gov.sandia.cognition.learning.algorithm.delta

Class CosineDeltaCategorizer<CategoryType>

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.learning.algorithm.delta.AbstractDeltaCategorizer<CategoryType>

gov.sandia.cognition.learning.algorithm.delta.CosineDeltaCategorizer<CategoryType>

Type Parameters:

CategoryType -

All Implemented Interfaces:

Evaluator<Vector,CategoryType>, Categorizer<Vector,CategoryType>, DiscriminantCategorizer<Vector,CategoryType,java.lang.Double>, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

@PublicationReferences(references=@PublicationReference(author="Peter W. H. Smith  and  W. Aldridge ",title="Improving Authorship Attribution: Optimizing Burrows\' Delta Method",type=Journal,year=2011,pages={63,88}))
public class CosineDeltaCategorizer<CategoryType>
extends AbstractDeltaCategorizer<CategoryType>

The Cosine Delta algorithm implementation. The same as Burrows' Delta except it uses cosine similarity.

Author:

alkilli

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CosineDeltaCategorizer.Learner<CategoryType> Learner for a CosineDeltaCategorizer.

Nested classes/interfaces inherited from class gov.sandia.cognition.learning.algorithm.delta.AbstractDeltaCategorizer

AbstractDeltaCategorizer.AbstractLearner<CategoryType>

Field Summary

Fields inherited from class gov.sandia.cognition.learning.algorithm.delta.AbstractDeltaCategorizer

featureStddev, learner

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	CosineDeltaCategorizer(CosineDeltaCategorizer.Learner<CategoryType> learner, java.util.ArrayList<java.lang.Double> featureStddev, java.util.ArrayList<java.lang.Double> featureMean) Constructor that takes learner, featureStddev, and featureMeans.

Method Summary

Modifier and Type	Method and Description
CategoryType	evaluate(Vector unknownInput) Evaluates an unknown input, but does not return the discriminant value.
ValueDiscriminantPair<CategoryType,java.lang.Double>	evaluateWithDiscriminant(Vector unknownVector) This method implements the evaluation aspect of CosineDelta.
java.util.List<java.lang.Double>	getFeatureMeans() Getter for featureMeans.

Methods inherited from class gov.sandia.cognition.learning.algorithm.delta.AbstractDeltaCategorizer

getCategories, getFeatureStddev

Methods inherited from class gov.sandia.cognition.util.AbstractCloneableSerializable

clone

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable

clone

Constructor Detail

CosineDeltaCategorizer

protected CosineDeltaCategorizer(CosineDeltaCategorizer.Learner<CategoryType> learner,
                                 java.util.ArrayList<java.lang.Double> featureStddev,
                                 java.util.ArrayList<java.lang.Double> featureMean)

Constructor that takes learner, featureStddev, and featureMeans.

Parameters:

learner -

featureStddev -

featureMean -

Method Detail

getFeatureMeans

public java.util.List<java.lang.Double> getFeatureMeans()

Getter for featureMeans.

Returns:

evaluateWithDiscriminant

public ValueDiscriminantPair<CategoryType,java.lang.Double> evaluateWithDiscriminant(Vector unknownVector)

This method implements the evaluation aspect of CosineDelta. That is, given an unknownVector, this method should return a discriminant value paired with the corresponding most likely category. The discriminant value is the score.

Specified by:

evaluateWithDiscriminant in interface DiscriminantCategorizer<Vector,CategoryType,java.lang.Double>

Specified by:

evaluateWithDiscriminant in class AbstractDeltaCategorizer<CategoryType>

Parameters:

unknownVector -

Returns:

evaluate

public CategoryType evaluate(Vector unknownInput)

Evaluates an unknown input, but does not return the discriminant value. Only returns the category that the unknown input most likely corresponds to.

Parameters:

unknownInput -

Returns: