public virtual void TestGetMaxedMarginals(TableFactor factor, int marginalizeTo)
{
if (!Arrays.Stream(factor.neighborIndices).Boxed().Collect(Collectors.ToSet()).Contains(marginalizeTo))
{
return;
}
int indexOfVariable = -1;
for (int i = 0; i < factor.neighborIndices.Length; i++)
{
if (factor.neighborIndices[i] == marginalizeTo)
{
indexOfVariable = i;
break;
}
}
Assume.AssumeTrue(indexOfVariable > -1);
double[] gold = new double[factor.GetDimensions()[indexOfVariable]];
for (int i_1 = 0; i_1 < gold.Length; i_1++)
{
gold[i_1] = double.NegativeInfinity;
}
foreach (int[] assignment in factor)
{
gold[assignment[indexOfVariable]] = Math.Max(gold[assignment[indexOfVariable]], factor.GetAssignmentValue(assignment));
}
Normalize(gold);
Assert.AssertArrayEquals(factor.GetMaxedMarginals()[indexOfVariable], 1.0e-5, gold);
}
public virtual void TestSumOut(TableFactor factor, int marginalize)
{
if (!Arrays.Stream(factor.neighborIndices).Boxed().Collect(Collectors.ToSet()).Contains(marginalize))
{
return;
}
if (factor.neighborIndices.Length <= 1)
{
return;
}
TableFactor summedOut = factor.SumOut((int)marginalize);
NUnit.Framework.Assert.AreEqual(factor.neighborIndices.Length - 1, summedOut.neighborIndices.Length);
NUnit.Framework.Assert.IsTrue(!Arrays.Stream(summedOut.neighborIndices).Boxed().Collect(Collectors.ToSet()).Contains(marginalize));
IDictionary<IList<int>, IList<int[]>> subsetToSuperset = SubsetToSupersetAssignments((TableFactor)factor, summedOut);
foreach (IList<int> subsetAssignmentList in subsetToSuperset.Keys)
{
double sum = 0.0;
foreach (int[] supersetAssignment in subsetToSuperset[subsetAssignmentList])
{
sum += factor.GetAssignmentValue(supersetAssignment);
}
int[] subsetAssignment = new int[subsetAssignmentList.Count];
for (int i = 0; i < subsetAssignment.Length; i++)
{
subsetAssignment[i] = subsetAssignmentList[i];
}
NUnit.Framework.Assert.AreEqual(summedOut.GetAssignmentValue(subsetAssignment), 1.0e-5, sum);
}
}
public virtual void TestObserve(TableFactor factor, int observe, int value)
{
if (!Arrays.Stream(factor.neighborIndices).Boxed().Collect(Collectors.ToSet()).Contains(observe))
{
return;
}
if (factor.neighborIndices.Length == 1)
{
return;
}
TableFactor observedOut = factor.Observe((int)observe, (int)value);
int observeIndex = -1;
for (int i = 0; i < factor.neighborIndices.Length; i++)
{
if (factor.neighborIndices[i] == observe)
{
observeIndex = i;
}
}
foreach (int[] assignment in factor)
{
if (assignment[observeIndex] == value)
{
NUnit.Framework.Assert.AreEqual(observedOut.GetAssignmentValue(SubsetAssignment(assignment, (TableFactor)factor, observedOut)), 1.0e-7, factor.GetAssignmentValue(assignment));
}
}
}
public virtual void TestConstructWithObservations(TableFactorTest.PartiallyObservedConstructorData data, ConcatVector weights)
{
int[] obsArray = new int[9];
for (int i = 0; i < obsArray.Length; i++)
{
obsArray[i] = -1;
}
for (int i_1 = 0; i_1 < data.observations.Length; i_1++)
{
obsArray[data.factor.neigborIndices[i_1]] = data.observations[i_1];
}
TableFactor normalObservations = new TableFactor(weights, data.factor);
for (int i_2 = 0; i_2 < obsArray.Length; i_2++)
{
if (obsArray[i_2] != -1)
{
normalObservations = normalObservations.Observe(i_2, obsArray[i_2]);
}
}
TableFactor constructedObservations = new TableFactor(weights, data.factor, data.observations);
Assert.AssertArrayEquals(normalObservations.neighborIndices, constructedObservations.neighborIndices);
foreach (int[] assn in normalObservations)
{
NUnit.Framework.Assert.AreEqual(constructedObservations.GetAssignmentValue(assn), 1.0e-9, normalObservations.GetAssignmentValue(assn));
}
}
public virtual void TestMaxOut(TableFactor factor, int marginalize)
{
if (!Arrays.Stream(factor.neighborIndices).Boxed().Collect(Collectors.ToSet()).Contains(marginalize))
{
return;
}
if (factor.neighborIndices.Length <= 1)
{
return;
}
TableFactor maxedOut = factor.MaxOut((int)marginalize);
NUnit.Framework.Assert.AreEqual(factor.neighborIndices.Length - 1, maxedOut.neighborIndices.Length);
NUnit.Framework.Assert.IsTrue(!Arrays.Stream(maxedOut.neighborIndices).Boxed().Collect(Collectors.ToSet()).Contains(marginalize));
foreach (int[] assignment in factor)
{
NUnit.Framework.Assert.IsTrue(factor.GetAssignmentValue(assignment) >= double.NegativeInfinity);
NUnit.Framework.Assert.IsTrue(factor.GetAssignmentValue(assignment) <= maxedOut.GetAssignmentValue(SubsetAssignment(assignment, (TableFactor)factor, maxedOut)));
}
IDictionary<IList<int>, IList<int[]>> subsetToSuperset = SubsetToSupersetAssignments((TableFactor)factor, maxedOut);
foreach (IList<int> subsetAssignmentList in subsetToSuperset.Keys)
{
double max = double.NegativeInfinity;
foreach (int[] supersetAssignment in subsetToSuperset[subsetAssignmentList])
{
max = Math.Max(max, factor.GetAssignmentValue(supersetAssignment));
}
int[] subsetAssignment = new int[subsetAssignmentList.Count];
for (int i = 0; i < subsetAssignment.Length; i++)
{
subsetAssignment[i] = subsetAssignmentList[i];
}
NUnit.Framework.Assert.AreEqual(maxedOut.GetAssignmentValue(subsetAssignment), 1.0e-5, max);
}
}
/// <summary>This is a key step in message passing.</summary>
/// <remarks>
/// This is a key step in message passing. When we are calculating a message, we want to marginalize out all variables
/// not relevant to the recipient of the message. This function does that.
