private void learnButton_Click(object sender, RoutedEventArgs e)
{
ReadSequenceBox();
ReadCharBox();
ReadStateBox();
ReadLikelihoodBox();
int[][] sequenceArray = SequenceListToArray();
hmm = new HiddenMarkovModel(alphabet, states);
hmm.Learn(sequenceArray, likelihood);
}
public override void Learn(SequenceData trainingData, SequenceData validationData, SequenceData testData)
{
//hmm = SparseHiddenMarkovModel.FromCompleteGraph(2, trainingData.NumSymbols);
hmm = new HiddenMarkovModel(trainingData.NumSymbols, 4);
double likelihood = 0.0;
double newLikelihood = Double.MinValue;
do
{
//HMMGraph graph = hmm.ToGraph();
HMMGraph graph = ModelConverter.HMM2Graph(hmm);
//CutEdges(graph, epsilon);
double[] viterbyScores = ComputeViterbyScores(validationData, true);
int[] statesToSplit = IdentifyWeakStates(viterbyScores).ToArray();
foreach (int weakPoint in statesToSplit)
{
SplitState(graph, weakPoint);
}
WriteLine(String.Format("Added {0} states", statesToSplit.Length));
//WriteLine(String.Format("Removed {0} states", RemoveUnpopularStates(graph, viterbyScores)));
//hmm = SparseHiddenMarkovModel.FromGraph(graph);
hmm = ModelConverter.Graph2HMM(graph);
WriteLine("Running Baum Welch...");
//hmm.Learn(trainingData.GetNonempty(), 0.0, 8);
hmm.Learn(trainingData.GetNonempty(), 8);
likelihood = newLikelihood;
newLikelihood = 0.0;
foreach (int[] signal in validationData.GetNonempty())
{
newLikelihood += hmm.Evaluate(signal, true);
}
WriteLine(String.Empty);
WriteLine(String.Format("Number of HMM States: {0}", NumberOfStates));
//WriteLine(String.Format("Transition Sparsity; {0}", hmm.TransitionSparsity));
WriteLine(String.Format("Log Likelihood: {0}", newLikelihood));
WriteLine(String.Empty);
}
while (Math.Abs(newLikelihood - likelihood) > convergenceThreshold);
}
public override void Learn(SequenceData trainingData, SequenceData validationData, SequenceData testData) {
//trainingData.AddSequences(validationData);
double[] initialProbabilities = new double[states];
double sum = 0.0;
for (int k = 0; k < states; k++)
{
initialProbabilities[k] = random.NextDouble();
sum += initialProbabilities[k];
}
for (int k = 0; k < states; k++)
{
initialProbabilities[k] /= sum;
}
double[,] transitionMatrix = new double[states, states];
for (int k = 0; k < states; k++)
{
sum = 0.0;
for (int l = 0; l < states; l++)
{
transitionMatrix[k, l] = random.NextDouble();
sum += transitionMatrix[k, l];
}
for (int l = 0; l < states; l++)
{
transitionMatrix[k, l] /= sum;
}
}
double[,] emissionMatrix = new double[states, testData.NumSymbols];
for (int k = 0; k < states; k++)
{
sum = 0.0;
for (int l = 0; l < testData.NumSymbols; l++)
{
emissionMatrix[k, l] = random.NextDouble();
sum += emissionMatrix[k, l];
}
for (int l = 0; l < testData.NumSymbols; l++)
{
emissionMatrix[k, l] /= sum;
}
}
//hmm = new HiddenMarkovModel(trainingData.NumSymbols, states);
