it.uniroma2.sag.kelp.learningalgorithm.classification.passiveaggressive

Class BudgetedPassiveAggressiveClassification

java.lang.Object

it.uniroma2.sag.kelp.learningalgorithm.budgetedAlgorithm.BudgetedLearningAlgorithm

it.uniroma2.sag.kelp.learningalgorithm.classification.passiveaggressive.BudgetedPassiveAggressiveClassification

All Implemented Interfaces:

BinaryLearningAlgorithm, KernelMethod, LearningAlgorithm, OnlineLearningAlgorithm

public class BudgetedPassiveAggressiveClassification
extends BudgetedLearningAlgorithm

Online Passive-Aggressive on a budget reference: Zhuang Wang and Slobodan Vucetic Online Passive-Aggressive Algorithms on a Budget

Author:

Simone Filice

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	BudgetedPassiveAggressiveClassification.DeletingPolicy It is the updating policy applied when the budget is full.

Field Summary

Fields inherited from class it.uniroma2.sag.kelp.learningalgorithm.budgetedAlgorithm.BudgetedLearningAlgorithm

budget, label

Constructor Summary

Constructors

Constructor and Description
BudgetedPassiveAggressiveClassification()
BudgetedPassiveAggressiveClassification(int budget, Kernel kernel, float c, boolean fairness, BudgetedPassiveAggressiveClassification.DeletingPolicy deletingPolicy, Label label)
BudgetedPassiveAggressiveClassification(int budget, Kernel kernel, float cp, float cn, BudgetedPassiveAggressiveClassification.DeletingPolicy deletingPolicy, Label label)

Method Summary

Methods

Modifier and Type	Method and Description
LearningAlgorithm	duplicate() Creates a new instance of the LearningAlgorithm initialized with the same parameters of the learningAlgorithm to be duplicated.
float	getCn()
float	getCp()
BudgetedPassiveAggressiveClassification.DeletingPolicy	getDeletingPolicy()
Kernel	getKernel() Returns the kernel exploited by this learner
BinaryKernelMachineClassifier	getPredictionFunction() Returns the predictionFunction learned during the training process
boolean	isFairness()
void	learn(Dataset dataset) It starts the training process exploiting the provided dataset
BinaryMarginClassifierOutput	learn(Example example) Applies the learning process on a single example, updating its current model
protected BinaryMarginClassifierOutput	predictAndLearnWithAvailableBudget(Example example)
protected BinaryMarginClassifierOutput	predictAndLearnWithFullBudget(Example example) Learns from a single example applying a specific policy that must be adopted when the budget is reached
void	reset() Resets all the learning process, returning to the default state.
void	setC(float c)
void	setCn(float cn)
void	setCp(float cp)
void	setDeletingPolicy(BudgetedPassiveAggressiveClassification.DeletingPolicy deletingPolicy)
void	setFairness(boolean fairness)
void	setKernel(Kernel kernel) Sets the kernel this
void	setPredictionFunction(PredictionFunction predictionFunction) Sets the predictionFunction learned during the training process.

Methods inherited from class it.uniroma2.sag.kelp.learningalgorithm.budgetedAlgorithm.BudgetedLearningAlgorithm

getBudget, getLabel, getLabels, setBudget, setLabel, setLabels

Methods inherited from class java.lang.Object

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

Constructor Detail

BudgetedPassiveAggressiveClassification

public BudgetedPassiveAggressiveClassification()

BudgetedPassiveAggressiveClassification

public BudgetedPassiveAggressiveClassification(int budget,
                                       Kernel kernel,
                                       float cp,
                                       float cn,
                                       BudgetedPassiveAggressiveClassification.DeletingPolicy deletingPolicy,
                                       Label label)

BudgetedPassiveAggressiveClassification

public BudgetedPassiveAggressiveClassification(int budget,
                                       Kernel kernel,
                                       float c,
                                       boolean fairness,
                                       BudgetedPassiveAggressiveClassification.DeletingPolicy deletingPolicy,
                                       Label label)

Method Detail

isFairness

public boolean isFairness()

Returns:

the fairness

setFairness

public void setFairness(boolean fairness)

Parameters:

fairness - the fairness to set

getCp

public float getCp()

Returns:

the aggressiveness parameter for positive examples

setCp

public void setCp(float cp)

Parameters:

cp - the aggressiveness parameter for positive examples

getCn

public float getCn()

Returns:

the aggressiveness parameter for negative examples

setCn

public void setCn(float cn)

Parameters:

cn - the aggressiveness parameter for negative examples

setC

public void setC(float c)

Parameters:

c - the aggressiveness parameter

getDeletingPolicy

public BudgetedPassiveAggressiveClassification.DeletingPolicy getDeletingPolicy()

Returns:

the deletingPolicy

setDeletingPolicy

public void setDeletingPolicy(BudgetedPassiveAggressiveClassification.DeletingPolicy deletingPolicy)

Parameters:

deletingPolicy - the deletingPolicy to set

duplicate

public LearningAlgorithm duplicate()

Description copied from interface: LearningAlgorithm

Creates a new instance of the LearningAlgorithm initialized with the same parameters of the learningAlgorithm to be duplicated. A shallow copy of the learning parameters is performed, while the state parameters are initialized to their default value. The labels are not initialized neither copied

reset

public void reset()

Description copied from interface: LearningAlgorithm

Resets all the learning process, returning to the default state. All the learned process is forgotten

getPredictionFunction

public BinaryKernelMachineClassifier getPredictionFunction()

Description copied from interface: LearningAlgorithm

Returns the predictionFunction learned during the training process

Returns:

the predictionFunction learned during the training process

getKernel

public Kernel getKernel()

Description copied from interface: KernelMethod

Returns the kernel exploited by this learner

Returns:

the kernel

setKernel

public void setKernel(Kernel kernel)

Description copied from interface: KernelMethod

Sets the kernel this

Parameters:

kernel - the kernel to set

predictAndLearnWithAvailableBudget

protected BinaryMarginClassifierOutput predictAndLearnWithAvailableBudget(Example example)

Specified by:

predictAndLearnWithAvailableBudget in class BudgetedLearningAlgorithm

predictAndLearnWithFullBudget

protected BinaryMarginClassifierOutput predictAndLearnWithFullBudget(Example example)

Description copied from class: BudgetedLearningAlgorithm

Learns from a single example applying a specific policy that must be adopted when the budget is reached

Specified by:

predictAndLearnWithFullBudget in class BudgetedLearningAlgorithm

Parameters:

example - the example to be exploited in the learning process

Returns:

the prediction on the given example, using the old classification function (before any possible update)

learn

public void learn(Dataset dataset)

Description copied from interface: LearningAlgorithm

It starts the training process exploiting the provided dataset

Specified by:

learn in interface LearningAlgorithm

Overrides:

learn in class BudgetedLearningAlgorithm

Parameters:

dataset - the training data

learn

public BinaryMarginClassifierOutput learn(Example example)

Description copied from interface: OnlineLearningAlgorithm

Applies the learning process on a single example, updating its current model

Specified by:

learn in interface OnlineLearningAlgorithm

Overrides:

learn in class BudgetedLearningAlgorithm

Parameters:

example - the instance to be exploited in the learning process

Returns:

the Prediction associated to example before the updating step

setPredictionFunction

public void setPredictionFunction(PredictionFunction predictionFunction)

Description copied from interface: LearningAlgorithm

Sets the predictionFunction learned during the training process. It can be used to change the default prediction function, or to set an already trained one.