public void ClassificationEnsembleModel_PredictProbability_single() { var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet(); var learners = new IIndexedLearner <ProbabilityPrediction>[] { new ClassificationDecisionTreeLearner(2), new ClassificationDecisionTreeLearner(5), new ClassificationDecisionTreeLearner(7), new ClassificationDecisionTreeLearner(9) }; var learner = new ClassificationEnsembleLearner(learners, new MeanProbabilityClassificationEnsembleStrategy()); var sut = learner.Learn(observations, targets); var rows = targets.Length; var predictions = new ProbabilityPrediction[rows]; for (int i = 0; i < rows; i++) { predictions[i] = sut.PredictProbability(observations.Row(i)); } var metric = new LogLossClassificationProbabilityMetric(); var actual = metric.Error(targets, predictions); Assert.AreEqual(0.32562112824941963, actual, 0.0000001); }
public void ClassificationStackingEnsembleModel_PredictProbability_single() { 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 <ProbabilityPrediction>[] { new ClassificationDecisionTreeLearner(2), new ClassificationDecisionTreeLearner(5), new ClassificationDecisionTreeLearner(7), new ClassificationDecisionTreeLearner(9) }; var learner = new ClassificationStackingEnsembleLearner(learners, new ClassificationDecisionTreeLearner(9), new RandomCrossValidation <ProbabilityPrediction>(5, 23), false); var sut = learner.Learn(observations, targets); var predictions = new ProbabilityPrediction[rows]; for (int i = 0; i < rows; i++) { predictions[i] = sut.PredictProbability(observations.Row(i)); } var metric = new LogLossClassificationProbabilityMetric(); var actual = metric.Error(targets, predictions); Assert.AreEqual(0.6696598716465223, actual, 0.0000001); }
public void LogLossClassificationMetric_ErrorString_TargetStringMapping() { var sut = new LogLossClassificationProbabilityMetric(1e-15); var predictions = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 1.0 }, { 1, 1.0 }, { 2, 1.0 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1, 1.0 }, { 2, 0.0 } }), new ProbabilityPrediction(2, new Dictionary <double, double> { { 0, 0.0 }, { 1, 0.0 }, { 2, 1.0 } }), }; var targets = new double[] { 0, 1, 2 }; var targetStringMapping = new Dictionary <double, string> { { 0, "One" }, { 1, "Two" }, { 2, "Three" } }; var actual = sut.ErrorString(targets, predictions, targetStringMapping); var expected = ";One;Two;Three;One;Two;Three\r\nOne;1.000;0.000;0.000;100.000;0.000;0.000\r\nTwo;0.000;1.000;0.000;0.000;100.000;0.000\r\nThree;0.000;0.000;1.000;0.000;0.000;100.000\r\nError: 36.620\r\n"; Assert.AreEqual(expected, actual); }
public void ClassificationNeuralNetModel_PredictProbability_Single() { var numberOfObservations = 500; var numberOfFeatures = 5; var numberOfClasses = 5; var random = new Random(32); var observations = new F64Matrix(numberOfObservations, numberOfFeatures); observations.Map(() => random.NextDouble()); var targets = Enumerable.Range(0, numberOfObservations) .Select(i => (double)random.Next(0, numberOfClasses)).ToArray(); var sut = ClassificationNeuralNetModel.Load(() => new StringReader(m_classificationNeuralNetModelText)); var predictions = new ProbabilityPrediction[numberOfObservations]; for (int i = 0; i < numberOfObservations; i++) { predictions[i] = sut.PredictProbability(observations.Row(i)); } var evaluator = new TotalErrorClassificationMetric <double>(); var actual = evaluator.Error(targets, predictions.Select(p => p.Prediction).ToArray()); Assert.AreEqual(0.762, actual); }
public void ClassificationStackingEnsembleModel_PredictProbability_single() { var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet(); var learners = new IIndexedLearner <ProbabilityPrediction>[] { new ClassificationDecisionTreeLearner(2), new ClassificationDecisionTreeLearner(5), new ClassificationDecisionTreeLearner(7), new ClassificationDecisionTreeLearner(9) }; var learner = new ClassificationStackingEnsembleLearner(learners, new ClassificationDecisionTreeLearner(9), new RandomCrossValidation <ProbabilityPrediction>(5, 23), false); var sut = learner.Learn(observations, targets); var rows = targets.Length; var predictions = new ProbabilityPrediction[rows]; for (int i = 0; i < rows; i++) { predictions[i] = sut.PredictProbability(observations.Row(i)); } var metric = new LogLossClassificationProbabilityMetric(); var actual = metric.Error(targets, predictions); Assert.AreEqual(0.6696598716465223, actual, 0.0000001); }
