Catalano.MachineLearning.Regression

Class BaggingLearning

java.lang.Object

Catalano.MachineLearning.Regression.BaggingLearning

All Implemented Interfaces:

IRegression, java.lang.Cloneable

public class BaggingLearning
extends java.lang.Object
implements IRegression

Bagging Learning (Bootstrap aggregation). Bootstrap aggregating, also called bagging, is a machine learning ensemble meta-algorithm designed to improve the stability and accuracy of machine learning algorithms used in statistical classification and regression.

Constructor Summary

Constructors

Constructor and Description
BaggingLearning(IRegression regression) Initializes a new instance of the BaggingLearning class.
BaggingLearning(IRegression regression, int times) Initializes a new instance of the BaggingLearning class.
BaggingLearning(IRegression regression, int times, boolean includeAttributes) Initializes a new instance of the BaggingLearning class.

Method Summary

Modifier and Type	Method and Description
IRegression	clone() Clone of the object.
boolean	isIncludeAttributes() Check if features are drawn with replacement.
void	Learn(DatasetRegression dataset) Learn.
void	Learn(double[][] input, double[] output) Learn.
double	Predict(double[] sample) Predict.
void	setIncludeAttributes(boolean includeAttributes) Set attributes in the bagging model.

Methods inherited from class java.lang.Object

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

Constructor Detail

BaggingLearning

public BaggingLearning(IRegression regression)

Initializes a new instance of the BaggingLearning class.

Parameters:

regression - Regression.

BaggingLearning

public BaggingLearning(IRegression regression,
                       int times)

Initializes a new instance of the BaggingLearning class.

Parameters:

regression - Regression.

times - Times to train.

BaggingLearning

public BaggingLearning(IRegression regression,
                       int times,
                       boolean includeAttributes)

Initializes a new instance of the BaggingLearning class.

Parameters:

regression - regression.

times - Times to train.

includeAttributes - Include attributes in the bagging process.

Method Detail

isIncludeAttributes

public boolean isIncludeAttributes()

Check if features are drawn with replacement.

Returns:

True, if the feature are included, otherwise false.

setIncludeAttributes

public void setIncludeAttributes(boolean includeAttributes)

Set attributes in the bagging model.

Parameters:

includeAttributes - True, if the feature are included, otherwise false.

Learn

public void Learn(DatasetRegression dataset)

Description copied from interface: IRegression

Learn.

Specified by:

Learn in interface IRegression

Parameters:

dataset - Dataset regression.

Learn

public void Learn(double[][] input,
                  double[] output)

Description copied from interface: IRegression

Learn.

Specified by:

Learn in interface IRegression

Parameters:

input - Input.

output - Output.

Predict

public double Predict(double[] sample)

Description copied from interface: IRegression

Predict.

Specified by:

Predict in interface IRegression

Parameters:

sample - Feature.

Returns:

Value.

clone

public IRegression clone()

Description copied from interface: IRegression

Clone of the object.

Specified by:

clone in interface IRegression

Overrides:

clone in class java.lang.Object

Returns:

A new copy of the object.