Tokenizer

Instance Constructors

new Tokenizer()
new Tokenizer(uid: String)

uid
required uid for storing annotator to disk

Type Members

type AnnotatorType = String

Definition Classes
HasAnnotatorType

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
def $$[T](feature: StructFeature[T]): T

Attributes
protected
Definition Classes
HasFeatures
def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

Attributes
protected
Definition Classes
HasFeatures
def $$[T](feature: ArrayFeature[T]): Array[T]

Attributes
protected
Definition Classes
HasFeatures
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def addInfixPattern(value: String): Tokenizer.this.type
def annotate(annotations: Seq[Annotation]): Seq[Annotation]

one to many annotation
one to many annotation
annotations
Annotations that correspond to inputAnnotationCols generated by previous annotators if any
returns
any number of annotations processed for every input annotation. Not necessary one to one relationship

Definition Classes
Tokenizer → AnnotatorModel
val annotatorType: AnnotatorType

Definition Classes
Tokenizer → HasAnnotatorType
final def asInstanceOf[T0]: T0

Definition Classes
Any
final def clear(param: Param[_]): Tokenizer.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
val compositeTokens: StringArrayParam
def copy(extra: ParamMap): Tokenizer

requirement for annotators copies
requirement for annotators copies

Definition Classes
AnnotatorModel → Model → Transformer → PipelineStage → Params
def copyValues[T <: Params](to: T, extra: ParamMap): T

Attributes
protected
Definition Classes
Params
final def defaultCopy[T <: Params](extra: ParamMap): T

Attributes
protected
Definition Classes
Params
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
val features: ArrayBuffer[Feature[_, _, _]]

Definition Classes
HasFeatures
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def get[T](feature: StructFeature[T]): Option[T]

Attributes
protected
Definition Classes
HasFeatures
def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

Attributes
protected
Definition Classes
HasFeatures
def get[T](feature: ArrayFeature[T]): Option[Array[T]]

Attributes
protected
Definition Classes
HasFeatures
final def get[T](param: Param[T]): Option[T]

Definition Classes
Params
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getCompositeTokens: Array[String]
final def getDefault[T](param: Param[T]): Option[T]

Definition Classes
Params
def getIncludeDefaults: Boolean
def getInfixPatterns: Array[String]
final def getInputCols: Array[String]

returns
input annotations columns currently used

Definition Classes
HasInputAnnotationCols
final def getOrDefault[T](param: Param[T]): T

Definition Classes
Params
final def getOutputCol: String

Gets annotation column name going to generate
Gets annotation column name going to generate

Definition Classes
HasOutputAnnotationCol
def getParam(paramName: String): Param[Any]

Definition Classes
Params
def getPrefixPattern: String
def getSuffixPattern: String
def getTargetPattern: String
final def hasDefault[T](param: Param[T]): Boolean

Definition Classes
Params
def hasParam(paramName: String): Boolean

Definition Classes
Params
def hasParent: Boolean

Definition Classes
Model
def hashCode(): Int

Definition Classes
AnyRef → Any
val includeDefaults: BooleanParam
val infixPatterns: StringArrayParam
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

Attributes
protected
Definition Classes
Logging
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
final val inputCols: StringArrayParam

columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified
columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

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
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
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def onWrite(path: String, spark: SparkSession): Unit

Definition Classes
ParamsAndFeaturesWritable
final val outputCol: Param[String]

Attributes
protected
Definition Classes
HasOutputAnnotationCol
lazy val params: Array[Param[_]]

Definition Classes
Params
var parent: Estimator[Tokenizer]

Definition Classes
Model
val prefixPattern: Param[String]
val requiredAnnotatorTypes: Array[AnnotatorType]

A Tokenizer could require only for now a SentenceDetector annotator
A Tokenizer could require only for now a SentenceDetector annotator

Definition Classes
Tokenizer → HasInputAnnotationCols
def save(path: String): Unit

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
def set[T](feature: StructFeature[T], value: T): Tokenizer.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): Tokenizer.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[T](feature: ArrayFeature[T], value: Array[T]): Tokenizer.this.type

Attributes
protected
Definition Classes
HasFeatures
final def set(paramPair: ParamPair[_]): Tokenizer.this.type

Attributes
protected
Definition Classes
Params
final def set(param: String, value: Any): Tokenizer.this.type

Attributes
protected
Definition Classes
Params
final def set[T](param: Param[T], value: T): Tokenizer.this.type

Definition Classes
Params
def setCompositeTokens(value: Array[String]): Tokenizer.this.type
def setDefault[T](feature: StructFeature[T], value: () ⇒ T): Tokenizer.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): Tokenizer.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): Tokenizer.this.type

Attributes
protected
Definition Classes
HasFeatures
final def setDefault(paramPairs: ParamPair[_]*): Tokenizer.this.type

