/// <summary>Product two factors, taking the multiplication at the intersections.</summary>
/// <param name="other">the other factor to be multiplied</param>
/// <returns>a factor containing the union of both variable sets</returns>
public virtual Edu.Stanford.Nlp.Loglinear.Inference.TableFactor Multiply(Edu.Stanford.Nlp.Loglinear.Inference.TableFactor other)
{
// Calculate the result domain
IList <int> domain = new List <int>();
IList <int> otherDomain = new List <int>();
IList <int> resultDomain = new List <int>();
foreach (int n in neighborIndices)
{
domain.Add(n);
resultDomain.Add(n);
}
foreach (int n_1 in other.neighborIndices)
{
otherDomain.Add(n_1);
if (!resultDomain.Contains(n_1))
{
resultDomain.Add(n_1);
}
}
// Create result TableFactor
int[] resultNeighborIndices = new int[resultDomain.Count];
int[] resultDimensions = new int[resultNeighborIndices.Length];
for (int i = 0; i < resultDomain.Count; i++)
{
int var = resultDomain[i];
resultNeighborIndices[i] = var;
// assert consistency about variable size, we can't have the same variable with two different sizes
System.Diagnostics.Debug.Assert(((GetVariableSize(var) == 0 && other.GetVariableSize(var) > 0) || (GetVariableSize(var) > 0 && other.GetVariableSize(var) == 0) || (GetVariableSize(var) == other.GetVariableSize(var))));
resultDimensions[i] = Math.Max(GetVariableSize(resultDomain[i]), other.GetVariableSize(resultDomain[i]));
}
Edu.Stanford.Nlp.Loglinear.Inference.TableFactor result = new Edu.Stanford.Nlp.Loglinear.Inference.TableFactor(resultNeighborIndices, resultDimensions);
// OPTIMIZATION:
// If we're a factor of size 2 receiving a message of size 1, then we can optimize that pretty heavily
// We could just use the general algorithm at the end of this set of special cases, but this is the fastest way
if (otherDomain.Count == 1 && (resultDomain.Count == domain.Count) && domain.Count == 2)
{
int msgVar = otherDomain[0];
int msgIndex = resultDomain.IndexOf(msgVar);
if (msgIndex == 0)
{
for (int i_1 = 0; i_1 < resultDimensions[0]; i_1++)
{
double d = other.values[i_1];
int k = i_1 * resultDimensions[1];
for (int j = 0; j < resultDimensions[1]; j++)
{
int index = k + j;
result.values[index] = values[index] + d;
}
}
}
else
{
if (msgIndex == 1)
{
for (int i_1 = 0; i_1 < resultDimensions[0]; i_1++)
{
int k = i_1 * resultDimensions[1];
for (int j = 0; j < resultDimensions[1]; j++)
{
int index = k + j;
result.values[index] = values[index] + other.values[j];
}
}
}
}
}
else
{
// OPTIMIZATION:
// The special case where we're a message of size 1, and the other factor is receiving the message, and of size 2
if (domain.Count == 1 && (resultDomain.Count == otherDomain.Count) && resultDomain.Count == 2)
{
return(other.Multiply(this));
}
else
{
// Otherwise we follow the big comprehensive, slow general purpose algorithm
// Calculate back-pointers from the result domain indices to original indices
int[] mapping = new int[result.neighborIndices.Length];
int[] otherMapping = new int[result.neighborIndices.Length];
for (int i_1 = 0; i_1 < result.neighborIndices.Length; i_1++)
{
mapping[i_1] = domain.IndexOf(result.neighborIndices[i_1]);
otherMapping[i_1] = otherDomain.IndexOf(result.neighborIndices[i_1]);
}
// Do the actual joining operation between the two tables, applying 'join' for each result element.
