Package edu.cmu.tetrad.bayes

Class RowSummingExactUpdater

java.lang.Object
edu.cmu.tetrad.bayes.RowSummingExactUpdater
All Implemented Interfaces:
BayesUpdater, ManipulatingBayesUpdater, TetradSerializable, Serializable
public final class RowSummingExactUpdater extends Object implements ManipulatingBayesUpdater
Performs updating operations on a BayesIm by summing over cells in the joint probability table for the BayesIm. Quite flexible and fast if almost all of the variables in the Bayes net are in evidence. Can be excruciatingly slow if numVars - numVarsInEvidence is more than 15.
Author:
josephramsey
See Also:

  • Constructor Details

    • RowSummingExactUpdater

      public RowSummingExactUpdater(BayesIm bayesIm)
      Constructs a new updater for the given Bayes net.

    • RowSummingExactUpdater

      public RowSummingExactUpdater(BayesIm bayesIm, Evidence evidence)
      Constructs a new updater for the given Bayes net.

  • Method Details

    • serializableInstance

      public static RowSummingExactUpdater serializableInstance()
      Generates a simple exemplar of this class to test serialization.

    • getBayesIm

      public BayesIm getBayesIm()
      The BayesIm that this updater bases its update on. This BayesIm is not modified; rather, a new BayesIm is created and updated.
      Specified by:
      getBayesIm in interface BayesUpdater
      Returns:
      the Bayes instantiated model that is being updated.

    • getManipulatedBayesIm

      public BayesIm getManipulatedBayesIm()
      Description copied from interface: ManipulatingBayesUpdater
      Returns the manipulated Bayes IM. This is the Bayes IM in which the variables in the manipulation have been removed from the graph.
      Specified by:
      getManipulatedBayesIm in interface ManipulatingBayesUpdater
      Returns:
      the updated BayesIm.

    • getManipulatedGraph

      public Graph getManipulatedGraph()
      Description copied from interface: ManipulatingBayesUpdater
      Returns the manipulated graph. This is the graph in which the variables in the manipulation have been removed from the graph.
      Specified by:
      getManipulatedGraph in interface ManipulatingBayesUpdater
      Returns:
      the graph for the manipulated BayesIm.

    • getUpdatedBayesIm

      public BayesIm getUpdatedBayesIm()
      The updated BayesIm. This is a different object from the source BayesIm.
      Specified by:
      getUpdatedBayesIm in interface ManipulatingBayesUpdater
      Returns:
      the updated Bayes IM--that is, the Bayes IM in which all probabilities of variables conditional on their parents have been updated.
      See Also:

    • getEvidence

      public Evidence getEvidence()
      Description copied from interface: ManipulatingBayesUpdater
      Returns the manipulation that was used to manipulate the Bayes IM.
      Specified by:
      getEvidence in interface ManipulatingBayesUpdater
      Returns:
      a defensive copy of the evidence.

    • setEvidence

      public void setEvidence(Evidence evidence)
      Description copied from interface: ManipulatingBayesUpdater
      Sets new evidence for the updater. Once this is called, old updating results should not longer be available.
      Specified by:
      setEvidence in interface BayesUpdater
      Specified by:
      setEvidence in interface ManipulatingBayesUpdater
      Parameters:
      evidence - the new evidence.

    • isJointMarginalSupported

      public boolean isJointMarginalSupported()
      Description copied from interface: BayesUpdater
      Returns the joint marginal probability of the given variables taking the given values, given the evidence.
      Specified by:
      isJointMarginalSupported in interface BayesUpdater
      Returns:
      true if the getJointMarginal() method is supported.

    • getJointMarginal

      public double getJointMarginal(int[] variables, int[] values)
      Description copied from interface: BayesUpdater
      Returns the joint marginal probability of the given variables taking the given values, given the evidence.
      Specified by:
      getJointMarginal in interface BayesUpdater
      Parameters:
      variables - variable indices
      values - category indices
      Returns:
      P(variables[i] = values[i] | evidence), where evidence is getEvidence().

    • getMarginal

      public double getMarginal(int variable, int value)
      Description copied from interface: ManipulatingBayesUpdater
      Returns the updated graph. This is the graph in which all probabilities of variables conditional on their parents have been updated.
      Specified by:
      getMarginal in interface BayesUpdater
      Specified by:
      getMarginal in interface ManipulatingBayesUpdater
      Parameters:
      variable - variable index
      value - category index
      Returns:
      P(variable = value | evidence) where evidence is getEvidence().

    • calculatePriorMarginals

      public double[] calculatePriorMarginals(int nodeIndex)
      Description copied from interface: BayesUpdater
      Calculates the prior marginal probabilities of the given node.
      Specified by:
      calculatePriorMarginals in interface BayesUpdater
      Parameters:
      nodeIndex - node index
      Returns:
      P(node = value), where value is the value of the node in the Bayes net.

    • calculateUpdatedMarginals

      public double[] calculateUpdatedMarginals(int nodeIndex)
      Description copied from interface: BayesUpdater
      Calculates the updated marginal probabilities of the given node, given the evidence.
      Specified by:
      calculateUpdatedMarginals in interface BayesUpdater
      Parameters:
      nodeIndex - node index
      Returns:
      P(node = value | evidence), where value is the value of the node in the Bayes net.

    • toString

      public String toString()
      Prints out the most recent marginal.
      Overrides:
      toString in class Object