Attributes
protected
Definition Classes
Params
final def setDefault[T](param: Param[T], value: T): Tokenizer.this.type

Attributes
protected
Definition Classes
Params
def setIncludeDefaults(value: Boolean): Tokenizer.this.type
def setInfixPatterns(value: Array[String]): Tokenizer.this.type
final def setInputCols(value: String*): Tokenizer.this.type

Definition Classes
HasInputAnnotationCols
final def setInputCols(value: Array[String]): Tokenizer.this.type

Overrides required annotators column if different than default
Overrides required annotators column if different than default

Definition Classes
HasInputAnnotationCols
final def setOutputCol(value: String): Tokenizer.this.type

Overrides annotation column name when transforming
Overrides annotation column name when transforming

Definition Classes
HasOutputAnnotationCol
def setParent(parent: Estimator[Tokenizer]): Tokenizer

Definition Classes
Model
def setPrefixPattern(value: String): Tokenizer.this.type
def setSuffixPattern(value: String): Tokenizer.this.type
def setTargetPattern(value: String): Tokenizer.this.type
val suffixPattern: Param[String]
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def tag(sentences: Seq[Sentence]): Seq[TokenizedSentence]
val targetPattern: Param[String]
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
final def transform(dataset: Dataset[_]): DataFrame

Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
dataset
Dataset[Row]

Definition Classes
AnnotatorModel → Transformer
def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

Definition Classes
Transformer
Annotations
@Since( "2.0.0" )
def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

Definition Classes
Transformer
Annotations
@Since( "2.0.0" ) @varargs()
final def transformSchema(schema: StructType): StructType

requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()

Definition Classes
TransformModelSchema
def transformSchema(schema: StructType, logging: Boolean): StructType

Attributes
protected
Definition Classes
PipelineStage
Annotations
@DeveloperApi()
val uid: String

required uid for storing annotator to disk
required uid for storing annotator to disk

Definition Classes
Tokenizer → Identifiable
def validate(schema: StructType): Boolean

takes a Dataset and checks to see if all the required annotation types are present.
takes a Dataset and checks to see if all the required annotation types are present.
schema
to be validated
returns
True if all the required types are present, else false

Attributes
protected
Definition Classes
HasInputAnnotationCols
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( ... )
def write: MLWriter

Definition Classes
ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Related Docs: object Tokenizer | package annotators

class Tokenizer extends AnnotatorModel[Tokenizer]

Instance Constructors

new Tokenizer()

new Tokenizer(uid: String)

Type Members

type AnnotatorType = String

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def $[T](param: Param[T]): T

def $$[T](feature: StructFeature[T]): T

def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

def $$[T](feature: ArrayFeature[T]): Array[T]

final def ==(arg0: Any): Boolean

def addInfixPattern(value: String): Tokenizer.this.type

def annotate(annotations: Seq[Annotation]): Seq[Annotation]

val annotatorType: AnnotatorType

final def asInstanceOf[T0]: T0

final def clear(param: Param[_]): Tokenizer.this.type

def clone(): AnyRef

val compositeTokens: StringArrayParam

def copy(extra: ParamMap): Tokenizer

def copyValues[T <: Params](to: T, extra: ParamMap): T

final def defaultCopy[T <: Params](extra: ParamMap): T

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def explainParam(param: Param[_]): String

def explainParams(): String

final def extractParamMap(): ParamMap

final def extractParamMap(extra: ParamMap): ParamMap

val features: ArrayBuffer[Feature[_, _, _]]

def finalize(): Unit

def get[T](feature: StructFeature[T]): Option[T]

def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

def get[T](feature: ArrayFeature[T]): Option[Array[T]]

final def get[T](param: Param[T]): Option[T]

final def getClass(): Class[_]

def getCompositeTokens: Array[String]

final def getDefault[T](param: Param[T]): Option[T]

def getIncludeDefaults: Boolean

def getInfixPatterns: Array[String]

final def getInputCols: Array[String]

final def getOrDefault[T](param: Param[T]): T

final def getOutputCol: String

def getParam(paramName: String): Param[Any]

def getPrefixPattern: String

def getSuffixPattern: String

def getTargetPattern: String

final def hasDefault[T](param: Param[T]): Boolean

def hasParam(paramName: String): Boolean

def hasParent: Boolean

def hashCode(): Int

val includeDefaults: BooleanParam

val infixPatterns: StringArrayParam

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

final val inputCols: StringArrayParam

final def isDefined(param: Param[_]): Boolean

final def isInstanceOf[T0]: Boolean

final def isSet(param: Param[_]): Boolean

def isTraceEnabled(): Boolean

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def onWrite(path: String, spark: SparkSession): Unit

final val outputCol: Param[String]