c

com.johnsnowlabs.nlp.annotators.deid

NameChunkObfuscator

class NameChunkObfuscator extends AnnotatorModel[NameChunkObfuscator] with HasSimpleAnnotate[NameChunkObfuscator] with NameChunkObfuscatorParams with CheckLicense

Contains all the parameters to transform a dataset with an Input Annotation of type CHUNK, into its obfuscated version of by obfuscating the given CHUNKS. Model can obfuscate the given names, remain others same.

To create an configured NameChunkObfuscator, please see the example of NameChunkObfuscatorApproach.

See also

NameChunkObfuscatorParams to see params

NameChunkObfuscatorApproach to train your own model

Linear Supertypes
CheckLicense, NameChunkObfuscatorParams, HasSimpleAnnotate[NameChunkObfuscator], AnnotatorModel[NameChunkObfuscator], CanBeLazy, RawAnnotator[NameChunkObfuscator], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[NameChunkObfuscator], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. NameChunkObfuscator
  2. CheckLicense
  3. NameChunkObfuscatorParams
  4. HasSimpleAnnotate
  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 NameChunkObfuscator()
  2. new NameChunkObfuscator(uid: String)

    uid

    a unique identifier for the instanced 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
    NameChunkObfuscator → 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], metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  16. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  17. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  18. def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  19. final def clear(param: Param[_]): NameChunkObfuscator.this.type
    Definition Classes
    Params
  20. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  21. def copy(extra: ParamMap): NameChunkObfuscator
    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. final val extraInputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  30. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  31. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  32. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  33. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  34. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  35. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  36. val genderAwareness: BooleanParam

    Whether to use gender-aware names or not during obfuscation.

    Whether to use gender-aware names or not during obfuscation. This param effects only names. If value is true, it might decrease performance. Default: False

    Definition Classes
    NameChunkObfuscatorParams
  37. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  39. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  40. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  41. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  42. def getAllTerms: Map[String, Seq[String]]

    dictionary, which contains all names from file for using later

  43. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  44. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  45. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  46. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  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. val inputAnnotatorTypes: Array[String]
    Definition Classes
    NameChunkObfuscator → HasInputAnnotationCols
  57. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  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 language: Param[String]

    The language used to select some faker names The values are the following: 'en'(English), 'de'(German), 'es'(Spanish), 'fr'(French), 'ar'(Arabic) or 'ro'(Romanian).

    The language used to select some faker names The values are the following: 'en'(English), 'de'(German), 'es'(Spanish), 'fr'(French), 'ar'(Arabic) or 'ro'(Romanian). Default:'en'

    Definition Classes
    NameChunkObfuscatorParams
  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. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  77. val nameEntities: StringArrayParam

    The nameEntities used to select entities during obfuscation.

    The nameEntities used to select entities during obfuscation. The supported name entities are NAME, PATIENT, and DOCTOR. Default: NAME

    Definition Classes
    NameChunkObfuscatorParams
  78. val namesTerm: StructFeature[Map[String, Seq[String]]]
  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. val obfuscateRefSource: Param[String]

    The source of obfuscation to obfuscate the names.

    The source of obfuscation to obfuscate the names. The values are the following: "file": Takes the names from the obfuscatorRefFile. "faker": Takes the names from the Faker module. "both": Takes the names from the obfuscatorRefFile and the faker module randomly. Default: "both"

    Definition Classes
    NameChunkObfuscatorParams
  83. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  84. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  85. val outputAnnotatorType: AnnotatorType
    Definition Classes
    NameChunkObfuscator → HasOutputAnnotatorType
  86. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  87. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  88. var parent: Estimator[NameChunkObfuscator]
    Definition Classes
    Model
  89. val sameLength: BooleanParam

    The sameLength used to select the same length names as original ones during obfuscation.

    The sameLength used to select the same length names as original ones during obfuscation. Example: 'John' --> 'Mike'. Default: true

    Definition Classes
    NameChunkObfuscatorParams
  90. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  91. val seed: IntParam

    It is the seed to select the names.With the seed you can reply an execution several times with the same output.

    It is the seed to select the names.With the seed you can reply an execution several times with the same output.

