public void RegressionStackingEnsembleModel_Predict_Multiple()
{
var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet();
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var learner = new RegressionStackingEnsembleLearner(learners,
new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var sut = learner.Learn(observations, targets);
var predictions = sut.Predict(observations);
var metric = new MeanSquaredErrorRegressionMetric();
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.26175213675213671, actual, 0.0000001);
}
public void RegressionStackingEnsembleLearner_Learn_Indexed()
{
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var sut = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var(observations, targets) = DataSetUtilities.LoadDecisionTreeDataSet();
var indices = Enumerable.Range(0, 25).ToArray();
var model = sut.Learn(observations, targets, indices);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.133930222950635, actual, 0.0001);
}
public void RegressionStackingEnsembleModel_GetRawVariableImportance()
{
var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet();
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var learner = new RegressionStackingEnsembleLearner(learners,
new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var sut = learner.Learn(observations, targets);
var actual = sut.GetRawVariableImportance();
var expected = new double[] { 0.255311355311355, 0.525592463092463, 0.753846153846154, 0.0128205128205128 };
Assert.AreEqual(expected.Length, actual.Length);
for (int i = 0; i < expected.Length; i++)
{
Assert.AreEqual(expected[i], actual[i], 0.000001);
}
}
public void RegressionStackingEnsembleLearner_CreateMetaFeatures_Then_Learn()
{
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var sut = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var(observations, targets) = DataSetUtilities.LoadDecisionTreeDataSet();
var metaObservations = sut.LearnMetaFeatures(observations, targets);
var model = sut.LearnStackingModel(observations, metaObservations, targets);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.06951934687172627, actual, 0.0001);
}
public void RegressionStackingEnsembleModel_Predict_Multiple()
{
var parser = new CsvParser(() => new StringReader(Resources.AptitudeData));
var observations = parser.EnumerateRows(v => v != "Pass").ToF64Matrix();
var targets = parser.EnumerateRows("Pass").ToF64Vector();
var rows = targets.Length;
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var learner = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var sut = learner.Learn(observations, targets);
var predictions = sut.Predict(observations);
var metric = new MeanSquaredErrorRegressionMetric();
var actual = metric.Error(targets, predictions);
Assert.AreEqual(0.26175213675213671, actual, 0.0000001);
}
public void RegressionStackingEnsembleModel_GetRawVariableImportance()
{
var parser = new CsvParser(() => new StringReader(Resources.AptitudeData));
var observations = parser.EnumerateRows(v => v != "Pass").ToF64Matrix();
var targets = parser.EnumerateRows("Pass").ToF64Vector();
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var learner = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var sut = learner.Learn(observations, targets);
var actual = sut.GetRawVariableImportance();
var expected = new double[] { 0.255311355311355, 0.525592463092463, 0.753846153846154, 0.0128205128205128 };
Assert.AreEqual(expected.Length, actual.Length);
for (int i = 0; i < expected.Length; i++)
{
Assert.AreEqual(expected[i], actual[i], 0.000001);
}
}
public void RegressionStackingEnsembleLearner_Learn_Keep_Original_Features()
{
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var sut = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), true);
var parser = new CsvParser(() => new StringReader(Resources.DecisionTreeData));
var observations = parser.EnumerateRows("F1", "F2").ToF64Matrix();
var targets = parser.EnumerateRows("T").ToF64Vector();
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.066184865331534531, actual, 0.0001);
}
public void RegressionStackingEnsembleLearner_CreateMetaFeatures_Then_Learn()
{
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var sut = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var parser = new CsvParser(() => new StringReader(Resources.DecisionTreeData));
var observations = parser.EnumerateRows("F1", "F2").ToF64Matrix();
var targets = parser.EnumerateRows("T").ToF64Vector();
var metaObservations = sut.LearnMetaFeatures(observations, targets);
var model = sut.LearnStackingModel(observations, metaObservations, targets);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.06951934687172627, actual, 0.0001);
}
public void RegressionStackingEnsembleLearner_Learn_Indexed()
{
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var sut = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var parser = new CsvParser(() => new StringReader(Resources.DecisionTreeData));
var observations = parser.EnumerateRows("F1", "F2").ToF64Matrix();
var targets = parser.EnumerateRows("T").ToF64Vector();
var indices = Enumerable.Range(0, 25).ToArray();
var model = sut.Learn(observations, targets, indices);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.133930222950635, actual, 0.0001);
}
public void RegressionStackingEnsembleLearner_Learn_Keep_Original_Features()
{
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var sut = new RegressionStackingEnsembleLearner(learners, new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), true);
var(observations, targets) = DataSetUtilities.LoadDecisionTreeDataSet();
var model = sut.Learn(observations, targets);
var predictions = model.Predict(observations);
var evaluator = new MeanSquaredErrorRegressionMetric();
var actual = evaluator.Error(targets, predictions);
Assert.AreEqual(0.066184865331534531, actual, 0.0001);
}
public void RegressionStackingEnsembleModel_GetVariableImportance()
{
var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet();
var featureNameToIndex = new Dictionary <string, int> {
{ "AptitudeTestScore", 0 },
{ "PreviousExperience_month", 1 }
};
var learners = new IIndexedLearner <double>[]
{
new RegressionDecisionTreeLearner(2),
new RegressionDecisionTreeLearner(5),
new RegressionDecisionTreeLearner(7),
new RegressionDecisionTreeLearner(9)
};
var learner = new RegressionStackingEnsembleLearner(learners,
new RegressionDecisionTreeLearner(9),
new RandomCrossValidation <double>(5, 23), false);
var sut = learner.Learn(observations, targets);
var actual = sut.GetVariableImportance(featureNameToIndex);
var expected = new Dictionary <string, double> {
{ "RegressionDecisionTreeModel_2", 100 }, { "RegressionDecisionTreeModel_1", 69.7214491857349 }, { "RegressionDecisionTreeModel_0", 33.8678328474247 }, { "RegressionDecisionTreeModel_3", 1.70068027210884 }
};
Assert.AreEqual(expected.Count, actual.Count);
var zip = expected.Zip(actual, (e, a) => new { Expected = e, Actual = a });
foreach (var item in zip)
{
Assert.AreEqual(item.Expected.Key, item.Actual.Key);
Assert.AreEqual(item.Expected.Value, item.Actual.Value, 0.000001);
}
}