public void ClassificationRandomModelSelectingEnsembleLearner_Learn()
{
var learners = new IIndexedLearner <ProbabilityPrediction>[]
{
new ClassificationDecisionTreeLearner(2),
new ClassificationDecisionTreeLearner(5),
new ClassificationDecisionTreeLearner(7),
new ClassificationDecisionTreeLearner(9),
new ClassificationDecisionTreeLearner(11),
new ClassificationDecisionTreeLearner(21),
new ClassificationDecisionTreeLearner(23),
new ClassificationDecisionTreeLearner(1),
new ClassificationDecisionTreeLearner(14),
new ClassificationDecisionTreeLearner(17),
new ClassificationDecisionTreeLearner(19),
new ClassificationDecisionTreeLearner(33)
};
var sut = new ClassificationRandomModelSelectingEnsembleLearner(learners, 5);
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var model = sut.Learn(observations, targets);
var predictions = model.PredictProbability(observations);
var metric = new LogLossClassificationProbabilityMetric();
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.60969181130388794, actual, 0.0001);
}
public void ClassificationModelSelectingEnsembleLearner_Learn_Start_With_3_Models()
{
var learners = new IIndexedLearner <ProbabilityPrediction>[]
{
new ClassificationDecisionTreeLearner(2),
new ClassificationDecisionTreeLearner(5),
new ClassificationDecisionTreeLearner(7),
new ClassificationDecisionTreeLearner(9),
new ClassificationDecisionTreeLearner(11),
new ClassificationDecisionTreeLearner(21),
new ClassificationDecisionTreeLearner(23),
new ClassificationDecisionTreeLearner(1),
new ClassificationDecisionTreeLearner(14),
new ClassificationDecisionTreeLearner(17),
new ClassificationDecisionTreeLearner(19),
new ClassificationDecisionTreeLearner(33)
};
var metric = new LogLossClassificationProbabilityMetric();
var ensembleStrategy = new MeanProbabilityClassificationEnsembleStrategy();
var ensembleSelection = new ForwardSearchClassificationEnsembleSelection(metric, ensembleStrategy, 5, 3, true);
var sut = new ClassificationModelSelectingEnsembleLearner(learners, new RandomCrossValidation <ProbabilityPrediction>(5, 23),
ensembleStrategy, ensembleSelection);
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var model = sut.Learn(observations, targets);
var predictions = model.PredictProbability(observations);
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.55183985816428427, actual, 0.0001);
}
public void ClassificationEnsembleLearner_Learn_Indexed()
{
var learners = new IIndexedLearner <ProbabilityPrediction>[]
{
new ClassificationDecisionTreeLearner(2),
new ClassificationDecisionTreeLearner(5),
new ClassificationDecisionTreeLearner(7),
new ClassificationDecisionTreeLearner(9)
};
var sut = new ClassificationEnsembleLearner(learners,
new MeanProbabilityClassificationEnsembleStrategy());
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var indices = Enumerable.Range(0, 25).ToArray();
var model = sut.Learn(observations, targets, indices);
var predictions = model.Predict(observations);
var metric = new TotalErrorClassificationMetric <double>();
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.67289719626168221, actual, 0.0001);
}
public void ClassificationBackwardEliminationModelSelectingEnsembleLearner_Learn_Indexed()
{
var learners = new IIndexedLearner <ProbabilityPrediction>[]
{
new ClassificationDecisionTreeLearner(2),
new ClassificationDecisionTreeLearner(5),
new ClassificationDecisionTreeLearner(7),
new ClassificationDecisionTreeLearner(9),
new ClassificationDecisionTreeLearner(11),
new ClassificationDecisionTreeLearner(21),
new ClassificationDecisionTreeLearner(23),
new ClassificationDecisionTreeLearner(1),
new ClassificationDecisionTreeLearner(14),
new ClassificationDecisionTreeLearner(17),
new ClassificationDecisionTreeLearner(19),
new ClassificationDecisionTreeLearner(33)
};
var metric = new LogLossClassificationProbabilityMetric();
var ensembleStrategy = new MeanProbabilityClassificationEnsembleStrategy();
var sut = new ClassificationBackwardEliminationModelSelectingEnsembleLearner(learners, 5,
new RandomCrossValidation <ProbabilityPrediction>(5, 23), ensembleStrategy, metric);
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var indices = Enumerable.Range(0, 25).ToArray();
var model = sut.Learn(observations, targets, indices);
var predictions = model.PredictProbability(observations);
var actual = metric.Error(targets, predictions);
Assert.AreEqual(2.3682546920482164, actual, 0.0001);
}
public void ClassificationRandomModelSelectingEnsembleLearner_Learn_Without_Replacement()
{
var learners = new IIndexedLearner <ProbabilityPrediction>[]
{
new ClassificationDecisionTreeLearner(2),
new ClassificationDecisionTreeLearner(5),
new ClassificationDecisionTreeLearner(7),
new ClassificationDecisionTreeLearner(9),
new ClassificationDecisionTreeLearner(11),
new ClassificationDecisionTreeLearner(21),
new ClassificationDecisionTreeLearner(23),
new ClassificationDecisionTreeLearner(1),
new ClassificationDecisionTreeLearner(14),
new ClassificationDecisionTreeLearner(17),
new ClassificationDecisionTreeLearner(19),
new ClassificationDecisionTreeLearner(33)
};
