Normalizer

Instance Constructors

new Normalizer()
new Normalizer(uid: String)

uid
required internal uid for saving annotator

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]): NormalizerModel

Attributes
protected
Definition Classes
AnnotatorApproach
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
val cleanupPatterns: StringArrayParam

normalization regex patterns which match will be removed from token
final def clear(param: Param[_]): Normalizer.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def copy(extra: ParamMap): Estimator[NormalizerModel]

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

Cleans out tokens
Cleans out tokens

Definition Classes
Normalizer → AnnotatorApproach
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[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def fit(dataset: Dataset[_]): NormalizerModel

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

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

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

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

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

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

Regular expressions list for normalization, defaults [^A-Za-z]
final def getDefault[T](param: Param[T]): Option[T]

Definition Classes
Params
def getInputCols: Array[String]

returns
input annotations columns currently used

Definition Classes
HasInputAnnotationCols
def getLazyAnnotator: Boolean

Definition Classes
CanBeLazy
def getLowercase: Boolean

Lowercase tokens, default true
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 getSlangMatchCase: Boolean

Whether to convert string to lowercase or not while checking
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
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[String]

Input Annotator Type : TOKEN
Input Annotator Type : TOKEN

Definition Classes
Normalizer → 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
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
val lowercase: BooleanParam

whether to convert strings to lowercase
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
final def notifyAll(): Unit

Definition Classes
AnyRef
def onTrained(model: NormalizerModel, spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
val outputAnnotatorType: AnnotatorType

Output Annotator Type : TOKEN
Output Annotator Type : TOKEN

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

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

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

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

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

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

Definition Classes
Params
def setCleanupPatterns(value: Array[String]): Normalizer.this.type

Regular expressions list for normalization, defaults [^A-Za-z]
final def setDefault(paramPairs: ParamPair[_]*): Normalizer.this.type

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

Attributes
protected
Definition Classes
Params
final def setInputCols(value: String*): Normalizer.this.type

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

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

Definition Classes
HasInputAnnotationCols
def setLazyAnnotator(value: Boolean): Normalizer.this.type

Definition Classes
CanBeLazy
def setLowercase(value: Boolean): Normalizer.this.type

Lowercase tokens, default true
final def setOutputCol(value: String): Normalizer.this.type

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

Definition Classes
HasOutputAnnotationCol
def setSlangDictionary(path: String, delimiter: String, readAs: Format = ReadAs.TEXT, options: Map[String, String] = Map("format" -> "text")): Normalizer.this.type

Txt file with delimited words to be transformed into something else
def setSlangDictionary(value: ExternalResource): Normalizer.this.type

Txt file with delimited words to be transformed into something else
def setSlangMatchCase(value: Boolean): Normalizer.this.type

Whether to convert string to lowercase or not while checking
val slangDictionary: ExternalResourceParam

delimited file with list of custom words to be manually corrected
val slangMatchCase: BooleanParam

whether or not to be case sensitive to match slangs.
whether or not to be case sensitive to match slangs. Defaults to false.
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]): NormalizerModel

Definition Classes
Normalizer → 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

required internal uid for saving annotator
required internal uid for saving annotator

Definition Classes
Normalizer → 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 Normalizer | package annotators

class Normalizer extends AnnotatorApproach[NormalizerModel]

Instance Constructors

new Normalizer()

new Normalizer(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 _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): NormalizerModel

final def asInstanceOf[T0]: T0

def beforeTraining(spark: SparkSession): Unit

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

val cleanupPatterns: StringArrayParam

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

def clone(): AnyRef

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

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

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[_]): NormalizerModel

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

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

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

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

final def getClass(): Class[_]

def getCleanupPatterns: Array[String]

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

def getInputCols: Array[String]

def getLazyAnnotator: Boolean

def getLowercase: Boolean

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

final def getOutputCol: String

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

def getSlangMatchCase: Boolean

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

def hasParam(paramName: String): Boolean

def hashCode(): Int

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

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

val inputAnnotatorTypes: Array[String]

final val inputCols: StringArrayParam

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

final def isInstanceOf[T0]: Boolean

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

def isTraceEnabled(): Boolean

val lazyAnnotator: BooleanParam

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

val lowercase: BooleanParam

def msgHelper(schema: StructType): String

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def onTrained(model: NormalizerModel, spark: SparkSession): Unit

val outputAnnotatorType: AnnotatorType

final val outputCol: Param[String]

lazy val params: Array[Param[_]]

def save(path: String): Unit