com.ibm.bluej.consistency.classifier

Class LibSVMClassifier

java.lang.Object

com.ibm.bluej.consistency.classifier.AbstractClassifier

com.ibm.bluej.consistency.classifier.LibSVMClassifier

All Implemented Interfaces:

java.io.Serializable

public class LibSVMClassifier
extends AbstractClassifier

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
libsvm.svm_parameter	param

Fields inherited from class com.ibm.bluej.consistency.classifier.AbstractClassifier

PRESENT

Constructor Summary

Constructors

Constructor and Description
LibSVMClassifier()

Method Summary

Methods

Modifier and Type	Method and Description
static void	main(java.lang.String[] args)
int	predict(java.util.Map<?,com.ibm.bluej.util.common.MutableDouble> features) Predict the most likely class label
double[]	predictProb(java.util.Map<?,com.ibm.bluej.util.common.MutableDouble> features) Predict a probability for each class
void	train(java.util.Collection<? extends java.util.Map<?,com.ibm.bluej.util.common.MutableDouble>>[] allVectors) Trains the model using the allVectors as training data

Methods inherited from class com.ibm.bluej.consistency.classifier.AbstractClassifier

convertBinaryFeatures, crossValidate, crossValidate, holdOut, probToWeight, pruneFeatures, testingData

Methods inherited from class java.lang.Object

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

Field Detail

param

public libsvm.svm_parameter param

Constructor Detail

LibSVMClassifier

public LibSVMClassifier()

Method Detail

train

public void train(java.util.Collection<? extends java.util.Map<?,com.ibm.bluej.util.common.MutableDouble>>[] allVectors)

Description copied from class: AbstractClassifier

Trains the model using the allVectors as training data

Specified by:

train in class AbstractClassifier

Parameters:

allVectors - The indices of the array correspond to the classes to be distinguished. Each class has an Iterable of instances - feature/value maps.

predictProb

public double[] predictProb(java.util.Map<?,com.ibm.bluej.util.common.MutableDouble> features)

Description copied from class: AbstractClassifier

Predict a probability for each class

Specified by:

predictProb in class AbstractClassifier

Parameters:

features - The features for the instance to be classified

Returns:

The probability for each class

predict

public int predict(java.util.Map<?,com.ibm.bluej.util.common.MutableDouble> features)

Description copied from class: AbstractClassifier

Predict the most likely class label

Specified by:

predict in class AbstractClassifier

Parameters:

features - The features for the instance to be classified

Returns:

The class label

main

public static void main(java.lang.String[] args)