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  43. def getInputType(): String

    Gets the inpytType param

  44. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  45. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  46. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  47. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  48. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  49. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  50. def hasParent: Boolean
    Definition Classes
    Model
  51. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  52. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  53. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  54. lazy val inputAnnotatorType: String

    Input annotator type: one of DOCUMENT, TOKEN, WORD_EMBEDDINGS, SENTENCE_EMBEDDINGS, CATEGORY, DATE, SENTIMENT, POS, CHUNK, NAMED_ENTITY, REGEX, DEPENDENCY, LABELED_DEPENDENCY, LANGUAGE, or KEYWORD

    Input annotator type: one of DOCUMENT, TOKEN, WORD_EMBEDDINGS, SENTENCE_EMBEDDINGS, CATEGORY, DATE, SENTIMENT, POS, CHUNK, NAMED_ENTITY, REGEX, DEPENDENCY, LABELED_DEPENDENCY, LANGUAGE, or KEYWORD

    Definition Classes
    AnnotationMerger → HasMultipleInputAnnotationCols
  55. lazy val inputAnnotatorTypes: Array[String]

    Input annotator types: one of DOCUMENT, TOKEN, WORD_EMBEDDINGS, SENTENCE_EMBEDDINGS, CATEGORY, DATE, SENTIMENT, POS, CHUNK, NAMED_ENTITY, REGEX, DEPENDENCY, LABELED_DEPENDENCY, LANGUAGE, or KEYWORD

    Input annotator types: one of DOCUMENT, TOKEN, WORD_EMBEDDINGS, SENTENCE_EMBEDDINGS, CATEGORY, DATE, SENTIMENT, POS, CHUNK, NAMED_ENTITY, REGEX, DEPENDENCY, LABELED_DEPENDENCY, LANGUAGE, or KEYWORD

    Definition Classes
    AnnotationMerger → HasMultipleInputAnnotationCols → HasInputAnnotationCols
  56. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  57. val inputType: Param[String]

    The type of the annotations that to merge.

    The type of the annotations that to merge.

    Possible values are document|token|wordpiece|word_embeddings|sentence_embeddings|category|date|sentiment|pos|chunk|named_entity|regex|dependency|labeled_dependency|language|keyword

  58. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  59. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  60. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  61. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  62. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  63. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  64. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  71. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  76. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  77. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  78. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  79. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  80. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  81. lazy val outputAnnotatorType: AnnotatorType

    Output annotator types: CHUNK

    Output annotator types: CHUNK

    Definition Classes
    AnnotationMerger → HasOutputAnnotatorType
  82. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  83. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  84. var parent: Estimator[AnnotationMerger]
    Definition Classes
    Model
  85. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  86. def set[T](feature: StructFeature[T], value: T): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  87. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  88. def set[T](feature: SetFeature[T], value: Set[T]): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  89. def set[T](feature: ArrayFeature[T], value: Array[T]): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  90. final def set(paramPair: ParamPair[_]): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    Params
  91. final def set(param: String, value: Any): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    Params
  92. final def set[T](param: Param[T], value: T): AnnotationMerger.this.type
    Definition Classes
    Params
  93. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  95. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  96. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  97. final def setDefault(paramPairs: ParamPair[_]*): AnnotationMerger.this.type
    Attributes
    protected
    Definition Classes
    Params
  98. final def setDefault[T](param: Param[T], value: T): AnnotationMerger.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  99. def setInputCols(value: Array[String]): AnnotationMerger.this.type
    Definition Classes
    HasMultipleInputAnnotationCols → HasInputAnnotationCols
  100. final def setInputCols(value: String*): AnnotationMerger.this.type
    Definition Classes
    HasInputAnnotationCols
  101. def setInputType(value: String): AnnotationMerger

    Sets the inpytType param

  102. def setLazyAnnotator(value: Boolean): AnnotationMerger.this.type
    Definition Classes
    CanBeLazy
  103. final def setOutputCol(value: String): AnnotationMerger.this.type
    Definition Classes
    HasOutputAnnotationCol
  104. def setParent(parent: Estimator[AnnotationMerger]): AnnotationMerger
    Definition Classes
    Model
  105. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  106. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  107. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  108. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  109. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  110. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  111. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  112. val uid: String
    Definition Classes
    AnnotationMerger → Identifiable
  113. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  114. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  115. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  116. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  117. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  118. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from HasSimpleAnnotate[AnnotationMerger]

Inherited from HasMultipleInputAnnotationCols

Inherited from CheckLicense

Inherited from AnnotatorModel[AnnotationMerger]

Inherited from CanBeLazy

Inherited from RawAnnotator[AnnotationMerger]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[AnnotationMerger]

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

Parameters

Annotator types

Required input and expected output annotator types

Members

Parameter getters