/// <summary>
/// Initializes a new instance of the <see cref="BPMShared"/> class.
/// </summary>
/// <param name="numClasses">The number of classes.</param>
/// <param name="noisePrecision">The precision of the noise.</param>
/// <param name="numFeatures">The number of features.</param>
/// <param name="numChunksTraining">The number of training set chunks.</param>
/// <param name="numChunksTesting">The number of test set chunks.</param>
public BPMShared(int numClasses, double noisePrecision, int numFeatures, int numChunksTraining, int numChunksTesting)
{
// Range over classes.
this.c = new Range(numClasses).Named("c");
// Setup shared weights and weights' prior.
this.weightsPrior = InitializePrior(numClasses, numFeatures);
this.weights = SharedVariable<Vector>.Random(this.c, this.weightsPrior).Named("w");
// Configure models.
this.trainModel = new Model(this.weights, this.c, numChunksTraining);
this.testModel = new Model(this.weights, this.c, numChunksTesting);
// Observe the noise precision.
this.trainModel.noisePrecision.ObservedValue = noisePrecision;
this.testModel.noisePrecision.ObservedValue = noisePrecision;
}
/// <summary>
/// Constructs a multi-component sparse Bayes Point Machine using shared variables for chunking data
/// </summary>
/// <param name="nClass">Number of components (classes)</param>
/// <param name="featureCount">Number of features</param>
/// <param name="noisePrec">Noise precision</param>
/// <param name="trainChunkSize">Chunk size for training</param>
/// <param name="testChunkSize">Chunk size for testing</param>
public BPMSparse_Shared(int nClass, int featureCount, double noisePrec, int trainChunkSize, int testChunkSize)
{
nComponents = nClass;
nFeatures = featureCount;
NoisePrec = noisePrec;
this.trainChunkSize = trainChunkSize;
this.testChunkSize = testChunkSize;
feature = new Range(nFeatures).Named("feature");
w = new SharedVariableArray<double>[nComponents];
IDistribution<double[]> wPrior0 = Distribution<double>.Array(nFeatures,
delegate(int index) { return Gaussian.PointMass(0); });
IDistribution<double[]> wPrior = Distribution<double>.Array(nFeatures,
delegate(int index) { return Gaussian.FromMeanAndPrecision(0.0, 1.0); });
for (int c = 0; c < nComponents; c++)
{
w[c] = (c == 0)
? SharedVariable<double>.Random(feature, (DistributionStructArray<Gaussian,double>)wPrior0).Named("w_" + c)
: SharedVariable<double>.Random(feature, (DistributionStructArray<Gaussian,double>)wPrior).Named("w_" + c);
}
trainModel = SpecifyTrainModel("_train", trainChunkSize);
testModel = SpecifyTestModel("_test", testChunkSize);
}
/// <summary>
/// Constructs an LDA model
/// </summary>
/// <param name="sizeVocab">Size of vocabulary</param>
/// <param name="numTopics">Number of topics</param>
public LDAShared(int numBatches, int sizeVocab, int numTopics)
{
SizeVocab = sizeVocab;
NumTopics = numTopics;
ThetaSparsity = Sparsity.Dense;
PhiSparsity = Sparsity.ApproximateWithTolerance(0.00000000001); // Allow for round-off error
NumDocuments = Variable.New <int>().Named("NumDocuments");
NumBatches = numBatches;
IterationsPerPass = new int[] { 1, 3, 5, 7, 9 };
//---------------------------------------------
// The model
//---------------------------------------------
Range D = new Range(NumDocuments).Named("D");
Range W = new Range(SizeVocab).Named("W");
Range T = new Range(NumTopics).Named("T");
