public void TestTrainModelReturnsAqnModel()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
var trainer = new QNTrainer();
var model = trainer.TrainModel(Iterations, di);
Assert.NotNull(model);
}
}
public void TestDomainDimensionSanity()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
di.Execute();
var func = new NegLogLikelihood(di);
var correctDomainDimension = di.GetPredLabels().Length *di.GetOutcomeLabels().Length;
Assert.AreEqual(correctDomainDimension, func.Dimension);
}
}
public void TestGradientAtNonInitialPoint()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
di.Execute();
var func = new NegLogLikelihood(di);
var gradientAtInitialPoint = func.GradientAt(func.GetInitialPoint());
var expectedGradient = new[] { -9.0, -14.0, -17.0, 20.0, 8.5, 9.0, 14.0, 17.0, -20.0, -8.5 };
Assert.True(CompareDoubleArray(expectedGradient, gradientAtInitialPoint, di, Tolerance1));
}
}
public void TestValueAtInitialPoint()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
di.Execute();
var func = new NegLogLikelihood(di);
const double expectedValue = 13.86294361;
var value = func.ValueAt(func.GetInitialPoint());
Assert.AreEqual(expectedValue, value, Tolerance1);
}
}
public void TestGradientSanity()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
di.Execute();
var func = new NegLogLikelihood(di);
var initial = func.GetInitialPoint();
var gradientAtInitial = func.GradientAt(initial);
// then
Assert.NotNull(gradientAtInitial);
}
}
public void TestSerializationModel()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
var trainer = new QNTrainer();
var model = trainer.TrainModel(Iterations, di);
Assert.NotNull(model);
QNModel deserialized;
using (var mem = new MemoryStream()) {
using (var modelWriter = new GenericModelWriter(model, new UnclosableStream(mem))) {
modelWriter.Persist();
modelWriter.Close();
}
mem.Flush();
mem.Seek(0, SeekOrigin.Begin);
using (var modelReader = new GenericModelReader(new BinaryFileDataReader(mem)))
deserialized = modelReader.GetModel() as QNModel;
}
Assert.NotNull(deserialized);
Assert.True(model.Equals(deserialized));
var features2Classify = new [] {
"feature2", "feature3", "feature3",
"feature3", "feature3", "feature3",
"feature3", "feature3", "feature3",
"feature3", "feature3", "feature3"
};
var eval01 = model.Eval(features2Classify);
var eval02 = deserialized.Eval(features2Classify);
Assert.AreEqual(eval01.Length, eval02.Length);
for (var i = 0; i < eval01.Length; i++)
{
Assert.AreEqual(eval01[i], eval02[i], 0.00000001);
}
}
}
public void TestInitialSanity()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
di.Execute();
var func = new NegLogLikelihood(di);
var initial = func.GetInitialPoint();
// ReSharper disable once ForCanBeConvertedToForeach
for (var i = 0; i < initial.Length; i++)
{
Assert.AreEqual(0, initial[i], Tolerance1);
}
}
}
public void TestValueAtNonInitialPoint02()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
di.Execute();
var func = new NegLogLikelihood(di);
var nonInitialPoint = new double[] { 3, 2, 3, 2, 3, 2, 3, 2, 3, 2 };
var value = func.ValueAt(DealignDoubleArrayForTestData(nonInitialPoint,
di.GetPredLabels(),
di.GetOutcomeLabels()));
const double expectedValue = 53.163219721099026;
Assert.AreEqual(expectedValue, value, Tolerance2);
}
}
public void TestGradientAtInitialPoint()
{
using (var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
di.Execute();
var func = new NegLogLikelihood(di);
var nonInitialPoint = new[] { 0.2, 0.5, 0.2, 0.5, 0.2, 0.5, 0.2, 0.5, 0.2, 0.5 };
var gradientAtNonInitialPoint = func.GradientAt(DealignDoubleArrayForTestData(nonInitialPoint, di.GetPredLabels(), di.GetOutcomeLabels()));
var expectedGradient =
new[] { -12.755042847945553, -21.227127506102434,
-72.57790706276435, 38.03525795198456,
15.348650889354925, 12.755042847945557,
21.22712750610244, 72.57790706276438,
-38.03525795198456, -15.348650889354925 };
Assert.True(CompareDoubleArray(expectedGradient, gradientAtNonInitialPoint, di, Tolerance1));
}
}
public void TestInTinyDevSet()
{
using (
var eventStream = new RealValueFileEventStream(Tests.GetFullPath(@"/opennlp/data/maxent/real-valued-weights-training-data.txt"), Encoding.UTF8)) {
var di = new OnePassRealValueDataIndexer(eventStream, 1);
var trainer = new QNTrainer();
var model = trainer.TrainModel(Iterations, di);
Assert.NotNull(model);
var features2Classify = new[] {
"feature2", "feature3", "feature3",
"feature3", "feature3", "feature3",
"feature3", "feature3", "feature3",
"feature3", "feature3", "feature3"
};
var eval = model.Eval(features2Classify);
Assert.NotNull(eval);
}
}