/// </remarks>
/// <param name="message">the message to marginalize</param>
/// <param name="relevant">the variables that are relevant</param>
/// <param name="marginalize">whether to use sum of max marginalization, for marginal or MAP inference</param>
/// <returns>the marginalized message</returns>
private static TableFactor MarginalizeMessage(TableFactor message, int[] relevant, CliqueTree.MarginalizationMethod marginalize)
{
TableFactor result = message;
foreach (int i in message.neighborIndices)
{
bool contains = false;
foreach (int j in relevant)
{
if (i == j)
{
contains = true;
break;
}
}
if (!contains)
{
switch (marginalize)
{
case CliqueTree.MarginalizationMethod.Sum:
{
result = result.SumOut(i);
break;
}
case CliqueTree.MarginalizationMethod.Max:
{
result = result.MaxOut(i);
break;
}
}
}
}
return(result);
}
public virtual void TestValueSum(TableFactor factor)
{
double sum = 0.0;
foreach (int[] assignment in factor)
{
sum += factor.GetAssignmentValue(assignment);
}
NUnit.Framework.Assert.AreEqual(factor.ValueSum(), 1.0e-5, sum);
}
/// <summary>Just a quick inline to check if two factors have overlapping domains.</summary>
/// <remarks>
/// Just a quick inline to check if two factors have overlapping domains. Since factor neighbor sets are super small,
/// this n^2 algorithm is fine.
/// </remarks>
/// <param name="f1">first factor to compare</param>
/// <param name="f2">second factor to compare</param>
/// <returns>whether their domains overlap</returns>
private static bool DomainsOverlap(TableFactor f1, TableFactor f2)
{
foreach (int n1 in f1.neighborIndices)
{
foreach (int n2 in f2.neighborIndices)
{
if (n1 == n2)
{
return(true);
}
}
}
return(false);
}
/// <summary>Convenience function to construct a subset to superset assignment map.</summary>
/// <remarks>
/// Convenience function to construct a subset to superset assignment map. Each subset assignment will be mapping
/// to a large number of superset assignments.
/// </remarks>
/// <param name="superset">the superset factor to map to</param>
/// <param name="subset">the subset factor to map from</param>
/// <returns>a map from subset assignment to list of superset assignment</returns>
private IDictionary<IList<int>, IList<int[]>> SubsetToSupersetAssignments(TableFactor superset, TableFactor subset)
{
IDictionary<IList<int>, IList<int[]>> subsetToSupersets = new Dictionary<IList<int>, IList<int[]>>();
foreach (int[] assignment in subset)
{
IList<int> subsetAssignmentList = Arrays.Stream(assignment).Boxed().Collect(Collectors.ToList());
IList<int[]> supersetAssignments = new List<int[]>();
foreach (int[] supersetAssignment in superset)
{
if (Arrays.Equals(assignment, SubsetAssignment(supersetAssignment, superset, subset)))
{
supersetAssignments.Add(supersetAssignment);
}
}
subsetToSupersets[subsetAssignmentList] = supersetAssignments;
}
return subsetToSupersets;
}
/// <summary>Takes a full assignment from a superset factor, and figures out how to map it into a subset factor.</summary>
/// <remarks>
/// Takes a full assignment from a superset factor, and figures out how to map it into a subset factor. This is very
/// useful for testing that functional properties are not violated across both product and marginalization steps.
/// </remarks>
/// <param name="supersetAssignment">the assignment in the superset factor</param>
/// <param name="superset">the superset factor, containing the variables from the subset</param>
/// <param name="subset">the subset factor, containing some of the variables found in the superset</param>
/// <returns>an assignment into the subset factor</returns>
private int[] SubsetAssignment(int[] supersetAssignment, TableFactor superset, TableFactor subset)
{
int[] subsetAssignment = new int[subset.neighborIndices.Length];
for (int i = 0; i < subset.neighborIndices.Length; i++)
{
int var = subset.neighborIndices[i];
subsetAssignment[i] = -1;
for (int j = 0; j < superset.neighborIndices.Length; j++)
{
if (superset.neighborIndices[j] == var)
{
subsetAssignment[i] = supersetAssignment[j];
break;
}
}
System.Diagnostics.Debug.Assert((subsetAssignment[i] != -1));
}
return subsetAssignment;
}
public virtual void TestMultiply(TableFactor factor1, TableFactor factor2)
{
TableFactor result = factor1.Multiply((TableFactor)factor2);
foreach (int[] assignment in result)
{
double factor1Value = factor1.GetAssignmentValue(SubsetAssignment(assignment, result, (TableFactor)factor1));
double factor2Value = factor2.GetAssignmentValue(SubsetAssignment(assignment, result, (TableFactor)factor2));
NUnit.Framework.Assert.AreEqual(result.GetAssignmentValue(assignment), 1.0e-5, factor1Value * factor2Value);
}
// Check for no duplication
for (int i = 0; i < result.neighborIndices.Length; i++)
{
for (int j = 0; j < result.neighborIndices.Length; j++)
{
if (i == j)
{
continue;
}
