public void RunTest()
{
Accord.Math.Random.Generator.Seed = 0;
int nstates = 3;
int symbols = 3;
int[][] sequences = new int[][]
{
new int[] { 0, 1, 1, 1, 2 },
new int[] { 0, 1, 1, 1, 2, 2, 2 },
new int[] { 0, 0, 1, 1, 2, 2 },
new int[] { 0, 1, 1, 1, 2, 2, 2 },
new int[] { 0, 1, 1, 1, 2, 2 },
new int[] { 0, 1, 1, 2, 2 },
new int[] { 0, 0, 1, 1, 1, 2, 2 },
new int[] { 0, 0, 0, 1, 1, 1, 2, 2 },
new int[] { 0, 1, 1, 2, 2, 2 },
};
var function = new MarkovDiscreteFunction(nstates, symbols, new NormalDistribution());
var model = new ConditionalRandomField <int>(nstates, function);
for (int i = 0; i < sequences.Length; i++)
{
double p;
int[] s = sequences[i];
int[] r = model.Compute(s, out p);
Assert.IsFalse(s.IsEqual(r));
}
var target = new QuasiNewtonLearning <int>(model);
target.ParallelOptions.MaxDegreeOfParallelism = 1;
int[][] labels = sequences;
int[][] observations = sequences;
double ll0 = model.LogLikelihood(observations, labels);
double actual = target.Run(observations, labels);
double ll1 = model.LogLikelihood(observations, labels);
Assert.IsTrue(ll1 > ll0);
Assert.AreEqual(-0.0010766857305242183, actual, 1e-6);
for (int i = 0; i < sequences.Length; i++)
{
double p;
int[] s = sequences[i];
int[] r = model.Compute(s, out p);
Assert.IsTrue(s.IsEqual(r));
}
}
public void RunTest()
{
int nstates = 3;
int symbols = 3;
int[][] sequences = new int[][]
{
new int[] { 0, 1, 1, 1, 2 },
new int[] { 0, 1, 1, 1, 2, 2, 2 },
new int[] { 0, 0, 1, 1, 2, 2 },
new int[] { 0, 1, 1, 1, 2, 2, 2 },
new int[] { 0, 1, 1, 1, 2, 2 },
new int[] { 0, 1, 1, 2, 2 },
new int[] { 0, 0, 1, 1, 1, 2, 2 },
new int[] { 0, 0, 0, 1, 1, 1, 2, 2 },
new int[] { 0, 1, 1, 2, 2, 2 },
};
var function = new MarkovDiscreteFunction(nstates, symbols);
var model = new ConditionalRandomField <int>(nstates, function);
for (int i = 0; i < sequences.Length; i++)
{
double p;
int[] s = sequences[i];
int[] r = model.Compute(s, out p);
Assert.IsFalse(s.IsEqual(r));
}
var target = new QuasiNewtonLearning <int>(model);
int[][] labels = sequences;
int[][] observations = sequences;
double ll0 = model.LogLikelihood(observations, labels);
double actual = target.Run(observations, labels);
double ll1 = model.LogLikelihood(observations, labels);
Assert.IsTrue(ll1 > ll0);
Assert.AreEqual(0, actual, 1e-8);
for (int i = 0; i < sequences.Length; i++)
{
double p;
int[] s = sequences[i];
int[] r = model.Compute(s, out p);
Assert.IsTrue(s.IsEqual(r));
}
}
public void learn_test()
{
#region doc_learn
Accord.Math.Random.Generator.Seed = 0;
int[][] input =
{
new int[] { 0, 1, 1, 1, 0, 0 },
new int[] { 0, 1, 1,0 },
new int[] { 0, 1, 1, 0, 0, 0 },
new int[] { 0, 1, 1, 1, 1, 0 },
new int[] { 0, 1, 1, 1, 0,0, 0, 0 },
new int[] { 0, 1, 1, 1, 0, 0 },
new int[] { 0, 1, 1,0 },
new int[] { 0, 1, 1, 1,0 },
};
int[][] output =
{
new int[] { 0, 0, 1, 1, 1, 2 },
new int[] { 0, 0, 1,2 },
new int[] { 0, 0, 1, 1, 1, 2 },
new int[] { 0, 0, 1, 1, 1, 2 },
new int[] { 0, 0, 1, 1, 1,1, 2, 2 },
new int[] { 0, 0, 1, 1, 1, 2 },
new int[] { 0, 0, 1,2 },
new int[] { 0, 1, 1, 1,2 },
};
// Create a new L-BFGS learning algorithm
var teacher = new QuasiNewtonLearning <int>()
{
Function = new MarkovDiscreteFunction(states: 3, symbols: 2, initialization: new NormalDistribution())
};
// Learn the Conditional Random Field model
ConditionalRandomField <int> crf = teacher.Learn(input, output);
// Use the model to classify the samples
int[][] prediction = crf.Decide(input);
var cm = new ConfusionMatrix(predicted: prediction.Reshape(), expected: output.Reshape());
double acc = cm.Accuracy;
#endregion
Assert.IsTrue(acc > 0.7);
}
public void chunking_dataset_crf()
{
Chunking chunking = new Chunking(path: Path.GetTempPath());
// Learn a mapping between each word to an integer class label:
var wordMap = new Codification().Learn(chunking.Words);
// Learn a mapping between each tag to an integer class labels:
var tagMap = new Codification().Learn(chunking.Tags);
// Convert the training and testing sets into integer labels:
int[][] trainX = wordMap.Transform(chunking.Training.Item1);
int[][] testX = wordMap.Transform(chunking.Testing.Item1);
// Convert the training and testing tags into integer labels:
int[][] trainY = tagMap.Transform(chunking.Training.Item2);
int[][] testY = tagMap.Transform(chunking.Testing.Item2);
int numberOfClasses = chunking.Tags.Length;
int numberOfSymbols = chunking.Words.Length;
// Learn one Markov model using the training data
var teacher = new QuasiNewtonLearning <int>()
{
Function = new MarkovDiscreteFunction(states: numberOfClasses, symbols: numberOfSymbols)
};
// Use the teacher to learn a Conditional Random Field model
ConditionalRandomField <int> crf = teacher.Learn(trainX, trainY);
// Use the crf to predict instances:
int[][] predY = crf.Decide(testX);
// Check the accuracy of the model:
var cm = new ConfusionMatrix(
predicted: predY.Concatenate(),
expected: testY.Concatenate());
double acc = cm.Accuracy;
Assert.AreEqual(0.99983114169322662, acc, 1e-10);
}
private static void crf(int[][] trainX, int[][] trainY, int[][] testX, int[][] testY)
{
int numberOfClasses = 44; // chunking.Tags.Length;
int numberOfSymbols = 21589; // chunking.Words.Length;
// Learn one Markov model using the training data
var teacher = new QuasiNewtonLearning <int>()
{
Function = new MarkovDiscreteFunction(states: numberOfClasses, symbols: numberOfSymbols)
};
// Use the teacher to learn a Conditional Random Field model
ConditionalRandomField <int> crf = teacher.Learn(trainX, trainY);
// Use the crf to predict instances:
int[][] predY = crf.Decide(testX);
// Check the accuracy of the model:
var cm = new ConfusionMatrix(predicted: predY.Concatenate(), expected: testY.Concatenate());
double acc = cm.Accuracy;
}