public void RocAucClassificationMetric_Error_Not_Binary() { var targets = new double[] { 0, 1, 2 }; var probabilities = new ProbabilityPrediction[0]; var sut = new RocAucClassificationProbabilityMetric(1); var actual = sut.Error(targets, probabilities); }
public void RocAucClassificationMetric_Error() { var targets = new double[] { 1, 0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1 }; var probabilities = new ProbabilityPrediction[] { new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.052380952 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.020725389 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.993377483 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.020725389 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.020725389 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.111111111 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.193377483 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.793377483 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.020725389 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.012345679 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.885860173 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.714285714 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.985860173 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.020725389 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.985860173 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.993377483 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.993377483 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.954545455 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.020725389 } }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.020725389 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.985860173 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 0.985860173 } }) }; var sut = new RocAucClassificationProbabilityMetric(1); var actual = sut.Error(targets, probabilities); Assert.AreEqual(0.0085470085470086277, actual, 0.00001); }
/// <summary> /// Predicts the observation subset provided by indices with probabilities /// </summary> /// <param name="observations"></param> /// <param name="indices"></param> /// <returns></returns> public ProbabilityPrediction[] PredictProbability(F64Matrix observations, int[] indices) { var rows = observations.RowCount; var predictions = new ProbabilityPrediction[indices.Length]; for (int i = 0; i < indices.Length; i++) { predictions[i] = Tree.PredictProbability(observations.Row(indices[i])); } return(predictions); }
/// <summary> /// Predicts a set of observations with probabilities /// </summary> /// <param name="observations"></param> /// <returns></returns> public ProbabilityPrediction[] PredictProbability(F64Matrix observations) { var rows = observations.RowCount; var predictions = new ProbabilityPrediction[rows]; for (int i = 0; i < rows; i++) { predictions[i] = PredictProbability(observations.Row(i)); } return(predictions); }
public void RocAucClassificationMetric_Error_No_Error() { var targets = new double[] { 0, 1 }; var probabilities = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0 }, { 1.0, 0.0 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 1 } }) }; var sut = new RocAucClassificationProbabilityMetric(1); var actual = sut.Error(targets, probabilities); Assert.AreEqual(0.0, actual); }
/// <summary> /// Predicts a single observation using the ensembled probabilities /// </summary> /// <param name="observation"></param> /// <returns></returns> public ProbabilityPrediction PredictProbability(double[] observation) { var ensembleCols = m_ensembleModels.Length; var ensemblePredictions = new ProbabilityPrediction[ensembleCols]; for (int i = 0; i < m_ensembleModels.Length; i++) { ensemblePredictions[i] = m_ensembleModels[i].Predict(observation); } return(m_ensembleStrategy.Combine(ensemblePredictions)); }
/// <summary> /// Predicts a set of observations using the ensembled probabilities /// </summary> /// <param name="observations"></param> /// <returns></returns> public ProbabilityPrediction[] PredictProbability(F64Matrix observations) { var predictions = new ProbabilityPrediction[observations.RowCount]; var observation = new double[observations.ColumnCount]; for (int i = 0; i < observations.RowCount; i++) { observations.Row(i, observation); predictions[i] = PredictProbability(observation); } return(predictions); }
