private void cluster( LanguageCode language )
{
PreprocessingContext context = preprocessingPipeline.preprocess( documents, query, language );
clusters = new List<Cluster>();
if ( context.hasLabels() )
{
VectorSpaceModelContext vsmContext = new VectorSpaceModelContext( context );
ReducedVectorSpaceModelContext reducedVsmContext = new ReducedVectorSpaceModelContext( vsmContext );
LingoProcessingContext lingoContext = new LingoProcessingContext( reducedVsmContext );
matrixBuilder.buildTermDocumentMatrix( vsmContext );
matrixBuilder.buildTermPhraseMatrix( vsmContext );
matrixReducer.reduce( reducedVsmContext, computeClusterCount( desiredClusterCountBase, documents.Count ) );
clusterBuilder.buildLabels( lingoContext, matrixBuilder.termWeighting );
clusterBuilder.assignDocuments( lingoContext );
clusterBuilder.merge( lingoContext );
int[] clusterLabelIndex = lingoContext.clusterLabelFeatureIndex;
BitSet[] clusterDocuments = lingoContext.clusterDocuments;
double[] clusterLabelScore = lingoContext.clusterLabelScore;
for ( int i = 0; i < clusterLabelIndex.length; i++ )
{
Cluster cluster = new Cluster();
int labelFeature = clusterLabelIndex[i];
if ( labelFeature < 0 )
{
// Cluster removed during merging
continue;
}
cluster.addPhrases( labelFormatter.format( context, labelFeature ) );
cluster.setAttribute( Cluster.SCORE, clusterLabelScore[i] );
BitSet bs = clusterDocuments[i];
for ( int bit = bs.nextSetBit( 0 ); bit >= 0; bit = bs.nextSetBit( bit + 1 ) )
{
cluster.addDocuments( documents.ElementAt( bit ) );
}
clusters.Add( cluster );
}
Collections.Sort( clusters, Cluster.byReversedWeightedScoreAndSizeComparator( scoreWeight ) );
}
Cluster.appendOtherTopics( documents, clusters );
}
