Package de.jstacs.scoringFunctions

Provides ScoringFunctions that can be used in a ScoreClassifier.

See:
Description

Interface Summary

NormalizableScoringFunction	The interface for normalizable ScoringFunctions.
SamplingScoringFunction	Interface for NormalizableScoringFunctions that can be used for Metropolis-Hastings sampling in a SamplingScoreBasedClassifier.
ScoringFunction	This interface is the main part of any ScoreClassifier.
VariableLengthScoringFunction	This is an interface for all NormalizableScoringFunctions that allow to score subsequences of arbitrary length.

Class Summary

AbstractNormalizableScoringFunction	This class is the main part of any ScoreClassifier.
AbstractVariableLengthScoringFunction	This abstract class implements some methods declared in NormalizableScoringFunction based on the declaration of methods in VariableLengthScoringFunction.
CMMScoringFunction	This scoring function implements a cyclic Markov model of arbitrary order and periodicity for any sequence length.
IndependentProductScoringFunction	This class enables the user to model parts of a sequence independent of each other.
MappingScoringFunction	This class implements a NormalizableScoringFunction that works on mapped Sequences.
MRFScoringFunction	This class implements the scoring function for any MRF (Markov Random Field).
NormalizedScoringFunction	This class makes an unnormalized NormalizableScoringFunction to a normalized NormalizableScoringFunction.
UniformScoringFunction	This ScoringFunction does nothing.

Package de.jstacs.scoringFunctions Description

Provides ScoringFunctions that can be used in a ScoreClassifier. Among the currently implemented ScoringFunctions are

• the BayesianNetworkScoringFunction, which provides structure learning for inhomogeneous Markov models, Bayesian trees, and permuted Markov models,
• the MixtureScoringFunction for mixtures of ScoringFunctions, and
• homogeneous ScoringFunctions.