/// <summary> /// Geometric mean probability classification ensemble strategy. Class probabilities are combined using the geometric mean across all models. /// </summary> /// <param name="ensemblePredictions"></param> /// <param name="predictions"></param> public void Combine(ProbabilityPrediction[][] ensemblePredictions, ProbabilityPrediction[] predictions) { var currentObservation = new ProbabilityPrediction[ensemblePredictions.Length]; for (int i = 0; i < predictions.Length; i++) { for (int j = 0; j < currentObservation.Length; j++) { currentObservation[j] = ensemblePredictions[j][i]; } predictions[i] = Combine(currentObservation); } }
public void RandomClassificationEnsembleSelection_Constructor_Number_Of_Availible_Models_Lower_Than_Number_Of_Models_To_Select() { var sut = new RandomClassificationEnsembleSelection( new LogLossClassificationProbabilityMetric(), new MeanProbabilityClassificationEnsembleStrategy(), 5, 1, true); var observations = new ProbabilityPrediction[3][]; observations.Select(t => new ProbabilityPrediction[10]).ToArray(); var targets = new double[10]; sut.Select(observations, targets); }
public void RocAucClassificationMetric_ErrorString() { var targets = new double[] { 0, 1 }; var probabilities = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0 }, { 1.0, 0.0 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 1 } }) }; var sut = new RocAucClassificationProbabilityMetric(1); var actual = sut.ErrorString(targets, probabilities); var expected = ";0;1;0;1\r\n0;1.000;0.000;100.000;0.000\r\n1;0.000;1.000;0.000;100.000\r\nError: 0.000\r\n"; Assert.AreEqual(expected, actual); }
/// <summary> /// /// </summary> /// <param name="observations"></param> /// <returns></returns> public ProbabilityPrediction[] PredictProbability(F64Matrix observations) { var rows = observations.RowCount; var cols = observations.ColumnCount; var observation = new double[cols]; var predictions = new ProbabilityPrediction[rows]; for (int row = 0; row < rows; row++) { observations.Row(row, observation); predictions[row] = PredictProbability(observation); } return(predictions); }
public void RocAucClassificationMetric_ErrorString_TargetStringMapping() { var targets = new double[] { 0, 1 }; var probabilities = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0 }, { 1.0, 0.0 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1.0, 1 } }) }; var sut = new RocAucClassificationProbabilityMetric(1); var targetStringMapping = new Dictionary <double, string> { { 0, "Negative" }, { 1, "Positive" } }; var actual = sut.ErrorString(targets, probabilities, targetStringMapping); var expected = ";Negative;Positive;Negative;Positive\r\nNegative;1.000;0.000;100.000;0.000\r\nPositive;0.000;1.000;0.000;100.000\r\nError: 0.000\r\n"; Assert.AreEqual(expected, actual); }
double SelectNextModelToAdd(ProbabilityPrediction[][] crossValidatedModelPredictions, double[] targets, double currentBestError) { var rows = crossValidatedModelPredictions.First().Length; var candidateModelMatrix = new ProbabilityPrediction[m_selectedModelIndices.Count + 1][]; var candidatePredictions = new ProbabilityPrediction[rows]; var candidateModelIndices = new int[m_selectedModelIndices.Count + 1]; var bestError = currentBestError; var bestIndex = -1; foreach (var index in m_remainingModelIndices) { m_selectedModelIndices.CopyTo(candidateModelIndices); candidateModelIndices[candidateModelIndices.Length - 1] = index; for (int i = 0; i < candidateModelIndices.Length; i++) { candidateModelMatrix[i] = crossValidatedModelPredictions[candidateModelIndices[i]]; } m_ensembleStrategy.Combine(candidateModelMatrix, candidatePredictions); var error = m_metric.Error(targets, candidatePredictions); if (error < bestError) { bestError = error; bestIndex = index; } } if(bestIndex != -1) { m_selectedModelIndices.Add(bestIndex); if(!m_selectWithReplacement) { m_remainingModelIndices.Remove(bestIndex); } } return bestError; }
double SelectNextModelToRemove(ProbabilityPrediction[][] crossValidatedModelPredictions, double[] targets, double currentBestError) { var rows = crossValidatedModelPredictions.First().Length; var candidateModelMatrix = new ProbabilityPrediction[m_remainingModelIndices.Count - 1][]; var candidatePredictions = new ProbabilityPrediction[rows]; var candidateModelIndices = new int[m_remainingModelIndices.Count - 1]; var bestError = currentBestError; var bestIndex = -1; foreach (var index in m_remainingModelIndices) { var candidateIndex = 0; for (int i = 0; i < m_remainingModelIndices.Count; i++) { var curIndex = m_remainingModelIndices[i]; if (curIndex != index) { candidateModelIndices[candidateIndex++] = m_remainingModelIndices[i]; } } for (int i = 0; i < candidateModelIndices.Length; i++) { candidateModelMatrix[i] = crossValidatedModelPredictions[candidateModelIndices[i]]; } m_ensembleStrategy.Combine(candidateModelMatrix, candidatePredictions); var error = m_metric.Error(targets, candidatePredictions); if (error < bestError) { bestError = error; bestIndex = index; } } m_remainingModelIndices.Remove(bestIndex); return(bestError); }