Assert.AssertNotEquals(result.neighborIndices[i], result.neighborIndices[j]);
}
}
}
public virtual void CheckMAPAgainstBruteForce(GraphicalModel model, ConcatVector weights, CliqueTree inference)
{
int[] map = inference.CalculateMAP();
ICollection <TableFactor> tableFactors = model.factors.Stream().Map(null).Collect(Collectors.ToSet());
// this is the super slow but obviously correct way to get global marginals
TableFactor bruteForce = null;
foreach (TableFactor factor in tableFactors)
{
if (bruteForce == null)
{
bruteForce = factor;
}
else
{
bruteForce = bruteForce.Multiply(factor);
}
}
System.Diagnostics.Debug.Assert((bruteForce != null));
// observe out all variables that have been registered
TableFactor observed = bruteForce;
foreach (int n in bruteForce.neighborIndices)
{
if (model.GetVariableMetaDataByReference(n).Contains(CliqueTree.VariableObservedValue))
{
int value = System.Convert.ToInt32(model.GetVariableMetaDataByReference(n)[CliqueTree.VariableObservedValue]);
if (observed.neighborIndices.Length > 1)
{
observed = observed.Observe(n, value);
}
else
{
// If we've observed everything, then just quit
return;
}
}
}
bruteForce = observed;
int largestVariableNum = 0;
foreach (GraphicalModel.Factor f in model.factors)
{
foreach (int i in f.neigborIndices)
{
if (i > largestVariableNum)
{
largestVariableNum = i;
}
}
}
// this is presented in true order, where 0 corresponds to var 0
int[] mapValueAssignment = new int[largestVariableNum + 1];
// this is kept in the order that the factor presents to us
int[] highestValueAssignment = new int[bruteForce.neighborIndices.Length];
foreach (int[] assignment in bruteForce)
{
if (bruteForce.GetAssignmentValue(assignment) > bruteForce.GetAssignmentValue(highestValueAssignment))
{
highestValueAssignment = assignment;
for (int i = 0; i < assignment.Length; i++)
{
mapValueAssignment[bruteForce.neighborIndices[i]] = assignment[i];
}
}
}
int[] forcedAssignments = new int[largestVariableNum + 1];
for (int i_1 = 0; i_1 < mapValueAssignment.Length; i_1++)
{
if (model.GetVariableMetaDataByReference(i_1).Contains(CliqueTree.VariableObservedValue))
{
mapValueAssignment[i_1] = System.Convert.ToInt32(model.GetVariableMetaDataByReference(i_1)[CliqueTree.VariableObservedValue]);
forcedAssignments[i_1] = mapValueAssignment[i_1];
}
}
if (!Arrays.Equals(mapValueAssignment, map))
{
System.Console.Error.WriteLine("---");
System.Console.Error.WriteLine("Relevant variables: " + Arrays.ToString(bruteForce.neighborIndices));
System.Console.Error.WriteLine("Var Sizes: " + Arrays.ToString(bruteForce.GetDimensions()));
System.Console.Error.WriteLine("MAP: " + Arrays.ToString(map));
System.Console.Error.WriteLine("Brute force map: " + Arrays.ToString(mapValueAssignment));
System.Console.Error.WriteLine("Forced assignments: " + Arrays.ToString(forcedAssignments));
}
foreach (int i_2 in bruteForce.neighborIndices)
{
// Only check defined variables
NUnit.Framework.Assert.AreEqual(mapValueAssignment[i_2], map[i_2]);
}
}
private void CheckMarginalsAgainstBruteForce(GraphicalModel model, ConcatVector weights, CliqueTree inference)
{
CliqueTree.MarginalResult result = inference.CalculateMarginals();
double[][] marginals = result.marginals;
ICollection <TableFactor> tableFactors = model.factors.Stream().Map(null).Collect(Collectors.ToSet());
System.Diagnostics.Debug.Assert((tableFactors.Count == model.factors.Count));
// this is the super slow but obviously correct way to get global marginals
TableFactor bruteForce = null;
foreach (TableFactor factor in tableFactors)
{
if (bruteForce == null)
{
bruteForce = factor;
}
else
{
bruteForce = bruteForce.Multiply(factor);
}
}
if (bruteForce != null)
{
// observe out all variables that have been registered
TableFactor observed = bruteForce;
for (int i = 0; i < bruteForce.neighborIndices.Length; i++)
{
int n = bruteForce.neighborIndices[i];
if (model.GetVariableMetaDataByReference(n).Contains(CliqueTree.VariableObservedValue))
{
int value = System.Convert.ToInt32(model.GetVariableMetaDataByReference(n)[CliqueTree.VariableObservedValue]);
// Check that the marginals reflect the observation
for (int j = 0; j < marginals[n].Length; j++)
{
NUnit.Framework.Assert.AreEqual(marginals[n][j], 1.0e-9, j == value ? 1.0 : 0.0);
}
if (observed.neighborIndices.Length > 1)
{
observed = observed.Observe(n, value);
}
else
{
// If we've observed everything, then just quit
return;
}
}
}
bruteForce = observed;
// Spot check each of the marginals in the brute force calculation
double[][] bruteMarginals = bruteForce.GetSummedMarginals();
int index = 0;
foreach (int i_1 in bruteForce.neighborIndices)
{
bool isEqual = true;
double[] brute = bruteMarginals[index];
index++;
System.Diagnostics.Debug.Assert((brute != null));
System.Diagnostics.Debug.Assert((marginals[i_1] != null));
for (int j = 0; j < brute.Length; j++)
{
if (double.IsNaN(brute[j]))
{
