Class RatioBasedEdaAlgorithm<G>
java.lang.Object
com.knezevic.edaf.v3.core.api.AbstractEdaAlgorithm<G>
com.knezevic.edaf.v3.algorithms.RatioBasedEdaAlgorithm<G>
- Type Parameters:
G- genotype type
- All Implemented Interfaces:
Algorithm<G>
- Direct Known Subclasses:
BlockCovarianceEdaAlgorithm,BmdaAlgorithm,BoaAlgorithm,CemAlgorithm,CgaAlgorithm,ChowLiuEdaAlgorithm,CmaEsAlgorithm,CopulaEdaAlgorithm,DependencyTreeEdaAlgorithm,EbnaAlgorithm,EhbsaAlgorithm,EhmPermutationEdaAlgorithm,FactorizedDiscreteEdaAlgorithm,FlowEdaAlgorithm,FullCovarianceEdaAlgorithm,GaussianDiagEdaAlgorithm,GmmEdaAlgorithm,HBoaAlgorithm,IgoAlgorithm,IndicatorEdaAlgorithm,KdeEdaAlgorithm,KendallPermutationEdaAlgorithm,LowRankCovarianceEdaAlgorithm,MallowsEdaAlgorithm,MimicAlgorithm,MimicContinuousAlgorithm,MoEdaSkeletonAlgorithm,ParetoEdaAlgorithm,PbilAlgorithm,PbilRealAlgorithm,PlackettLuceEdaAlgorithm,PositionBasedPermutationEdaAlgorithm,SNesAlgorithm,TreeEdaAlgorithm,UmdaAlgorithm,UmdaContinuousAlgorithm,XNesAlgorithm
Generic ratio-based EDA driver.
This base class implements the canonical EDA cycle from
AbstractEdaAlgorithm: initialize population, evaluate, select elites,
fit model, sample offspring, and apply replacement. The only strategy detail
overridden here is elite size:
eliteCount = round(selectionRatio * populationSize)clipped to at least one individual.
Dedicated algorithm aliases (UMDA, BOA, PBIL, etc.) inherit this behavior and express algorithm identity through plugin/model selection in configuration.
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionid()Algorithm identifier (e.g. umda, gaussian-diag-eda, ehm-eda).protected intselectionSize(AlgorithmContext<G> context, Population<G> population) Returns how many individuals are used for model fitting.Methods inherited from class com.knezevic.edaf.v3.core.api.AbstractEdaAlgorithm
afterIteration, complete, evaluateGenotype, initialize, iterate, postProcessPopulation, restoreState, result, run, state
-
Constructor Details
-
RatioBasedEdaAlgorithm
- Parameters:
id- stable algorithm identifier used in events, persistence and CLIselectionRatio- fraction of population used for model fitting
-
-
Method Details
-
id
-
selectionSize
Description copied from class:AbstractEdaAlgorithmReturns how many individuals are used for model fitting.- Specified by:
selectionSizein classAbstractEdaAlgorithm<G>
-