ChunkTokenizer

Instance Constructors

new ChunkTokenizer()
new ChunkTokenizer(uid: String)

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 addContextChars(v: String): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def addException(value: String): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def addInfixPattern(value: String): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def addSplitChars(v: String): ChunkTokenizer.this.type

Definition Classes
Tokenizer
final def asInstanceOf[T0]: T0

Definition Classes
Any
def beforeTraining(spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
def buildRuleFactory: RuleFactory

Definition Classes
Tokenizer
val caseSensitiveExceptions: BooleanParam

Definition Classes
Tokenizer
final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def clear(param: Param[_]): ChunkTokenizer.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
val contextChars: StringArrayParam

Definition Classes
Tokenizer
final def copy(extra: ParamMap): Estimator[TokenizerModel]

Definition Classes
AnnotatorApproach → Estimator → 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
val description: String

Definition Classes
Tokenizer → AnnotatorApproach
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
val exceptions: StringArrayParam

Definition Classes
Tokenizer
val exceptionsPath: ExternalResourceParam

Definition Classes
Tokenizer
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[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def fit(dataset: Dataset[_]): TokenizerModel

Definition Classes
AnnotatorApproach → Estimator
def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[TokenizerModel]

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], paramMap: ParamMap): TokenizerModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): TokenizerModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" ) @varargs()
final def get[T](param: Param[T]): Option[T]

Definition Classes
Params
def getCaseSensitiveExceptions(value: Boolean): Boolean

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

Definition Classes
AnyRef → Any
def getContextChars: Array[String]

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

Definition Classes
Params
def getExceptions: Array[String]

Definition Classes
Tokenizer
def getInfixPatterns: Array[String]

Definition Classes
Tokenizer
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

Definition Classes
Tokenizer
def getSplitChars: Array[String]

Definition Classes
Tokenizer
def getSuffixPattern: String

Definition Classes
Tokenizer
def getTargetPattern: String

Definition Classes
Tokenizer
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
val infixPatterns: StringArrayParam

Definition Classes
Tokenizer
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]

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

Definition Classes
ChunkTokenizer → Tokenizer → HasInputAnnotationCols
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 onTrained(model: TokenizerModel, spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
val outputAnnotatorType: AnnotatorType

Definition Classes
ChunkTokenizer → Tokenizer → HasOutputAnnotatorType
final val outputCol: Param[String]

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

Definition Classes
Params
val prefixPattern: Param[String]

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

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
final def set(paramPair: ParamPair[_]): ChunkTokenizer.this.type

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

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

Definition Classes
Params
def setCaseSensitiveExceptions(value: Boolean): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def setContextChars(v: Array[String]): ChunkTokenizer.this.type

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

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

Attributes
protected
Definition Classes
Params
def setExceptions(value: Array[String]): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def setExceptionsPath(path: String, readAs: Format = ReadAs.LINE_BY_LINE, options: Map[String, String] = Map("format" -> "text")): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def setInfixPatterns(value: Array[String]): ChunkTokenizer.this.type

Definition Classes
Tokenizer
final def setInputCols(value: String*): ChunkTokenizer.this.type

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

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

Definition Classes
HasOutputAnnotationCol
def setPrefixPattern(value: String): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def setSplitChars(v: Array[String]): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def setSuffixPattern(value: String): ChunkTokenizer.this.type

Definition Classes
Tokenizer
def setTargetPattern(value: String): ChunkTokenizer.this.type

Definition Classes
Tokenizer
val splitChars: StringArrayParam

Definition Classes
Tokenizer
val suffixPattern: Param[String]

Definition Classes
Tokenizer
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
val targetPattern: Param[String]

Definition Classes
Tokenizer
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): TokenizerModel

Definition Classes
ChunkTokenizer → Tokenizer → AnnotatorApproach
final def transformSchema(schema: StructType): StructType

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

Definition Classes
AnnotatorApproach → PipelineStage
def transformSchema(schema: StructType, logging: Boolean): StructType

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

Definition Classes
ChunkTokenizer → 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
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( ... )
def write: MLWriter

Definition Classes
DefaultParamsWritable → MLWritable

Related Docs: object ChunkTokenizer | package annotators

class ChunkTokenizer extends Tokenizer

Instance Constructors

new ChunkTokenizer()

new ChunkTokenizer(uid: String)

Type Members

type AnnotatorType = String

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

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

final def ==(arg0: Any): Boolean

def addContextChars(v: String): ChunkTokenizer.this.type

def addException(value: String): ChunkTokenizer.this.type

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

def addSplitChars(v: String): ChunkTokenizer.this.type

final def asInstanceOf[T0]: T0

def beforeTraining(spark: SparkSession): Unit

def buildRuleFactory: RuleFactory

val caseSensitiveExceptions: BooleanParam

final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

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

def clone(): AnyRef

val contextChars: StringArrayParam

final def copy(extra: ParamMap): Estimator[TokenizerModel]

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

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

val description: String

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

val exceptions: StringArrayParam

val exceptionsPath: ExternalResourceParam

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

def explainParams(): String

final def extractParamMap(): ParamMap

final def extractParamMap(extra: ParamMap): ParamMap

def finalize(): Unit

final def fit(dataset: Dataset[_]): TokenizerModel

def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[TokenizerModel]

def fit(dataset: Dataset[_], paramMap: ParamMap): TokenizerModel

def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): TokenizerModel

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

def getCaseSensitiveExceptions(value: Boolean): Boolean

final def getClass(): Class[_]

def getContextChars: Array[String]

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

def getExceptions: Array[String]

def getInfixPatterns: Array[String]

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 getSplitChars: Array[String]

def getSuffixPattern: String

def getTargetPattern: String

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

def hasParam(paramName: String): Boolean

def hashCode(): Int

val infixPatterns: StringArrayParam

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

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

val inputAnnotatorTypes: Array[AnnotatorType]

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