class NerChunker extends AnnotatorModel[NerChunker] with HasSimpleAnnotate[NerChunker]

Extracts phrases that fits into a known pattern using the NER tags. Useful for entity groups with neighboring tokens when there is no pretrained NER model to address certain issues. A Regex needs to be provided to extract the tokens between entities.

Example

Defining pipeline stages for NER

val data= Seq("She has cystic cyst on her kidney.").toDF("text")

val documentAssembler=new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentenceDetector=new SentenceDetector()
  .setInputCols("document")
  .setOutputCol("sentence")
  .setUseAbbreviations(false)

val tokenizer=new Tokenizer()
  .setInputCols(Array("sentence"))
  .setOutputCol("token")

val embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
  .setInputCols("sentence","token")
  .setOutputCol("embeddings")
  .setCaseSensitive(false)

val ner = MedicalNerModel.pretrained("ner_radiology", "en", "clinical/models")
  .setInputCols("sentence","token","embeddings")
  .setOutputCol("ner")
  .setIncludeConfidence(true)

Define the NerChunker to combine to chunks

val chunker = new NerChunker()
  .setInputCols(Array("sentence","ner"))
  .setOutputCol("ner_chunk")
  .setRegexParsers(Array("<ImagingFindings>.*<BodyPart>"))

val pipeline=new Pipeline().setStages(Array(
  documentAssembler,
  sentenceDetector,
  tokenizer,
  embeddings,
  ner,
  chunker
))

val result = pipeline.fit(data).transform(data)

Show results:

result.selectExpr("explode(arrays_zip(ner.metadata , ner.result))")
  .selectExpr("col['0'].word as word" , "col['1'] as ner").show(truncate=false)
+------+-----------------+
|word  |ner              |
+------+-----------------+
|She   |O                |
|has   |O                |
|cystic|B-ImagingFindings|
|cyst  |I-ImagingFindings|
|on    |O                |
|her   |O                |
|kidney|B-BodyPart       |
|.     |O                |
+------+-----------------+

result.select("ner_chunk.result").show(truncate=false)
+---------------------------+
|result                     |
+---------------------------+
|[cystic cyst on her kidney]|
+---------------------------+
Linear Supertypes
HasSimpleAnnotate[NerChunker], AnnotatorModel[NerChunker], CanBeLazy, RawAnnotator[NerChunker], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[NerChunker], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. NerChunker
  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 NerChunker()
  2. new NerChunker(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 addRegexParser(value: String): NerChunker

    adds a pattern to the current list of chunk patterns, for example: “‹DT›?‹JJ›*‹NN›”

  11. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  12. def annotate(annotations: Seq[Annotation]): Seq[Annotation]
    Definition Classes
    NerChunker → HasSimpleAnnotate
  13. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  14. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  15. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  16. final def clear(param: Param[_]): NerChunker.this.type
    Definition Classes
    Params
  17. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  18. def copy(extra: ParamMap): NerChunker
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  19. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  20. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  21. def dfAnnotate: UserDefinedFunction
    Definition Classes
    HasSimpleAnnotate
  22. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  23. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  24. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  25. def explainParams(): String
    Definition Classes
    Params
  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. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  32. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  33. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  34. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  37. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  38. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  39. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  40. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  41. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  42. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  43. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  44. def getRegexParsers: Array[String]

    A list of regex patterns to match chunks, for example: Array(“‹DT›?‹JJ›*‹NN›”)

  45. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  46. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  47. def hasParent: Boolean
    Definition Classes
    Model
  48. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  49. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  50. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  51. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator type : DOCUMENT, NAMED_ENTITY

    Input annotator type : DOCUMENT, NAMED_ENTITY

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

    Output annotator type : CHUNK

    Output annotator type : CHUNK

    Definition Classes
    NerChunker → HasOutputAnnotatorType
  76. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  77. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  78. var parent: Estimator[NerChunker]
    Definition Classes
    Model
  79. val regexParsers: StringArrayParam

    An array of grammar based chunk parsers

  80. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  81. def set[T](feature: StructFeature[T], value: T): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  82. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  83. def set[T](feature: SetFeature[T], value: Set[T]): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  84. def set[T](feature: ArrayFeature[T], value: Array[T]): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  85. final def set(paramPair: ParamPair[_]): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    Params
  86. final def set(param: String, value: Any): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    Params
  87. final def set[T](param: Param[T], value: T): NerChunker.this.type
    Definition Classes
    Params
  88. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  89. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  90. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  91. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  92. final def setDefault(paramPairs: ParamPair[_]*): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    Params
  93. final def setDefault[T](param: Param[T], value: T): NerChunker.this.type
    Attributes
    protected
    Definition Classes
    Params
  94. final def setInputCols(value: String*): NerChunker.this.type
    Definition Classes
    HasInputAnnotationCols
  95. final def setInputCols(value: Array[String]): NerChunker.this.type
    Definition Classes
    HasInputAnnotationCols
  96. def setLazyAnnotator(value: Boolean): NerChunker.this.type
    Definition Classes
    CanBeLazy
  97. final def setOutputCol(value: String): NerChunker.this.type
    Definition Classes
    HasOutputAnnotationCol
  98. def setParent(parent: Estimator[NerChunker]): NerChunker
    Definition Classes
    Model
  99. def setRegexParsers(value: Array[String]): NerChunker

    A list of regex patterns to match chunks, for example: Array(“‹DT›?‹JJ›*‹NN›”)

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

Inherited from HasSimpleAnnotate[NerChunker]

Inherited from AnnotatorModel[NerChunker]

Inherited from CanBeLazy

Inherited from RawAnnotator[NerChunker]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[NerChunker]

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 setters

Parameter getters