isEqual = false;
break;
}
if (Math.Abs(brute[j] - marginals[i_1][j]) > 3.0e-2)
{
isEqual = false;
break;
}
}
if (!isEqual)
{
System.Console.Error.WriteLine("Arrays not equal! Variable " + i_1);
System.Console.Error.WriteLine("\tGold: " + Arrays.ToString(brute));
System.Console.Error.WriteLine("\tResult: " + Arrays.ToString(marginals[i_1]));
}
Assert.AssertArrayEquals(marginals[i_1], 3.0e-2, brute);
}
// Spot check the partition function
double goldPartitionFunction = bruteForce.ValueSum();
// Correct to within 3%
NUnit.Framework.Assert.AreEqual(result.partitionFunction, goldPartitionFunction * 3.0e-2, goldPartitionFunction);
// Check the joint marginals
foreach (GraphicalModel.Factor f in model.factors)
{
NUnit.Framework.Assert.IsTrue(result.jointMarginals.Contains(f));
TableFactor bruteForceJointMarginal = bruteForce;
foreach (int n in bruteForce.neighborIndices)
{
foreach (int i_2 in f.neigborIndices)
{
if (i_2 == n)
{
goto outer_continue;
}
}
if (bruteForceJointMarginal.neighborIndices.Length > 1)
{
bruteForceJointMarginal = bruteForceJointMarginal.SumOut(n);
}
else
{
int[] fixedAssignment = new int[f.neigborIndices.Length];
for (int i_3 = 0; i_3 < fixedAssignment.Length; i_3++)
{
fixedAssignment[i_3] = System.Convert.ToInt32(model.GetVariableMetaDataByReference(f.neigborIndices[i_3])[CliqueTree.VariableObservedValue]);
}
foreach (int[] assn in result.jointMarginals[f])
{
if (Arrays.Equals(assn, fixedAssignment))
{
NUnit.Framework.Assert.AreEqual(result.jointMarginals[f].GetAssignmentValue(assn), 1.0e-7, 1.0);
}
else
{
if (result.jointMarginals[f].GetAssignmentValue(assn) != 0)
{
TableFactor j = result.jointMarginals[f];
foreach (int[] assignment in j)
{
System.Console.Error.WriteLine(Arrays.ToString(assignment) + ": " + j.GetAssignmentValue(assignment));
}
}
NUnit.Framework.Assert.AreEqual(result.jointMarginals[f].GetAssignmentValue(assn), 1.0e-7, 0.0);
}
}
goto marginals_continue;
}
}
outer_break :;
// Find the correspondence between the brute force joint marginal, which may be missing variables
// because they were observed out of the table, and the output joint marginals, which are always an exact
// match for the original factor
int[] backPointers = new int[f.neigborIndices.Length];
int[] observedValue = new int[f.neigborIndices.Length];
for (int i_4 = 0; i_4 < backPointers.Length; i_4++)
{
if (model.GetVariableMetaDataByReference(f.neigborIndices[i_4]).Contains(CliqueTree.VariableObservedValue))
{
observedValue[i_4] = System.Convert.ToInt32(model.GetVariableMetaDataByReference(f.neigborIndices[i_4])[CliqueTree.VariableObservedValue]);
backPointers[i_4] = -1;
}
else
{
observedValue[i_4] = -1;
backPointers[i_4] = -1;
for (int j = 0; j < bruteForceJointMarginal.neighborIndices.Length; j++)
{
if (bruteForceJointMarginal.neighborIndices[j] == f.neigborIndices[i_4])
{
backPointers[i_4] = j;
}
}
System.Diagnostics.Debug.Assert((backPointers[i_4] != -1));
}
}
double sum = bruteForceJointMarginal.ValueSum();
if (sum == 0.0)
{
sum = 1;
}
foreach (int[] assignment_1 in result.jointMarginals[f])
{
int[] bruteForceMarginalAssignment = new int[bruteForceJointMarginal.neighborIndices.Length];
for (int i_2 = 0; i_2 < assignment_1.Length; i_2++)
{
if (backPointers[i_2] != -1)
{
bruteForceMarginalAssignment[backPointers[i_2]] = assignment_1[i_2];
}
else
{
// Make sure all assignments that don't square with observations get 0 weight
System.Diagnostics.Debug.Assert((observedValue[i_2] != -1));
if (assignment_1[i_2] != observedValue[i_2])
{
if (result.jointMarginals[f].GetAssignmentValue(assignment_1) != 0)
{
System.Console.Error.WriteLine("Joint marginals: " + Arrays.ToString(result.jointMarginals[f].neighborIndices));
System.Console.Error.WriteLine("Assignment: " + Arrays.ToString(assignment_1));
System.Console.Error.WriteLine("Observed Value: " + Arrays.ToString(observedValue));
foreach (int[] assn in result.jointMarginals[f])
{
System.Console.Error.WriteLine("\t" + Arrays.ToString(assn) + ":" + result.jointMarginals[f].GetAssignmentValue(assn));
}
}
NUnit.Framework.Assert.AreEqual(result.jointMarginals[f].GetAssignmentValue(assignment_1), 1.0e-7, 0.0);
goto outer_continue;
}
}
}
NUnit.Framework.Assert.AreEqual(result.jointMarginals[f].GetAssignmentValue(assignment_1), 1.0e-3, bruteForceJointMarginal.GetAssignmentValue(bruteForceMarginalAssignment) / sum);
}
outer_break :;
}
marginals_break :;
}
else
{
foreach (double[] marginal in marginals)
{
foreach (double d in marginal)
{
NUnit.Framework.Assert.AreEqual(d, 3.0e-2, 1.0 / marginal.Length);
}
}
}
}
// OPTIMIZATION:
// cache the last list of factors, and the last set of messages passed, in case we can recycle some
/// <summary>Does tree shaped message passing.</summary>
/// <remarks>
/// Does tree shaped message passing. The algorithm calls for first passing down to the leaves, then passing back up
/// to the root.
