com.johnsnowlabs.nlp.annotators.deid
ObfuscatorAnnotatorApproach
Companion object ObfuscatorAnnotatorApproach
class ObfuscatorAnnotatorApproach extends AnnotatorApproach[ObfuscatorAnnotatorModel] with DeidApproachParams with ObfuscatorParams
- Grouped
- Alphabetic
- By Inheritance
- ObfuscatorAnnotatorApproach
- ObfuscatorParams
- BaseDeidParams
- DeidApproachParams
- AnnotatorApproach
- CanBeLazy
- DefaultParamsWritable
- MLWritable
- HasOutputAnnotatorType
- HasOutputAnnotationCol
- HasInputAnnotationCols
- Estimator
- PipelineStage
- Logging
- Params
- Serializable
- Serializable
- Identifiable
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Instance Constructors
Type Members
-
type
AnnotatorType = String
- Definition Classes
- HasOutputAnnotatorType
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
$[T](param: Param[T]): T
- Attributes
- protected
- Definition Classes
- Params
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
_fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): ObfuscatorAnnotatorModel
- Attributes
- protected
- Definition Classes
- AnnotatorApproach
-
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
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
beforeTraining(spark: SparkSession): Unit
- Definition Classes
- AnnotatorApproach
-
final
def
checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
final
def
clear(param: Param[_]): ObfuscatorAnnotatorApproach.this.type
- Definition Classes
- Params
-
def
clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
final
def
copy(extra: ParamMap): Estimator[ObfuscatorAnnotatorModel]
- Definition Classes
- AnnotatorApproach → Estimator → PipelineStage → Params
-
def
copyValues[T <: Params](to: T, extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
val
dateFormats: StringArrayParam
Format of dates to displace
Format of dates to displace
- Definition Classes
- BaseDeidParams
-
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
-
final
def
defaultCopy[T <: Params](extra: ParamMap): T
- Attributes
- protected
- Definition Classes
- Params
-
val
description: String
- Definition Classes
- ObfuscatorAnnotatorApproach → AnnotatorApproach
-
val
entity: Param[String]
- Definition Classes
- ObfuscatorParams
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
explainParam(param: Param[_]): String
- Definition Classes
- Params
-
def
explainParams(): String
- Definition Classes
- Params
-
final
def
extractParamMap(): ParamMap
- Definition Classes
- Params
-
final
def
extractParamMap(extra: ParamMap): ParamMap
- Definition Classes
- Params
-
def
finalize(): Unit
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
fit(dataset: Dataset[_]): ObfuscatorAnnotatorModel
- Definition Classes
- AnnotatorApproach → Estimator
-
def
fit(dataset: Dataset[_], paramMaps: Seq[ParamMap]): Seq[ObfuscatorAnnotatorModel]
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], paramMap: ParamMap): ObfuscatorAnnotatorModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" )
-
def
fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): ObfuscatorAnnotatorModel
- Definition Classes
- Estimator
- Annotations
- @Since( "2.0.0" ) @varargs()
-
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
-
final
def
get[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
getDateFormats: Array[String]
- Definition Classes
- BaseDeidParams
-
def
getDays: Int
- Definition Classes
- BaseDeidParams
-
final
def
getDefault[T](param: Param[T]): Option[T]
- Definition Classes
- Params
-
def
getInputCols: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
def
getLanguage: String
- Definition Classes
- BaseDeidParams
-
def
getLazyAnnotator: Boolean
- Definition Classes
- CanBeLazy
-
def
getObfuscateRefSource: String
- Definition Classes
- BaseDeidParams
-
final
def
getOrDefault[T](param: Param[T]): T
- Definition Classes
- Params
-
final
def
getOutputCol: String
- Definition Classes
- HasOutputAnnotationCol
-
def
getParam(paramName: String): Param[Any]
- Definition Classes
- Params
-
def
getSameLengthFormattedEntities(): Array[String]
- Definition Classes
- BaseDeidParams
-
def
getSeed(): Int
- Definition Classes
- BaseDeidParams
-
final
def
hasDefault[T](param: Param[T]): Boolean
- Definition Classes
- Params
-
def
hasParam(paramName: String): Boolean
- Definition Classes
- Params
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
def
initializeLogIfNecessary(isInterpreter: Boolean): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
val
inputAnnotatorTypes: Array[AnnotatorType]
- Definition Classes
- ObfuscatorAnnotatorApproach → HasInputAnnotationCols
-
final
val
inputCols: StringArrayParam
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
final
def
isDefined(param: Param[_]): Boolean
- Definition Classes
- Params
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
final
def
isSet(param: Param[_]): Boolean
- Definition Classes
- Params
-
def
isTraceEnabled(): Boolean
- Attributes
- protected
- Definition Classes
- Logging
-
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
-
val
lazyAnnotator: BooleanParam
- Definition Classes
- CanBeLazy
-
def
log: Logger
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logDebug(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logError(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logInfo(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logName: String
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logTrace(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String, throwable: Throwable): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
logWarning(msg: ⇒ String): Unit
- Attributes
- protected
- Definition Classes
- Logging
-
def
msgHelper(schema: StructType): String
