public void TestMaxentOnPrepAttachData()
{
var model = new GISTrainer().TrainModel(100,
new TwoPassDataIndexer(PrepAttachDataUtility.CreateTrainingStream(), 1), 1);
PrepAttachDataUtility.TestModel(model, 0.7997028967566229d);
}
public void TestPerceptronOnPrepAttachData()
{
var model = new PerceptronTrainer().TrainModel(400,
new TwoPassDataIndexer(PrepAttachDataUtility.CreateTrainingStream(), 1, false), 1);
PrepAttachDataUtility.TestModel(model, 0.7650408516959644);
}
public void TestPerceptronOnPrepAttachDataWithStepSizeDecrease()
{
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.Perceptron);
trainParams.Set(Parameters.Cutoff, "1");
trainParams.Set(Parameters.Iterations, "500");
trainParams.Set(Parameters.StepSizeDecrease, "0.06");
var trainer = TrainerFactory.GetEventTrainer(trainParams, null, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
/*
* The java test gives an error too, soo.... for now i'll assume that is correct :P
*
* java.lang.AssertionError: expected:<0.7756870512503095> but was:<0.7766773953948998>
* at org.junit.Assert.fail(Assert.java:91)
* at org.junit.Assert.failNotEquals(Assert.java:645)
* at org.junit.Assert.assertEquals(Assert.java:441)
* at org.junit.Assert.assertEquals(Assert.java:510)
*/
//PrepAttachDataUtility.TestModel(model, 0.7756870512503095); < OpenNLP value
PrepAttachDataUtility.TestModel(model, 0.77742015350334237);
}
public void TestQnOnPrepAttachData()
{
var model = new QNTrainer().TrainModel(100,
new TwoPassDataIndexer(PrepAttachDataUtility.CreateTrainingStream(), 1));
TestModel(model, 0.8155484030700668);
}
public void TestNaiveBayesOnPrepAttachData()
{
var model = NaiveBayesTests.TrainModel(PrepAttachDataUtility.CreateTrainingStream());
Assert.NotNull(model);
PrepAttachDataUtility.TestModel(model, 0.7897994553107205);
}
public void TestMaxentOnPrepAttachData2Threads()
{
var trainer = new GISTrainer();
var di = new TwoPassDataIndexer(PrepAttachDataUtility.CreateTrainingStream(), 1);
var model = trainer.TrainModel(100, di, new UniformPrior(), 1, 2);
PrepAttachDataUtility.TestModel(model, 0.7997028967566229d);
}
public void TestMaxentOnPrepAttachDataWithParamsDefault()
{
var reportMap = new Dictionary <string, string>();
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.MaxEnt);
var trainer = TrainerFactory.GetEventTrainer(trainParams, reportMap, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
PrepAttachDataUtility.TestModel(model, 0.8086159940579352d);
}
public void TestQnOnPrepAttachDataWithParamsDefault()
{
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.MaxEntQn);
var trainer = TrainerFactory.GetEventTrainer(trainParams, null, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
TestModel(model, 0.8115870264917059);
}
public void TestPerceptronOnPrepAttachDataWithSkippedAveraging()
{
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.Perceptron);
trainParams.Set(Parameters.Cutoff, "1");
trainParams.Set(Parameters.UseSkippedAveraging, "true");
var trainer = TrainerFactory.GetEventTrainer(trainParams, null, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
PrepAttachDataUtility.TestModel(model, 0.773706362961129);
}
public void TestMaxentOnPrepAttachDataWithParams()
{
var reportMap = new Dictionary <string, string>();
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.MaxEnt);
trainParams.Set(Parameters.DataIndexer, Parameters.DataIndexers.TwoPass);
trainParams.Set(Parameters.Cutoff, "1");
var trainer = TrainerFactory.GetEventTrainer(trainParams, reportMap, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
PrepAttachDataUtility.TestModel(model, 0.7997028967566229d);
}
public void TestPerceptronOnPrepAttachDataWithTolerance()
{
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.Perceptron);
trainParams.Set(Parameters.Cutoff, "1");
trainParams.Set(Parameters.Iterations, "500");
trainParams.Set(Parameters.Tolerance, "0.0001");
var trainer = TrainerFactory.GetEventTrainer(trainParams, null, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
PrepAttachDataUtility.TestModel(model, 0.7677642980935875);
}
public void TestQnOnPrepAttachDataInParallel()
{
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.MaxEntQn);
//trainParams.Set(Parameters.Iterations, "100");
trainParams.Set(Parameters.Threads, "2");
var trainer = TrainerFactory.GetEventTrainer(trainParams, null, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
TestModel(model, 0.8115870264917059);
}
public void TestQnOnPrepAttachDataWithL2Params()
{
var trainParams = new TrainingParameters();
trainParams.Set(Parameters.Algorithm, Parameters.Algorithms.MaxEntQn);
trainParams.Set(Parameters.DataIndexer, Parameters.DataIndexers.TwoPass);
trainParams.Set(Parameters.Cutoff, "1");
trainParams.Set(Parameters.L1Cost, "0");
trainParams.Set(Parameters.L2Cost, "1.0");
var trainer = TrainerFactory.GetEventTrainer(trainParams, null, null);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
TestModel(model, 0.8227283981183461);
}
public void TestNaiveBayesOnPrepAttachDataUsingTrainUtilWithCutoff5()
{
var parameters = TrainingParameters.DefaultParameters();
parameters.Set(Parameters.Algorithm, Parameters.Algorithms.NaiveBayes);
parameters.Set(Parameters.Cutoff, "5");
var trainer = TrainerFactory.GetEventTrainer(parameters, null, null);
Assert.NotNull(trainer);
Assert.IsInstanceOf <NaiveBayesTrainer>(trainer);
var model = trainer.Train(PrepAttachDataUtility.CreateTrainingStream());
Assert.NotNull(model);
PrepAttachDataUtility.TestModel(model, 0.7945035899975241);
}
private static void TestModel(IMaxentModel model, double expectedAccuracy)
{
var devEvents = PrepAttachDataUtility.ReadPpaFile(@"devset");
var total = 0;
var correct = 0;
foreach (var ev in devEvents)
{
var targetLabel = ev.Outcome;
var ocs = model.Eval(ev.Context);
var best = 0;
for (var i = 1; i < ocs.Length; i++)
{
if (ocs[i] > ocs[best])
{
best = i;
}
}
var predictedLabel = model.GetOutcome(best);
if (targetLabel.Equals(predictedLabel))
{
correct++;
}
total++;
}
var accuracy = correct / (double)total;
Debug.WriteLine("Accuracy on PPA devset: (" + correct + "/" + total + ") " + accuracy);
Assert.AreEqual(expectedAccuracy, accuracy, .00001);
}