/// </remarks>
/// <param name="marginalize">the method for marginalization, controls MAP or marginals</param>
/// <returns>the marginal messages</returns>
private CliqueTree.MarginalResult MessagePassing(CliqueTree.MarginalizationMethod marginalize, bool includeJointMarginalsAndPartition)
{
// Using the behavior of brute force factor multiplication as ground truth, the desired
// outcome of marginal calculation with an impossible factor is a uniform probability dist.,
// since we have a resulting factor of all 0s. That is of course assuming that normalizing
// all 0s gives you uniform, which is not real math, but that's a useful tolerance to include, so we do.
bool impossibleObservationMade = false;
// Message passing will look at fully observed cliques as non-entities, but their
// log-likelihood (the log-likelihood of the single observed value) is still relevant for the
// partition function.
double partitionFunction = 1.0;
if (includeJointMarginalsAndPartition)
{
foreach (GraphicalModel.Factor f in model.factors)
{
foreach (int n in f.neigborIndices)
{
if (!model.GetVariableMetaDataByReference(n).Contains(VariableObservedValue))
{
goto outer_continue;
}
}
int[] assignment = new int[f.neigborIndices.Length];
for (int i = 0; i < f.neigborIndices.Length; i++)
{
assignment[i] = System.Convert.ToInt32(model.GetVariableMetaDataByReference(f.neigborIndices[i])[VariableObservedValue]);
}
double assignmentValue = f.featuresTable.GetAssignmentValue(assignment).Get().DotProduct(weights);
if (double.IsInfinite(assignmentValue))
{
impossibleObservationMade = true;
}
else
{
partitionFunction *= Math.Exp(assignmentValue);
}
}
outer_break :;
}
// Create the cliques by multiplying out table factors
// TODO:OPT This could be made more efficient by observing first, then dot product
IList <TableFactor> cliquesList = new List <TableFactor>();
IDictionary <int, GraphicalModel.Factor> cliqueToFactor = new Dictionary <int, GraphicalModel.Factor>();
int numFactorsCached = 0;
foreach (GraphicalModel.Factor f_1 in model.factors)
{
bool allObserved = true;
int maxVar = 0;
foreach (int n in f_1.neigborIndices)
{
if (!model.GetVariableMetaDataByReference(n).Contains(VariableObservedValue))
{
allObserved = false;
}
if (n > maxVar)
{
maxVar = n;
}
}
if (allObserved)
{
continue;
}
TableFactor clique = null;
// Retrieve cache if exists and none of the observations have changed
if (cachedFactors.Contains(f_1))
{
CliqueTree.CachedFactorWithObservations obs = cachedFactors[f_1];
bool allConsistent = true;
for (int i = 0; i < f_1.neigborIndices.Length; i++)
{
int n_1 = f_1.neigborIndices[i];
if (model.GetVariableMetaDataByReference(n_1).Contains(VariableObservedValue) && (obs.observations[i] == -1 || System.Convert.ToInt32(model.GetVariableMetaDataByReference(n_1)[VariableObservedValue]) != obs.observations[i]))
{
allConsistent = false;
break;
}
// NOTE: This disqualifies lots of stuff for some reason...
if (!model.GetVariableMetaDataByReference(n_1).Contains(VariableObservedValue) && (obs.observations[i] != -1))
{
allConsistent = false;
break;
}
}
if (allConsistent)
{
clique = obs.cachedFactor;
numFactorsCached++;
if (obs.impossibleObservation)
{
impossibleObservationMade = true;
}
}
}
// Otherwise make a new cache
if (clique == null)
{
int[] observations = new int[f_1.neigborIndices.Length];
for (int i = 0; i < observations.Length; i++)
{
IDictionary <string, string> metadata = model.GetVariableMetaDataByReference(f_1.neigborIndices[i]);
if (metadata.Contains(VariableObservedValue))
{
int value = System.Convert.ToInt32(metadata[VariableObservedValue]);
observations[i] = value;
}
else
{
observations[i] = -1;
}
}
clique = new TableFactor(weights, f_1, observations);
CliqueTree.CachedFactorWithObservations cache = new CliqueTree.CachedFactorWithObservations();
cache.cachedFactor = clique;
cache.observations = observations;
// Check for an impossible observation
bool nonZeroValue = false;
foreach (int[] assignment in clique)
{
if (clique.GetAssignmentValue(assignment) > 0)
{
nonZeroValue = true;
break;
}
}
if (!nonZeroValue)
{
impossibleObservationMade = true;
cache.impossibleObservation = true;
}
cachedFactors[f_1] = cache;
}
cliqueToFactor[cliquesList.Count] = f_1;
cliquesList.Add(clique);
}
TableFactor[] cliques = Sharpen.Collections.ToArray(cliquesList, new TableFactor[cliquesList.Count]);
// If we made any impossible observations, we can just return a uniform distribution for all the variables that
// weren't observed, since that's the semantically correct thing to do (our 'probability' is broken at this
// point).
if (impossibleObservationMade)
{
int maxVar = 0;
foreach (TableFactor c in cliques)
{
foreach (int i in c.neighborIndices)
{
if (i > maxVar)
{
maxVar = i;
}
}
}
double[][] result = new double[maxVar + 1][];
foreach (TableFactor c_1 in cliques)
{
for (int i = 0; i < c_1.neighborIndices.Length; i++)
{
result[c_1.neighborIndices[i]] = new double[c_1.GetDimensions()[i]];
for (int j = 0; j < result[c_1.neighborIndices[i]].Length; j++)
{
result[c_1.neighborIndices[i]][j] = 1.0 / result[c_1.neighborIndices[i]].Length;
}
}
}
// Create a bunch of uniform joint marginals, constrained by observations, and fill up the joint marginals
// with them
IDictionary <GraphicalModel.Factor, TableFactor> jointMarginals = new IdentityHashMap <GraphicalModel.Factor, TableFactor>();
if (includeJointMarginalsAndPartition)
{
foreach (GraphicalModel.Factor f in model.factors)
{
TableFactor uniformZero = new TableFactor(f_1.neigborIndices, f_1.featuresTable.GetDimensions());
foreach (int[] assignment in uniformZero)
{
uniformZero.SetAssignmentValue(assignment, 0.0);
}
jointMarginals[f_1] = uniformZero;
}
}
return(new CliqueTree.MarginalResult(result, 1.0, jointMarginals));
}
// Find the largest contained variable, so that we can size arrays appropriately
int maxVar_1 = 0;
foreach (GraphicalModel.Factor fac in model.factors)
{
foreach (int i in fac.neigborIndices)
{
if (i > maxVar_1)
{
maxVar_1 = i;
}
}
}
// Indexed by (start-clique, end-clique), this array will remain mostly null in most graphs
TableFactor[][] messages = new TableFactor[cliques.Length][];
// OPTIMIZATION:
// check if we've only added one factor since the last time we ran marginal inference. If that's the case, we
// can use the new factor as the root, all the messages passed in from the leaves will not have changed. That
// means we can cut message passing computation in half.