public void ClassificationDecisionTreeModel_PredictProbability_Multiple_Indexed() { 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 learner = new ClassificationDecisionTreeLearner(100, 5, 2, 0.001, 42); var sut = learner.Learn(observations, targets); var indices = new int[] { 0, 3, 4, 5, 6, 7, 8, 9, 20, 21 }; var actual = sut.PredictProbability(observations, indices); var indexedTargets = targets.GetIndices(indices); var evaluator = new TotalErrorClassificationMetric <double>(); var error = evaluator.Error(indexedTargets, actual.Select(p => p.Prediction).ToArray()); Assert.AreEqual(0.1, error, 0.0000001); var expected = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.571428571428571 }, { 1, 0.428571428571429 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.571428571428571 }, { 1, 0.428571428571429 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.428571428571429 }, { 1, 0.571428571428571 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.75 }, { 1, 0.25 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.285714285714286 }, { 1, 0.714285714285714 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.75 }, { 1, 0.25 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.857142857142857 }, { 1, 0.142857142857143 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.285714285714286 }, { 1, 0.714285714285714 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.857142857142857 }, { 1, 0.142857142857143 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.285714285714286 }, { 1, 0.714285714285714 }, }), }; CollectionAssert.AreEqual(expected, actual); }
/// <summary> /// Greedy forward selection of ensemble models. /// </summary> /// <param name="crossValidatedModelPredictions">cross validated predictions from multiple models. /// Each row in the matrix corresponds to predictions from a separate model</param> /// <param name="targets">Corresponding targets</param> /// <returns>The indices of the selected model</returns> public int[] Select(ProbabilityPrediction[][] crossValidatedModelPredictions, double[] targets) { if (crossValidatedModelPredictions.Length < m_numberOfModelsToSelect) { throw new ArgumentException("Availible models: " + crossValidatedModelPredictions.Length + " is smaller than number of models to select: " + m_numberOfModelsToSelect); } m_allIndices = Enumerable.Range(0, crossValidatedModelPredictions.Length).ToArray(); var rows = crossValidatedModelPredictions.First().Length; var candidateModelMatrix = new ProbabilityPrediction[m_numberOfModelsToSelect][]; var candidatePredictions = new ProbabilityPrediction[rows]; var candidateModelIndices = new int[m_numberOfModelsToSelect]; var bestModelIndices = new int[m_numberOfModelsToSelect]; var bestError = double.MaxValue; for (int i = 0; i < m_iterations; i++) { SelectNextRandomIndices(candidateModelIndices); for (int j = 0; j < candidateModelIndices.Length; j++) { candidateModelMatrix[j] = crossValidatedModelPredictions[candidateModelIndices[j]]; } m_ensembleStrategy.Combine(candidateModelMatrix, candidatePredictions); var error = m_metric.Error(targets, candidatePredictions); if (error < bestError) { bestError = error; candidateModelIndices.CopyTo(bestModelIndices, 0); Trace.WriteLine("Models selected: " + bestModelIndices.Length + ": " + error); } } Trace.WriteLine("Selected model indices: " + string.Join(", ", bestModelIndices.ToArray())); return(bestModelIndices); }
public void LogLossClassificationMetric_Error_1() { var sut = new LogLossClassificationProbabilityMetric(1e-15); var predictions = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 1.0 }, { 1, 0.0 }, { 2, 0.0 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1, 1.0 }, { 2, 0.0 } }), new ProbabilityPrediction(2, new Dictionary <double, double> { { 0, 0.0 }, { 1, 0.0 }, { 2, 1.0 } }), }; var targets = new double[] { 0, 1, 2 }; var actual = sut.Error(targets, predictions); Assert.AreEqual(9.9920072216264128e-16, actual, 1e-17); }
public void LogLossClassificationMetric_Error_2() { var sut = new LogLossClassificationProbabilityMetric(1e-15); var predictions = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 1.0 }, { 1, 1.0 }, { 2, 1.0 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1, 1.0 }, { 2, 0.0 } }), new ProbabilityPrediction(2, new Dictionary <double, double> { { 0, 0.0 }, { 1, 0.0 }, { 2, 1.0 } }), }; var targets = new double[] { 0, 1, 2 }; var actual = sut.Error(targets, predictions); Assert.AreEqual(0.36620409622270467, actual, 0.0001); }
