org.encog.ml.importance

Class AbstractFeatureImportance

java.lang.Object

org.encog.ml.importance.AbstractFeatureImportance

All Implemented Interfaces:

FeatureImportance

Direct Known Subclasses:

CorrelationFeatureImportanceCalc, NeuralFeatureImportanceCalc, PerturbationFeatureImportanceCalc

public abstract class AbstractFeatureImportance
extends java.lang.Object
implements FeatureImportance

Provides basic functionality for a feature ranking algorithm.

Constructor Summary

Constructors

Constructor and Description
AbstractFeatureImportance()

Method Summary

Modifier and Type	Method and Description
java.util.List<FeatureRank>	getFeatures()
java.util.Collection<FeatureRank>	getFeaturesSorted()
MLRegression	getModel()
void	init(MLRegression theModel, java.lang.String[] theFeatureNames) Initialize a model
java.lang.String	toString()

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.encog.ml.importance.FeatureImportance

performRanking, performRanking

Constructor Detail

AbstractFeatureImportance

public AbstractFeatureImportance()

Method Detail

init

public void init(MLRegression theModel,
                 java.lang.String[] theFeatureNames)

Initialize a model

Specified by:

init in interface FeatureImportance

Parameters:

theModel - The model that will be used for ranking.

theFeatureNames - The names of the fields.

getFeatures

public java.util.List<FeatureRank> getFeatures()

Specified by:

getFeatures in interface FeatureImportance

Returns:

The individual rankings of each feature.

getFeaturesSorted

public java.util.Collection<FeatureRank> getFeaturesSorted()

Specified by:

getFeaturesSorted in interface FeatureImportance

Returns:

The features sorted by importance.

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

getModel

public MLRegression getModel()

Specified by:

getModel in interface FeatureImportance

Returns:

The model that was evaluated.