SmartTextVectorizerModel

Type Members

final type InputFeatures = Array[FeatureLike[T]]

Definition Classes
OpPipelineStageN → OpPipelineStage → InputParams
type KeyValue = (String) ⇒ Any

Definition Classes
OpTransformer
final type OutputFeatures = FeatureLike[OPVector]

Definition Classes
OpPipelineStage → OpPipelineStageBase

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
val args: SmartTextVectorizerModelArgs
final def asInstanceOf[T0]: T0

Definition Classes
Any
final val autoDetectLanguage: BooleanParam

Indicates whether to attempt language detection.
Indicates whether to attempt language detection.

Definition Classes
LanguageDetectionParams
final val autoDetectThreshold: DoubleParam

Language detection threshold.
Language detection threshold. If none of the detected languages have confidence greater than the threshold then defaultLanguage is used.

Definition Classes
LanguageDetectionParams
final def checkInputLength(features: Array[_]): Boolean

Definition Classes
OpPipelineStageN → InputParams
final def checkSerializable: Try[Unit]

Definition Classes
OpTransformerN → OpPipelineStageBase
def cleanTextFn(s: String, shouldClean: Boolean): String

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

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def convertToSet(in: Text): Set[String]

Attributes
protected
Definition Classes
SmartTextVectorizerModel → OneHotModelFun
final def copy(extra: ParamMap): SmartTextVectorizerModel.this.type

Definition Classes
OpPipelineStageBase → 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 val defaultLanguage: Param[String]

Default language to assume in case autoDetectLanguage is disabled or failed to make a good enough prediction.
Default language to assume in case autoDetectLanguage is disabled or failed to make a good enough prediction.

Definition Classes
LanguageDetectionParams
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 get[T](param: Param[T]): Option[T]

Definition Classes
Params
def getAutoDetectLanguage: Boolean

Definition Classes
LanguageDetectionParams
def getAutoDetectThreshold: Double

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

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

Definition Classes
Params
def getDefaultLanguage: Language

Definition Classes
LanguageDetectionParams
final def getInputFeature[T <: FeatureType](i: Int): Option[FeatureLike[T]]

Definition Classes
InputParams
final def getInputFeatures(): Array[OPFeature]

Definition Classes
InputParams
final def getInputSchema(): StructType

Definition Classes
OpPipelineStageParams
final def getMetadata(): Metadata

Definition Classes
OpPipelineStageParams
def getMinTokenLength: Int

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

Definition Classes
Params
def getOutput(): FeatureLike[OPVector]

Definition Classes
HasOut
final def getOutputFeatureName: String

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

Definition Classes
Params
def getToLowercase: Boolean

Definition Classes
TextMatchingParams
final def getTransientFeature(i: Int): Option[TransientFeature]

Definition Classes
InputParams
final def getTransientFeatures(): Array[TransientFeature]

Definition Classes
InputParams
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 hash[T <: OPCollection](in: Seq[T], features: Array[TransientFeature], params: HashingFunctionParams): OPVector

Hashes input sequence of values into OPVector using the supplied hashing params
Hashes input sequence of values into OPVector using the supplied hashing params

Attributes
protected
Definition Classes
HashingFun
def hashCode(): Int

Definition Classes
AnyRef → Any
def hashingTF(params: HashingFunctionParams): HashingTF

HashingTF instance
HashingTF instance

Attributes
protected
Definition Classes
HashingFun
final def inN: Array[TransientFeature]

Attributes
protected
Definition Classes
HasInN
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

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

Attributes
protected
Definition Classes
Logging
final def inputAsArray(in: InputFeatures): Array[OPFeature]

Definition Classes
OpPipelineStageN → InputParams
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 isSharedHashSpace(p: HashingFunctionParams, numFeatures: Option[Int] = None): Boolean

Determine if the transformer should use a shared hash space for all features or not
Determine if the transformer should use a shared hash space for all features or not
returns
true if the shared hashing space to be used, false otherwise

Attributes
protected
Definition Classes
HashingFun
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
def makeVectorColumnMetadata(features: Array[TransientFeature], params: HashingFunctionParams): Array[OpVectorColumnMetadata]

Attributes
protected
Definition Classes
HashingFun
def makeVectorMetadata(features: Array[TransientFeature], params: HashingFunctionParams, outputName: String): OpVectorMetadata

Attributes
protected
Definition Classes
HashingFun
final val minTokenLength: IntParam

Minimum token length, >= 1.
Minimum token length, >= 1.