public void ClassificationDecisionTreeModel_PredictProbability_Multiple_Indexed() { var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet(); var learner = new ClassificationDecisionTreeLearner(100, 5, 2, 0.001, 42); var sut = learner.Learn(observations, targets); var indices = new int[] { 0, 3, 4, 5, 6, 7, 8, 9, 20, 21 }; var actual = sut.PredictProbability(observations, indices); var indexedTargets = targets.GetIndices(indices); var evaluator = new TotalErrorClassificationMetric <double>(); var error = evaluator.Error(indexedTargets, actual.Select(p => p.Prediction).ToArray()); Assert.AreEqual(0.1, error, 0.0000001); var expected = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.571428571428571 }, { 1, 0.428571428571429 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.571428571428571 }, { 1, 0.428571428571429 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.428571428571429 }, { 1, 0.571428571428571 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.75 }, { 1, 0.25 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.285714285714286 }, { 1, 0.714285714285714 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.75 }, { 1, 0.25 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.857142857142857 }, { 1, 0.142857142857143 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.285714285714286 }, { 1, 0.714285714285714 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.857142857142857 }, { 1, 0.142857142857143 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.285714285714286 }, { 1, 0.714285714285714 }, }), }; CollectionAssert.AreEqual(expected, actual); }
public void LogLossClassificationMetric_ErrorString() { var sut = new LogLossClassificationProbabilityMetric(1e-15); var predictions = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 1.0 }, { 1, 1.0 }, { 2, 1.0 } }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.0 }, { 1, 1.0 }, { 2, 0.0 } }), new ProbabilityPrediction(2, new Dictionary <double, double> { { 0, 0.0 }, { 1, 0.0 }, { 2, 1.0 } }), }; var targets = new double[] { 0, 1, 2 }; var actual = sut.ErrorString(targets, predictions); var expected = ";0;1;2;0;1;2\r\n0;1.000;0.000;0.000;100.000;0.000;0.000\r\n1;0.000;1.000;0.000;0.000;100.000;0.000\r\n2;0.000;0.000;1.000;0.000;0.000;100.000\r\nError: 36.620\r\n"; Assert.AreEqual(expected, actual); }
public void MeanProbabilityClassificationEnsembleStrategy_Combine() { var values = new ProbabilityPrediction[] { new ProbabilityPrediction(1.0, new Dictionary <double, double> { { 0.0, 0.3 }, { 1.0, 0.88 } }), new ProbabilityPrediction(0.0, new Dictionary <double, double> { { 0.0, 0.66 }, { 1.0, 0.33 } }), new ProbabilityPrediction(1.0, new Dictionary <double, double> { { 0.0, 0.01 }, { 1.0, 0.99 } }), }; var sut = new MeanProbabilityClassificationEnsembleStrategy(); var actual = sut.Combine(values); var expected = new ProbabilityPrediction(1.0, new Dictionary <double, double> { { 0.0, 0.323333333333333 }, { 1.0, 0.733333333333333 } }); Assert.AreEqual(expected, actual); }
public void GeometricMeanProbabilityClassificationEnsembleStrategy_Combine() { var values = new ProbabilityPrediction[] { new ProbabilityPrediction(1.0, new Dictionary <double, double> { { 0.0, 0.3 }, { 1.0, 0.88 } }), new ProbabilityPrediction(0.0, new Dictionary <double, double> { { 0.0, 0.66 }, { 1.0, 0.33 } }), new ProbabilityPrediction(1.0, new Dictionary <double, double> { { 0.0, 0.01 }, { 1.0, 0.99 } }), }; var sut = new GeometricMeanProbabilityClassificationEnsembleStrategy(); var actual = sut.Combine(values); var expected = new ProbabilityPrediction(1.0, new Dictionary <double, double> { { 0.0, 0.159846490962181 }, { 1.0, 0.840153509037819 } }); Assert.AreEqual(expected, actual); }
