OpTextPivotVectorizer

Instance Constructors

new OpTextPivotVectorizer(operationName: String = "pivotText", uid: String = UID[OpSetVectorizer[_]])(implicit tti: scala.reflect.api.JavaUniverse.TypeTag[T], ttiv: scala.reflect.api.JavaUniverse.TypeTag[Option[String]])

operationName
unique name of the operation this stage performs
uid
uid for instance

Type Members

final type InputFeatures = Array[FeatureLike[T]]

Definition Classes
OpPipelineStageN → OpPipelineStage → InputParams
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
final def asInstanceOf[T0]: T0

Definition Classes
Any
implicit def booleanToDouble(v: Boolean): Double

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

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

Definition Classes
SequenceEstimator → OpPipelineStageBase
final val cleanText: BooleanParam

Definition Classes
TextParams
def cleanTextFn(s: String, shouldClean: Boolean): String

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

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def convertToSeqOfMaps(dataset: Dataset[Seq[Option[String]]]): RDD[Seq[Map[String, Int]]]

Attributes
protected
Definition Classes
OpTextPivotVectorizer → OpOneHotVectorizer
final def copy(extra: ParamMap): OpTextPivotVectorizer.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 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] )
def fit(dataset: Dataset[_]): SequenceModel[T, OPVector]

Definition Classes
SequenceEstimator → Estimator
def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[SequenceModel[T, OPVector]]

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

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

Definition Classes
Estimator
Annotations
@Since( "2.0.0" ) @varargs()
def fitFn(dataset: Dataset[Seq[T.Value]]): SequenceModel[T, OPVector]

Definition Classes
OpOneHotVectorizer → SequenceEstimator
final def get[T](param: Param[T]): Option[T]

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

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

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

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

Definition Classes
OpPipelineStageN → OpPipelineStageBase
final def getOutputFeatureName: String

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

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

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

Definition Classes
InputParams
def getUnseenName: String

Definition Classes
SaveOthersParams
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
final def inN: Array[TransientFeature]

Attributes
protected
Definition Classes
HasInN
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 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 makeModel(topValues: Seq[Seq[String]], shouldCleanText: Boolean, shouldTrackNulls: Boolean, operationName: String, uid: String): OpTextPivotVectorizerModel[T]

Attributes
protected
Definition Classes
OpTextPivotVectorizer → OpOneHotVectorizer
def makeVectorColumnMetadata(shouldTrackNulls: Boolean, unseen: Option[String], topValues: Seq[Seq[String]], features: Array[TransientFeature]): Array[OpVectorColumnMetadata]

Attributes
protected
Definition Classes
OneHotFun
def makeVectorMetadata(shouldTrackNulls: Boolean, unseen: Option[String], topValues: Seq[Seq[String]], outputName: String, features: Array[TransientFeature], stageName: String): OpVectorMetadata

Attributes
protected
Definition Classes
OneHotFun
final val minSupport: IntParam

Definition Classes
MinSupportParam
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

Definition Classes
VectorizerDefaults → OpPipelineStageBase
val operationName: String

unique name of the operation this stage performs
unique name of the operation this stage performs

Definition Classes
SequenceEstimator → 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
def outputVectorMeta: OpVectorMetadata

Get the metadata describing the output vector
Get the metadata describing the output vector
This does not trigger onGetMetadata()
returns
Metadata of output vector

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

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

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
val seqIConvert: FeatureTypeSparkConverter[T]

Definition Classes
SequenceEstimator
implicit val seqIEncoder: Encoder[Seq[T.Value]]

Definition Classes
SequenceEstimator
final def set(paramPair: ParamPair[_]): OpTextPivotVectorizer.this.type

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

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

Definition Classes
Params
def setCleanText(clean: Boolean): OpTextPivotVectorizer.this.type

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

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

Attributes
protected
Definition Classes
Params
final def setInput(features: FeatureLike[T]*): OpTextPivotVectorizer.this.type

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

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

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

Definition Classes
OpPipelineStageParams
def setMinSupport(min: Int): OpTextPivotVectorizer.this.type

Definition Classes
MinSupportParam
def setOutputFeatureName(name: String): OpTextPivotVectorizer.this.type

