public TopicModelDiagnostics(ParallelTopicModel model, int numTopWords) { numTopics = model.getNumTopics(); this.numTopWords = numTopWords; this.model = model; alphabet = model.getAlphabet(); topicSortedWords = model.getSortedWords(); topicTopWords = new String[numTopics][numTopWords]; numRank1Documents = new int[numTopics]; numNonZeroDocuments = new int[numTopics]; numDocumentsAtProportions = new int[numTopics][DEFAULT_DOC_PROPORTIONS.length]; sumCountTimesLogCount = new double[numTopics]; diagnostics = new ArrayList<TopicScores>(); for (int topic = 0; topic < numTopics; topic++) { int position = 0; TreeSet<IDSorter> sortedWords = topicSortedWords.get(topic); // How many words should we report? Some topics may have fewer than // the default number of words with non-zero weight. int limit = numTopWords; if (sortedWords.size() < numTopWords) { limit = sortedWords.size(); } Iterator<IDSorter> iterator = sortedWords.iterator(); for (int i = 0; i < limit; i++) { IDSorter info = iterator.next(); topicTopWords[topic][i] = (String) alphabet.lookupObject(info.getID()); } } collectDocumentStatistics(); diagnostics.add(getTokensPerTopic(model.tokensPerTopic)); diagnostics.add(getDocumentEntropy(model.tokensPerTopic)); diagnostics.add(getWordLengthScores()); diagnostics.add(getCoherence()); diagnostics.add(getDistanceFromUniform()); diagnostics.add(getDistanceFromCorpus()); diagnostics.add(getEffectiveNumberOfWords()); diagnostics.add(getTokenDocumentDiscrepancies()); diagnostics.add(getRank1Percent()); diagnostics.add(getDocumentPercentRatio(FIFTY_PERCENT_INDEX, TWO_PERCENT_INDEX)); diagnostics.add(getDocumentPercent(5)); diagnostics.add(getExclusivity()); }