cc.mallet.classify

Class MaxEnt

java.lang.Object

cc.mallet.classify.Classifier

cc.mallet.classify.MaxEnt

All Implemented Interfaces:

AlphabetCarrying, java.io.Serializable

Direct Known Subclasses:

RankMaxEnt

public class MaxEnt
extends Classifier
implements java.io.Serializable

Maximum Entropy (AKA Multivariate Logistic Regression) classifier.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
MaxEnt(Pipe dataPipe, double[] parameters)
MaxEnt(Pipe dataPipe, double[] parameters, FeatureSelection featureSelection)
MaxEnt(Pipe dataPipe, double[] parameters, FeatureSelection[] perClassFeatureSelection)
MaxEnt(Pipe dataPipe, double[] parameters, FeatureSelection featureSelection, FeatureSelection[] perClassFeatureSelection)

Method Summary

Modifier and Type	Method and Description
Classification	classify(Instance instance)
void	getClassificationScores(Instance instance, double[] scores)
void	getClassificationScoresWithTemperature(Instance instance, double temperature, double[] scores)
int	getDefaultFeatureIndex()
FeatureSelection	getFeatureSelection()
int	getNumParameters()
static int	getNumParameters(Pipe instancePipe)
double[]	getParameters()
FeatureSelection[]	getPerClassFeatureSelection()
void	getUnnormalizedClassificationScores(Instance instance, double[] scores)
void	print() Outputs human-readable description of classifier (e.g., list of weights, decision tree) to System.out
void	print(java.io.PrintStream out)
void	print(java.io.PrintWriter out)
void	printExtremeFeatures(java.io.PrintWriter out, int num)
void	printRank(java.io.PrintWriter out)
void	setDefaultFeatureIndex(int defaultFeatureIndex)
MaxEnt	setFeatureSelection(FeatureSelection fs)
void	setParameter(int classIndex, int featureIndex, double value)
void	setParameters(double[] parameters)
MaxEnt	setPerClassFeatureSelection(FeatureSelection[] fss)

Methods inherited from class cc.mallet.classify.Classifier

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

Methods inherited from class java.lang.Object

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

Constructor Detail

MaxEnt

public MaxEnt(Pipe dataPipe,
              double[] parameters,
              FeatureSelection featureSelection,
              FeatureSelection[] perClassFeatureSelection)

MaxEnt

public MaxEnt(Pipe dataPipe,
              double[] parameters,
              FeatureSelection featureSelection)

MaxEnt

public MaxEnt(Pipe dataPipe,
              double[] parameters,
              FeatureSelection[] perClassFeatureSelection)

MaxEnt

public MaxEnt(Pipe dataPipe,
              double[] parameters)

Method Detail

getParameters

public double[] getParameters()

getNumParameters

public int getNumParameters()

getNumParameters

public static int getNumParameters(Pipe instancePipe)

setParameters

public void setParameters(double[] parameters)

setParameter

public void setParameter(int classIndex,
                         int featureIndex,
                         double value)

getFeatureSelection

public FeatureSelection getFeatureSelection()

Overrides:

getFeatureSelection in class Classifier

setFeatureSelection

public MaxEnt setFeatureSelection(FeatureSelection fs)

getPerClassFeatureSelection

public FeatureSelection[] getPerClassFeatureSelection()

Overrides:

getPerClassFeatureSelection in class Classifier

setPerClassFeatureSelection

public MaxEnt setPerClassFeatureSelection(FeatureSelection[] fss)

getDefaultFeatureIndex

public int getDefaultFeatureIndex()

setDefaultFeatureIndex

public void setDefaultFeatureIndex(int defaultFeatureIndex)

getUnnormalizedClassificationScores

public void getUnnormalizedClassificationScores(Instance instance,
                                                double[] scores)

getClassificationScores

public void getClassificationScores(Instance instance,
                                    double[] scores)

getClassificationScoresWithTemperature

public void getClassificationScoresWithTemperature(Instance instance,
                                                   double temperature,
                                                   double[] scores)

classify

public Classification classify(Instance instance)

Specified by:

classify in class Classifier

print

public void print()

Description copied from class: Classifier

Outputs human-readable description of classifier (e.g., list of weights, decision tree) to System.out

Overrides:

print in class Classifier

print

public void print(java.io.PrintWriter out)

Overrides:

print in class Classifier

print

public void print(java.io.PrintStream out)

printRank

public void printRank(java.io.PrintWriter out)

printExtremeFeatures

public void printExtremeFeatures(java.io.PrintWriter out,
                                 int num)