gov.sandia.cognition.learning.algorithm.ensemble

Class AbstractCategorizerOutOfBagStoppingCriteria<InputType,CategoryType>

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.algorithm.event.AbstractIterativeAlgorithmListener

gov.sandia.cognition.learning.algorithm.ensemble.AbstractCategorizerOutOfBagStoppingCriteria<InputType,CategoryType>

Type Parameters:

InputType - The type of the input for the categorizer to learn.

CategoryType - The type of the category that is the output for the categorizer to learn.

All Implemented Interfaces:

IterativeAlgorithmListener, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

Direct Known Subclasses:

BaggingCategorizerLearner.OutOfBagErrorStoppingCriteria, IVotingCategorizerLearner.OutOfBagErrorStoppingCriteria

public abstract class AbstractCategorizerOutOfBagStoppingCriteria<InputType,CategoryType>
extends AbstractIterativeAlgorithmListener

Abstract class for implementing a out-of-bag stopping criteria for a bagging-based ensemble.

Since:

4.0.0

Author:

Justin Basilico

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static int	DEFAULT_SMOOTHING_WINDOW_SIZE The default smoothing window size is 25.
protected BagBasedCategorizerEnsembleLearner<InputType,CategoryType>	learner The learner the stopping criteria is for.
protected boolean[]	outOfBagCorrect A boolean for each example indicating whether or not it is currently a correct or incorrect out-of-bag vote.
protected int	outOfBagErrorCount The total number of out-of-bag errors.
protected double	previousSmoothedErrorRate The smoothed error rate of the previous iteration.
protected java.util.ArrayList<java.lang.Double>	rawErrorRates The raw out-of-bag error rate, per iteration.
protected java.util.ArrayList<java.lang.Double>	smoothedErrorRates The smoothed out-of-bag error rates, per iteration.
protected FiniteCapacityBuffer<java.lang.Double>	smoothingBuffer The buffer used for smoothing.
protected int	smoothingWindowSize The size of window of data to look at to determine if learning has hit a minimum.

Constructor Summary

Constructors

Constructor and Description
AbstractCategorizerOutOfBagStoppingCriteria() Creates a new OutOfBagErrorStoppingCriteria.
AbstractCategorizerOutOfBagStoppingCriteria(int smoothingWindowSize) Creates a new OutOfBagErrorStoppingCriteria with the given smoothing window size.

Method Summary

Modifier and Type	Method and Description
void	algorithmEnded(IterativeAlgorithm algorithm) This method is called when the algorithm has ended, after the last step of the algorithm.
void	algorithmStarted(IterativeAlgorithm algorithm) This method is called when a algorithm has started, before the first step of the algorithm.
abstract DataDistribution<CategoryType>	getOutOfBagEstimate(int index) Gets the out-of-bag estimate distribution across categories for the training example with the given index.
int	getSmoothingWindowSize() Gets the size of the smoothing window.
void	setSmoothingWindowSize(int smoothingWindowSize) Sets the smoothing window size.
void	stepEnded(IterativeAlgorithm algorithm) This method is called when the algorithm has ended a step of its execution.

Methods inherited from class gov.sandia.cognition.algorithm.event.AbstractIterativeAlgorithmListener

stepStarted

Methods inherited from class gov.sandia.cognition.util.AbstractCloneableSerializable

clone

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_SMOOTHING_WINDOW_SIZE

public static final int DEFAULT_SMOOTHING_WINDOW_SIZE

The default smoothing window size is 25.

See Also:

Constant Field Values

smoothingWindowSize

protected int smoothingWindowSize

The size of window of data to look at to determine if learning has hit a minimum.

learner

protected transient BagBasedCategorizerEnsembleLearner<InputType,CategoryType> learner

The learner the stopping criteria is for.

outOfBagCorrect

protected transient boolean[] outOfBagCorrect

A boolean for each example indicating whether or not it is currently a correct or incorrect out-of-bag vote. This should be the same size as the collection of data.

outOfBagErrorCount

protected transient int outOfBagErrorCount

The total number of out-of-bag errors. This should equal the number of false values in the outOfBagCorrect array.

rawErrorRates

protected transient java.util.ArrayList<java.lang.Double> rawErrorRates

The raw out-of-bag error rate, per iteration.

smoothedErrorRates

protected transient java.util.ArrayList<java.lang.Double> smoothedErrorRates

The smoothed out-of-bag error rates, per iteration.

smoothingBuffer

protected transient FiniteCapacityBuffer<java.lang.Double> smoothingBuffer

The buffer used for smoothing.

previousSmoothedErrorRate

protected transient double previousSmoothedErrorRate

The smoothed error rate of the previous iteration.

Constructor Detail

AbstractCategorizerOutOfBagStoppingCriteria

public AbstractCategorizerOutOfBagStoppingCriteria()

Creates a new OutOfBagErrorStoppingCriteria.

AbstractCategorizerOutOfBagStoppingCriteria

public AbstractCategorizerOutOfBagStoppingCriteria(int smoothingWindowSize)

Creates a new OutOfBagErrorStoppingCriteria with the given smoothing window size.

Parameters:

smoothingWindowSize - The smoothing window size to use. Must be positive.

Method Detail

algorithmStarted

public void algorithmStarted(IterativeAlgorithm algorithm)

Description copied from interface: IterativeAlgorithmListener

This method is called when a algorithm has started, before the first step of the algorithm.

Specified by:

algorithmStarted in interface IterativeAlgorithmListener

Overrides:

algorithmStarted in class AbstractIterativeAlgorithmListener

Parameters:

algorithm - The algorithm that has started.

algorithmEnded

public void algorithmEnded(IterativeAlgorithm algorithm)

Description copied from interface: IterativeAlgorithmListener

This method is called when the algorithm has ended, after the last step of the algorithm.

Specified by:

algorithmEnded in interface IterativeAlgorithmListener

Overrides:

algorithmEnded in class AbstractIterativeAlgorithmListener

Parameters:

algorithm - The algorithm that has ended.

getOutOfBagEstimate

public abstract DataDistribution<CategoryType> getOutOfBagEstimate(int index)

Gets the out-of-bag estimate distribution across categories for the training example with the given index.

Parameters:

index - The 0-based index for the training example.

Returns:

The distribution over output categories for the out-of-bag estimate for the example at that index. May be empty.

stepEnded

public void stepEnded(IterativeAlgorithm algorithm)

Description copied from interface: IterativeAlgorithmListener

This method is called when the algorithm has ended a step of its execution.

Specified by:

stepEnded in interface IterativeAlgorithmListener

Overrides:

stepEnded in class AbstractIterativeAlgorithmListener

Parameters:

algorithm - The algorithm that has ended another step of its execution.

getSmoothingWindowSize

public int getSmoothingWindowSize()

Gets the size of the smoothing window.

Returns:

The size of the smoothing window.

setSmoothingWindowSize

public void setSmoothingWindowSize(int smoothingWindowSize)

Sets the smoothing window size.

Parameters:

smoothingWindowSize - The smoothing window size. Must be positive.