FeatureLike

Abstract Value Members

abstract val distributions: Seq[FeatureDistributionLike]

The distribution information of the feature (is a sequence because map features have distribution for each key)
abstract val isResponse: Boolean

Is this feature a response or a predictor
abstract val name: String

Feature name
abstract val originStage: OpPipelineStage[O]

Origin stage which resulted into creating this feature (transformer or estimator)
abstract val parents: Seq[OPFeature]

The input features of the origin stage
abstract val uid: String

Unique identifier of the feature instance
implicit abstract val wtt: scala.reflect.api.JavaUniverse.WeakTypeTag[O]

Weak type tag of the feature type O

Concrete 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
final def asRaw(isResponse: Boolean = isResponse): FeatureLike[O]

Construct a raw feature instance from this feature which can be applied on a Dataframe.
Construct a raw feature instance from this feature which can be applied on a Dataframe. Use this functionality when stacking workflows, e.g. when some features of a workflow are used as raw or input features of another workflow.
isResponse
should make response or a predictor feature
returns
new raw feature of the same type
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def equals(in: Any): Boolean

Tests the equality of the FeatureLike objects
Tests the equality of the FeatureLike objects
Origin Stage is tested by uid
Parents are test by uid and order dependent. This is because they are used as inputs to the origin stage and input parameters may not be commutative

Definition Classes
FeatureLike → AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
final def hashCode(): Int

Returns the hash code of this feature
Returns the hash code of this feature
returns
hash code

Definition Classes
FeatureLike → AnyRef → Any
final def history(): FeatureHistory

History of all stages and origin features used to create a given feature
History of all stages and origin features used to create a given feature
returns
FeatureHistory containing all feature history information
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def isRaw: Boolean

Is this feature is raw or not (i.e.
Is this feature is raw or not (i.e. has no parent features)
returns
true if the feature is raw, false otherwise
final def isSubtypeOf[T <: FeatureType](implicit arg0: scala.reflect.api.JavaUniverse.WeakTypeTag[T]): Boolean

Check whether this feature's type O is a subtype of the given feature type T
Check whether this feature's type O is a subtype of the given feature type T
T
the feature type to check
returns
true if O conforms to T, false otherwise
lazy val log: Logger

A handy logger instance
A handy logger instance

Attributes
protected
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
final def prettyParentStages: String

Pretty print feature's parent stages tree
Pretty print feature's parent stages tree
returns
feature's parent stages tree with indentation
final def sameOrigin(in: Any): Boolean

Tests the equality of the FeatureLike objects
Tests the equality of the FeatureLike objects
Origin Stage is tested by uid
Parents are test by uid and order dependent. This is because they are used as inputs to the origin stage and input parameters may not be commutative
final def scoringDistributions: Seq[FeatureDistributionLike]

The distribution information of the feature computed during scoring (is a sequence because map features have distribution for each key)
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
final def toJson(pretty: Boolean = true): String

Convert this feature to json string
Convert this feature to json string
pretty
should pretty print
returns
json string for feature
final def toString(): String

Definition Classes
FeatureLike → AnyRef → Any
final def trainingDistributions: Seq[FeatureDistributionLike]

The distribution information of the feature computed during training (is a sequence because map features have distribution for each key)
final def transformWith[U <: FeatureType](stage: OpPipelineStageN[O, U], fs: Array[FeatureLike[O]]): FeatureLike[U]

Transform the feature with a given transformation stage and input features
Transform the feature with a given transformation stage and input features
U
output type
stage
transformer/estimator
fs
other features
returns
transformed feature
final def transformWith[I1 <: FeatureType, I2 <: FeatureType, I3 <: FeatureType, U <: FeatureType](stage: OpPipelineStage4[O, I1, I2, I3, U], f1: FeatureLike[I1], f2: FeatureLike[I2], f3: FeatureLike[I3]): FeatureLike[U]

Transform the feature with a given transformation stage and input features
Transform the feature with a given transformation stage and input features
I1
f1 input type
I2
f2 input type
I3
f3 input type
U
output type
stage
transformer/estimator
f1
other feature1
f2
other feature2
f3
other feature2
returns
transformed feature
final def transformWith[I1 <: FeatureType, I2 <: FeatureType, U <: FeatureType](stage: OpPipelineStage3[O, I1, I2, U], f1: FeatureLike[I1], f2: FeatureLike[I2]): FeatureLike[U]

Transform the feature with a given transformation stage and input features
Transform the feature with a given transformation stage and input features
I1
f1 input type
I2
f2 input type
U
output type
stage
transformer/estimator
f1
other feature1
f2
other feature2
returns
transformed feature
final def transformWith[I <: FeatureType, U <: FeatureType](stage: OpPipelineStage2[O, I, U], f: FeatureLike[I]): FeatureLike[U]

Transform the feature with a given transformation stage and input features
Transform the feature with a given transformation stage and input features
I
other feature input type
U
output type
stage
transformer/estimator
f
other feature
returns
transformed feature
final def transformWith[U <: FeatureType](stage: OpPipelineStage1[O, U]): FeatureLike[U]

Transform the feature with a given transformation stage and an input feature
Transform the feature with a given transformation stage and an input feature
U
output type
stage
transformer/estimator
returns
transformed feature
final def typeName: String

Feature type name
Feature type name
returns
feature type name
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 features

trait FeatureLike[O <: FeatureType] extends AnyRef

Abstract Value Members

abstract val distributions: Seq[FeatureDistributionLike]

abstract val isResponse: Boolean

abstract val name: String

abstract val originStage: OpPipelineStage[O]

abstract val parents: Seq[OPFeature]

abstract val uid: String

implicit abstract val wtt: scala.reflect.api.JavaUniverse.WeakTypeTag[O]

Concrete Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

final def asRaw(isResponse: Boolean = isResponse): FeatureLike[O]

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

final def equals(in: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

final def hashCode(): Int

final def history(): FeatureHistory

final def isInstanceOf[T0]: Boolean

final def isRaw: Boolean

final def isSubtypeOf[T <: FeatureType](implicit arg0: scala.reflect.api.JavaUniverse.WeakTypeTag[T]): Boolean

lazy val log: Logger

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

final def prettyParentStages: String

final def sameOrigin(in: Any): Boolean

final def scoringDistributions: Seq[FeatureDistributionLike]

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

final def toJson(pretty: Boolean = true): String

final def toString(): String

final def trainingDistributions: Seq[FeatureDistributionLike]

final def transformWith[U <: FeatureType](stage: OpPipelineStageN[O, U], fs: Array[FeatureLike[O]]): FeatureLike[U]

final def transformWith[I1 <: FeatureType, I2 <: FeatureType, I3 <: FeatureType, U <: FeatureType](stage: OpPipelineStage4[O, I1, I2, I3, U], f1: FeatureLike[I1], f2: FeatureLike[I2], f3: FeatureLike[I3]): FeatureLike[U]

final def transformWith[I1 <: FeatureType, I2 <: FeatureType, U <: FeatureType](stage: OpPipelineStage3[O, I1, I2, U], f1: FeatureLike[I1], f2: FeatureLike[I2]): FeatureLike[U]

final def transformWith[I <: FeatureType, U <: FeatureType](stage: OpPipelineStage2[O, I, U], f: FeatureLike[I]): FeatureLike[U]

final def transformWith[U <: FeatureType](stage: OpPipelineStage1[O, U]): FeatureLike[U]

final def typeName: String

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