NumWordsInDoc = Variable.Array <int>(D).Named("NumWordsInDoc");
Range WInD = new Range(NumWordsInDoc[D]).Named("WInD");
Evidence = SharedVariable <bool> .Random(new Bernoulli(0.5)).Named("Evidence");
Evidence.IsEvidenceVariable = true;
Phi = SharedVariable <Vector> .Random(T, CreateUniformDirichletArray(numTopics, sizeVocab, PhiSparsity)).Named("Phi");
// Phi definition sub-model - just one copy
PhiDefModel = new Model(1).Named("PhiDefModel");
IfBlock evidencePhiDefBlock = null;
EvidencePhiDef = Evidence.GetCopyFor(PhiDefModel).Named("EvidencePhiDef");
evidencePhiDefBlock = Variable.If(EvidencePhiDef);
PhiDef = Variable.Array <Vector>(T).Named("PhiDef");
PhiDef.SetSparsity(PhiSparsity);
PhiDef.SetValueRange(W);
PhiPrior = Variable.Array <Dirichlet>(T).Named("PhiPrior");
PhiDef[T] = Variable <Vector> .Random(PhiPrior[T]);
Phi.SetDefinitionTo(PhiDefModel, PhiDef);
evidencePhiDefBlock.CloseBlock();
// Document sub-model - many copies
DocModel = new Model(numBatches).Named("DocModel");
IfBlock evidenceDocBlock = null;
EvidenceDoc = Evidence.GetCopyFor(DocModel).Named("EvidenceDoc");
evidenceDocBlock = Variable.If(EvidenceDoc);
Theta = Variable.Array <Vector>(D).Named("Theta");
Theta.SetSparsity(ThetaSparsity);
Theta.SetValueRange(T);
ThetaPrior = Variable.Array <Dirichlet>(D).Named("ThetaPrior");
Theta[D] = Variable <Vector> .Random(ThetaPrior[D]);
PhiDoc = Phi.GetCopyFor(DocModel);
PhiDoc.AddAttribute(new MarginalPrototype(Dirichlet.Uniform(sizeVocab, PhiSparsity)));
Words = Variable.Array(Variable.Array <int>(WInD), D).Named("Words");
WordCounts = Variable.Array(Variable.Array <double>(WInD), D).Named("WordCounts");
using (Variable.ForEach(D))
{
using (Variable.ForEach(WInD))
{
using (Variable.Repeat(WordCounts[D][WInD]))
{
Variable <int> topic = Variable.Discrete(Theta[D]).Named("topic");
using (Variable.Switch(topic))
{
Words[D][WInD] = Variable.Discrete(PhiDoc[topic]);
}
}
}
}
evidenceDocBlock.CloseBlock();
// Initialization to break symmetry
ThetaInit = Variable.Array <Dirichlet>(D).Named("ThetaInit");
Theta[D].InitialiseTo(ThetaInit[D]);
EnginePhiDef = new InferenceEngine(new VariationalMessagePassing());
EnginePhiDef.Compiler.ShowWarnings = false;
EnginePhiDef.ModelName = "LDASharedPhiDef";
Engine = new InferenceEngine(new VariationalMessagePassing());
Engine.OptimiseForVariables = new IVariable[] { Theta, PhiDoc, EvidenceDoc };
Engine.Compiler.ShowWarnings = false;
Engine.ModelName = "LDAShared";
Engine.Compiler.ReturnCopies = false;
Engine.Compiler.FreeMemory = true;
}
public Model(SharedVariableArray<Vector> w, Range c, int numChunks)
{
// Items.
numItems = Variable.New<int>().Named("numItems");
i = new Range(numItems).Named("i");
i.AddAttribute(new Sequential());
// The model identifier for the shared variables.
model = new MicrosoftResearch.Infer.Models.Model(numChunks).Named("model");
// The weight vector for each submodel.
wModel = w.GetCopyFor(model).Named("wModel");
noisePrecision = Variable.New<double>().Named("noisePrecision");
// Arrays of <see cref="Vector"/>-valued items (feature vectors) and integer labels.
x = Variable.Array<Vector>(i).Named("x");
y = Variable.Array<int>(i).Named("y");
// For all items...
using (Variable.ForEach(i))
{
// ...compute the score of this item across all classes...
score = BPMUtils.ComputeClassScores(wModel, x[i], noisePrecision);
y[i] = Variable.DiscreteUniform(c);
// ... and constrain the output.
