cc.factorie.app.classify

LinearVectorClassifier

class LinearVectorClassifier[L <: DiscreteVar , F <: VectorVar ] extends LinearMulticlassClassifier with VectorClassifier[L, F]

A VectorClassifier in which the score for each class is a dot-product between the observed feature vector and a vector of parameters. Examples include NaiveBayes, MultivariateLogisticRegression, LinearSVM, and many others. Counter-examples include KNearestNeighbor.

Linear Supertypes
VectorClassifier[L, F], Classifier[L], LinearMulticlassClassifier, OptimizablePredictor[la.Tensor1, la.Tensor1], model.Parameters, MulticlassClassifier[la.Tensor1], backend.Classifier[la.Tensor1, la.Tensor1], Predictor[la.Tensor1, la.Tensor1], AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. LinearVectorClassifier
  2. VectorClassifier
  3. Classifier
  4. LinearMulticlassClassifier
  5. OptimizablePredictor
  6. Parameters
  7. MulticlassClassifier
  8. Classifier
  9. Predictor
  10. AnyRef
  11. Any
Visibility
  1. Public
  2. All

Instance Constructors

  1. new LinearVectorClassifier(numLabels: Int, numFeatures: Int, labelToFeatures: (L) ⇒ F)

Value Members

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

    Definition Classes
    AnyRef

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

    Definition Classes
    Any

  3. final def ##(): Int

    Definition Classes
    AnyRef → Any

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

    Definition Classes
    AnyRef

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

    Definition Classes
    Any

  6. def Weights(t4: ⇒ Tensor4 ): Weights4

    Definition Classes
    Parameters

  7. def Weights(t3: ⇒ Tensor3 ): Weights3

    Definition Classes
    Parameters

  8. def Weights(t2: ⇒ Tensor2 ): Weights2

    Definition Classes
    Parameters

  9. def Weights(t1: ⇒ Tensor1 ): Weights1

    Definition Classes
    Parameters

  10. def accumulateObjectiveGradient(accumulator: WeightsMapAccumulator , features: la.Tensor1 , gradient: la.Tensor1 , weight: Double): Unit

    Put gradient of objective with respect to parameters into the accumulator.

    Put gradient of objective with respect to parameters into the accumulator. The contract states we cannot mutate the "input" argument inside this method.

    accumulator

    Accumulator to hold gradient

    weight

    Weight mutliplier for gradient

    Definition Classes
    LinearMulticlassClassifier → OptimizablePredictor

  11. def accuracy(labels: Iterable[L with LabeledDiscreteVar]): Double

    Definition Classes
    Classifier

  12. def asDotTemplate[T <: LabeledMutableDiscreteVar ](l2f: (T) ⇒ TensorVar )(implicit ml: Manifest[T]): DotTemplateWithStatistics2[T, TensorVar] { ... /* 2 definitions in type refinement */ }

    Definition Classes
    LinearMulticlassClassifier

  13. final def asInstanceOf[T0]: T0

    Definition Classes
    Any

  14. def asTemplate[Value <: DiscreteValue , T <: LabeledMutableDiscreteVar , F <: variable.Var { type Value = cc.factorie.la.Tensor1 }](l2f: (T) ⇒ F)(implicit ml: Manifest[T], mf: Manifest[F]): ClassifierTemplate[la.Tensor1, Value, T, F]

    Definition Classes
    MulticlassClassifier

  15. def bestLabelIndex(v: L): Int

    Definition Classes
    LinearVectorClassifier → Classifier

  16. def classification(v: L): Classification[L]

    Definition Classes
    LinearVectorClassifier → Classifier

  17. def classification(input: la.Tensor1 ): MulticlassClassification

    Definition Classes
    MulticlassClassifier → Classifier

  18. def classifications(labels: Iterable[L]): Seq[Classification[L]]

    Definition Classes
    Classifier

  19. def classify(labels: Iterable[L with MutableDiscreteVar]): Seq[Classification[L]]

    Definition Classes
    Classifier

  20. def classify[L2 <: L with MutableDiscreteVar ](v: L2): Classification[L]

    Definition Classes
    Classifier

  21. def clone(): AnyRef

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

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

    Definition Classes
    AnyRef

  23. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any

  24. val featureSize: Int

    Definition Classes
    LinearMulticlassClassifier

  25. def finalize(): Unit

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

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

    Definition Classes
    AnyRef → Any

  27. def hashCode(): Int

    Definition Classes
    AnyRef → Any

  28. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any

  29. val labelSize: Int

    Definition Classes
    LinearMulticlassClassifier

  30. val labelToFeatures: (L) ⇒ F

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

    Definition Classes
    AnyRef

  32. final def notify(): Unit

    Definition Classes
    AnyRef

  33. final def notifyAll(): Unit

    Definition Classes
    AnyRef

  34. val parameters: WeightsSet

    Definition Classes
    Parameters

  35. def predict(features: la.Tensor1 ): la.Tensor1

    Definition Classes
    LinearMulticlassClassifier → Predictor

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

    Definition Classes
    AnyRef

  37. def toString(): String

    Definition Classes
    AnyRef → Any

  38. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  41. val weights: Weights2

    Definition Classes
    LinearMulticlassClassifier

Inherited from VectorClassifier[L, F]

Inherited from Classifier[L]

Inherited from LinearMulticlassClassifier

Inherited from OptimizablePredictor[la.Tensor1, la.Tensor1]

Inherited from model.Parameters

Inherited from MulticlassClassifier[la.Tensor1]

Inherited from backend.Classifier[la.Tensor1, la.Tensor1]

Inherited from Predictor[la.Tensor1, la.Tensor1]

Inherited from AnyRef

Inherited from Any

Ungrouped

AltStyle によって変換されたページ (->オリジナル) /