net.sf.tweety.logics.ml

Class SimpleSamplingMlnReasoner

java.lang.Object

net.sf.tweety.commons.Reasoner

net.sf.tweety.logics.ml.AbstractMlnReasoner

net.sf.tweety.logics.ml.SimpleSamplingMlnReasoner

public class SimpleSamplingMlnReasoner
extends AbstractMlnReasoner

This MLN reasoner employs simple random sampling from the set of interpretations to compute the probability of a formula.

Author:

Matthias Thimm

Field Summary

Fields

Modifier and Type	Field and Description
private int	numOfPositiveTests
private double	precision The computation is aborted when the given precision is reached for at least numOfPositive number of consecutive tests.

Constructor Summary

Constructors

Constructor and Description
SimpleSamplingMlnReasoner(BeliefBase beliefBase, FolSignature signature, double precision, int numOfPositiveTests) Creates a new SimpleSamplingMlnReasoner for the given Markov logic network.

Method Summary

Modifier and Type	Method and Description
protected double	doQuery(FolFormula query) Performs the actual querying.
void	reset() Resets this reasoner (removes cached files etc.)

Methods inherited from class net.sf.tweety.logics.ml.AbstractMlnReasoner

computeWeight, getSignature, numberOfGroundSatisfactions, query

Methods inherited from class net.sf.tweety.commons.Reasoner

getKnowledgeBase

Methods inherited from class java.lang.Object

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

Field Detail

precision

private double precision

The computation is aborted when the given precision is reached for at least numOfPositive number of consecutive tests.

numOfPositiveTests

private int numOfPositiveTests

Constructor Detail

SimpleSamplingMlnReasoner

public SimpleSamplingMlnReasoner(BeliefBase beliefBase,
                                 FolSignature signature,
                                 double precision,
                                 int numOfPositiveTests)

Creates a new SimpleSamplingMlnReasoner for the given Markov logic network.

Parameters:

beliefBase - a Markov logic network.

signature - another signature (if the probability distribution should be defined on that one (that one should subsume the signature of the Markov logic network)

precision - the precision

numOfPositiveTests - the number of positive consecutive tests on precision

Method Detail

reset

public void reset()

Description copied from class: AbstractMlnReasoner

Resets this reasoner (removes cached files etc.)

Specified by:

reset in class AbstractMlnReasoner

doQuery

protected double doQuery(FolFormula query)

Description copied from class: AbstractMlnReasoner

Performs the actual querying.

Specified by:

doQuery in class AbstractMlnReasoner

Parameters:

query - a fol formula guaranteed to be ground.

Returns:

the answer of the query.