public void ClassificationGradientBoostLearner_LearnWithEarlyStopping_ToFewIterations()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var splitter = new StratifiedTrainingTestIndexSplitter <double>(0.6, 1234);
var split = splitter.SplitSet(observations, targets);
var sut = new ClassificationBinomialGradientBoostLearner(10, 0.01, 9, 1, 1e-6, .5, 1);
var evaluator = new TotalErrorClassificationMetric <double>();
var model = sut.LearnWithEarlyStopping(split.TrainingSet.Observations, split.TrainingSet.Targets,
split.TestSet.Observations, split.TestSet.Targets, evaluator, 10);
}
public void ClassificationBinomialGradientBoostLearner_MultiClass_Learn()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new ClassificationBinomialGradientBoostLearner(30, 0.1, 3, 1, 1e-6, 1.0, 0, false);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.018691588785046728, actual);
}
public void ClassificationBinomialGradientBoostLearner_Stochastic_Learn()
{
var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet();
var sut = new ClassificationBinomialGradientBoostLearner(50, 0.1, 3, 1, 1e-6, .3, 0, false);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.076923076923076927, actual);
}
public void ClassificationGradientBoostLearner_LearnWithEarlyStopping_ToFewIterations()
{
var parser = new CsvParser(() => new StringReader(Resources.Glass));
var observations = parser.EnumerateRows(r => r != "Target").ToF64Matrix();
var targets = parser.EnumerateRows("Target").ToF64Vector();
var splitter = new StratifiedTrainingTestIndexSplitter <double>(0.6, 1234);
var split = splitter.SplitSet(observations, targets);
var sut = new ClassificationBinomialGradientBoostLearner(10, 0.01, 9, 1, 1e-6, .5, 1);
var evaluator = new TotalErrorClassificationMetric <double>();
var model = sut.LearnWithEarlyStopping(split.TrainingSet.Observations, split.TrainingSet.Targets,
split.TestSet.Observations, split.TestSet.Targets, evaluator, 10);
}
public void ClassificationBinomialGradientBoostLearner_Stochastic_Learn()
{
var parser = new CsvParser(() => new StringReader(Resources.AptitudeData));
var observations = parser.EnumerateRows("AptitudeTestScore", "PreviousExperience_month").ToF64Matrix();
var targets = parser.EnumerateRows("Pass").ToF64Vector();
var sut = new ClassificationBinomialGradientBoostLearner(50, 0.1, 3, 1, 1e-6, .3, 0, false);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.076923076923076927, actual);
}
public void ClassificationBinomialGradientBoostLearner_MultiClass_Stochastic_Learn()
{
var parser = new CsvParser(() => new StringReader(Resources.Glass));
var observations = parser.EnumerateRows(r => r != "Target").ToF64Matrix();
var targets = parser.EnumerateRows("Target").ToF64Vector();
var sut = new ClassificationBinomialGradientBoostLearner(30, 0.1, 3, 1, 1e-6, 0.5, 0, false);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.046728971962616821, actual);
}
public void ClassificationGradientBoostLearner_LearnWithEarlyStopping()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var splitter = new StratifiedTrainingTestIndexSplitter <double>(0.6, 1234);
var split = splitter.SplitSet(observations, targets);
var sut = new ClassificationBinomialGradientBoostLearner(100, 0.01, 9, 1, 1e-6, .5, 0, false);
var evaluator = new TotalErrorClassificationMetric <double>();
var model = sut.LearnWithEarlyStopping(split.TrainingSet.Observations, split.TrainingSet.Targets,
split.TestSet.Observations, split.TestSet.Targets, evaluator, 10);
var predictions = model.Predict(split.TestSet.Observations);
var actual = evaluator.Error(split.TestSet.Targets, predictions);
Assert.AreEqual(0.16279069767441862, actual, 0.000001);
Assert.AreEqual(90, model.Trees.First().ToArray().Length);
}
public void ClassificationGradientBoostLearner_LearnWithEarlyStopping()
{
var parser = new CsvParser(() => new StringReader(Resources.Glass));
var observations = parser.EnumerateRows(r => r != "Target").ToF64Matrix();
var targets = parser.EnumerateRows("Target").ToF64Vector();
var splitter = new StratifiedTrainingTestIndexSplitter <double>(0.6, 1234);
var split = splitter.SplitSet(observations, targets);
var sut = new ClassificationBinomialGradientBoostLearner(100, 0.01, 9, 1, 1e-6, .5, 0, false);
var evaluator = new TotalErrorClassificationMetric <double>();
var model = sut.LearnWithEarlyStopping(split.TrainingSet.Observations, split.TrainingSet.Targets,
split.TestSet.Observations, split.TestSet.Targets, evaluator, 10);
var predictions = model.Predict(split.TestSet.Observations);
var actual = evaluator.Error(split.TestSet.Targets, predictions);
Assert.AreEqual(0.16279069767441862, actual, 0.000001);
Assert.AreEqual(90, model.Trees.First().ToArray().Length);
}
public void ClassificationBinomialGradientBoostLearner_Stochastic_Learn_Indexed()
{
var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet();
var sut = new ClassificationBinomialGradientBoostLearner(30, 0.1, 3, 1, 1e-6, .5, 0, false);
var indices = Enumerable.Range(0, targets.Length).ToArray();
indices.Shuffle(new Random(42));
indices = indices.Take((int)(targets.Length * 0.7))
.ToArray();
var model = sut.Learn(observations, targets, indices);
var predictions = model.Predict(observations);
var indexedPredictions = predictions.GetIndices(indices);
var indexedTargets = targets.GetIndices(indices);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(indexedTargets, indexedPredictions);
Assert.AreEqual(0.055555555555555552, actual);
}
public void ClassificationBinomialGradientBoostLearner_Stochastic_Learn_Indexed()
{
var parser = new CsvParser(() => new StringReader(Resources.AptitudeData));
var observations = parser.EnumerateRows("AptitudeTestScore", "PreviousExperience_month").ToF64Matrix();
var targets = parser.EnumerateRows("Pass").ToF64Vector();
var sut = new ClassificationBinomialGradientBoostLearner(30, 0.1, 3, 1, 1e-6, .5, 0, false);
var indices = Enumerable.Range(0, targets.Length).ToArray();
indices.Shuffle(new Random(42));
indices = indices.Take((int)(targets.Length * 0.7))
.ToArray();
var model = sut.Learn(observations, targets, indices);
var predictions = model.Predict(observations);
var indexedPredictions = predictions.GetIndices(indices);
var indexedTargets = targets.GetIndices(indices);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(indexedTargets, indexedPredictions);
Assert.AreEqual(0.055555555555555552, actual);
}
public void ClassificationBinomialGradientBoostLearner_MultiClass_Stochastic_FeaturePrSplit_Learn_Indexed()
{
var parser = new CsvParser(() => new StringReader(Resources.Glass));
var observations = parser.EnumerateRows(v => v != "Target").ToF64Matrix();
var targets = parser.EnumerateRows("Target").ToF64Vector();
var sut = new ClassificationBinomialGradientBoostLearner(30, 0.1, 3, 1, 1e-6, 0.5, 3, false);
var indices = Enumerable.Range(0, targets.Length).ToArray();
indices.Shuffle(new Random(42));
indices = indices.Take((int)(targets.Length * 0.7))
.ToArray();
var model = sut.Learn(observations, targets, indices);
var predictions = model.Predict(observations);
var indexedPredictions = predictions.GetIndices(indices);
var indexedTargets = targets.GetIndices(indices);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(indexedTargets, indexedPredictions);
Assert.AreEqual(0.033557046979865772, actual);
}