    Definition Classes
    NameChunkObfuscatorParams
  92. def set[T](feature: StructFeature[T], value: T): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. def set[T](feature: SetFeature[T], value: Set[T]): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  95. def set[T](feature: ArrayFeature[T], value: Array[T]): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  96. final def set(paramPair: ParamPair[_]): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    Params
  97. final def set(param: String, value: Any): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    Params
  98. final def set[T](param: Param[T], value: T): NameChunkObfuscator.this.type
    Definition Classes
    Params
  99. def setAllTerms(value: Map[String, Seq[String]]): NameChunkObfuscator.this.type
  100. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  101. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  104. final def setDefault(paramPairs: ParamPair[_]*): NameChunkObfuscator.this.type
    Attributes
    protected
    Definition Classes
    Params
  105. final def setDefault[T](param: Param[T], value: T): NameChunkObfuscator.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  106. def setExtraInputCols(value: Array[String]): NameChunkObfuscator.this.type
    Definition Classes
    HasInputAnnotationCols
  107. def setGenderAwareness(value: Boolean): NameChunkObfuscator.this.type

    Whether to use gender-aware names or not during obfuscation.

    Whether to use gender-aware names or not during obfuscation. This param effects only names. If value is true, it might decrease performance. Default: False

    Definition Classes
    NameChunkObfuscatorParams
  108. final def setInputCols(value: String*): NameChunkObfuscator.this.type
    Definition Classes
    HasInputAnnotationCols
  109. def setInputCols(value: Array[String]): NameChunkObfuscator.this.type
    Definition Classes
    HasInputAnnotationCols
  110. def setLanguage(s: String): NameChunkObfuscator.this.type

    The language used to select some faker names.

    The language used to select some faker names. The values are the following: 'en'(English), 'de'(German), 'es'(Spanish), 'fr'(French), 'ar'(Arabic) or 'ro'(Romanian). Default:'en'

    Definition Classes
    NameChunkObfuscatorParams
  111. def setLazyAnnotator(value: Boolean): NameChunkObfuscator.this.type
    Definition Classes
    CanBeLazy
  112. def setNameEntities(value: Array[String]): NameChunkObfuscator.this.type

    The nameEntities used to select entities during obfuscation.

    The nameEntities used to select entities during obfuscation. The supported name entities are NAME, PATIENT, and DOCTOR. Default: NAME

    Definition Classes
    NameChunkObfuscatorParams
  113. def setObfuscateRefSource(s: String): NameChunkObfuscator.this.type

    The source of obfuscation to obfuscate the names.

    The source of obfuscation to obfuscate the names. The values are the following: "file": Takes the names from the obfuscatorRefFile. "faker": Takes the names from the Faker module. "both": Takes the names from the obfuscatorRefFile and the faker module randomly. Default: "both"

    Definition Classes
    NameChunkObfuscatorParams
  114. final def setOutputCol(value: String): NameChunkObfuscator.this.type
    Definition Classes
    HasOutputAnnotationCol
  115. def setParent(parent: Estimator[NameChunkObfuscator]): NameChunkObfuscator
    Definition Classes
    Model
  116. def setSameLength(value: Boolean): NameChunkObfuscator.this.type

    The sameLength used to select the same length names as original ones during obfuscation.

    The sameLength used to select the same length names as original ones during obfuscation. Example: 'John' --> 'Mike'. Default: true

    Definition Classes
    NameChunkObfuscatorParams
  117. def setSeed(s: Int): NameChunkObfuscator.this.type

    It is the seed to select the names.With the seed you can reply an execution several times with the same output.

    It is the seed to select the names.With the seed you can reply an execution several times with the same output.

    Definition Classes
    NameChunkObfuscatorParams
  118. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  119. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  120. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  121. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  122. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  123. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  124. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  125. val uid: String
    Definition Classes
    NameChunkObfuscator → Identifiable
  126. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  127. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  128. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  129. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  130. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  131. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from CheckLicense

Inherited from NameChunkObfuscatorParams

Inherited from HasSimpleAnnotate[NameChunkObfuscator]

Inherited from AnnotatorModel[NameChunkObfuscator]

Inherited from CanBeLazy

Inherited from RawAnnotator[NameChunkObfuscator]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[NameChunkObfuscator]

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

Parameter setters

Parameter getters