public static ListMatrix<Double> run(Classifier algorithm, ListDataSet dataSet) throws Exception { return run(algorithm, dataSet, 10, 10, System.currentTimeMillis()); }
@Test public void testIrisClassification() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new ConstantClassifier(); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.21, results.getMeanValue(), 0.04); }
@Test public void testMalletAdaBoost() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new MalletClassifier(MalletClassifiers.AdaBoost); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.93, results.getMeanValue(), 0.02); }
@Test public void testMalletNaiveBayes() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new MalletClassifier(MalletClassifiers.NaiveBayes); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.9273, results.getMeanValue(), 0.01); }
@Test public void testIrisClassification() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new NaiveBayesClassifier(); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.959, results.getMeanValue(), 0.04); }
@Test public void testIrisClassification() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new LibSVMClassifier(Kernel.RBF); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.95, results.getMeanValue(), 0.04); }
@Test public void testIrisClassification2() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Regressor c = new LinearRegression(3); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.80, results.getMeanValue(), 0.01); }
@Test public void testIrisClassification() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); KNNClassifier c = new KNNClassifier(5); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.96, results.getMeanValue(), 0.01); }
@Test public void testIrisClassification() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new RandomClassifier(); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.33, results.getMeanValue(), 0.04); }
@Test public void testIrisClassification() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new LibLinearClassifier(); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.95, results.getMeanValue(), 0.04); }
@Test public void testMalletDecisionTree() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new MalletClassifier(MalletClassifiers.DecisionTree); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.934, results.getMeanValue(), 0.01); }
@Test public void testIrisClassification1() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Regressor c = new LinearRegression(); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.82, results.getMeanValue(), 0.01); }
@Test public void testIrisClassification() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); Classifier c = new WekaClassifier(WekaClassifierType.AdaBoostM1, false); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.954, results.getMeanValue(), 0.01); }
@Test public void testIrisClassification2() throws Exception { ListDataSet iris = ListDataSet.Factory.IRIS(); String del1 = null; String del2 = null; for (Sample s : iris) { int c = s.getTargetClass(); if (c == 0) { del1 = s.getId(); break; } } for (Sample s : iris) { int c = s.getTargetClass(); if (c == 1) { del2 = s.getId(); break; } } iris.remove(del1); iris.remove(del2); Classifier c = new ConstantClassifier(); ListMatrix<Double> results = CrossValidation.run(c, iris, 10, 10, 0); assertEquals(0.23, results.getMeanValue(), 0.04); }