BPMUtils.ConstrainMaximum(y[i], score);
}
// Inference engine settings (EP).
engine.Compiler.UseSerialSchedules = true;
engine.ShowProgress = false;
}
/// <summary>
/// Constructs an LDA model
/// </summary>
/// <param name="sizeVocab">Size of vocabulary</param>
/// <param name="numTopics">Number of topics</param>
public LDAShared(int numBatches, int sizeVocab, int numTopics)
{
SizeVocab = sizeVocab;
NumTopics = numTopics;
ThetaSparsity = Sparsity.Dense;
PhiSparsity = Sparsity.ApproximateWithTolerance(0.00000000001); // Allow for round-off error
NumDocuments = Variable.New<int>().Named("NumDocuments");
NumBatches = numBatches;
IterationsPerPass = new int[] { 1, 3, 5, 7, 9 };
//---------------------------------------------
// The model
//---------------------------------------------
Range D = new Range(NumDocuments).Named("D");
Range W = new Range(SizeVocab).Named("W");
Range T = new Range(NumTopics).Named("T");
NumWordsInDoc = Variable.Array<int>(D).Named("NumWordsInDoc");
Range WInD = new Range(NumWordsInDoc[D]).Named("WInD");
Evidence = SharedVariable<bool>.Random(new Bernoulli(0.5)).Named("Evidence");
Evidence.IsEvidenceVariable = true;
Phi = SharedVariable<Vector>.Random(T, CreateUniformDirichletArray(numTopics, sizeVocab, PhiSparsity)).Named("Phi");
// Phi definition sub-model - just one copy
PhiDefModel = new Model(1).Named("PhiDefModel");
IfBlock evidencePhiDefBlock = null;
EvidencePhiDef = Evidence.GetCopyFor(PhiDefModel).Named("EvidencePhiDef");
evidencePhiDefBlock = Variable.If(EvidencePhiDef);
PhiDef = Variable.Array<Vector>(T).Named("PhiDef");
PhiDef.SetSparsity(PhiSparsity);
PhiDef.SetValueRange(W);
PhiPrior = Variable.Array<Dirichlet>(T).Named("PhiPrior");
PhiDef[T] = Variable<Vector>.Random(PhiPrior[T]);
Phi.SetDefinitionTo(PhiDefModel, PhiDef);
evidencePhiDefBlock.CloseBlock();
// Document sub-model - many copies
DocModel = new Model(numBatches).Named("DocModel");
IfBlock evidenceDocBlock = null;
EvidenceDoc = Evidence.GetCopyFor(DocModel).Named("EvidenceDoc");
evidenceDocBlock = Variable.If(EvidenceDoc);
Theta = Variable.Array<Vector>(D).Named("Theta");
Theta.SetSparsity(ThetaSparsity);
Theta.SetValueRange(T);
ThetaPrior = Variable.Array<Dirichlet>(D).Named("ThetaPrior");
Theta[D] = Variable<Vector>.Random(ThetaPrior[D]);
PhiDoc = Phi.GetCopyFor(DocModel);
PhiDoc.AddAttribute(new MarginalPrototype(Dirichlet.Uniform(sizeVocab, PhiSparsity)));
Words = Variable.Array(Variable.Array<int>(WInD), D).Named("Words");
WordCounts = Variable.Array(Variable.Array<double>(WInD), D).Named("WordCounts");
using (Variable.ForEach(D))
{
using (Variable.ForEach(WInD))
{
using (Variable.Repeat(WordCounts[D][WInD]))
{
Variable<int> topic = Variable.Discrete(Theta[D]).Named("topic");
using (Variable.Switch(topic))
Words[D][WInD] = Variable.Discrete(PhiDoc[topic]);
}
}
}
evidenceDocBlock.CloseBlock();
// Initialization to break symmetry
ThetaInit = Variable.New<IDistribution<Vector[]>>().Named("ThetaInit");
Theta.InitialiseTo(ThetaInit);
EnginePhiDef = new InferenceEngine(new VariationalMessagePassing());
EnginePhiDef.Compiler.ShowWarnings = false;
EnginePhiDef.ModelName = "LDASharedPhiDef";
Engine = new InferenceEngine(new VariationalMessagePassing());
Engine.OptimiseForVariables = new IVariable[] { Theta, PhiDoc, EvidenceDoc };
Engine.Compiler.ShowWarnings = false;
Engine.ModelName = "LDAShared";
Engine.Compiler.ReturnCopies = false;
Engine.Compiler.FreeMemory = true;
}