public void ClassificationAdaBoostModel_PredictProbability_Single() { var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet(); var learner = new ClassificationAdaBoostLearner(10, 1, 3); var sut = learner.Learn(observations, targets); var rows = targets.Length; var actual = new ProbabilityPrediction[rows]; for (int i = 0; i < rows; i++) { actual[i] = sut.PredictProbability(observations.Row(i)); } var evaluator = new TotalErrorClassificationMetric <double>(); var error = evaluator.Error(targets, actual.Select(p => p.Prediction).ToArray()); Assert.AreEqual(0.038461538461538464, error, 0.0000001); var expected = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.553917222019051 }, { 1, 0.446082777980949 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.455270122123639 }, { 1, 0.544729877876361 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.590671208378385 }, { 1, 0.409328791621616 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.564961572849738 }, { 1, 0.435038427150263 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.455270122123639 }, { 1, 0.544729877876361 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.549970403132686 }, { 1, 0.450029596867314 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.417527839140627 }, { 1, 0.582472160859373 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.409988559960094 }, { 1, 0.590011440039906 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.630894242807786 }, { 1, 0.369105757192214 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.436954866525023 }, { 1, 0.563045133474978 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.461264944069783 }, { 1, 0.538735055930217 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.590671208378385 }, { 1, 0.409328791621616 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.549503146925505 }, { 1, 0.450496853074495 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.537653803214063 }, { 1, 0.462346196785938 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.37650723540928 }, { 1, 0.62349276459072 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.573579890413618 }, { 1, 0.426420109586382 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.549970403132686 }, { 1, 0.450029596867314 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.524371409810479 }, { 1, 0.475628590189522 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.436954866525023 }, { 1, 0.563045133474978 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.471117379964633 }, { 1, 0.528882620035367 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.630894242807786 }, { 1, 0.369105757192214 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.436954866525023 }, { 1, 0.563045133474978 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.404976804073458 }, { 1, 0.595023195926542 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.573579890413618 }, { 1, 0.426420109586382 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.549970403132686 }, { 1, 0.450029596867314 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.630894242807786 }, { 1, 0.369105757192214 }, }), }; CollectionAssert.AreEqual(expected, actual); }
public void ClassificationGradientBoostModel_PredictProbability_Single() { var(observations, targets) = DataSetUtilities.LoadAptitudeDataSet(); var learner = new ClassificationGradientBoostLearner(100, 0.1, 3, 1, 1e-6, 1, 0, new GradientBoostBinomialLoss(), false); var sut = learner.Learn(observations, targets); var rows = targets.Length; var actual = new ProbabilityPrediction[rows]; for (int i = 0; i < rows; i++) { actual[i] = sut.PredictProbability(observations.Row(i)); } var evaluator = new TotalErrorClassificationMetric <double>(); var error = evaluator.Error(targets, actual.Select(p => p.Prediction).ToArray()); Assert.AreEqual(0.038461538461538464, error, 0.0000001); var expected = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00153419685769873 }, { 0, 0.998465803142301 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.497135615200052 }, { 0, 0.502864384799948 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00674291737944022 }, { 0, 0.99325708262056 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00153419685769873 }, { 0, 0.998465803142301 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.497135615200052 }, { 0, 0.502864384799948 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00428497228545111 }, { 0, 0.995715027714549 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.987907185249206 }, { 0, 0.0120928147507945 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.982783250692275 }, { 0, 0.0172167493077254 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00262490179961228 }, { 0, 0.997375098200388 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.996417847055106 }, { 0, 0.00358215294489364 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.995341658753364 }, { 0, 0.00465834124663571 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00674291737944022 }, { 0, 0.99325708262056 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.0118633115475969 }, { 0, 0.988136688452403 