bool[][] backwardPassedMessages = new bool[cliques.Length][];
int forceRootForCachedMessagePassing = -1;
int[] cachedCliquesBackPointers = null;
if (CacheMessages && (numFactorsCached == cliques.Length - 1) && (numFactorsCached > 0))
{
cachedCliquesBackPointers = new int[cliques.Length];
// Sometimes we'll have cached versions of the factors, but they're from inference steps a long time ago, so we
// don't get consistent backpointers to our cache of factors. This is a flag to indicate if this happens.
bool backPointersConsistent = true;
// Calculate the correspondence between the old cliques list and the new cliques list
for (int i = 0; i < cliques.Length; i++)
{
cachedCliquesBackPointers[i] = -1;
for (int j = 0; j < cachedCliqueList.Length; j++)
{
if (cliques[i] == cachedCliqueList[j])
{
cachedCliquesBackPointers[i] = j;
break;
}
}
if (cachedCliquesBackPointers[i] == -1)
{
if (forceRootForCachedMessagePassing != -1)
{
backPointersConsistent = false;
break;
}
forceRootForCachedMessagePassing = i;
}
}
if (!backPointersConsistent)
{
forceRootForCachedMessagePassing = -1;
}
}
// Create the data structures to hold the tree pattern
bool[] visited = new bool[cliques.Length];
int numVisited = 0;
int[] visitedOrder = new int[cliques.Length];
int[] parent = new int[cliques.Length];
for (int i_1 = 0; i_1 < parent.Length; i_1++)
{
parent[i_1] = -1;
}
// Figure out which cliques are connected to which trees. This is important for calculating the partition
// function later, since each tree will converge to its own partition function by multiplication, and we will
// need to multiply the partition function of each of the trees to get the global one.
int[] trees = new int[cliques.Length];
// Forward pass, record a BFS forest pattern that we can use for message passing
int treeIndex = -1;
bool[] seenVariable = new bool[maxVar_1 + 1];
while (numVisited < cliques.Length)
{
treeIndex++;
// Pick the largest connected graph remaining as the root for message passing
int root = -1;
// OPTIMIZATION: if there's a forced root for message passing (a node that we just added) then make it the
// root
if (CacheMessages && forceRootForCachedMessagePassing != -1 && !visited[forceRootForCachedMessagePassing])
{
root = forceRootForCachedMessagePassing;
}
else
{
for (int i = 0; i_1 < cliques.Length; i_1++)
{
if (!visited[i_1] && (root == -1 || cliques[i_1].neighborIndices.Length > cliques[root].neighborIndices.Length))
{
root = i_1;
}
}
}
System.Diagnostics.Debug.Assert((root != -1));
IQueue <int> toVisit = new ArrayDeque <int>();
toVisit.Add(root);
bool[] toVisitArray = new bool[cliques.Length];
toVisitArray[root] = true;
while (toVisit.Count > 0)
{
int cursor = toVisit.Poll();
// toVisitArray[cursor] = false;
trees[cursor] = treeIndex;
if (visited[cursor])
{
log.Info("Visited contains: " + cursor);
log.Info("Visited: " + Arrays.ToString(visited));
log.Info("To visit: " + toVisit);
}
System.Diagnostics.Debug.Assert((!visited[cursor]));
visited[cursor] = true;
visitedOrder[numVisited] = cursor;
foreach (int i in cliques[cursor].neighborIndices)
{
seenVariable[i_1] = true;
}
numVisited++;
for (int i_2 = 0; i_2 < cliques.Length; i_2++)
{
if (i_2 == cursor)
{
continue;
}
if (i_2 == parent[cursor])
{
continue;
}
if (DomainsOverlap(cliques[cursor], cliques[i_2]))
{
// Make sure that for every variable that we've already seen somewhere in the graph, if it's
// in the child, it's in the parent. Otherwise we'll break the property of continuous
// transmission of information about variables through messages.
