c

com.johnsnowlabs.nlp.annotators.deid

ObfuscatorAnnotatorModel

class ObfuscatorAnnotatorModel extends AnnotatorModel[ObfuscatorAnnotatorModel] with ObfuscatorParams with DeidModelParams with HasSimpleAnnotate[ObfuscatorAnnotatorModel]

Linear Supertypes
HasSimpleAnnotate[ObfuscatorAnnotatorModel], DeidModelParams, ObfuscatorParams, BaseDeidParams, AnnotatorModel[ObfuscatorAnnotatorModel], CanBeLazy, RawAnnotator[ObfuscatorAnnotatorModel], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[ObfuscatorAnnotatorModel], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. ObfuscatorAnnotatorModel
  2. HasSimpleAnnotate
  3. DeidModelParams
  4. ObfuscatorParams
  5. BaseDeidParams
  6. AnnotatorModel
  7. CanBeLazy
  8. RawAnnotator
  9. HasOutputAnnotationCol
  10. HasInputAnnotationCols
  11. HasOutputAnnotatorType
  12. ParamsAndFeaturesWritable
  13. HasFeatures
  14. DefaultParamsWritable
  15. MLWritable
  16. Model
  17. Transformer
  18. PipelineStage
  19. Logging
  20. Params
  21. Serializable
  22. Serializable
  23. Identifiable
  24. AnyRef
  25. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

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. val ageRanges: IntArrayParam

    List of integers specifying limits of the age groups to preserve during obfuscation

    List of integers specifying limits of the age groups to preserve during obfuscation

    Definition Classes
    BaseDeidParams
  12. val ageRangesByHipaa: BooleanParam

    A Boolean variable indicating whether to obfuscate ages based on HIPAA (Health Insurance Portability and Accountability Act) Privacy Rule.

    A Boolean variable indicating whether to obfuscate ages based on HIPAA (Health Insurance Portability and Accountability Act) Privacy Rule.

    The HIPAA Privacy Rule mandates that ages from patients older than 90 years must be obfuscated, while age for patients 90 years or younger can remain unchanged.

    When true, age entities larger than 90 will be obfuscated as per HIPAA Privacy Rule, the others will remain unchanged. When false, ageRanges parameter is valid.

    Definition Classes
    ObfuscatorParams
  13. val allTerms: SetFeature[String]
  14. def annotate(annotations: Seq[Annotation]): Seq[Annotation]
    Definition Classes
    ObfuscatorAnnotatorModel → HasSimpleAnnotate
  15. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  16. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  17. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  18. final def clear(param: Param[_]): ObfuscatorAnnotatorModel.this.type
    Definition Classes
    Params
  19. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  20. val consistentAcrossNameParts: BooleanParam

    Param that indicates whether consistency should be enforced across different parts of a name (e.g., first name, middle name, last name).

    Param that indicates whether consistency should be enforced across different parts of a name (e.g., first name, middle name, last name). When set to true, the same transformation or obfuscation will be applied consistently to all parts of the same name entity, even if those parts appear separately.

    For example, if "John Smith" is obfuscated as "Liam Brown", then:

    • When the full name "John Smith" appears, it will be replaced with "Liam Brown"
    • When "John" or "Smith" appear individually, they will still be obfuscated as "Liam" and "Brown" respectively, ensuring consistency in name transformation.

    Default: true

    Definition Classes
    BaseDeidParams
  21. def copy(extra: ParamMap): ObfuscatorAnnotatorModel
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  22. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. val dateFormats: StringArrayParam

    Format of dates to displace

    Format of dates to displace

    Definition Classes
    BaseDeidParams
  24. val days: IntParam

    Number of days to obfuscate the dates by displacement.

    Number of days to obfuscate the dates by displacement. If not provided a random integer between 1 and 60 will be used

    Definition Classes
    BaseDeidParams
  25. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  26. def dfAnnotate: UserDefinedFunction
    Definition Classes
    HasSimpleAnnotate
  27. val entity: Param[String]
    Definition Classes
    ObfuscatorParams
  28. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  29. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  30. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  31. def explainParams(): String
    Definition Classes
    Params
  32. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  33. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  34. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  35. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  36. val fakerLengthOffset: IntParam

    It specifies how much length deviation is accepted in obfuscation, with keepTextSizeForObfuscation enabled.