- Attributes
- protected
- Definition Classes
- HasInputAnnotationCols
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
val
obfuscateRefFile: Param[String]
File with the terms to be used for Obfuscation
File with the terms to be used for Obfuscation
- Definition Classes
- DeidApproachParams
-
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
-
def
onTrained(model: ObfuscatorAnnotatorModel, spark: SparkSession): Unit
- Definition Classes
- AnnotatorApproach
-
val
optionalInputAnnotatorTypes: Array[String]
- Definition Classes
- HasInputAnnotationCols
-
val
outputAnnotatorType: AnnotatorType
- Definition Classes
- ObfuscatorAnnotatorApproach → HasOutputAnnotatorType
-
final
val
outputCol: Param[String]
- Attributes
- protected
- Definition Classes
- HasOutputAnnotationCol
-
lazy val
params: Array[Param[_]]
- Definition Classes
- Params
-
val
refFileFormat: Param[String]
Format of the reference file for Obfuscation the default value for that is "csv"
Format of the reference file for Obfuscation the default value for that is "csv"
- Definition Classes
- DeidApproachParams
-
val
refSep: Param[String]
Separator character for the csv reference file for Obfuscation de default value is "#"
Separator character for the csv reference file for Obfuscation de default value is "#"
- Definition Classes
- DeidApproachParams
-
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
-
def
save(path: String): Unit
- Definition Classes
- MLWritable
- Annotations
- @Since( "1.6.0" ) @throws( ... )
-
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
-
final
def
set(paramPair: ParamPair[_]): ObfuscatorAnnotatorApproach.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set(param: String, value: Any): ObfuscatorAnnotatorApproach.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
set[T](param: Param[T], value: T): ObfuscatorAnnotatorApproach.this.type
- Definition Classes
- Params
-
def
setAgeRanges(mode: Array[Int]): ObfuscatorAnnotatorApproach.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
-
def
setDateFormats(s: Array[String]): ObfuscatorAnnotatorApproach.this.type
Format of dates to displace
Format of dates to displace
- Definition Classes
- BaseDeidParams
-
def
setDays(k: Int): ObfuscatorAnnotatorApproach.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
-
final
def
setDefault(paramPairs: ParamPair[_]*): ObfuscatorAnnotatorApproach.this.type
- Attributes
- protected
- Definition Classes
- Params
-
final
def
setDefault[T](param: Param[T], value: T): ObfuscatorAnnotatorApproach.this.type
- Attributes
- protected[org.apache.spark.ml]
- Definition Classes
- Params
-
def
setEntity(e: String): ObfuscatorAnnotatorApproach.this.type
- Definition Classes
- ObfuscatorParams
-
def
setGenderAwareness(value: Boolean): ObfuscatorAnnotatorApproach.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
-
final
def
setInputCols(value: String*): ObfuscatorAnnotatorApproach.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setInputCols(value: Array[String]): ObfuscatorAnnotatorApproach.this.type
- Definition Classes
- HasInputAnnotationCols
-
def
setLanguage(s: String): ObfuscatorAnnotatorApproach.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
-
def
setLazyAnnotator(value: Boolean): ObfuscatorAnnotatorApproach.this.type
- Definition Classes
- CanBeLazy
-
def
setObfuscateRefFile(f: String): ObfuscatorAnnotatorApproach.this.type
File with the terms to be used for Obfuscation
File with the terms to be used for Obfuscation
- Definition Classes
- DeidApproachParams
-
def
setObfuscateRefSource(s: String): ObfuscatorAnnotatorApproach.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
-
final
def
setOutputCol(value: String): ObfuscatorAnnotatorApproach.this.type
- Definition Classes
- HasOutputAnnotationCol
-
def
setRefFileFormat(f: String): ObfuscatorAnnotatorApproach.this.type
File with the terms to be used for Obfuscation
File with the terms to be used for Obfuscation
- Definition Classes
- DeidApproachParams
-
def
setRefSep(f: String): ObfuscatorAnnotatorApproach.this.type
Separator character for the csv reference file for Obfuscation de default value is "#"
Separator character for the csv reference file for Obfuscation de default value is "#"
- Definition Classes
- DeidApproachParams
-
def
setSameLengthFormattedEntities(entities: Array[String]): ObfuscatorAnnotatorApproach.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
-
def
setSeed(s: Int): ObfuscatorAnnotatorApproach.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
- BaseDeidParams
-
def
setUseRandomDateDisplacement(s: Boolean): ObfuscatorAnnotatorApproach.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
-
val
supportedFormattedEntities: Array[String]
- Attributes
- protected
- Definition Classes
- BaseDeidParams
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- Identifiable → AnyRef → Any
-
def
train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): ObfuscatorAnnotatorModel
- Definition Classes
- ObfuscatorAnnotatorApproach → AnnotatorApproach
-
final
def
transformSchema(schema: StructType): StructType
- Definition Classes
- AnnotatorApproach → PipelineStage
-
def
transformSchema(schema: StructType, logging: Boolean): StructType
- Attributes
- protected
- Definition Classes
- PipelineStage
- Annotations
- @DeveloperApi()
-
val
uid: String
- Definition Classes
- ObfuscatorAnnotatorApproach → Identifiable
-
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
-
def
validate(schema: StructType): Boolean
- Attributes
- protected
- Definition Classes
- AnnotatorApproach
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... ) @native()
-
def
write: MLWriter
- Definition Classes
- DefaultParamsWritable → MLWritable