cc.mallet.grmm.learning
Class ACRF.UnrolledGraph

java.lang.Object
  cc.mallet.grmm.types.FactorGraph
      cc.mallet.grmm.types.UndirectedModel
          cc.mallet.grmm.learning.ACRF.UnrolledGraph

All Implemented Interfaces:

Factor, java.io.Serializable, java.lang.Cloneable

Enclosing class:

ACRF

public static class ACRF.UnrolledGraph
extends UndirectedModel

See Also:

Serialized Form

Constructor Summary

ACRF.UnrolledGraph(Instance inst, ACRF.Template[] templates, ACRF.Template[] fixed)

ACRF.UnrolledGraph(Instance inst, ACRF.Template[] templates, java.util.List fixed, boolean setupPotentials)
Creates a graphical model for a given instance.

Method Summary

void	addClique(ACRF.UnrolledVarSet clique)
double[]	computeCurrentResids()
Variable	get(int idx) Returns a variable from this model with a given index.
Assignment	getAssignment() Returns an Assignment object that corresponds to the LabelSequence for which this graph was unrolled.
int	getIndex(Variable var) Returns a unique numeric index for a variable in this model.
int	getIndex(VarSet vs)
double[]	getLastResids()
double	getLogNumAssignments()
ACRF.UnrolledVarSet	getUnrolledVarSet(Factor f)
ACRF.UnrolledVarSet	getUnrolledVarSet(int cnum)
int	numSlices()
int	observedValue(Variable var)
void	setObserved(Variable var, int outcome)
java.util.Iterator	unrolledVarSetIterator()
Variable	varOfIndex(int t, int j)

Methods inherited from class cc.mallet.grmm.types.UndirectedModel

addFactor, createBoltzmannMachine, getEdgeSet, isConnected

Methods inherited from class cc.mallet.grmm.types.FactorGraph

addFactor, afterFactorAdd, allFactorsContaining, allFactorsContaining, allFactorsOf, allFactorsOf, almostEquals, almostEquals, argmax, assignmentIterator, asTable, beforeFactorAdd, clear, containsVar, divideBy, dump, dump, dumpToString, duplicate, entropy, exponentiate, extractMax, extractMax, extractMax, factorOf, factorOf, factorOf, factorOf, factorProduct, factors, factorsIterator, findVariable, getAdjacentVertices, getDegree, getFactor, getIndex, getInferenceCache, getVariable, isAdjacent, isNaN, logify, logValue, logValue, logValue, marginalize, marginalize, marginalize, marginalizeOut, marginalizeOut, multiply, multiplyBy, normalize, numVariables, prettyOutputString, printAsDot, printAsDot, remove, remove, sample, sampleContinuousVars, setInferenceCache, slice, slice, sum, toString, value, value, variablesIterator, variablesSet, varSet, varSetIterator

Methods inherited from class java.lang.Object

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

Constructor Detail

ACRF.UnrolledGraph

public ACRF.UnrolledGraph(Instance inst,
                          ACRF.Template[] templates,
                          ACRF.Template[] fixed)

ACRF.UnrolledGraph

public ACRF.UnrolledGraph(Instance inst,
                          ACRF.Template[] templates,
                          java.util.List fixed,
                          boolean setupPotentials)

Creates a graphical model for a given instance. This is called unrolling a dynamic model.

Method Detail

addClique

public void addClique(ACRF.UnrolledVarSet clique)

getLastResids

public double[] getLastResids()

getAssignment

public Assignment getAssignment()

Returns an Assignment object that corresponds to the LabelSequence for which this graph was unrolled.

setObserved

public void setObserved(Variable var,
                        int outcome)

observedValue

public int observedValue(Variable var)

unrolledVarSetIterator

public java.util.Iterator unrolledVarSetIterator()

getUnrolledVarSet

public ACRF.UnrolledVarSet getUnrolledVarSet(int cnum)

getIndex

public int getIndex(VarSet vs)

get

public Variable get(int idx)

Description copied from class: FactorGraph

Returns a variable from this model with a given index. Every UndirectedModel mdl maintains a mapping between its variables and the integers 0...size(mdl)-1 , which is suitable for caching the variables in an array.

getIndex and get are inverses. That is, if idx == getIndex (var), then get(idx) will return var.

Overrides:

get in class FactorGraph

See Also:

FactorGraph.getIndex(Variable)

getIndex

public int getIndex(Variable var)

Description copied from class: FactorGraph

Returns a unique numeric index for a variable in this model. Every UndirectedModel mdl maintains a mapping between its variables and the integers 0...size(mdl)-1 , which is suitable for caching the variables in an array.

getIndex and get are inverses. That is, if idx == getIndex (var), then get(idx) will return var.

Overrides:

getIndex in class FactorGraph

Parameters:

var - A variable contained in this graphical model

Returns:

The numeric index of var

See Also:

FactorGraph.get(int)

getLogNumAssignments

public double getLogNumAssignments()

varOfIndex

public Variable varOfIndex(int t,
                           int j)

numSlices

public int numSlices()

computeCurrentResids

public double[] computeCurrentResids()

getUnrolledVarSet

public ACRF.UnrolledVarSet getUnrolledVarSet(Factor f)