Class/Object

com.github.gradientgmm

MetricAggregator

Related Docs: object MetricAggregator | package gradientgmm

Permalink

class MetricAggregator extends Serializable

Distributed aggregator of necessary statistics

In each worker it computes and aggregates the current batch log-likelihood, and the terms that will later be used to compute the gradient. The class structure is based on Spark's ExpectationSum

Linear Supertypes
Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. MetricAggregator
  2. Serializable
  3. Serializable
  4. AnyRef
  5. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new MetricAggregator(weightsGradient: DenseVector[Double], posteriorsAgg: DenseVector[Double], outerProductsAgg: Array[Array[Double]], loss: Double, counter: Int, currentBatch: Int)

    Permalink

    weightsGradient

    Aggregated posterior responsability for each component

    posteriorsAgg

    Sum of posterior cluster responsibilities

    outerProductsAgg

    Sum of weighted outer products

    loss

    Aggregated log-likelihood

    counter

    Batch size counter

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. def +=(x: MetricAggregator): MetricAggregator

    Permalink

  4. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  5. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  6. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  7. var counter: Int

    Permalink

    Batch size counter

  8. var currentBatch: Int

    Permalink

  9. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  10. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  11. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  12. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any

  13. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  14. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  15. val k: Int

    Permalink

    Number of components in the model

  16. var loss: Double

    Permalink

    Aggregated log-likelihood

  17. val m: Int

    Permalink

    Adder for other MetricAggregator instances

    Adder for other MetricAggregator instances

    Used for further aggregation between each worker's aggregates

  18. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  19. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  20. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  21. val outerProductsAgg: Array[Array[Double]]

    Permalink

    Sum of weighted outer products

  22. val posteriorsAgg: DenseVector[Double]

    Permalink

    Sum of posterior cluster responsibilities

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

    Permalink
    Definition Classes
    AnyRef

  24. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  25. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  27. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  28. val weightsGradient: DenseVector[Double]

    Permalink

    Aggregated posterior responsability for each component

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped