/**
* A test to determine if we can create and destroy {@link Cluster}s.
*
* @throws Exception
*/
@Test
public void testClusterBuilding() throws Exception {
final int CLUSTER_SIZE = 5;
AvailablePortIterator portIterator = new AvailablePortIterator(40000);
ClusterMemberSchema schema =
new ClusterMemberSchema()
.setEnvironmentVariables(PropertiesBuilder.fromCurrentEnvironmentVariables())
.setSingleServerMode()
.setClusterPort(portIterator.next())
.setJMXPort(portIterator)
.setJMXManagementMode(JMXManagementMode.LOCAL_ONLY);
Cluster cluster = null;
try {
ClusterBuilder builder = new ClusterBuilder();
builder.addBuilder(new ClusterMemberBuilder(), schema, "DCCF", CLUSTER_SIZE);
cluster = builder.realize(new SystemApplicationConsole());
final Cluster initialCluster = cluster;
ResourceProvider<Cluster> resource =
new AbstractDeferredResourceProvider<Cluster>("Cluster", 500, 60000) {
@Override
protected Cluster ensureResource() throws ResourceUnavailableException {
return initialCluster.iterator().next().getClusterSize() == CLUSTER_SIZE
? initialCluster
: null;
}
};
Assert.assertNotNull(resource.getResource());
} catch (Exception e) {
e.printStackTrace();
Assert.fail();
} finally {
if (cluster != null) {
cluster.destroy();
}
}
}
/**
* Performs the actual clustering with an assumption that all documents are written in one <code>
* language</code>.
*/
private void cluster(LanguageCode language) {
// Preprocessing of documents
final PreprocessingContext context =
preprocessingPipeline.preprocess(documents, query, language);
// Further processing only if there are words to process
clusters = Lists.newArrayList();
if (context.hasLabels()) {
// Term-document matrix building and reduction
final VectorSpaceModelContext vsmContext = new VectorSpaceModelContext(context);
final ReducedVectorSpaceModelContext reducedVsmContext =
new ReducedVectorSpaceModelContext(vsmContext);
LingoProcessingContext lingoContext = new LingoProcessingContext(reducedVsmContext);
matrixBuilder.buildTermDocumentMatrix(vsmContext);
matrixBuilder.buildTermPhraseMatrix(vsmContext);
matrixReducer.reduce(
reducedVsmContext, computeClusterCount(desiredClusterCountBase, documents.size()));
// Cluster label building
clusterBuilder.buildLabels(lingoContext, matrixBuilder.termWeighting);
// Document assignment
clusterBuilder.assignDocuments(lingoContext);
// Cluster merging
clusterBuilder.merge(lingoContext);
// Format final clusters
final int[] clusterLabelIndex = lingoContext.clusterLabelFeatureIndex;
final BitSet[] clusterDocuments = lingoContext.clusterDocuments;
final double[] clusterLabelScore = lingoContext.clusterLabelScore;
for (int i = 0; i < clusterLabelIndex.length; i++) {
final Cluster cluster = new Cluster();
final int labelFeature = clusterLabelIndex[i];
if (labelFeature < 0) {
// Cluster removed during merging
continue;
}
// Add label and score
cluster.addPhrases(labelFormatter.format(context, labelFeature));
cluster.setAttribute(Cluster.SCORE, clusterLabelScore[i]);
// Add documents
final BitSet bs = clusterDocuments[i];
for (int bit = bs.nextSetBit(0); bit >= 0; bit = bs.nextSetBit(bit + 1)) {
cluster.addDocuments(documents.get(bit));
}
// Add cluster
clusters.add(cluster);
}
Collections.sort(clusters, Cluster.byReversedWeightedScoreAndSizeComparator(scoreWeight));
}
Cluster.appendOtherTopics(documents, clusters);
}