foreach (int child in cliques[i_2].neighborIndices)
{
if (seenVariable[child])
{
foreach (int j in cliques[cursor].neighborIndices)
{
if (j == child)
{
goto childNeighborLoop_continue;
}
}
// If we get here it means that this clique is not good as a child, since we can't pass
// it all the information it needs from other elements of the tree
goto childLoop_continue;
}
}
childNeighborLoop_break :;
if (parent[i_2] == -1 && !visited[i_2])
{
if (!toVisitArray[i_2])
{
toVisit.Add(i_2);
toVisitArray[i_2] = true;
foreach (int j in cliques[i_2].neighborIndices)
{
seenVariable[j] = true;
}
}
parent[i_2] = cursor;
}
}
childLoop_continue :;
}
childLoop_break :;
}
// No cycles in the tree
System.Diagnostics.Debug.Assert((parent[root] == -1));
}
System.Diagnostics.Debug.Assert((numVisited == cliques.Length));
// Backward pass, run the visited list in reverse
for (int i_3 = numVisited - 1; i_3 >= 0; i_3--)
{
int cursor = visitedOrder[i_3];
if (parent[cursor] == -1)
{
continue;
}
backwardPassedMessages[cursor][parent[cursor]] = true;
// OPTIMIZATION:
// if these conditions are met we can avoid calculating the message, and instead retrieve from the cache,
// since they should be the same
if (CacheMessages && forceRootForCachedMessagePassing != -1 && cachedCliquesBackPointers[cursor] != -1 && cachedCliquesBackPointers[parent[cursor]] != -1 && cachedMessages[cachedCliquesBackPointers[cursor]][cachedCliquesBackPointers[parent[cursor
]]] != null && cachedBackwardPassedMessages[cachedCliquesBackPointers[cursor]][cachedCliquesBackPointers[parent[cursor]]])
{
messages[cursor][parent[cursor]] = cachedMessages[cachedCliquesBackPointers[cursor]][cachedCliquesBackPointers[parent[cursor]]];
}
else
{
// Calculate the message to the clique's parent, given all incoming messages so far
TableFactor message = cliques[cursor];
for (int k = 0; k < cliques.Length; k++)
{
if (k == parent[cursor])
{
continue;
}
if (messages[k][cursor] != null)
{
message = message.Multiply(messages[k][cursor]);
}
}
messages[cursor][parent[cursor]] = MarginalizeMessage(message, cliques[parent[cursor]].neighborIndices, marginalize);
// Invalidate any cached outgoing messages
if (CacheMessages && forceRootForCachedMessagePassing != -1 && cachedCliquesBackPointers[parent[cursor]] != -1)
{
for (int k_1 = 0; k_1 < cachedCliqueList.Length; k_1++)
{
cachedMessages[cachedCliquesBackPointers[parent[cursor]]][k_1] = null;
}
}
}
}
// Forward pass, run the visited list forward
for (int i_4 = 0; i_4 < numVisited; i_4++)
{
int cursor = visitedOrder[i_4];
for (int j = 0; j < cliques.Length; j++)
{
if (parent[j] != cursor)
{
continue;
}
TableFactor message = cliques[cursor];
for (int k = 0; k < cliques.Length; k++)
{
if (k == j)
{
continue;
}
if (messages[k][cursor] != null)
{
message = message.Multiply(messages[k][cursor]);
}
}
messages[cursor][j] = MarginalizeMessage(message, cliques[j].neighborIndices, marginalize);
}
}
// OPTIMIZATION:
// cache the messages, and the current list of cliques
cachedCliqueList = cliques;
cachedMessages = messages;
cachedBackwardPassedMessages = backwardPassedMessages;
// Calculate final marginals for each variable
double[][] marginals = new double[maxVar_1 + 1][];
// Include observed variables as deterministic
foreach (GraphicalModel.Factor fac_1 in model.factors)
{
for (int i = 0; i_4 < fac_1.neigborIndices.Length; i_4++)
{
int n = fac_1.neigborIndices[i_4];
if (model.GetVariableMetaDataByReference(n).Contains(VariableObservedValue))
{
double[] deterministic = new double[fac_1.featuresTable.GetDimensions()[i_4]];
int assignment = System.Convert.ToInt32(model.GetVariableMetaDataByReference(n)[VariableObservedValue]);
if (assignment > deterministic.Length)
{
throw new InvalidOperationException("Variable " + n + ": Can't have as assignment (" + assignment + ") that is out of bounds for dimension size (" + deterministic.Length + ")");
}
deterministic[assignment] = 1.0;
marginals[n] = deterministic;
}
}
}
IDictionary <GraphicalModel.Factor, TableFactor> jointMarginals_1 = new IdentityHashMap <GraphicalModel.Factor, TableFactor>();
if (marginalize == CliqueTree.MarginalizationMethod.Sum && includeJointMarginalsAndPartition)
{
bool[] partitionIncludesTrees = new bool[treeIndex + 1];
double[] treePartitionFunctions = new double[treeIndex + 1];
for (int i = 0; i_4 < cliques.Length; i_4++)
{
TableFactor convergedClique = cliques[i_4];
for (int j = 0; j < cliques.Length; j++)
{
if (i_4 == j)
{
continue;
}
if (messages[j][i_4] == null)
{
continue;
}
convergedClique = convergedClique.Multiply(messages[j][i_4]);
}
// Calculate the partition function when we're calculating marginals
// We need one contribution per tree in our forest graph
if (!partitionIncludesTrees[trees[i_4]])
{
partitionIncludesTrees[trees[i_4]] = true;
treePartitionFunctions[trees[i_4]] = convergedClique.ValueSum();
partitionFunction *= treePartitionFunctions[trees[i_4]];
}
else
{
// This is all just an elaborate assert
// Check that our partition function is the same as the trees we're attached to, or with %.1, for numerical reasons.
// Sometimes the partition function will explode in value, which can make a non-%-based assert worthless here
if (AssertsEnabled() && !TableFactor.UseExpApprox)
{
double valueSum = convergedClique.ValueSum();
if (double.IsFinite(valueSum) && double.IsFinite(treePartitionFunctions[trees[i_4]]))
{
if (Math.Abs(treePartitionFunctions[trees[i_4]] - valueSum) >= 1.0e-3 * treePartitionFunctions[trees[i_4]])
{
log.Info("Different partition functions for tree " + trees[i_4] + ": ");
log.Info("Pre-existing for tree: " + treePartitionFunctions[trees[i_4]]);
log.Info("This clique for tree: " + valueSum);
}
System.Diagnostics.Debug.Assert((Math.Abs(treePartitionFunctions[trees[i_4]] - valueSum) < 1.0e-3 * treePartitionFunctions[trees[i_4]]));
}
}
}
// Calculate the factor this clique corresponds to, and put in an entry for joint marginals
GraphicalModel.Factor f = cliqueToFactor[i_4];
System.Diagnostics.Debug.Assert((f_1 != null));
if (!jointMarginals_1.Contains(f_1))
{
int[] observedAssignments = GetObservedAssignments(f_1);
// Collect back pointers and check if this factor matches the clique we're using
int[] backPointers = new int[observedAssignments.Length];
int cursor = 0;
for (int j_1 = 0; j_1 < observedAssignments.Length; j_1++)
{
if (observedAssignments[j_1] == -1)
{
backPointers[j_1] = cursor;
cursor++;
}
else
{
// This is not strictly necessary but will trigger array OOB exception if things go wrong, so is nice
backPointers[j_1] = -1;
}
}
double sum = convergedClique.ValueSum();
TableFactor jointMarginal = new TableFactor(f_1.neigborIndices, f_1.featuresTable.GetDimensions());
// OPTIMIZATION:
// Rather than use the standard iterator, which creates lots of int[] arrays on the heap, which need to be GC'd,
// we use the fast version that just mutates one array. Since this is read once for us here, this is ideal.
