/** Build the cluster's label from suffix tree edge indices. */
private String buildLabel(int[] phraseIndices) {
final boolean joinWithSpace =
context.language.getLanguageCode() != LanguageCode.CHINESE_SIMPLIFIED;
// Count the number of terms first.
int termsCount = 0;
for (int j = 0; j < phraseIndices.length; j += 2) {
termsCount += phraseIndices[j + 1] - phraseIndices[j] + 1;
}
// Extract terms info for the phrase and construct the label.
final boolean[] stopwords = new boolean[termsCount];
final char[][] images = new char[termsCount][];
final short[] tokenTypes = context.allWords.type;
int k = 0;
for (int i = 0; i < phraseIndices.length; i += 2) {
for (int j = phraseIndices[i]; j <= phraseIndices[i + 1]; j++, k++) {
final int termIndex = sb.input.get(j);
images[k] = context.allWords.image[termIndex];
stopwords[k] = TokenTypeUtils.isCommon(tokenTypes[termIndex]);
}
}
return LabelFormatter.format(images, stopwords, joinWithSpace);
}
/**
* 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);
}