public void LearnTest_validInput_ModelDescribingTheData ()
{
// Arrange
HMMGraph hmm = new HMMGraph(NUMBER_OF_SYMBOLS_IN_HMMGRAPH);
//int[] t = {2,3,5,6,2,12,4,6,3,36,62,2,144,3,531,44,23,234,21};
List<int[]> obs = new List<int[]>();
Random rnd = new Random();
for(int i=0;i<4;i++) {
obs.Add(Enumerable.Range(1,49).OrderBy(x => rnd.Next()).ToArray());
}
hmm.AddNode(new Node());
hmm.AddNode(new Node());
hmm.AddNode(new Node());
hmm.AddNode(new Node());
BaumWelch BW = new BaumWelch();
// Act
HMMGraph result = BW.Learn(hmm, obs.ToArray());
// Assert
Assert.IsNotNull(result);
Assert.Inconclusive();
}
public void Learn_HMMWithRandomDistributedProbs_LearnsAConsistentModelBasedOnData()
{
// Arrange
int[] symbols = Enumerable.Range(1, 42).ToArray();
List<int[]> obs = new List<int[]>();
Random rnd = new Random();
for (int i = 0; i < 10; i++)
{
obs.Add(symbols.OrderBy(x => rnd.Next()).ToArray());
}
HMMGraph hmm = new HMMGraph(symbols.Length);
hmm.AddNode(new Node());
hmm.AddNode(new Node());
hmm.AddNode(new Node());
hmm.AddNode(new Node());
foreach (Node n in hmm.Nodes)
{
foreach (Node m in hmm.Nodes)
{
n.SetTransition(m, 0.5);
}
foreach (int i in symbols)
{
n.SetEmission(i, 0.5);
}
}
hmm.Normalize();
BaumWelch bw = new BaumWelch(obs.Count, hmm);
// Act
for (int i = 0; i < 5; i++)
{
bw.Learn(hmm, obs.ToArray());
}
// Assert
const double PRECISION = .00000000001;
foreach (Node n in hmm.Nodes)
{
//check transitions
double sum = 0;
foreach (Node nb in n.Transitions.Keys)
{
sum += n.Transitions[nb];
}
Assert.IsTrue(1.0 - PRECISION < sum && sum < 1.0 + PRECISION);
sum = 0;
foreach (int o in n.Emissions.Keys)
{
sum += n.Emissions[o];
}
Assert.IsTrue(1.0 - PRECISION < sum && sum < 1.0 + PRECISION);
}
}
private HMMGraph Splitstate(Node qPrime, HMMGraph graph) {
Random random = new Random();
Node q1 = new Node();
foreach (Node x in graph.Nodes) {
q1.SetTransition(x, random.NextDouble());
}
foreach (int symbol in qPrime.Emissions.Keys) {
q1.SetEmission(symbol, qPrime.Emissions[symbol]);
}
q1.InitialProbability = qPrime.InitialProbability;
foreach (Node n in graph.Nodes) {
n.Transitions[q1] = random.NextDouble();
}
q1.SetTransition(q1,random.NextDouble());
graph.AddNode(q1);
graph.Normalize();
return graph;
}
static HMMGraph CreateGraph(int numberOfSymbols, int numberOfStates, double outDegree)
{
HMMGraph graph = new HMMGraph(numberOfSymbols);
double initialProbabilitySum = 0.0;
for (int i = 0; i < numberOfStates; i++)
{
Node node = new Node();
node.InitialProbability = random.NextDouble();
initialProbabilitySum += node.InitialProbability;
node.Emissions = new Dictionary<int, double>();
for (int j = 0; j < numberOfSymbols; j++)
{
node.Emissions.Add(j, random.NextDouble());
}
double emissionSum = node.Emissions.Values.Sum();
for (int j = 0; j < numberOfSymbols; j++)
{
node.Emissions[j] /= emissionSum;
}
graph.AddNode(node);
}
for (int i = 0; i < numberOfStates; i++)
{
graph.Nodes[i].InitialProbability /= initialProbabilitySum;
graph.Nodes[i].Transitions = new Dictionary<Node, double>();
int outDeg = (int)(((i % 2) == 1) ? Math.Floor(outDegree) : Math.Ceiling(outDegree));
for (int j = 0; j < outDeg; j++)
{
graph.Nodes[i].Transitions.Add(graph.Nodes[((i + j) % numberOfStates)], random.NextDouble());
}
double transitionSum = graph.Nodes[i].Transitions.Values.Sum();
for (int j = 0; j < outDeg; j++)
{
graph.Nodes[i].Transitions[graph.Nodes[((i + j) % numberOfStates)]] /= transitionSum;
}
}
return graph;
}
public static HMMGraph HMM2Graph(HiddenMarkovModel hmm){
HMMGraph g = new HMMGraph(hmm.Symbols);
Node[] nodes = new Node[hmm.States];
for (int i = 0; i < hmm.States; i++) {
nodes[i] = new Node();
g.AddNode(nodes[i]);
}
for (int i = 0; i < hmm.States; i++) {
nodes[i].InitialProbability = hmm.Probabilities[i];
for (int j = 0; j < hmm.States; j++)
nodes[i].SetTransition(nodes[j], hmm.Transitions[i, j]);
for (int k = 0; k < hmm.Symbols; k++)
nodes[i].SetEmission(k, hmm.Emissions[i, k]);
}
return g;
}
public HMMGraph ToGraph()
{
HMMGraph graph = new HMMGraph(NumberOfSymbols);
for (int i = 0; i < NumberOfStates; i++)
{
Node node = new Node();
node.InitialProbability = initialDistribution[i];
node.Emissions = emissions[i].ToDictionary(j => j, j => emissionProbabilities[i, j]);
graph.AddNode(node);
}
for (int i = 0; i < NumberOfStates; i++)
{
graph.Nodes[i].Transitions = transitionsOut[i].ToDictionary(j => graph.Nodes[j], j => transitionProbabilities[i, j]);
}
return graph;
}
public override void Learn(SequenceData trainingData,
SequenceData validationData, SequenceData testData)
{
#region Junk
//hmm.Learn(trainingData.GetNonempty(), 1);
//foreach (int[] O in trainingData.GetAll()) {
// // 1. convert to hmm to graph model.