var metric = new LogLossClassificationProbabilityMetric();
var ensembleStrategy = new MeanProbabilityClassificationEnsembleStrategy();
var sut = new ClassificationRandomModelSelectingEnsembleLearner(learners, 5,
new StratifiedCrossValidation <ProbabilityPrediction>(5, 23), ensembleStrategy, metric, 1, false);
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var model = sut.Learn(observations, targets);
var predictions = model.PredictProbability(observations);
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.5805783545646459, actual, 0.0001);
}
public void ClassificationStackingEnsembleLearner_CreateMetaFeatures_Then_Learn()
{
var learners = new IIndexedLearner <ProbabilityPrediction>[]
{
new ClassificationDecisionTreeLearner(2),
new ClassificationDecisionTreeLearner(5),
new ClassificationDecisionTreeLearner(7),
new ClassificationDecisionTreeLearner(9)
};
var sut = new ClassificationStackingEnsembleLearner(learners, new ClassificationDecisionTreeLearner(9),
new RandomCrossValidation <ProbabilityPrediction>(5, 23), false);
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var metaObservations = sut.LearnMetaFeatures(observations, targets);
var model = sut.LearnStackingModel(observations, metaObservations, targets);
var predictions = model.Predict(observations);
var metric = new TotalErrorClassificationMetric <double>();
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.63551401869158874, actual, 0.0001);
}
public void ClassificationBackwardEliminationModelSelectingEnsembleLearner_CreateMetaFeatures_Then_Learn()
{
var learners = new IIndexedLearner <ProbabilityPrediction>[]
{
new ClassificationDecisionTreeLearner(2),
new ClassificationDecisionTreeLearner(5),
new ClassificationDecisionTreeLearner(7),
new ClassificationDecisionTreeLearner(9),
new ClassificationDecisionTreeLearner(11),
new ClassificationDecisionTreeLearner(21),
new ClassificationDecisionTreeLearner(23),
new ClassificationDecisionTreeLearner(1),
new ClassificationDecisionTreeLearner(14),
new ClassificationDecisionTreeLearner(17),
new ClassificationDecisionTreeLearner(19),
new ClassificationDecisionTreeLearner(33)
};
var sut = new ClassificationBackwardEliminationModelSelectingEnsembleLearner(learners, 5);
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var metaObservations = sut.LearnMetaFeatures(observations, targets);
var model = sut.SelectModels(observations, metaObservations, targets);
var predictions = model.PredictProbability(observations);
var metric = new LogLossClassificationProbabilityMetric();
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.52351727716455632, actual, 0.0001);
}
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);
}
double ClassificationDecisionTreeLearner_Learn_Glass(int treeDepth)
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new ClassificationDecisionTreeLearner(treeDepth, 1, observations.ColumnCount, 0.001, 42);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var error = evaluator.Error(targets, predictions);
return(error);
}
public void RegressionRandomForestLearnerTest_Learn_Glass_100_Trees_Parallel()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new RegressionRandomForestLearner(100, 1, 100, 1, 0.0001, 1.0, 42, true);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.22701441864756075, error, m_delta);
}
public void ClassificationAdaBoostLearner_Learn_Glass()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new ClassificationAdaBoostLearner(10, 1, 5);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.0, actual);
}
double RegressionRandomForestLearnerTest_Learn_Glass(int trees, double subSampleRatio = 1.0)
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new RegressionRandomForestLearner(trees, 1, 100, 1, 0.0001, subSampleRatio, 42, false);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var error = evaluator.Error(targets, predictions);
return(error);
}
double ClassificationExtremelyRandomizedTreesLearner_Learn_Glass(int trees, double subSampleRatio = 1.0)
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new ClassificationExtremelyRandomizedTreesLearner(trees, 1, 100, 1, 0.0001, subSampleRatio, 42, false);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var error = evaluator.Error(targets, predictions);
return(error);
}
public void RegressionAdaBoostLearner_Learn_Glass()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new RegressionAdaBoostLearner(10);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new MeanAbsolutErrorRegressionMetric();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.54723570404775324, actual);
}
public void ClassificationRandomForestLearner_Learn_Glass_100_Trees_Parallel()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new ClassificationRandomForestLearner(100, 1, 100, 1, 0.0001, 1.0, 42, true);
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.018691588785046728, error, m_delta);
}
public void RegressionXGBoostLearner_Learn()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = CreateLearner();
using (var model = sut.Learn(observations, targets))
{
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.0795934933096642, error, m_delta);
