FeatureDistribution

Instance Constructors

new FeatureDistribution(name: String, key: Option[String], count: Long, nulls: Long, distribution: Array[Double], summaryInfo: Array[Double], moments: Option[Moments] = None, cardEstimate: Option[TextStats] = None, type: FeatureDistributionType = FeatureDistributionType.Training)

name

name of the feature

key

map key associated with distribution (when the feature is a map)

count

total count of feature seen

nulls

number of empties seen in feature

distribution

binned counts of feature values (hashed for strings, evenly spaced bins for numerics)

summaryInfo

either min and max number of tokens for text data, or splits used for bins for numeric data

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
val cardEstimate: Option[TextStats]
def clone(): AnyRef

Attributes

protected[java.lang]

Definition Classes

AnyRef

Annotations

@throws( ... )
val count: Long

total count of feature seen

total count of feature seen

Definition Classes

FeatureDistribution → FeatureDistributionLike
val distribution: Array[Double]

binned counts of feature values (hashed for strings, evenly spaced bins for numerics)

binned counts of feature values (hashed for strings, evenly spaced bins for numerics)

Definition Classes

FeatureDistribution → FeatureDistributionLike
final def eq(arg0: AnyRef): Boolean

Definition Classes

AnyRef
def equals(that: Any): Boolean

Definition Classes

FeatureDistribution → Equals → AnyRef → Any
def featureKey: FeatureKey

Get feature key associated to this distribution
def fillRate(): Double

Get fill rate of feature

Get fill rate of feature

returns

fraction of data that is non empty
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

FeatureDistribution → AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes

Any
def jsDivergence(fd: FeatureDistribution): Double

Jensen-Shannon divergence from this distribution to the other distribution fed in

Jensen-Shannon divergence from this distribution to the other distribution fed in

fd

other feature distribution

returns

the KL divergence
val key: Option[String]

map key associated with distribution (when the feature is a map)

map key associated with distribution (when the feature is a map)

Definition Classes

FeatureDistribution → FeatureDistributionLike
val moments: Option[Moments]
val name: String

name of the feature

name of the feature

Definition Classes

FeatureDistribution → FeatureDistributionLike
final def ne(arg0: AnyRef): Boolean

Definition Classes

AnyRef
final def notify(): Unit

Definition Classes

AnyRef
final def notifyAll(): Unit

Definition Classes

AnyRef
val nulls: Long

number of empties seen in feature

number of empties seen in feature

Definition Classes

FeatureDistribution → FeatureDistributionLike
def reduce(fd: FeatureDistribution): FeatureDistribution

Combine feature distributions

Combine feature distributions

fd

other feature distribution (from the same feature)

returns

summed distribution information
def relativeFillRate(fd: FeatureDistribution): Double

Absolute difference in empty rates

Absolute difference in empty rates

fd

feature distribution to compare to

returns

absolute difference of rates
def relativeFillRatio(fd: FeatureDistribution): Double

Ratio of fill rates between the two distributions symetric with larger value on the top

Ratio of fill rates between the two distributions symetric with larger value on the top

fd

feature distribution to compare to

returns

ratio of fill rates
val summaryInfo: Array[Double]

either min and max number of tokens for text data, or splits used for bins for numeric data

either min and max number of tokens for text data, or splits used for bins for numeric data

Definition Classes

FeatureDistribution → FeatureDistributionLike
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes

AnyRef
def toString(): String

Definition Classes

FeatureDistribution → AnyRef → Any
val type: FeatureDistributionType

feature distribution type: training or scoring

feature distribution type: training or scoring

Definition Classes

FeatureDistribution → FeatureDistributionLike
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 Docs: object FeatureDistribution | package filters

Instance Constructors

new FeatureDistribution(name: String, key: Option[String], count: Long, nulls: Long, distribution: Array[Double], summaryInfo: Array[Double], moments: Option[Moments] = None, cardEstimate: Option[TextStats] = None, type: FeatureDistributionType = FeatureDistributionType.Training)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

val cardEstimate: Option[TextStats]

def clone(): AnyRef

val count: Long

val distribution: Array[Double]

final def eq(arg0: AnyRef): Boolean

def equals(that: Any): Boolean

def featureKey: FeatureKey

def fillRate(): Double

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

def jsDivergence(fd: FeatureDistribution): Double

val key: Option[String]

val moments: Option[Moments]

val name: String

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val nulls: Long

def reduce(fd: FeatureDistribution): FeatureDistribution

def relativeFillRate(fd: FeatureDistribution): Double

def relativeFillRatio(fd: FeatureDistribution): Double

val summaryInfo: Array[Double]

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

def toString(): String

val type: FeatureDistributionType

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from FeatureDistributionLike

Inherited from AnyRef

Inherited from Any

Ungrouped