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00048646805791186 }, { 0, 0.999513531942088 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.999891769651047 }, { 0, 0.000108230348952856 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00334655581934884 }, { 0, 0.996653444180651 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00428497228545111 }, { 0, 0.995715027714549 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.0118633115475969 }, { 0, 0.988136688452403 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.996417847055106 }, { 0, 0.00358215294489362 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.993419876193791 }, { 0, 0.00658012380620933 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00262490179961228 }, { 0, 0.997375098200388 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.996417847055106 }, { 0, 0.00358215294489362 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 1, 0.988568859753437 }, { 0, 0.0114311402465632 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00334655581934884 }, { 0, 0.996653444180651 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00428497228545111 }, { 0, 0.995715027714549 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 1, 0.00262490179961228 }, { 0, 0.997375098200388 }, }), }; CollectionAssert.AreEqual(expected, actual); }
public void ClassificationForestModel_PredictProbability_Single() { 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 learner = new ClassificationRandomForestLearner(100, 1, 100, 1, 0.0001, 1.0, 42, false); var sut = learner.Learn(observations, targets); var actual = new ProbabilityPrediction[rows]; for (int i = 0; i < rows; i++) { actual[i] = sut.PredictProbability(observations.Row(i)); } var evaluator = new TotalErrorClassificationMetric <double>(); var error = evaluator.Error(targets, actual.Select(p => p.Prediction).ToArray()); Assert.AreEqual(0.076923076923076927, error, m_delta); var expected = new ProbabilityPrediction[] { new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.650149027443145 }, { 1, 0.349850972556855 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.566943847818848 }, { 1, 0.433056152181152 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.726936489980608 }, { 1, 0.273063510019392 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.752781908451026 }, { 1, 0.247218091548974 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.566943847818848 }, { 1, 0.433056152181152 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.792506836300954 }, { 1, 0.207493163699046 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.491736055611056 }, { 1, 0.508263944388944 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.574583315377433 }, { 1, 0.425416684622567 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.838724674018791 }, { 1, 0.161275325981208 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.241480824730825 }, { 1, 0.758519175269175 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.385258186258186 }, { 1, 0.614741813741813 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.726936489980608 }, { 1, 0.273063510019392 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.706733044733045 }, { 1, 0.293266955266955 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.801266011766012 }, { 1, 0.198733988233988 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.294952297702298 }, { 1, 0.705047702297702 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.821706914001031 }, { 1, 0.178293085998968 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.780062391856509 }, { 1, 0.21993760814349 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.554444388944389 }, { 1, 0.445555611055611 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.261349872349872 }, { 1, 0.738650127650127 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.419758186258186 }, { 1, 0.580241813741813 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.71382231249143 }, { 1, 0.28617768750857 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.241480824730825 }, { 1, 0.758519175269175 }, }), new ProbabilityPrediction(1, new Dictionary <double, double> { { 0, 0.47562148962149 }, { 1, 0.52437851037851 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.821706914001031 }, { 1, 0.178293085998968 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.792506836300954 }, { 1, 0.207493163699046 }, }), new ProbabilityPrediction(0, new Dictionary <double, double> { { 0, 0.666244987039105 }, { 1, 0.333755012960895 }, }) }; CollectionAssert.AreEqual(expected, actual); }