}
}
double ClassificationDecisionTreeLearner_Learn_Glass_Weighted(int treeDepth, double weight)
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var weights = targets.Select(v => Weight(v, 1, weight)).ToArray();
var sut = new ClassificationDecisionTreeLearner(treeDepth, 1, observations.ColumnCount, 0.001, 42);
var model = sut.Learn(observations, targets, weights);
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
Trace.WriteLine(evaluator.ErrorString(targets, predictions));
var error = evaluator.Error(targets, predictions);
return(error);
}
public void ClassificationXGBoostLearner_Learn()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = CreateLearner();
using (var model = sut.Learn(observations, targets))
{
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.17757009345794392, error, m_delta);
}
}
public void BestFirstTreeBuilder_Build_Leaf_Nodes_4()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new DecisionTreeLearner(new BestFirstTreeBuilder(2000, 4, observations.ColumnCount, 0.000001, 42,
new OnlyUniqueThresholdsSplitSearcher(1), new GiniClassificationImpurityCalculator()));
var model = new ClassificationDecisionTreeModel(sut.Learn(observations, targets));
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.37383177570093457, actual, 0.00001);
}
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 ClassificationRandomForestLearner_Learn_Glass_100_Indices()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new ClassificationRandomForestLearner(100, 1, 100, 1, 0.0001, 1.0, 42, 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 evaluator = new TotalErrorClassificationMetric <double>();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.098130841121495324, error, m_delta);
}
public void RegressionXGBoostModel_Save_Load()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var learner = CreateLearner();
var sut = learner.Learn(observations, targets);
var predictions = sut.Predict(observations);
var modelFilePath = "model.xgb";
using (var sutPreSave = learner.Learn(observations, targets))
{
AssertModel(observations, targets, sutPreSave);
sutPreSave.Save(modelFilePath);
}
using (var sutAfterSave = RegressionXGBoostModel.Load(modelFilePath))
{
AssertModel(observations, targets, sutAfterSave);
}
}
public void RegressionRandomForestLearnerTest_Learn_Glass_100_Indices()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new RegressionRandomForestLearner(100, 1, 100, 1, 0.0001, 1.0, 42, 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 evaluator = new MeanSquaredErrorRegressionMetric();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.49709813080602938, error, m_delta);
}
public void RegressionXGBoostModel_Predict_Single()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var learner = CreateLearner();
using (var sut = learner.Learn(observations, targets))
{
var rows = targets.Length;
var predictions = new double[rows];
for (int i = 0; i < rows; i++)
{
predictions[i] = sut.Predict(observations.Row(i));
}
var evaluator = new MeanSquaredErrorRegressionMetric();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.0795934933096642, error, m_delta);
}
}
public void ClassificationXGBoostLearner_Learn_indexed()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var indices = Enumerable.Range(0, targets.Length).ToArray();
indices.Shuffle(new Random(42));
indices = indices.Take((int)(targets.Length * 0.7))
.ToArray();
var sut = CreateLearner();
using (var model = sut.Learn(observations, targets, indices))
{
var predictions = model.Predict(observations);
var evaluator = new TotalErrorClassificationMetric <double>();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.228971962616822, error, m_delta);
}
}
public void ClassificationAdaBoostLearner_Learn_Glass_Indexed()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new ClassificationAdaBoostLearner(10, 1, 5);
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(0.0, actual);
}
public void RegressionXGBoostLearner_Learn_Indexed()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var indices = Enumerable.Range(0, targets.Length).ToArray();
indices.Shuffle(new Random(42));
indices = indices.Take((int)(targets.Length * 0.7))
.ToArray();
var sut = CreateLearner();
using (var model = sut.Learn(observations, targets, indices))
{
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var error = evaluator.Error(targets, predictions);
Assert.AreEqual(0.33589853954956522, error, m_delta);
}
}
public void ClassificationBinomialGradientBoostLearner_MultiClass_Stochastic_FeaturePrSplit_Learn_Indexed()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
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);
}
public void RegressionAbsoluteLossGradientBoostLearner_Learn_Indexed()
{
var(observations, targets) = DataSetUtilities.LoadGlassDataSet();
var sut = new RegressionAbsoluteLossGradientBoostLearner(50, 0.1, 3, 1, 1e-6, 1.0, 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 MeanAbsolutErrorRegressionMetric();
var actual = evaluator.Error(indexedTargets, indexedPredictions);
Assert.AreEqual(0.41246374405350877, actual, 0.0001);
}
