mulan.classifier.transformation
Class LabelPowerset

java.lang.Object
  mulan.classifier.MultiLabelLearnerBase
      mulan.classifier.transformation.TransformationBasedMultiLabelLearner
          mulan.classifier.transformation.LabelPowerset

All Implemented Interfaces:

Serializable, MultiLabelLearner, TechnicalInformationHandler

Direct Known Subclasses:

LabelsetPruning

public class LabelPowerset
extends TransformationBasedMultiLabelLearner

Class that implements a label powerset classifier

Version:

2012.02.27

Author:

Grigorios Tsoumakas, Robert Friberg

See Also:

Serialized Form

Field Summary

protected boolean	makePredictionsBasedOnConfidences Whether the method introduced by the PPT algorithm will be used to actually get the 1/0 output bipartition based on the confidences (requires a threshold)
protected Random	Rand Random number generator for randomly solving tied predictions
protected double	threshold Threshold used for deciding the 1/0 output value of each label based on the corresponding confidences as calculated by the method introduced in the PPT algorithm
protected LabelPowersetTransformation	transformation The object that performs the data transformation

Fields inherited from class mulan.classifier.transformation.TransformationBasedMultiLabelLearner

baseClassifier

Fields inherited from class mulan.classifier.MultiLabelLearnerBase

featureIndices, labelIndices, numLabels

Constructor Summary

LabelPowerset(Classifier classifier)
Conststructor that initializes the learner with a base classifier

Method Summary

protected void	buildInternal(MultiLabelInstances mlData) Learner specific implementation of building the model from MultiLabelInstances training data set.
protected MultiLabelOutput	makePredictionInternal(Instance instance) Learner specific implementation for predicting on specified data based on trained model.
void	setConfidenceCalculationMethod(int method) Sets the method of calculating probabilities for each label
void	setMakePredictionsBasedOnConfidences(boolean value) Sets a threshold for obtaining the bipartition
void	setSeed(int s) Setting a seed for random selection in case of ties during prediction
void	setThreshold(double t) The threshold for obtaining the bipartition from probabilities

Methods inherited from class mulan.classifier.transformation.TransformationBasedMultiLabelLearner

getBaseClassifier, getTechnicalInformation, globalInfo

Methods inherited from class mulan.classifier.MultiLabelLearnerBase

build, debug, getDebug, isModelInitialized, isUpdatable, makeCopy, makePrediction, setDebug

Methods inherited from class java.lang.Object

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

Field Detail

makePredictionsBasedOnConfidences

protected boolean makePredictionsBasedOnConfidences

Whether the method introduced by the PPT algorithm will be used to actually get the 1/0 output bipartition based on the confidences (requires a threshold)

threshold

protected double threshold

Threshold used for deciding the 1/0 output value of each label based on the corresponding confidences as calculated by the method introduced in the PPT algorithm

transformation

protected LabelPowersetTransformation transformation

The object that performs the data transformation

Rand

protected Random Rand

Random number generator for randomly solving tied predictions

Constructor Detail

LabelPowerset

public LabelPowerset(Classifier classifier)

Conststructor that initializes the learner with a base classifier

Parameters:

classifier - the base single-label classification algorithm

Method Detail

setMakePredictionsBasedOnConfidences

public void setMakePredictionsBasedOnConfidences(boolean value)

Sets a threshold for obtaining the bipartition

Parameters:

value - the threshold's value

setSeed

public void setSeed(int s)

Setting a seed for random selection in case of ties during prediction

Parameters:

s - the seed

setThreshold

public void setThreshold(double t)

The threshold for obtaining the bipartition from probabilities

Parameters:

t -

setConfidenceCalculationMethod

public void setConfidenceCalculationMethod(int method)

Sets the method of calculating probabilities for each label

Parameters:

method -

buildInternal

protected void buildInternal(MultiLabelInstances mlData)
                      throws Exception

Description copied from class: MultiLabelLearnerBase

Learner specific implementation of building the model from MultiLabelInstances training data set. This method is called from MultiLabelLearnerBase.build(MultiLabelInstances) method, where behavior common across all learners is applied.

Specified by:

buildInternal in class MultiLabelLearnerBase

Parameters:

mlData - the training data set

Throws:

Exception - if learner model was not created successfully

makePredictionInternal

protected MultiLabelOutput makePredictionInternal(Instance instance)
                                           throws Exception

Description copied from class: MultiLabelLearnerBase

Learner specific implementation for predicting on specified data based on trained model. This method is called from MultiLabelLearnerBase.makePrediction(weka.core.Instance) which guards for model initialization and apply common handling/behavior.

Specified by:

makePredictionInternal in class MultiLabelLearnerBase

Parameters:

instance - the data instance to predict on

Returns:

the output of the learner for the given instance

Throws:

Exception - if an error occurs while making the prediction.

InvalidDataException - if specified instance data is invalid and can not be processed by the learner