Definition Classes
TextTokenizerParams
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def onGetMetadata(): Unit

Attributes
protected
Definition Classes
OpPipelineStageParams
def onSetInput(): Unit

Attributes
protected
Definition Classes
InputParams
val operationName: String

Definition Classes
SequenceModel → OpPipelineStageBase
final def outputAsArray(out: OutputFeatures): Array[OPFeature]

Definition Classes
OpPipelineStage → OpPipelineStageBase
def outputFeatureUid: String

Attributes
protected[com.salesforce.op]
Definition Classes
OpPipelineStageN → OpPipelineStage
def outputIsResponse: Boolean

Definition Classes
OpPipelineStage
lazy val params: Array[Param[_]]

Definition Classes
Params
var parent: Estimator[SequenceModel[T, OPVector]]

Definition Classes
Model
def pivotFn(topValues: Seq[Seq[String]], shouldCleanText: Boolean, shouldTrackNulls: Boolean): (Seq[Text]) ⇒ OPVector

Attributes
protected
Definition Classes
OneHotModelFun
def prepare[T <: OPCollection](el: T, shouldHashWithIndex: Boolean, shouldPrependFeatureName: Boolean, featureNameHash: Int): Iterable[Any]

Function that prepares the input columns to be hashed Note that MurMur3 hashing algorithm only defined for primitive types so need to convert tuples to strings.
Function that prepares the input columns to be hashed Note that MurMur3 hashing algorithm only defined for primitive types so need to convert tuples to strings. MultiPickList sets are hashed as is since there is no meaningful order in the selected choices. Lists and vectors can be hashed with or without their indices, since order may be important. Maps are hashed as (key,value) strings.
el
element we are hashing (eg. an OPList, OPMap, etc.)
returns
an Iterable object corresponding to the hashed element

Attributes
protected
Definition Classes
HashingFun
def save(path: String): Unit

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

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

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

Definition Classes
Params
def setAutoDetectLanguage(value: Boolean): SmartTextVectorizerModel.this.type

Definition Classes
LanguageDetectionParams
def setAutoDetectThreshold(value: Double): SmartTextVectorizerModel.this.type

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

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

Attributes
protected
Definition Classes
Params
def setDefaultLanguage(value: Language): SmartTextVectorizerModel.this.type

Definition Classes
LanguageDetectionParams
final def setInput(features: FeatureLike[T]*): SmartTextVectorizerModel.this.type

Definition Classes
OpPipelineStageN
final def setInput(features: InputFeatures): SmartTextVectorizerModel.this.type

Definition Classes
OpPipelineStageBase
final def setInputFeatures[S <: OPFeature](features: Array[S]): SmartTextVectorizerModel.this.type

Attributes
protected
Definition Classes
InputParams
final def setMetadata(m: Metadata): SmartTextVectorizerModel.this.type

Definition Classes
OpPipelineStageParams
def setMinTokenLength(value: Int): SmartTextVectorizerModel.this.type

Definition Classes
TextTokenizerParams
def setOutputFeatureName(name: String): SmartTextVectorizerModel.this.type

Definition Classes
OpPipelineStage
def setParent(parent: Estimator[SequenceModel[T, OPVector]]): SequenceModel[T, OPVector]

Definition Classes
Model
def setToLowercase(value: Boolean): SmartTextVectorizerModel.this.type

Definition Classes
TextMatchingParams
def setTrackTextLen(v: Boolean): SmartTextVectorizerModel.this.type

Option to keep track of text lengths
Option to keep track of text lengths

Definition Classes
TrackTextLenParam
final def stageName: String

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

Definition Classes
AnyRef
final val toLowercase: BooleanParam

Indicates whether to convert all characters to lowercase before string operation.
Indicates whether to convert all characters to lowercase before string operation.

