class Replacer extends AnnotatorModel[NerQuestionGenerator] with HasSimpleAnnotate[NerQuestionGenerator] with CheckLicense

Replaces entities in the original text with new ones.

This class allows to replace entities in the original text with the ones obtained with, for example, DeIdentificationModel or DateNormalizer.

Example

val documentAssembler = DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("sentence")

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

val word_embeddings = WordEmbeddingsModel.pretrained("embeddings_clinical", "en", "clinical/models")
        .setInputCols(["sentence", "token"])
        .setOutputCol("embeddings")

val clinical_ner = MedicalNerModel.pretrained("ner_deid_generic_augmented", "en", "clinical/models")
        .setInputCols(["sentence", "token", "embeddings"])
        .setOutputCol("ner")

val ner_converter_name = NerConverterInternal()
        .setInputCols(["sentence","token","ner"])
        .setOutputCol("ner_chunk")

val nameChunkObfuscator = NameChunkObfuscatorApproach()
    .setInputCols("ner_chunk")
    .setOutputCol("replacement")
    .setRefFileFormat("csv")
    .setObfuscateRefFile("names_test.txt")
    .setRefSep("#")

val replacer_name = Replacer()
    .setInputCols("replacement","sentence")
    .setOutputCol("obfuscated_document_name")
    .setUseReplacement(True)

val nlpPipeline = new Pipeline().setStages=Array(
        documentAssembler,
        tokenizer,
        word_embeddings,
        clinical_ner,
        ner_converter_name,
        nameChunkObfuscator,
        replacer_name,
        ))

val empty_data = spark.createDataFrame([[""]]).toDF("text")
val model_chunck_obfuscator = nlpPipeline.fit(empty_data)
val sample_text = "John Davies is a 62 y.o. patient admitted. Mr. Davies was seen by attending physician Dr. Lorand and was scheduled for emergency assessment."
val lmodel = new LightPipeline(model_chunck_obfuscator)
val res = lmodel.fullAnnotate(sample_text)
"Original text.  : " + res[0]['sentence'][0].result)
"Obfuscated text : " + res[0]['obfuscated_document_name'][0].result)
Original text.  :  John Davies is a 62 y.o. patient admitted. Mr. Davies was seen by attending physician Dr. Lorand and was scheduled for emergency assessment.
Obfuscated text :  Fitzpatrick is a <AGE> y.o. patient admitted. Mr. Bowman was seen by attending physician Dr. Acosta and was scheduled for emergency assessment.
Linear Supertypes
CheckLicense, HasSimpleAnnotate[NerQuestionGenerator], AnnotatorModel[NerQuestionGenerator], CanBeLazy, RawAnnotator[NerQuestionGenerator], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[NerQuestionGenerator], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. Replacer
  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 Replacer()
  2. new Replacer(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
    Replacer → AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]
    Definition Classes
    Replacer → 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[_]): Replacer.this.type
    Definition Classes
    Params
  20. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  21. def copy(extra: ParamMap): NerQuestionGenerator
    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 getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  44. def getMappingsColumn: String
  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. def getReturnEntityMappings: Boolean
  49. def getStaticEntityMappings: Map[String, String]
  50. def getStaticEntityMappingsStr: String
  51. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  52. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  53. def hasParent: Boolean
    Definition Classes
    Model
  54. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  55. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  56. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  57. val inputAnnotatorTypes: Array[String]

    Input annotator types: DOCUMENT, CHUNK

    Input annotator types: DOCUMENT, CHUNK

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

    This column maps the annotations to their corresponding chunks before the entities are replaced

  77. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  78. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  79. val noneValuesTo: Param[String]

    Determines the action to take when encountering a value of 'NONE' in the annotation.

    Determines the action to take when encountering a value of 'NONE' in the annotation. This parameter can take one of the following three string values: - "entity": Replaces 'NONE' values with the entity field extracted from the annotation, if available. If the entity field is not available, it uses the string "NONE" wrapped by the specified delimiters. - "place_holder": Replaces 'NONE' values with a placeholder string wrapped by the specified delimiters. - "skip": Retains the original annotation result or uses the target_text from the annotation's metadata if available. - "prioritize_static_entity": If a static entity mapping is available for the entity type, it will use this values for mapping. Allowed Values: "entity", "place_holder", "skip", "prioritize_static_entity" Error Handling: If an unrecognized value is provided, an IllegalArgumentException will be thrown.

  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. val outputAnnotatorType: AnnotatorType

    Output annotator types: DOCUMENT

    Output annotator types: DOCUMENT

    Definition Classes
    Replacer → 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[NerQuestionGenerator]
    Definition Classes
    Model
  88. val placeHolder: Param[String]

    Specifies the placeholder string to use when noneValuesTo is set to "place_holder".

    Specifies the placeholder string to use when noneValuesTo is set to "place_holder". This placeholder string will be wrapped by the delimiters if placeHolderDelimiters are defined.

  89. val placeHolderDelimiters: StringArrayParam

    An array of two strings used as delimiters to wrap the placeholder or entity field when noneValuesTo is set to "place_holder" or "entity".

