/** Performs by URL clustering. */
@Override
public void process() throws ProcessingException {
final Map<Object, Cluster> clusterMap = Maps.newHashMap();
for (Document document : documents) {
final Object field = document.getField(fieldName);
if (field instanceof Collection<?>) {
for (Object value : (Collection<?>) field) {
addToCluster(clusterMap, value, document);
}
} else {
addToCluster(clusterMap, field, document);
}
}
clusters = Lists.newArrayList(clusterMap.values());
Collections.sort(clusters, Cluster.BY_REVERSED_SIZE_AND_LABEL_COMPARATOR);
Cluster.appendOtherTopics(documents, clusters);
}
/**
* Create the junk (unassigned documents) cluster and create the final set of clusters in Carrot2
* format.
*/
private void postProcessing(ArrayList<ClusterCandidate> clusters) {
// Adapt to Carrot2 classes, counting used documents on the way.
final BitSet all = new BitSet(documents.size());
final ArrayList<Document> docs = Lists.newArrayListWithCapacity(documents.size());
final ArrayList<String> phrases = Lists.newArrayListWithCapacity(3);
for (ClusterCandidate c : clusters) {
final Cluster c2 = new Cluster();
c2.addPhrases(collectPhrases(phrases, c));
c2.addDocuments(collectDocuments(docs, c.documents));
c2.setScore((double) c.score);
this.clusters.add(c2);
all.or(c.documents);
docs.clear();
phrases.clear();
}
Cluster.appendOtherTopics(this.documents, this.clusters);
}
/**
* If there are unclustered documents, appends the "Other Topics" group to the <code>clusters
* </code>.
*
* @see #buildOtherTopics(List, List)
*/
public static void appendOtherTopics(List<Document> allDocuments, List<Cluster> clusters) {
appendOtherTopics(allDocuments, clusters, OTHER_TOPICS_LABEL);
}
/**
* 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);
}