// HMMGraph hmmGraph = ModelConverter.HMM2Graph(hmm);
// // 2. find argmax gamma
// BaumWelch bw = new BaumWelch(O.Length, hmmGraph);
// //Node qPrime = (from n in hmmGraph.Nodes
// // where hmmGraph.Nodes.TrueForAll(x => bw.ComputeGamma(n,
// // hmmGraph, O) > bw.ComputeGamma(x, hmmGraph, O))
// // select n).Single();
// Node qPrime = (from n in hmmGraph.Nodes
// where hmmGraph.Nodes.TrueForAll(x
// => bw.ComputeGamma(n, hmmGraph, O) >= bw.ComputeGamma(x, hmmGraph, O))
// select n).First();
// // 3. split node if transition or emission probs
// // are above uniformity threshold.
// double[] transValues = qPrime.Transitions.Values.ToArray();
// double[] emissionValues = qPrime.Emissions.Values.ToArray();
// if (!isUniform(transValues, TRANSITION_UNIFORMITY_THRESHOLD)
// || !isUniform(emissionValues, EMISSION_UNIFORMITY_THRESHOLD)) {
// // 4. assign new probs and normalize.
// Node q1 = new Node();
// Node q2 = new Node();
// if (!isUniform(transValues, TRANSITION_UNIFORMITY_THRESHOLD)) {
// AssignTransitions(qPrime, q1, q2);
// }
// if (!isUniform(emissionValues, EMISSION_UNIFORMITY_THRESHOLD)) {
// AssignEmissions(qPrime, q1, q2);
// }
// AssignIncomingTransitions(qPrime, q1, q2, hmmGraph);
// q1.InitialProbability = qPrime.InitialProbability / 2;
// q2.InitialProbability = qPrime.InitialProbability / 2;
// hmmGraph.AddNode(q1);
// hmmGraph.AddNode(q2);
// hmmGraph.RemoveNode(qPrime);
// }
// // 5. convert graph model back to hmm
// //hmmGraph.Normalize();
// hmm = ModelConverter.Graph2HMM(hmmGraph);
// // 6. ReLearn model using BW.
// hmm.Learn(trainingData.GetAll(), ITERATIONS);
//}
#endregion
intermediateOutputFile = new System.IO.StreamWriter(intermediateOutputFileName + (run++) + ".csv");
intermediateOutputFile.WriteLine("States, Likelihood");
// Initialize graph
HMMGraph graph = new HMMGraph(trainingData.NumSymbols);
for (int i = 0; i < MINIMUM_STATES; i++) {
graph.AddNode(new Node());
}
foreach (Node n in graph.Nodes) {
foreach (Node m in graph.Nodes) {
n.SetTransition(m, 0.5);
}
for (int i = 0; i < trainingData.NumSymbols; i++) {
n.SetEmission(i, 0.5);
}
}
graph.Normalize();
this.hmm = SparseHiddenMarkovModel.FromGraph(graph);
CleanGraph(graph);
Random rnd = new Random();
List<int> cList = new List<int>();
foreach (int[] a in trainingData.GetAll()) {
cList.AddRange(a);
}
int[] combinedTrainData = cList.ToArray();
// Run iterations.
int iteration = 1;
int stuckAt = 1;
int stuckFor = 1;
while(hmm.NumberOfStates < maximum_states
&& iteration < maximum_iterations) {
Console.WriteLine("* Iteration {0} of {1} Model contains {2} states",iteration,maximum_iterations,hmm.NumberOfStates);
graph = hmm.ToGraph();
Node qPrime = FindQPrime(graph, combinedTrainData);
// check to see if the algorithm is stuck
if (stuckAt == hmm.NumberOfStates) {
stuckFor++;
}
else {
stuckAt = hmm.NumberOfStates;
stuckFor = 1;
}
bool isStuck = stuckFor > MAX_STUCK ? true : false;
if (isUniform(qPrime.Transitions.Values.ToArray(),TRANSITION_UNIFORMITY_THRESHOLD)
|| isUniform(qPrime.Emissions.Values.ToArray(),EMISSION_UNIFORMITY_THRESHOLD)
|| isStuck)
{
if (isStuck) {
Console.WriteLine("Algorithm is stuck: FORCING SPLIT");
}
graph = Splitstate(qPrime, graph);
}
hmm = SparseHiddenMarkovModel.FromGraph(graph);
hmm.Learn(trainingData.GetAll(), THRESHOLD, BW_ITERATIONS);
OutputIntermediate(validationData);
iteration++;
}
hmm = SparseHiddenMarkovModel.FromGraph(graph);
intermediateOutputFile.Close();
}
