Packages

class Router extends AnnotatorModel[Router] with HasSimpleAnnotate[Router] with CheckLicense

This class allows to filter any annotation based on the medatata fields.

val testData = ResourceHelper.spark.createDataFrame(Seq(
   (1, "\"Jesus live in Leon. Madrid is the capital of Spain")
 )).toDF("id", "text")

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

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

 val regexMatcher = new RegexMatcher()
   .setExternalRules(ExternalResource("src/test/resources/regex-matcher/rules2.txt", ReadAs.TEXT, Map("delimiter" -> ",")))
   .setInputCols(Array("sentence"))
   .setOutputCol("regex")
   .setStrategy("MATCH_ALL")

 val chunk2Doc = new Chunk2Doc().setInputCols("regex").setOutputCol("doc_chunk")

 val embeddings = BertSentenceEmbeddings.pretrained("sent_small_bert_L2_128")
   .setInputCols("doc_chunk")
   .setOutputCol("bert")
   .setCaseSensitive(false)
   .setMaxSentenceLength(32)

 val routerName = new Router()
   .setInputType("sentence_embeddings")
   .setInputCols(Array("bert"))
   .setMetadataField("identifier")
   .setFilterFieldsElements(Array("name"))
   .setOutputCol("names")
 val routerCity = new Router()
   .setInputType("sentence_embeddings")
   .setInputCols(Array("bert"))
   .setMetadataField("identifier")
   .setFilterFieldsElements(Array("city"))
   .setOutputCol("cities")
Linear Supertypes
CheckLicense, HasSimpleAnnotate[Router], AnnotatorModel[Router], CanBeLazy, RawAnnotator[Router], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[Router], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. Router
  2. CheckLicense
  3. HasSimpleAnnotate
  4. AnnotatorModel
  5. CanBeLazy
  6. RawAnnotator
  7. HasOutputAnnotationCol
  8. HasInputAnnotationCols
  9. HasOutputAnnotatorType
  10. ParamsAndFeaturesWritable
  11. HasFeatures
  12. DefaultParamsWritable
  13. MLWritable
  14. Model
  15. Transformer
  16. PipelineStage
  17. Logging
  18. Params
  19. Serializable
  20. Serializable
  21. Identifiable
  22. AnyRef
  23. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Router()
  2. new Router(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
    Definition Classes
    Router → AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]
    Definition Classes
    Router → HasSimpleAnnotate
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Definition Classes
    Router → AnnotatorModel
  14. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  15. def checkValidEnvironment(spark: Option[SparkContext]): Unit
    Definition Classes
    CheckLicense
  16. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  17. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkContext], checkLp: Boolean): Unit
    Definition Classes
    CheckLicense
  18. final def clear(param: Param[_]): Router.this.type
    Definition Classes
    Params
  19. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  20. def copy(extra: ParamMap): Router
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  21. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  22. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. def dfAnnotate: UserDefinedFunction
    Definition Classes
    HasSimpleAnnotate
  24. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  25. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  26. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  27. def explainParams(): String
    Definition Classes
    Params
  28. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  29. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  30. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  31. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  32. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  33. val filterFieldsElements: StringArrayParam

    The filterfieldsElements are the allowed values for the metadata field that is being used

  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 getFilterFieldsElements(): Array[String]
  43. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  44. def getInputType(): String
  45. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  46. def getMetadataField(): String
  47. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  48. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  49. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  50. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  51. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  52. def hasParent: Boolean
    Definition Classes
    Model
  53. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  54. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  55. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  56. lazy val inputAnnotatorTypes: Array[String]
    Definition Classes
    Router → HasInputAnnotationCols
  57. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  58. val inputType: Param[String]

    The type of the entity that you want to filter by default sentence_embeddings.Possible values document|token|wordpiece|word_embeddings| sentence_embeddings|category|date|sentiment|pos|chunk|named_entity|regex|dependency|labeled_dependency|language|keyword

  59. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  60. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  61. def isLp(): Boolean
    Definition Classes
    CheckLicense
  62. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  63. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  64. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  65. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  66. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  73. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. val metadataField: Param[String]

    The metadataField is the field that in metadata that you want to filter (by default 'entity')

  78. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  79. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  80. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  81. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  82. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  83. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  84. lazy val outputAnnotatorType: AnnotatorType
    Definition Classes
    Router → HasOutputAnnotatorType
  85. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  86. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  87. var parent: Estimator[Router]
    Definition Classes
    Model
  88. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  89. def set[T](feature: StructFeature[T], value: T): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  90. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  91. def set[T](feature: SetFeature[T], value: Set[T]): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  92. def set[T](feature: ArrayFeature[T], value: Array[T]): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. final def set(paramPair: ParamPair[_]): Router.this.type
    Attributes
    protected
    Definition Classes
    Params
  94. final def set(param: String, value: Any): Router.this.type
    Attributes
    protected
    Definition Classes
    Params
  95. final def set[T](param: Param[T], value: T): Router.this.type
    Definition Classes
    Params
  96. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  97. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  98. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  99. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): Router.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  100. final def setDefault(paramPairs: ParamPair[_]*): Router.this.type
    Attributes
    protected
    Definition Classes
    Params
  101. final def setDefault[T](param: Param[T], value: T): Router.this.type
    Attributes
    protected
    Definition Classes
    Params
  102. def setFilterFieldsElements(value: Array[String]): Router
  103. final def setInputCols(value: String*): Router.this.type
    Definition Classes
    HasInputAnnotationCols
  104. def setInputCols(value: Array[String]): Router.this.type
    Definition Classes
    HasInputAnnotationCols
  105. def setInputType(value: String): Router
  106. def setLazyAnnotator(value: Boolean): Router.this.type
    Definition Classes
    CanBeLazy
  107. def setMetadataField(value: String): Router
  108. final def setOutputCol(value: String): Router.this.type
    Definition Classes
    HasOutputAnnotationCol
  109. def setParent(parent: Estimator[Router]): Router
    Definition Classes
    Model
  110. val storageRef: Param[String]
  111. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  112. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  113. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  114. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  115. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  116. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  117. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  118. val uid: String
    Definition Classes
    Router → Identifiable
  119. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  120. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  121. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  122. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  123. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  124. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from CheckLicense

Inherited from HasSimpleAnnotate[Router]

Inherited from AnnotatorModel[Router]

Inherited from CanBeLazy

Inherited from RawAnnotator[Router]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[Router]

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

Members