@Test
public void testGaussianClusterClassification() {
ClusterClassifier classifier = newGaussianClassifier();
Vector pdf = classifier.classify(new DenseVector(2));
assertEquals("[0,0]", "[0.212, 0.576, 0.212]", AbstractCluster.formatVector(pdf, null));
pdf = classifier.classify(new DenseVector(2).assign(2));
assertEquals("[2,2]", "[0.952, 0.047, 0.000]", AbstractCluster.formatVector(pdf, null));
}
@Test
public void testSoftClusterClassification() {
ClusterClassifier classifier = newSoftClusterClassifier();
Vector pdf = classifier.classify(new DenseVector(2));
assertEquals("[0,0]", "[0.000, 1.000, 0.000]", AbstractCluster.formatVector(pdf, null));
pdf = classifier.classify(new DenseVector(2).assign(2));
assertEquals("[2,2]", "[0.735, 0.184, 0.082]", AbstractCluster.formatVector(pdf, null));
}
@Test
public void testClusterClassification() {
ClusterClassifier classifier = newClusterClassifier();
Vector pdf = classifier.classify(new DenseVector(2));
assertEquals("[0,0]", "[0.107, 0.787, 0.107]", AbstractCluster.formatVector(pdf, null));
pdf = classifier.classify(new DenseVector(2).assign(2));
assertEquals("[2,2]", "[0.867, 0.117, 0.016]", AbstractCluster.formatVector(pdf, null));
}
@Test(expected = UnsupportedOperationException.class)
public void testMSCanopyClassification() {
List<Cluster> models = Lists.newArrayList();
DistanceMeasure measure = new ManhattanDistanceMeasure();
models.add(new MeanShiftCanopy(new DenseVector(2).assign(1), 0, measure));
models.add(new MeanShiftCanopy(new DenseVector(2), 1, measure));
models.add(new MeanShiftCanopy(new DenseVector(2).assign(-1), 2, measure));
ClusterClassifier classifier = new ClusterClassifier(models);
classifier.classify(new DenseVector(2));
}
@Test
public void testClusterIteratorDirichlet() {
List<Vector> data = TestKmeansClustering.getPoints(TestKmeansClustering.REFERENCE);
ClusteringPolicy policy = new DirichletClusteringPolicy(3, 1);
ClusterClassifier prior = newClusterClassifier();
ClusterIterator iterator = new ClusterIterator(policy);
ClusterClassifier posterior = iterator.iterate(data, prior, 5);
assertEquals(3, posterior.getModels().size());
for (Cluster cluster : posterior.getModels()) {
System.out.println(cluster.asFormatString(null));
}
}
@Test
public void testCanopyClassification() {
List<Cluster> models = Lists.newArrayList();
DistanceMeasure measure = new ManhattanDistanceMeasure();
models.add(new Canopy(new DenseVector(2).assign(1), 0, measure));
models.add(new Canopy(new DenseVector(2), 1, measure));
models.add(new Canopy(new DenseVector(2).assign(-1), 2, measure));
ClusterClassifier classifier = new ClusterClassifier(models);
Vector pdf = classifier.classify(new DenseVector(2));
assertEquals("[0,0]", "[0.107, 0.787, 0.107]", AbstractCluster.formatVector(pdf, null));
pdf = classifier.classify(new DenseVector(2).assign(2));
assertEquals("[2,2]", "[0.867, 0.117, 0.016]", AbstractCluster.formatVector(pdf, null));
}
@Test
public void testSeqFileClusterIteratorKMeans() throws IOException {
Path pointsPath = getTestTempDirPath("points");
Path priorPath = getTestTempDirPath("prior");
Path outPath = getTestTempDirPath("output");
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(conf);
List<VectorWritable> points =
TestKmeansClustering.getPointsWritable(TestKmeansClustering.REFERENCE);
ClusteringTestUtils.writePointsToFile(points, new Path(pointsPath, "file1"), fs, conf);
Path path = new Path(priorPath, "priorClassifier");
ClusterClassifier prior = newClusterClassifier();
writeClassifier(prior, conf, path, fs);
assertEquals(3, prior.getModels().size());
System.out.println("Prior");
for (Cluster cluster : prior.getModels()) {
System.out.println(cluster.asFormatString(null));
}
ClusteringPolicy policy = new KMeansClusteringPolicy();
ClusterIterator iterator = new ClusterIterator(policy);
iterator.iterate(pointsPath, path, outPath, 5);
for (int i = 1; i <= 5; i++) {
System.out.println("Classifier-" + i);
ClusterClassifier posterior = readClassifier(conf, new Path(outPath, "classifier-" + i), fs);
assertEquals(3, posterior.getModels().size());
for (Cluster cluster : posterior.getModels()) {
System.out.println(cluster.asFormatString(null));
}
}
}
@Test
public void testGaussianClassifierSerialization() throws Exception {
ClusterClassifier classifier = newGaussianClassifier();
ClusterClassifier classifierOut = writeAndRead(classifier);
assertEquals(classifier.getModels().size(), classifierOut.getModels().size());
assertEquals(
classifier.getModels().get(0).getClass().getName(),
classifierOut.getModels().get(0).getClass().getName());
}