IEnumerator <int[]> fastPassByReferenceIterator = convergedClique.FastPassByReferenceIterator();
int[] assignment = fastPassByReferenceIterator.Current;
while (true)
{
if (backPointers.Length == assignment.Length)
{
jointMarginal.SetAssignmentValue(assignment, convergedClique.GetAssignmentValue(assignment) / sum);
}
else
{
int[] jointAssignment = new int[backPointers.Length];
for (int j_2 = 0; j_2 < jointAssignment.Length; j_2++)
{
if (observedAssignments[j_2] != -1)
{
jointAssignment[j_2] = observedAssignments[j_2];
}
else
{
jointAssignment[j_2] = assignment[backPointers[j_2]];
}
}
jointMarginal.SetAssignmentValue(jointAssignment, convergedClique.GetAssignmentValue(assignment) / sum);
}
// Set the assignment arrays correctly
if (fastPassByReferenceIterator.MoveNext())
{
fastPassByReferenceIterator.Current;
}
else
{
break;
}
}
jointMarginals_1[f_1] = jointMarginal;
}
bool anyNull = false;
for (int j_3 = 0; j_3 < convergedClique.neighborIndices.Length; j_3++)
{
int k = convergedClique.neighborIndices[j_3];
if (marginals[k] == null)
{
anyNull = true;
}
}
if (anyNull)
{
double[][] cliqueMarginals = null;
switch (marginalize)
{
case CliqueTree.MarginalizationMethod.Sum:
{
cliqueMarginals = convergedClique.GetSummedMarginals();
break;
}
case CliqueTree.MarginalizationMethod.Max:
{
cliqueMarginals = convergedClique.GetMaxedMarginals();
break;
}
}
for (int j_1 = 0; j_1 < convergedClique.neighborIndices.Length; j_1++)
{
int k = convergedClique.neighborIndices[j_1];
if (marginals[k] == null)
{
marginals[k] = cliqueMarginals[j_1];
}
}
}
}
}
else
{
// If we don't care about joint marginals, we can be careful about not calculating more cliques than we need to,
// by explicitly sorting by which cliques are most profitable to calculate over. In this way we can avoid, in
// the case of a chain CRF, calculating almost half the joint factors.
// First do a pass where we only calculate all-null neighbors
for (int i = 0; i_4 < cliques.Length; i_4++)
{
bool allNull = true;
foreach (int k in cliques[i_4].neighborIndices)
{
if (marginals[k] != null)
{
allNull = false;
}
}
if (allNull)
{
TableFactor convergedClique = cliques[i_4];
for (int j = 0; j < cliques.Length; j++)
{
if (i_4 == j)
{
continue;
}
if (messages[j][i_4] == null)
{
continue;
}
convergedClique = convergedClique.Multiply(messages[j][i_4]);
}
double[][] cliqueMarginals = null;
switch (marginalize)
{
case CliqueTree.MarginalizationMethod.Sum:
{
cliqueMarginals = convergedClique.GetSummedMarginals();
break;
}
case CliqueTree.MarginalizationMethod.Max:
{
cliqueMarginals = convergedClique.GetMaxedMarginals();
break;
}
}
for (int j_1 = 0; j_1 < convergedClique.neighborIndices.Length; j_1++)
{
int k_1 = convergedClique.neighborIndices[j_1];
if (marginals[k_1] == null)
{
marginals[k_1] = cliqueMarginals[j_1];
}
}
}
}
// Now we calculate any remaining cliques with any non-null variables
for (int i_2 = 0; i_2 < cliques.Length; i_2++)
{
bool anyNull = false;
for (int j = 0; j < cliques[i_2].neighborIndices.Length; j++)
{
int k = cliques[i_2].neighborIndices[j];
if (marginals[k] == null)
{
anyNull = true;
}
}
if (anyNull)
{
TableFactor convergedClique = cliques[i_2];
for (int j_1 = 0; j_1 < cliques.Length; j_1++)
{
if (i_2 == j_1)
{
continue;
}
if (messages[j_1][i_2] == null)
{
continue;
}
convergedClique = convergedClique.Multiply(messages[j_1][i_2]);
}
double[][] cliqueMarginals = null;
switch (marginalize)
{
case CliqueTree.MarginalizationMethod.Sum:
{
cliqueMarginals = convergedClique.GetSummedMarginals();
break;
}
case CliqueTree.MarginalizationMethod.Max:
{
cliqueMarginals = convergedClique.GetMaxedMarginals();
break;
}
}
for (int j_2 = 0; j_2 < convergedClique.neighborIndices.Length; j_2++)
{
int k = convergedClique.neighborIndices[j_2];
if (marginals[k] == null)
{
marginals[k] = cliqueMarginals[j_2];
}
}
}
}
}
// Add any factors to the joint marginal map that were fully observed and so didn't get cliques
if (marginalize == CliqueTree.MarginalizationMethod.Sum && includeJointMarginalsAndPartition)
{
foreach (GraphicalModel.Factor f in model.factors)
{
if (!jointMarginals_1.Contains(f_1))
{
// This implies that every variable in the factor is observed. If that's the case, we need to construct
// a one hot TableFactor representing the deterministic distribution.
TableFactor deterministicJointMarginal = new TableFactor(f_1.neigborIndices, f_1.featuresTable.GetDimensions());
int[] observedAssignment = GetObservedAssignments(f_1);
foreach (int i in observedAssignment)
{
System.Diagnostics.Debug.Assert((i_4 != -1));
}
deterministicJointMarginal.SetAssignmentValue(observedAssignment, 1.0);
jointMarginals_1[f_1] = deterministicJointMarginal;
}
}
}
return(new CliqueTree.MarginalResult(marginals, partitionFunction, jointMarginals_1));
}
