Package cc.mallet.classify

Class Winnow

java.lang.Object

cc.mallet.classify.Classifier

cc.mallet.classify.Winnow

All Implemented Interfaces:

AlphabetCarrying, java.io.Serializable

public class Winnow
extends Classifier

Classification methods of Winnow2 algorithm.

See Also:

WinnowTrainer, Serialized Form

Field Summary

Fields inherited from class cc.mallet.classify.Classifier

instancePipe

Constructor Summary

Constructors

Constructor	Description
Winnow(Pipe dataPipe, double[][] newWeights, double theta, int idim, int jdim)	Passes along data pipe and weights from WinnowTrainer

Method Summary

Modifier and Type	Method	Description
Classification	classify(Instance instance)	Classifies an instance using Winnow's weights

Methods inherited from class cc.mallet.classify.Classifier

alphabetsMatch, classify, classify, classify, getAccuracy, getAlphabet, getAlphabets, getAverageRank, getF1, getF1, getF1, getFeatureSelection, getInstancePipe, getLabelAlphabet, getPerClassFeatureSelection, getPrecision, getPrecision, getPrecision, getRecall, getRecall, getRecall, print, print

Methods inherited from class java.lang.Object

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

Constructor Detail

Winnow

public Winnow(Pipe dataPipe,
              double[][] newWeights,
              double theta,
              int idim,
              int jdim)

Passes along data pipe and weights from WinnowTrainer

Parameters:

dataPipe - needed for dictionary, labels, feature vectors, etc

newWeights - weights calculated during training phase

theta - value used for threshold

idim - i dimension of weights array

jdim - j dimension of weights array

Method Detail

classify

public Classification classify(Instance instance)

Classifies an instance using Winnow's weights

Specified by:

classify in class Classifier

Parameters:

instance - an instance to be classified

Returns:

an object containing the classifier's guess