    It specifies how much length deviation is accepted in obfuscation, with keepTextSizeForObfuscation enabled. Value must be greater than 0. Default is 3.

    Definition Classes
    BaseDeidParams
  37. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  38. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  39. 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
    BaseDeidParams
  40. def generateFakeBySameLength(wordToReplace: String, entity: String): String

    obfuscating digits to new digits, letters to new letters and others remains the same

    obfuscating digits to new digits, letters to new letters and others remains the same

    Definition Classes
    DeidModelParams
  41. def generateFakeBySameLengthUsingHash(wordToReplace: String, entity: String): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  42. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  43. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  44. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  45. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  46. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  47. def getAllTerms: Set[String]
  48. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  49. def getConsistentAcrossNameParts: Boolean

    Gets the value of consistentAcrossNameParts.

    Gets the value of consistentAcrossNameParts.

    returns

    Boolean value indicating if consistency is enforced across name parts

    Definition Classes
    BaseDeidParams
  50. def getDateFormats: Array[String]
    Definition Classes
    BaseDeidParams
  51. def getDays: Int
    Definition Classes
    BaseDeidParams
  52. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  53. def getEntity: String
    Definition Classes
    ObfuscatorParams
  54. def getEntityField(annotation: Annotation): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  55. def getFakeByHashcode(fakes: Seq[String], wordToReplace: String, entity: String, seed: Int): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  56. def getFakeWithSameSize(fakes: Seq[String], wordToReplace: String, entity: String, lengthDeviation: Int, seed: Int): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  57. def getFakerLengthOffset: Int

    Gets fakerLengthOffset param

    Gets fakerLengthOffset param

    Definition Classes
    BaseDeidParams
  58. def getFakersEntity(entity: String, result: String): Seq[String]
    Definition Classes
    DeidModelParams
  59. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  60. def getKeepMonth: Boolean

    Gets keepMonth param

    Gets keepMonth param

    Definition Classes
    ObfuscatorParams
  61. def getKeepTextSizeForObfuscation: Boolean

    Gets keepTextSizeForObfuscation param

    Gets keepTextSizeForObfuscation param

    Definition Classes
    BaseDeidParams
  62. def getKeepYear: Boolean

    Gets keepYear param

    Gets keepYear param

    Definition Classes
    ObfuscatorParams
  63. def getLanguage: String
    Definition Classes
    BaseDeidParams
  64. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  65. def getMaskEntity(entityClazz: String): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  66. def getMaskStatus(entityClass: String): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  67. def getMaxSentence(annotations: Seq[Annotation]): Int
    Attributes
    protected
    Definition Classes
    DeidModelParams
  68. def getObfuscateRefSource: String
    Definition Classes
    BaseDeidParams
  69. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  70. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  71. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  72. def getSameLengthFormattedEntities(): Array[String]
    Definition Classes
    BaseDeidParams
  73. def getSeed(): Int
    Definition Classes
    BaseDeidParams
  74. def getUnnormalizedDateMode: String

    Gets unnormalizedDateMode param

    Gets unnormalizedDateMode param

    Definition Classes
    ObfuscatorParams
  75. def getValidAgeRanges: Array[Int]

    Gets validAgeRanges parameter

    Gets validAgeRanges parameter

    Attributes
    protected
    Definition Classes
    ObfuscatorAnnotatorModel → DeidModelParams
  76. def handleCasing(originalFake: String, wordToReplace: String): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  77. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  78. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  79. def hasParent: Boolean
    Definition Classes
    Model
  80. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  81. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  82. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  83. val inputAnnotatorTypes: Array[AnnotatorType]
    Definition Classes
    ObfuscatorAnnotatorModel → HasInputAnnotationCols
  84. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  85. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  86. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  87. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  88. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  89. val keepMonth: BooleanParam

    Whether to keep the month intact when obfuscating date entities.

    Whether to keep the month intact when obfuscating date entities. If true, the month will remain unchanged during the obfuscation process. If false, the month will be modified along with the year and day. Default: false.