    An array of two strings used as delimiters to wrap the placeholder or entity field when noneValuesTo is set to "place_holder" or "entity". The first element of the array is the prefix delimiter, and the second element is the suffix delimiter.

  90. val returnEntityMappings: BooleanParam

    With this property, you can select if you want to return mapping column.

  91. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  92. def set[T](feature: StructFeature[T], value: T): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. def set[T](feature: SetFeature[T], value: Set[T]): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  95. def set[T](feature: ArrayFeature[T], value: Array[T]): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  96. final def set(paramPair: ParamPair[_]): Replacer.this.type
    Attributes
    protected
    Definition Classes
    Params
  97. final def set(param: String, value: Any): Replacer.this.type
    Attributes
    protected
    Definition Classes
    Params
  98. final def set[T](param: Param[T], value: T): Replacer.this.type
    Definition Classes
    Params
  99. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  100. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  101. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): Replacer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. final def setDefault(paramPairs: ParamPair[_]*): Replacer.this.type
    Attributes
    protected
    Definition Classes
    Params
  104. final def setDefault[T](param: Param[T], value: T): Replacer.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  105. final def setInputCols(value: String*): Replacer.this.type
    Definition Classes
    HasInputAnnotationCols
  106. def setInputCols(value: Array[String]): Replacer.this.type
    Definition Classes
    HasInputAnnotationCols
  107. def setLazyAnnotator(value: Boolean): Replacer.this.type
    Definition Classes
    CanBeLazy
  108. def setMappingsColumn(s: String): Replacer.this.type

    This column maps the annotations to their corresponding chunks before the entities are replaced

  109. def setNoneValuesTo(value: String): Replacer.this.type

    Determines the action to take when encountering a value of 'NONE' in the annotation.

    Determines the action to take when encountering a value of 'NONE' in the annotation. This parameter can take one of the following three string values: - "entity": Replaces 'NONE' values with the entity field extracted from the annotation, if available. If the entity field is not available, it uses the string "NONE" wrapped by the specified delimiters. - "place_holder": Replaces 'NONE' values with a placeholder string wrapped by the specified delimiters. - "skip": Retains the original target_text from the annotation's metadata if available. If not available, it retains the original annotation result. - "prioritize_static_entity": If a static entity mapping is available for the entity type, it will use this values for mapping. Allowed Values: "entity", "place_holder", "skip", "prioritize_static_entity" Error Handling: If an unrecognized value is provided, an IllegalArgumentException will be thrown.

  110. final def setOutputCol(value: String): Replacer.this.type
    Definition Classes
    HasOutputAnnotationCol
  111. def setParent(parent: Estimator[NerQuestionGenerator]): NerQuestionGenerator
    Definition Classes
    Model
  112. def setPlaceHolder(value: String): Replacer.this.type

    Sets the placeholder string to use when noneValuesTo is set to "place_holder".

    Sets the placeholder string to use when noneValuesTo is set to "place_holder". This placeholder string will be wrapped by the delimiters defined in placeHolderDelimiters.

  113. def setPlaceHolderDelimiters(value: Array[String]): Replacer.this.type

    Sets an array of two strings used as delimiters to wrap the placeholder or entity field when noneValuesTo is set to "place_holder" or "entity".

    Sets an array of two strings used as delimiters to wrap the placeholder or entity field when noneValuesTo is set to "place_holder" or "entity". The first element of the array is the prefix delimiter, and the second element is the suffix delimiter.

  114. def setReturnEntityMappings(s: Boolean): Replacer.this.type

    With this property, you can select if you want to return mapping column.

  115. def setStaticEntityMappings(entities: HashMap[String, String]): Replacer.this.type

    Sets map of entity types to their replacement values

  116. def setStaticEntityMappings(value: Map[String, String]): Replacer.this.type

    Sets map of entity types to their replacement values

  117. def setStaticEntityMappingsFallback(value: String): Replacer.this.type

    Fallback option for static entity mappings.

    Fallback option for static entity mappings. Allowed values: 'entity', 'place_holder', 'skip', 'error'

  118. def setUseReplacement(value: Boolean): Replacer.this.type
  119. val staticEntityMappings: MapFeature[String, String]

    A map of entity types to their replacement values

  120. val staticEntityMappingsFallback: Param[String]

    Fallback option for static entity mappings.

    Fallback option for static entity mappings. Allowed values: 'entity', 'place_holder', 'skip', 'error'

  121. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  122. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  123. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  124. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  125. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  126. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  127. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  128. val uid: String
    Definition Classes
    Replacer → Identifiable
  129. val useReplacement: BooleanParam

    Specifies whether to use the replacement field from the metadata if it exists..

    Specifies whether to use the replacement field from the metadata if it exists.. Default: true.

  130. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  131. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  132. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  133. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  134. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  135. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from CheckLicense

Inherited from HasSimpleAnnotate[NerQuestionGenerator]

Inherited from AnnotatorModel[NerQuestionGenerator]

Inherited from CanBeLazy

Inherited from RawAnnotator[NerQuestionGenerator]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[NerQuestionGenerator]

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