hmm = new HiddenMarkovModel(transitionMatrix, emissionMatrix, initialProbabilities);
Stopwatch sw = new Stopwatch();
sw.Start();
hmm.Learn(trainingData.GetNonempty(), tolerance);
sw.Stop();
Console.WriteLine(sw.Elapsed.TotalSeconds);
}
public void EquivalenceTest() {
double[] pi = new double[]{0.23, 0.52, 0.25};
double[,] A = new double[,]{{ 3.0 / 6.0, 2.0 / 6.0, 1.0 / 6.0 },
{ 11.0 / 17.0, 2.0 / 17.0, 4.0 / 17.0},
{4.0 / 20.0, 7.0 / 20.0, 9.0 / 20.0}};
double[,] B = new double[,]{{ 1.0 / 6.0, 1.0 / 6.0, 4.0 / 6.0 },
{ 2.0 / 17.0, 3.0 / 17.0, 12.0 / 17.0},
{13.0 / 20.0, 2.0 / 20.0, 5.0 / 20.0}};
int[][] observations = new int[][]{
new int[] {0, 0, 1, 2, 1, 1, 1, 2, 0, 0, 0, 1, 2, 1, 2, 1, 0, 1},
new int[] {1, 1, 2, 1, 2, 0},
new int[] {1, 1, 2, 2, 2, 2, 1, 1, 2, 1, 2, 1, 2, 1},
new int[] {1, 1, 2, 1, 0, 0, 2, 1, 0, 1, 1, 1},
new int[] {1, 2, 2, 0, 2},
new int[] {1, 1, 1, 1, 2, 1, 2, 1}
};
//Run BW with 20 iterations
HiddenMarkovModel hmm = new HiddenMarkovModel(Clone(A), Clone(B), Clone(pi));
hmm.Learn(observations, 20);
HiddenMarkovModel hmmLM = new HiddenMarkovModel(Clone(A), Clone(B), Clone(pi));
hmmLM.Learn(observations, 20);
for (int i = 0; i < hmm.Probabilities.Length; i++)
Assert.AreEqual(hmm.Probabilities[i], hmmLM.Probabilities[i]);
for (int i = 0; i < hmm.Transitions.GetLength(0); i++)
for (int p = 0; p < hmm.Transitions.GetLength(1); p++)
Assert.AreEqual(hmm.Transitions[i, p], hmmLM.Transitions[i, p]);
for (int i = 0; i < hmm.Emissions.GetLength(0); i++)
for (int p = 0; p < hmm.Emissions.GetLength(1); p++)
Assert.AreEqual(hmm.Emissions[i, p], hmmLM.Emissions[i, p]);
//Run BW with 1 iteration
hmm = new HiddenMarkovModel(Clone(A), Clone(B), Clone(pi));
hmm.Learn(observations, 1);
hmmLM = new HiddenMarkovModel(Clone(A), Clone(B), Clone(pi));
hmmLM.Learn(observations, 1);
for (int i = 0; i < hmm.Probabilities.Length; i++)
Assert.AreEqual(hmm.Probabilities[i], hmmLM.Probabilities[i]);
for (int i = 0; i < hmm.Transitions.GetLength(0); i++)
for (int p = 0; p < hmm.Transitions.GetLength(1); p++)
Assert.AreEqual(hmm.Transitions[i, p], hmmLM.Transitions[i, p]);
for (int i = 0; i < hmm.Emissions.GetLength(0); i++)
for (int p = 0; p < hmm.Emissions.GetLength(1); p++)
Assert.AreEqual(hmm.Emissions[i, p], hmmLM.Emissions[i, p]);
//Run BW with threshold 0.1
hmm = new HiddenMarkovModel(Clone(A), Clone(B), Clone(pi));
hmm.Learn(observations, 0.1);
hmmLM = new HiddenMarkovModel(Clone(A), Clone(B), Clone(pi));
hmmLM.Learn(observations, 0.1);
for (int i = 0; i < hmm.Probabilities.Length; i++)
Assert.AreEqual(hmm.Probabilities[i], hmmLM.Probabilities[i]);
for (int i = 0; i < hmm.Transitions.GetLength(0); i++)
for (int p = 0; p < hmm.Transitions.GetLength(1); p++)
Assert.AreEqual(hmm.Transitions[i, p], hmmLM.Transitions[i, p]);
for (int i = 0; i < hmm.Emissions.GetLength(0); i++)
for (int p = 0; p < hmm.Emissions.GetLength(1); p++)
Assert.AreEqual(hmm.Emissions[i, p], hmmLM.Emissions[i, p]);
}