Definition Classes
TextMatchingParams
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
def tokenize(text: Text, languageDetector: LanguageDetector = TextTokenizer.LanguageDetector, analyzer: TextAnalyzer = TextTokenizer.Analyzer): TextTokenizerResult

Definition Classes
TextTokenizerParams
final val trackTextLen: BooleanParam

Definition Classes
TrackTextLenParam
def transform(dataset: Dataset[_]): DataFrame

Definition Classes
OpTransformerN → 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()
def transformFn: (Seq[Text]) ⇒ OPVector

Definition Classes
SmartTextVectorizerModel → OpTransformerN
lazy val transformKeyValue: (KeyValue) ⇒ Any

Definition Classes
OpTransformerN → OpTransformer
def transformMap: (Map[String, Any]) ⇒ Any

Definition Classes
OpTransformer
def transformRow: (Row) ⇒ Any

Definition Classes
OpTransformer
final def transformSchema(schema: StructType): StructType

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

Attributes
protected
Definition Classes
PipelineStage
Annotations
@DeveloperApi()
implicit val tti: scala.reflect.api.JavaUniverse.TypeTag[T]

Definition Classes
SequenceModel → OpTransformerN
implicit val tto: scala.reflect.api.JavaUniverse.TypeTag[OPVector]

Definition Classes
SequenceModel → HasOut
implicit val ttov: scala.reflect.api.JavaUniverse.TypeTag[Value]

Definition Classes
SequenceModel → HasOut
val uid: String

Definition Classes
SequenceModel → Identifiable
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( ... )
final def write: MLWriter

Definition Classes
OpPipelineStageBase → MLWritable

Related Doc: package feature

final class SmartTextVectorizerModel[T <: Text] extends SequenceModel[T, OPVector] with TextTokenizerParams with TrackTextLenParam with HashingFun with OneHotModelFun[Text]

Type Members

final type InputFeatures = Array[FeatureLike[T]]

type KeyValue = (String) ⇒ Any

final type OutputFeatures = FeatureLike[OPVector]

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

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

final def ==(arg0: Any): Boolean

val args: SmartTextVectorizerModelArgs

final def asInstanceOf[T0]: T0

final val autoDetectLanguage: BooleanParam

final val autoDetectThreshold: DoubleParam

final def checkInputLength(features: Array[_]): Boolean

final def checkSerializable: Try[Unit]

def cleanTextFn(s: String, shouldClean: Boolean): String

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

def clone(): AnyRef

def convertToSet(in: Text): Set[String]

final def copy(extra: ParamMap): SmartTextVectorizerModel.this.type

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

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

final val defaultLanguage: Param[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 get[T](param: Param[T]): Option[T]

def getAutoDetectLanguage: Boolean

def getAutoDetectThreshold: Double

final def getClass(): Class[_]

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

def getDefaultLanguage: Language

final def getInputFeature[T <: FeatureType](i: Int): Option[FeatureLike[T]]

final def getInputFeatures(): Array[OPFeature]

final def getInputSchema(): StructType

final def getMetadata(): Metadata

def getMinTokenLength: Int

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

def getOutput(): FeatureLike[OPVector]

final def getOutputFeatureName: String

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

def getToLowercase: Boolean

final def getTransientFeature(i: Int): Option[TransientFeature]

final def getTransientFeatures(): Array[TransientFeature]

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

def hasParam(paramName: String): Boolean

def hasParent: Boolean

def hash[T <: OPCollection](in: Seq[T], features: Array[TransientFeature], params: HashingFunctionParams): OPVector

def hashCode(): Int

def hashingTF(params: HashingFunctionParams): HashingTF

final def inN: Array[TransientFeature]

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

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

final def inputAsArray(in: InputFeatures): Array[OPFeature]

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

final def isInstanceOf[T0]: Boolean

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

def isSharedHashSpace(p: HashingFunctionParams, numFeatures: Option[Int] = None): 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

def makeVectorColumnMetadata(features: Array[TransientFeature], params: HashingFunctionParams): Array[OpVectorColumnMetadata]

def makeVectorMetadata(features: Array[TransientFeature], params: HashingFunctionParams, outputName: String): OpVectorMetadata