dfs.discardInfrequent(2);
NGramTfDf ngtd = NGramTfDf.analyseFiles(clusterFiles);
ngtd.calculateNGrams();
Bag<String> bs = ngtd.getDfBag(2);
bs.discardInfrequent(2);
Map<String,List<String>> termStems = ngtd.ngramsByStem();
Map<String,Double> scores = new HashMap<String,Double>();
Map<String,Integer> overlaps = new HashMap<String,Integer>();
IndexSearcher is = new IndexSearcher(ir);
int docTotal = ir.numDocs();