java.lang.Object
es.upm.fi.cig.multictbnc.learning.structure.optimisation.scores.AbstractLikelihood
es.upm.fi.cig.multictbnc.learning.structure.optimisation.scores.ctbn.CTBNLogLikelihood
All Implemented Interfaces:
CTBNScoreFunction

public class CTBNLogLikelihood extends AbstractLikelihood implements CTBNScoreFunction
Implements the log-likelihood score for CTBNs with nodes that have CIMs.
  • Constructor Details

    • CTBNLogLikelihood

      public CTBNLogLikelihood(String penalisationFunction)
      Receives the name of the penalisation function for the structure complexity.
      Parameters:
      penalisationFunction - name of the penalisation function
  • Method Details

    • compute

      public double compute(CTBN<? extends Node> ctbn)
      Description copied from interface: CTBNScoreFunction
      Computes the score for a continuous-time Bayesian network.
      Specified by:
      compute in interface CTBNScoreFunction
      Parameters:
      ctbn - a continuous-time Bayesian network
      Returns:
      score
    • compute

      public double compute(CTBN<? extends Node> ctbn, int idxNode)
      Computes the (penalised) log-likelihood score at a given node of a discrete continuous-time Bayesian network.
      Specified by:
      compute in interface CTBNScoreFunction
      Parameters:
      ctbn - continuous-time Bayesian network
      idxNode - index of the node
      Returns:
      penalised log-likelihood score
    • isDecomposable

      public boolean isDecomposable()
      Description copied from interface: CTBNScoreFunction
      Determines if the score is decomposable.
      Specified by:
      isDecomposable in interface CTBNScoreFunction
      Returns:
      true if the score is decomposable, false otherwise
    • getIdentifier

      public String getIdentifier()
      Description copied from interface: CTBNScoreFunction
      Gets an identifier for the score function.
      Specified by:
      getIdentifier in interface CTBNScoreFunction
      Returns:
      identifier for the score function.