    Definition Classes
    ObfuscatorParams
  90. val keepTextSizeForObfuscation: BooleanParam

    It specifies whether the output should maintain the same character length as the input text.

    It specifies whether the output should maintain the same character length as the input text. the output text will remain the same if same length is available, else length might vary.

    Definition Classes
    BaseDeidParams
  91. val keepYear: BooleanParam

    Whether to keep the year intact when obfuscating date entities.

    Whether to keep the year intact when obfuscating date entities. If true, the year will remain unchanged during the obfuscation process. If false, the year will be modified along with the month and day. Default: false.

    Definition Classes
    ObfuscatorParams
  92. val language: Param[String]

    The language used to select the regex file and some faker entities.

    The language used to select the regex file and some faker entities. 'en'(English),'de'(German), 'es'(Spanish), 'fr'(French), 'ar'(Arabic) or 'ro'(Romanian) Default:'en'

    Definition Classes
    BaseDeidParams
  93. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  94. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  95. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  96. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  97. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  98. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  99. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  100. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  101. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  102. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  103. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  104. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  105. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  106. def maskEntity(annotation: Annotation, maskingPolicy: String, maskedEntity: String, fixedMaskLength: Int): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  107. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  108. val nameEntities: Seq[String]
    Attributes
    protected
    Definition Classes
    DeidModelParams
  109. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  110. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  111. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  112. def obfuscateNameEntity(originalName: String, keepTextSize: Boolean, lengthDeviation: Int, namePartsMemory: Map[String, String]): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  113. val obfuscateRefSource: Param[String]

    The source of obfuscation to obfuscate the entities.

    The source of obfuscation to obfuscate the entities. The values ar the following: 'file': Takes the entities from the obfuscatorRefFile 'faker': Takes the entities from the Faker module 'both': Takes the entities from the obfuscatorRefFile and the faker module randomly.

    Definition Classes
    BaseDeidParams
  114. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  115. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  116. val outputAnnotatorType: AnnotatorType
    Definition Classes
    ObfuscatorAnnotatorModel → HasOutputAnnotatorType
  117. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  118. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  119. var parent: Estimator[ObfuscatorAnnotatorModel]
    Definition Classes
    Model
  120. val random: SecureRandom
    Attributes
    protected
    Definition Classes
    DeidModelParams
  121. val region: Param[String]

    With this property, you can select particular dateFormats.

    With this property, you can select particular dateFormats. This property is especially used when obfuscating dates. You can decide whether the first part of 11/11/2023 is a day or the second part is a day when obfuscating dates. The values are following: 'eu' for European Union 'us' for USA Default: 'eu'

    Definition Classes
    ObfuscatorParams
  122. val sameLengthFormattedEntities: StringArrayParam

    List of formatted entities to generate the same length outputs as original ones during obfuscation.

    List of formatted entities to generate the same length outputs as original ones during obfuscation. The supported and default formatted entities are: "phone", "fax", "contact," "id", "idnum", "bioid", "medicalrecord", "zip", "vin", "ssn", "dln", "plate", "license", "IRS", "CFN", "account".

    Definition Classes
    BaseDeidParams
  123. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  124. val seed: IntParam

    It is the seed to select the entities on obfuscate mode.

    It is the seed to select the entities on obfuscate mode. With the seed, you can reply to an execution several times with the same output.

    Definition Classes
    BaseDeidParams
  125. def selectFakeFromAllFakes(wordToReplace: String, entityClass: String, maskedEntity: String, allFakes: Seq[String]): String
    Attributes
    protected
    Definition Classes
    DeidModelParams
  126. def set[T](feature: StructFeature[T], value: T): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  127. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  128. def set[T](feature: SetFeature[T], value: Set[T]): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  129. def set[T](feature: ArrayFeature[T], value: Array[T]): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  130. final def set(paramPair: ParamPair[_]): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  131. final def set(param: String, value: Any): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  132. final def set[T](param: Param[T], value: T): ObfuscatorAnnotatorModel.this.type
    Definition Classes
    Params
  133. def setAgeRanges(mode: Array[Int]): ObfuscatorAnnotatorModel.this.type

    List of integers specifying limits of the age groups to preserve during obfuscation

    List of integers specifying limits of the age groups to preserve during obfuscation

    Definition Classes
    BaseDeidParams
  134. def setAgeRangesByHipaa(value: Boolean): ObfuscatorAnnotatorModel.this.type

    Sets whether to obfuscate ages based on HIPAA (Health Insurance Portability and Accountability Act) Privacy Rule.

