Packages

class MultiAnnotationSplitter extends AnnotatorModel[MultiAnnotationSplitter] with HasSimpleAnnotate[MultiAnnotationSplitter] with ParamsAndFeaturesWritable

Splits a mixed-type annotation column (e.g. the output of com.johnsnowlabs.nlp.annotators.ner.PretrainedZeroShotMultiTask) into separate columns, one per annotatorType.

For example PretrainedZeroShotMultiTask emits all extraction results in a single column as Array[Annotation] containing annotations of different types:

  • "chunk" — entity spans
  • "category" — classifications and relations
  • "struct" — structured records

These can be split into separate columns using MultiAnnotationSplitter by providing a output column name and the type of annotation to split for each column. For example, to split out the entity spans into a column named ner_chunk, you would set splitType to "chunk" and outputCol to "ner_chunk".

Example

val splitter = new MultiAnnotationSplitter()
  .setInputCols("extractions")
  .setOutputCol("ner_chunk")
  .setSplitType("chunk")

val result = splitter.transform(df)
result.select("extractions", "ner_chunk").show(false)
+--------------------+--------------------+
|         extractions|           ner_chunk|
+--------------------+--------------------+
|[{chunk, 0, 4, Al...|[{chunk, 0, 4, Al...|
+--------------------+--------------------+
Linear Supertypes
HasSimpleAnnotate[MultiAnnotationSplitter], AnnotatorModel[MultiAnnotationSplitter], CanBeLazy, RawAnnotator[MultiAnnotationSplitter], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[MultiAnnotationSplitter], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. MultiAnnotationSplitter
  2. HasSimpleAnnotate
  3. AnnotatorModel
  4. CanBeLazy
  5. RawAnnotator
  6. HasOutputAnnotationCol
  7. HasInputAnnotationCols
  8. HasOutputAnnotatorType
  9. ParamsAndFeaturesWritable
  10. HasFeatures
  11. DefaultParamsWritable
  12. MLWritable
  13. Model
  14. Transformer
  15. PipelineStage
  16. Logging
  17. Params
  18. Serializable
  19. Serializable
  20. Identifiable
  21. AnyRef
  22. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

    uid

    UID for the Spark ML pipeline stage

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
    MultiAnnotationSplitter → 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. final def clear(param: Param[_]): MultiAnnotationSplitter.this.type
    Definition Classes
    Params
  16. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  17. def copy(extra: ParamMap): MultiAnnotationSplitter
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  18. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  19. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  20. def dfAnnotate: UserDefinedFunction
    Definition Classes
    HasSimpleAnnotate
  21. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  22. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  23. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  24. def explainParams(): String
    Definition Classes
    Params
  25. final val extraInputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  26. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  27. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  28. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  29. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  30. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  31. val filterByCategoryType: Param[String]

    If splitType is set to "category", this parameter can be used to filter annotations by a specific category type.

    If splitType is set to "category", this parameter can be used to filter annotations by a specific category type. The category type is determined by the value of the category_type field in the annotation metadata, which is set by the annotator that produced the category annotations (e.g. PretrainedZeroShotMultiTask).

  32. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  33. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  34. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  38. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  39. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  40. def getFilterByCategoryType: String

    Gets filterByCategoryType param.

  41. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  42. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  43. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  44. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  45. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  46. def getSplitType: String

    Gets splitType param

  47. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  48. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  49. def hasParent: Boolean
    Definition Classes
    Model
  50. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  51. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  52. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  53. val inputAnnotatorTypes: Array[String]
    Definition Classes
    MultiAnnotationSplitter → HasInputAnnotationCols
  54. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  55. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  56. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  57. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  58. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  59. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  60. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  61. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  62. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  63. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  64. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  68. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  73. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  74. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  75. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  76. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  77. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  78. val outputAnnotatorType: AnnotatorType
    Definition Classes
    MultiAnnotationSplitter → HasOutputAnnotatorType
  79. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  80. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  81. var parent: Estimator[MultiAnnotationSplitter]
    Definition Classes
    Model
  82. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  83. def set[T](feature: StructFeature[T], value: T): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  84. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  85. def set[T](feature: SetFeature[T], value: Set[T]): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  86. def set[T](feature: ArrayFeature[T], value: Array[T]): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  87. final def set(paramPair: ParamPair[_]): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    Params
  88. final def set(param: String, value: Any): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    Params
  89. final def set[T](param: Param[T], value: T): MultiAnnotationSplitter.this.type
    Definition Classes
    Params
  90. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  91. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  92. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. final def setDefault(paramPairs: ParamPair[_]*): MultiAnnotationSplitter.this.type
    Attributes
    protected
    Definition Classes
    Params
  95. final def setDefault[T](param: Param[T], value: T): MultiAnnotationSplitter.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  96. def setExtraInputCols(value: Array[String]): MultiAnnotationSplitter.this.type
    Definition Classes
    HasInputAnnotationCols
  97. def setFilterByCategoryType(value: String): MultiAnnotationSplitter.this.type

    Sets the category type to filter by when splitting category annotations.

    Sets the category type to filter by when splitting category annotations. This parameter is only applicable when splitType is set to "category". If provided, only category annotations with a matching category type in their metadata will be included in the output column. It should be one of the following values: - "relation" - "classification"

    Default: "" (no filtering, include all category annotations)

  98. final def setInputCols(value: String*): MultiAnnotationSplitter.this.type
    Definition Classes
    HasInputAnnotationCols
  99. def setInputCols(value: Array[String]): MultiAnnotationSplitter.this.type
    Definition Classes
    HasInputAnnotationCols
  100. def setLazyAnnotator(value: Boolean): MultiAnnotationSplitter.this.type
    Definition Classes
    CanBeLazy
  101. final def setOutputCol(value: String): MultiAnnotationSplitter.this.type
    Definition Classes
    HasOutputAnnotationCol
  102. def setParent(parent: Estimator[MultiAnnotationSplitter]): MultiAnnotationSplitter
    Definition Classes
    Model
  103. def setSplitType(value: String): MultiAnnotationSplitter.this.type

    Sets the type of annotation to split into separate column.

    Sets the type of annotation to split into separate column. It should be one of the following values: - "chunk" - "category" - "struct"

    Default: "chunk"

  104. val splitType: Param[String]

    The type of annotation to split into separate column.

    The type of annotation to split into separate column. It should be one of the following values: - "chunk" - "category" - "struct" Default: "chunk"

  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
    MultiAnnotationSplitter → 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[MultiAnnotationSplitter]

Inherited from AnnotatorModel[MultiAnnotationSplitter]

Inherited from CanBeLazy

Inherited from RawAnnotator[MultiAnnotationSplitter]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[MultiAnnotationSplitter]

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

getParam

param

setParam

Ungrouped