it.uniroma2.sag.kelp.predictionfunction.classifier.multiclass

Class MultiLabelClassificationOutput

java.lang.Object

it.uniroma2.sag.kelp.predictionfunction.classifier.multiclass.MultiLabelClassificationOutput

All Implemented Interfaces:

ClassificationOutput, Prediction

public class MultiLabelClassificationOutput
extends Object
implements ClassificationOutput

It is the output provided by a multi label classifier. It is suitable for multi label classification tasks where every instance can be associated to zero, one or multiple class. Basically, given a multi label classification task with C classes, starting from the output provided by C different binary classifiers, the final predicted classes are the ones associated to a positive score

Author:

Simone Filice

Constructor Summary

Constructors

Constructor and Description
MultiLabelClassificationOutput()

Method Summary

Methods

Modifier and Type	Method and Description
void	addBinaryPrediction(Label label, float prediction) Sets the score associated to a given class
List<Label>	getAllClasses() Returns all the classes involved in the classification process (both predicted and not)
List<Label>	getPredictedClasses() Returns all the classes that the classifier has predicted
Float	getScore(Label label) Return the prediction score associated to a given label
boolean	isClassPredicted(Label label) Returns a boolean identifying the predicted membership to a specified class

Methods inherited from class java.lang.Object

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

Constructor Detail

MultiLabelClassificationOutput

public MultiLabelClassificationOutput()

Method Detail

addBinaryPrediction

public void addBinaryPrediction(Label label,
                       float prediction)

Sets the score associated to a given class

Parameters:

label - the class

prediction - the score

getScore

public Float getScore(Label label)

Description copied from interface: Prediction

Return the prediction score associated to a given label

Specified by:

getScore in interface Prediction

Parameters:

label - the label whose associated score is required

Returns:

the score associated to a given label

isClassPredicted

public boolean isClassPredicted(Label label)

Description copied from interface: ClassificationOutput

Returns a boolean identifying the predicted membership to a specified class

Specified by:

isClassPredicted in interface ClassificationOutput

Parameters:

label - the class whose membership is required

Returns:

a boolean identifying the predicted membership to a specified class

getPredictedClasses

public List<Label> getPredictedClasses()

Description copied from interface: ClassificationOutput

Returns all the classes that the classifier has predicted

Specified by:

getPredictedClasses in interface ClassificationOutput

Returns:

the predicted classes

getAllClasses

public List<Label> getAllClasses()

Description copied from interface: ClassificationOutput

Returns all the classes involved in the classification process (both predicted and not)

Specified by:

getAllClasses in interface ClassificationOutput

Returns:

all the classes involved in the classification process (both predicted and not)