int[] assignment = new int[neighborIndices.Length];
int[] otherAssignment = new int[other.neighborIndices.Length];
// 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 = result.FastPassByReferenceIterator();
int[] resultAssignment = fastPassByReferenceIterator.Current;
while (true)
{
// Set the assignment arrays correctly
for (int i_2 = 0; i_2 < resultAssignment.Length; i_2++)
{
if (mapping[i_2] != -1)
{
assignment[mapping[i_2]] = resultAssignment[i_2];
}
if (otherMapping[i_2] != -1)
{
otherAssignment[otherMapping[i_2]] = resultAssignment[i_2];
}
}
result.SetAssignmentLogValue(resultAssignment, GetAssignmentLogValue(assignment) + other.GetAssignmentLogValue(otherAssignment));
// This mutates the resultAssignment[] array, rather than creating a new one
if (fastPassByReferenceIterator.MoveNext())
{
fastPassByReferenceIterator.Current;
}
else
{
break;
}
}
}
}
return(result);
}
/// <summary>
/// Marginalizes out a variable by applying an associative join operation for each possible assignment to the
/// marginalized variable.
/// </summary>
/// <param name="variable">the variable (by 'name', not offset into neighborIndices)</param>
/// <param name="startingValue">associativeJoin is basically a foldr over a table, and this is the initialization</param>
/// <param name="curriedFoldr">
/// the associative function to use when applying the join operation, taking first the
/// assignment to the value being marginalized, and then a foldr operation
/// </param>
/// <returns>
/// a new TableFactor that doesn't contain 'variable', where values were gotten through associative
/// marginalization.
/// </returns>
private Edu.Stanford.Nlp.Loglinear.Inference.TableFactor Marginalize(int variable, double startingValue, IBiFunction <int, int[], IBiFunction <double, double, double> > curriedFoldr)
{
// Can't marginalize the last variable
System.Diagnostics.Debug.Assert((GetDimensions().Length > 1));
// Calculate the result domain
IList <int> resultDomain = new List <int>();
foreach (int n in neighborIndices)
{
if (n != variable)
{
resultDomain.Add(n);
}
}
// Create result TableFactor
int[] resultNeighborIndices = new int[resultDomain.Count];
int[] resultDimensions = new int[resultNeighborIndices.Length];
for (int i = 0; i < resultDomain.Count; i++)
{
int var = resultDomain[i];
resultNeighborIndices[i] = var;
resultDimensions[i] = GetVariableSize(var);
}
Edu.Stanford.Nlp.Loglinear.Inference.TableFactor result = new Edu.Stanford.Nlp.Loglinear.Inference.TableFactor(resultNeighborIndices, resultDimensions);
// Calculate forward-pointers from the old domain to new domain
int[] mapping = new int[neighborIndices.Length];
for (int i_1 = 0; i_1 < neighborIndices.Length; i_1++)
{
mapping[i_1] = resultDomain.IndexOf(neighborIndices[i_1]);
}
// Initialize
foreach (int[] assignment in result)
{
result.SetAssignmentLogValue(assignment, startingValue);
}
// Do the actual fold into the result
int[] resultAssignment = new int[result.neighborIndices.Length];
int marginalizedVariableValue = 0;
// 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 = FastPassByReferenceIterator();
int[] assignment_1 = fastPassByReferenceIterator.Current;
while (true)
{
// Set the assignment arrays correctly
for (int i_2 = 0; i_2 < assignment_1.Length; i_2++)
{
if (mapping[i_2] != -1)
{
resultAssignment[mapping[i_2]] = assignment_1[i_2];
}
else
{
marginalizedVariableValue = assignment_1[i_2];
}
}
result.SetAssignmentLogValue(resultAssignment, curriedFoldr.Apply(marginalizedVariableValue, resultAssignment).Apply(result.GetAssignmentLogValue(resultAssignment), GetAssignmentLogValue(assignment_1)));
if (fastPassByReferenceIterator.MoveNext())
{
fastPassByReferenceIterator.Current;
}
else
{
break;
}
}
return(result);
}
/// <summary>Marginalize out a variable by taking a sum.</summary>
/// <param name="variable">the variable to be summed out</param>
/// <returns>a factor with variable removed</returns>
public virtual Edu.Stanford.Nlp.Loglinear.Inference.TableFactor SumOut(int variable)
{
// OPTIMIZATION: This is by far the most common case, for linear chain inference, and is worth making fast
// We can use closed loops, and not bother with using the basic iterator to loop through indices.