    Sets whether to obfuscate ages based on HIPAA (Health Insurance Portability and Accountability Act) Privacy Rule.

    The HIPAA Privacy Rule mandates that ages from patients older than 90 years must be obfuscated, while age for patients 90 years or younger can remain unchanged.

    value

    If true, age entities larger than 90 will be obfuscated as per HIPAA Privacy Rule, the others will remain unchanged. If false, ageRanges parameter is valid. Default: false.

    Definition Classes
    ObfuscatorParams
  135. def setAllTerms(value: Set[String]): ObfuscatorAnnotatorModel.this.type
  136. def setConsistentAcrossNameParts(value: Boolean): ObfuscatorAnnotatorModel.this.type

    Sets the value of consistentAcrossNameParts.

    Sets the value of consistentAcrossNameParts.

    value

    Boolean flag to enforce consistency across name parts

    returns

    this instance

    Definition Classes
    BaseDeidParams
  137. def setDateFormats(s: Array[String]): ObfuscatorAnnotatorModel.this.type

    Format of dates to displace

    Format of dates to displace

    Definition Classes
    BaseDeidParams
  138. def setDays(k: Int): ObfuscatorAnnotatorModel.this.type

    Number of days to obfuscate the dates by displacement.

    Number of days to obfuscate the dates by displacement. If not provided a random integer between 1 and 60 will be used

    Definition Classes
    BaseDeidParams
  139. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  140. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  141. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  142. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  143. final def setDefault(paramPairs: ParamPair[_]*): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected
    Definition Classes
    Params
  144. final def setDefault[T](param: Param[T], value: T): ObfuscatorAnnotatorModel.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  145. def setEntity(e: String): ObfuscatorAnnotatorModel.this.type
    Definition Classes
    ObfuscatorParams
  146. def setFakerLengthOffset(value: Int): ObfuscatorAnnotatorModel.this.type

    Sets fakerLengthOffset param

    Sets fakerLengthOffset param

    Definition Classes
    BaseDeidParams
  147. def setGenderAwareness(value: Boolean): ObfuscatorAnnotatorModel.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
    BaseDeidParams
  148. final def setInputCols(value: String*): ObfuscatorAnnotatorModel.this.type
    Definition Classes
    HasInputAnnotationCols
  149. def setInputCols(value: Array[String]): ObfuscatorAnnotatorModel.this.type
    Definition Classes
    HasInputAnnotationCols
  150. def setKeepMonth(value: Boolean): ObfuscatorAnnotatorModel.this.type

    Sets whether to keep the month intact when obfuscating date entities.

    Sets whether to keep the month intact when obfuscating date entities. If true, the month will remain unchanged during the obfuscation process. If false, the month will be modified along with the year and day. Default: false.

    Definition Classes
    ObfuscatorParams
  151. def setKeepTextSizeForObfuscation(value: Boolean): ObfuscatorAnnotatorModel.this.type

    Sets keepTextSizeForObfuscation param

    Sets keepTextSizeForObfuscation param

    Definition Classes
    BaseDeidParams
  152. def setKeepYear(value: Boolean): ObfuscatorAnnotatorModel.this.type

    Sets whether to keep the year intact when obfuscating date entities.

    Sets whether to keep the year intact when obfuscating date entities. If true, the year will remain unchanged during the obfuscation process. If false, the year will be modified along with the month and day. Default: false.

    Definition Classes
    ObfuscatorParams
  153. def setLanguage(s: String): ObfuscatorAnnotatorModel.this.type

    The language used to select the regex file and some faker entities.

