Package com.bayesserver.learning.structure

Class FeatureSelection

java.lang.Object

com.bayesserver.learning.structure.FeatureSelection

public final class FeatureSelection
extends Object

Contains methods to determine which variables are likely to be good features (predictors) or not.

Method Summary

Modifier and Type	Method	Description
static FeatureSelectionOutput	detect(List<Variable> variables, EvidenceReaderCommand evidenceReaderCommand, Variable target, FeatureSelectionOptions options)	Determines which variables are likely to be good features (predictors) of a target variable.

Methods inherited from class java.lang.Object

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

Method Detail

detect

public static FeatureSelectionOutput detect(List<Variable> variables,
                                            EvidenceReaderCommand evidenceReaderCommand,
                                            Variable target,
                                            FeatureSelectionOptions options)

Determines which variables are likely to be good features (predictors) of a target variable.

Parameters:

variables - The variables to test against the target.

evidenceReaderCommand - The data.

target - The target variable.

options - Options governing the tests.

Returns:

Test information for each variable.