@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 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));
}
}