Definition Classes
OpPipelineStage
def setTopK(numberToKeep: Int): OpTextPivotVectorizer.this.type

Definition Classes
PivotParams
def setTrackNulls(v: Boolean): OpTextPivotVectorizer.this.type

Option to keep track of values that were missing
Option to keep track of values that were missing

Definition Classes
TrackNullsParam
def setUnseenName(unseenNameIn: String): OpTextPivotVectorizer.this.type

Definition Classes
SaveOthersParams
final def stageName: String

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

Definition Classes
AnyRef
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
final val topK: IntParam

Definition Classes
PivotParams
final val trackNulls: BooleanParam

Definition Classes
TrackNullsParam
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
SequenceEstimator
implicit val ttiv: scala.reflect.api.JavaUniverse.TypeTag[T.Value]

Definition Classes
SequenceEstimator
implicit val tto: scala.reflect.api.JavaUniverse.TypeTag[OPVector]

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

Definition Classes
SequenceEstimator → OpPipelineStageN
val uid: String

uid for instance
uid for instance

Definition Classes
SequenceEstimator → Identifiable
final val unseenName: Param[String]

Definition Classes
SaveOthersParams
def vectorMetadataFromInputFeatures: OpVectorMetadata

Compute the output vector metadata only from the input features.
Compute the output vector metadata only from the input features. Vectorizers use this to derive the full vector, including pivot columns or indicator features.
returns
Vector metadata from input features

Attributes
protected
Definition Classes
VectorizerDefaults
def vectorMetadataWithNullIndicators: OpVectorMetadata

Attributes
protected
Definition Classes
VectorizerDefaults
def vectorOutputName: String

Get the name of the output vector
Get the name of the output vector
returns
Output vector name as a string

Attributes
protected
Definition Classes
VectorizerDefaults
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

class OpTextPivotVectorizer[T <: Text] extends OpOneHotVectorizer[T]

Instance Constructors

new OpTextPivotVectorizer(operationName: String = "pivotText", uid: String = UID[OpSetVectorizer[_]])(implicit tti: scala.reflect.api.JavaUniverse.TypeTag[T], ttiv: scala.reflect.api.JavaUniverse.TypeTag[Option[String]])

Type Members

final type InputFeatures = Array[FeatureLike[T]]

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

final def asInstanceOf[T0]: T0

implicit def booleanToDouble(v: Boolean): Double

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

final def checkSerializable: Try[Unit]

final val cleanText: BooleanParam

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

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

def clone(): AnyRef

def convertToSeqOfMaps(dataset: Dataset[Seq[Option[String]]]): RDD[Seq[Map[String, Int]]]

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

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

def finalize(): Unit

def fit(dataset: Dataset[_]): SequenceModel[T, OPVector]

def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[SequenceModel[T, OPVector]]

def fit(dataset: Dataset[_], paramMap: ParamMap): SequenceModel[T, OPVector]

def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): SequenceModel[T, OPVector]

def fitFn(dataset: Dataset[Seq[T.Value]]): SequenceModel[T, OPVector]

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

final def getClass(): Class[_]

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

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

final def getInputFeatures(): Array[OPFeature]

final def getInputSchema(): StructType

final def getMetadata(): Metadata

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

def getOutput(): FeatureLike[OPVector]

final def getOutputFeatureName: String

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

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

final def getTransientFeatures(): Array[TransientFeature]

def getUnseenName: String

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

def hasParam(paramName: String): Boolean

def hashCode(): Int

final def inN: Array[TransientFeature]

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 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 makeModel(topValues: Seq[Seq[String]], shouldCleanText: Boolean, shouldTrackNulls: Boolean, operationName: String, uid: String): OpTextPivotVectorizerModel[T]

def makeVectorColumnMetadata(shouldTrackNulls: Boolean, unseen: Option[String], topValues: Seq[Seq[String]], features: Array[TransientFeature]): Array[OpVectorColumnMetadata]

def makeVectorMetadata(shouldTrackNulls: Boolean, unseen: Option[String], topValues: Seq[Seq[String]], outputName: String, features: Array[TransientFeature], stageName: String): OpVectorMetadata

final val minSupport: IntParam

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit