RichOPSetFeature

Instance Constructors

new RichOPSetFeature(f: FeatureLike[T])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T], ttiv: scala.reflect.api.JavaUniverse.TypeTag[T.Value])

f

OPSet Feature

Value Members

final def !=(arg0: Any): Boolean

Definition Classes

AnyRef → Any
final def ##(): Int

Definition Classes

AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes

AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes

Any
def clone(): AnyRef

Attributes

protected[java.lang]

Definition Classes

AnyRef

Annotations

@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes

AnyRef
def equals(arg0: Any): Boolean

Definition Classes

AnyRef → Any
val f: FeatureLike[T]

OPSet Feature
def finalize(): Unit

Attributes

protected[java.lang]

Definition Classes

AnyRef

Annotations

@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes

AnyRef → Any
def hashCode(): Int

Definition Classes

AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes

Any
final def ne(arg0: AnyRef): Boolean

Definition Classes

AnyRef
final def notify(): Unit

Definition Classes

AnyRef
final def notifyAll(): Unit

Definition Classes

AnyRef
def pivot(others: Array[FeatureLike[T]] = Array.empty, topK: Int = TransmogrifierDefaults.TopK, minSupport: Int = TransmogrifierDefaults.MinSupport, cleanText: Boolean = TransmogrifierDefaults.CleanText, trackNulls: Boolean = TransmogrifierDefaults.TrackNulls, maxPctCardinality: Double = ...): FeatureLike[OPVector]

Converts a sequence of OPSet features into a vector keeping the top K most common occurrences of each OPSet feature (ie the final vector has length k * number of OPSet inputs).

Converts a sequence of OPSet features into a vector keeping the top K most common occurrences of each OPSet feature (ie the final vector has length k * number of OPSet inputs). Plus an additional column for "other" values - which will capture values that do not make the cut or values not seen in training

others

other features to include in the pivot

topK

keep topK values

minSupport

min occurrences to keep a value

cleanText

if true ignores capitalization and punctuations when grouping categories

trackNulls

keep a count of nulls

maxPctCardinality

max percentage of distinct values a categorical feature can have (between 0.0 and 1.00)
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes

AnyRef
def toString(): String

Definition Classes

AnyRef → Any
def vectorize(topK: Int, minSupport: Int, cleanText: Boolean, trackNulls: Boolean = TransmogrifierDefaults.TrackNulls, others: Array[FeatureLike[T]] = Array.empty, maxPctCardinality: Double = ...): FeatureLike[OPVector]

Converts a sequence of OPSet features into a vector keeping the top K most common occurrences of each OPSet feature (ie the final vector has length k * number of OPSet inputs).

Converts a sequence of OPSet features into a vector keeping the top K most common occurrences of each OPSet feature (ie the final vector has length k * number of OPSet inputs). Plus an additional column for "other" values - which will capture values that do not make the cut or values not seen in training

topK

keep topK values

minSupport

min occurrences to keep a value

cleanText

if true ignores capitalization and punctuations when grouping categories

trackNulls

keep a count of nulls

others

other features to include in the pivot

maxPctCardinality

max percentage of distinct values a categorical feature can have (between 0.0 and 1.00)
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( ... )

Related Doc: package RichSetFeature

implicit class RichOPSetFeature[T <: OPSet[_]] extends AnyRef

Instance Constructors

new RichOPSetFeature(f: FeatureLike[T])(implicit arg0: scala.reflect.api.JavaUniverse.TypeTag[T], ttiv: scala.reflect.api.JavaUniverse.TypeTag[T.Value])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

val f: FeatureLike[T]

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

def vectorize(topK: Int, minSupport: Int, cleanText: Boolean, trackNulls: Boolean = TransmogrifierDefaults.TrackNulls, others: Array[FeatureLike[T]] = Array.empty, maxPctCardinality: Double = ...): FeatureLike[OPVector]

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from AnyRef

Inherited from Any

Ungrouped