    The language used to select the regex file and some faker entities. 'en'(English),'de'(German), 'es'(Spanish), 'fr'(French), 'ar'(Arabic) or 'ro'(Romanian). Default:'en'

    Definition Classes
    BaseDeidParams
  154. def setLazyAnnotator(value: Boolean): ObfuscatorAnnotatorModel.this.type
    Definition Classes
    CanBeLazy
  155. def setObfuscateRefSource(s: String): ObfuscatorAnnotatorModel.this.type

    The source of obfuscation to obfuscate the entities.

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

    Definition Classes
    BaseDeidParams
  156. final def setOutputCol(value: String): ObfuscatorAnnotatorModel.this.type
    Definition Classes
    HasOutputAnnotationCol
  157. def setParent(parent: Estimator[ObfuscatorAnnotatorModel]): ObfuscatorAnnotatorModel
    Definition Classes
    Model
  158. def setRegion(s: String): ObfuscatorAnnotatorModel.this.type

    With this property, you can select particular dateFormats.

    With this property, you can select particular dateFormats. This property is especially used when obfuscating dates. You can decide whether the first part of 11/11/2023 is a day or the second part is a day when obfuscating dates. The values are following: 'eu' for European Union 'us' for USA Default: 'eu'

    Definition Classes
    ObfuscatorParams
  159. def setSameLengthFormattedEntities(entities: Array[String]): ObfuscatorAnnotatorModel.this.type

    List of formatted entities to generate the same length outputs as original ones during obfuscation.

    List of formatted entities to generate the same length outputs as original ones during obfuscation. The supported and default formatted entities are: PHONE, FAX, CONTACT, ID, IDNUM, BIOID, MEDICALRECORD, ZIP, VIN, SSN, DLN, LICENSE, PLATE, IRS, CFN, ACCOUNT.

    Definition Classes
    BaseDeidParams
  160. def setSeed(s: Int): ObfuscatorAnnotatorModel.this.type

    It is the seed to select the entities on obfuscate mode.

    It is the seed to select the entities on obfuscate mode. With the seed, you can reply to an execution several times with the same output.

    Definition Classes
    DeidModelParams → BaseDeidParams
  161. def setUnnormalizedDateMode(mode: String): ObfuscatorAnnotatorModel.this.type

    The mode to use if the date is not formatted.

    The mode to use if the date is not formatted. [mask, obfuscate, skip] Default: obfuscate

    Definition Classes
    ObfuscatorParams
  162. def setUseRandomDateDisplacement(s: Boolean): ObfuscatorAnnotatorModel.this.type

    Use a random displacement days in dates entities,that random number is based on the BaseDeidParams.seed If true use random displacement days in dates entities, if false use the BaseDeidParams.days The default value is false.

    Use a random displacement days in dates entities,that random number is based on the BaseDeidParams.seed If true use random displacement days in dates entities, if false use the BaseDeidParams.days The default value is false.

    Definition Classes
    ObfuscatorParams
  163. def shouldUseConsistentNameParts(entityClass: String): Boolean
    Attributes
    protected
    Definition Classes
    DeidModelParams
  164. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  165. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  166. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  167. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  168. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  169. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  170. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  171. val uid: String
    Definition Classes
    ObfuscatorAnnotatorModel → Identifiable
  172. val unnormalizedDateMode: Param[String]

    The mode to use if the date is not formatted.

    The mode to use if the date is not formatted. [mask, obfuscate, skip] Default: obfuscate

    Definition Classes
    ObfuscatorParams
  173. val useRandomDateDisplacement: BooleanParam

    Use a random displacement days in dates entities,that random number is based on the seed If true use random displacement days in dates entities,if false use the ObfuscatorParams.days The default value is false.

    Use a random displacement days in dates entities,that random number is based on the seed If true use random displacement days in dates entities,if false use the ObfuscatorParams.days The default value is false.

    Definition Classes
    ObfuscatorParams
  174. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  175. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  176. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  177. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  178. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  179. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from HasSimpleAnnotate[ObfuscatorAnnotatorModel]

Inherited from DeidModelParams

Inherited from ObfuscatorParams

Inherited from BaseDeidParams

Inherited from AnnotatorModel[ObfuscatorAnnotatorModel]

Inherited from CanBeLazy

Inherited from RawAnnotator[ObfuscatorAnnotatorModel]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[ObfuscatorAnnotatorModel]

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

Parameter setters

Ungrouped