// If this special case doesn't trip, we fall back to the standard (but slower) algorithm for the general case
if (GetDimensions().Length == 2)
{
if (neighborIndices[0] == variable)
{
Edu.Stanford.Nlp.Loglinear.Inference.TableFactor marginalized = new Edu.Stanford.Nlp.Loglinear.Inference.TableFactor(new int[] { neighborIndices[1] }, new int[] { GetDimensions()[1] });
for (int i = 0; i < marginalized.values.Length; i++)
{
marginalized.values[i] = 0;
}
// We use the stable log-sum-exp trick here, so first we calculate the max
double[] max = new double[GetDimensions()[1]];
for (int j = 0; j < GetDimensions()[1]; j++)
{
max[j] = double.NegativeInfinity;
}
for (int i_1 = 0; i_1 < GetDimensions()[0]; i_1++)
{
int k = i_1 * GetDimensions()[1];
for (int j_1 = 0; j_1 < GetDimensions()[1]; j_1++)
{
int index = k + j_1;
if (values[index] > max[j_1])
{
max[j_1] = values[index];
}
}
}
// Then we take the sum, minus the max
for (int i_2 = 0; i_2 < GetDimensions()[0]; i_2++)
{
int k = i_2 * GetDimensions()[1];
for (int j_1 = 0; j_1 < GetDimensions()[1]; j_1++)
{
int index = k + j_1;
if (double.IsFinite(max[j_1]))
{
marginalized.values[j_1] += Math.Exp(values[index] - max[j_1]);
}
}
}
// And now we exponentiate, and add back in the values
for (int j_2 = 0; j_2 < GetDimensions()[1]; j_2++)
{
if (double.IsFinite(max[j_2]))
{
marginalized.values[j_2] = max[j_2] + Math.Log(marginalized.values[j_2]);
}
else
{
marginalized.values[j_2] = max[j_2];
}
}
return(marginalized);
}
else
{
System.Diagnostics.Debug.Assert((neighborIndices[1] == variable));
Edu.Stanford.Nlp.Loglinear.Inference.TableFactor marginalized = new Edu.Stanford.Nlp.Loglinear.Inference.TableFactor(new int[] { neighborIndices[0] }, new int[] { GetDimensions()[0] });
for (int i = 0; i < marginalized.values.Length; i++)
{
marginalized.values[i] = 0;
}
// We use the stable log-sum-exp trick here, so first we calculate the max
double[] max = new double[GetDimensions()[0]];
for (int i_1 = 0; i_1 < GetDimensions()[0]; i_1++)
{
max[i_1] = double.NegativeInfinity;
}
for (int i_2 = 0; i_2 < GetDimensions()[0]; i_2++)
{
int k = i_2 * GetDimensions()[1];
for (int j = 0; j < GetDimensions()[1]; j++)
{
int index = k + j;
if (values[index] > max[i_2])
{
max[i_2] = values[index];
}
}
}
// Then we take the sum, minus the max
for (int i_3 = 0; i_3 < GetDimensions()[0]; i_3++)
{
int k = i_3 * GetDimensions()[1];
for (int j = 0; j < GetDimensions()[1]; j++)
{
int index = k + j;
if (double.IsFinite(max[i_3]))
{
marginalized.values[i_3] += Math.Exp(values[index] - max[i_3]);
}
}
}
// And now we exponentiate, and add back in the values
for (int i_4 = 0; i_4 < GetDimensions()[0]; i_4++)
{
if (double.IsFinite(max[i_4]))
{
marginalized.values[i_4] = max[i_4] + Math.Log(marginalized.values[i_4]);
}
else
{
marginalized.values[i_4] = max[i_4];
}
}
return(marginalized);
}
}
else
{
// This is a little tricky because we need to use the stable log-sum-exp trick on top of our marginalize
// dataflow operation.
// First we calculate all the max values to use as pivots to prevent overflow
Edu.Stanford.Nlp.Loglinear.Inference.TableFactor maxValues = MaxOut(variable);
// Then we do the sum against an offset from the pivots
Edu.Stanford.Nlp.Loglinear.Inference.TableFactor marginalized = Marginalize(variable, 0, null);
// Then we factor the max values back in, and
foreach (int[] assignment in marginalized)
{
marginalized.SetAssignmentLogValue(assignment, maxValues.GetAssignmentLogValue(assignment) + Math.Log(marginalized.GetAssignmentLogValue(assignment)));
}
return(marginalized);
}
}
