public void doInference() { try { ParallelTopicModel model = ParallelTopicModel.read(new File(inferencerFile)); TopicInferencer inferencer = model.getInferencer(); // TopicInferencer inferencer = // TopicInferencer.read(new File(inferencerFile)); // InstanceList testing = readFile(); readFile(); InstanceList testing = generateInstanceList(); // readFile(); for (int i = 0; i < testing.size(); i++) { StringBuilder probabilities = new StringBuilder(); double[] testProbabilities = inferencer.getSampledDistribution(testing.get(i), 10, 1, 5); ArrayList probabilityList = new ArrayList(); for (int j = 0; j < testProbabilities.length; j++) { probabilityList.add(new Pair<Integer, Double>(j, testProbabilities[j])); } Collections.sort(probabilityList, new CustomComparator()); for (int j = 0; j < testProbabilities.length && j < topN; j++) { if (j > 0) probabilities.append(" "); probabilities.append( ((Pair<Integer, Double>) probabilityList.get(j)).getFirst().toString() + "," + ((Pair<Integer, Double>) probabilityList.get(j)).getSecond().toString()); } System.out.println(docIds.get(i) + "," + probabilities.toString()); } } catch (Exception e) { e.printStackTrace(); System.err.println(e.getMessage()); } }
public void test() throws Exception { ParallelTopicModel model = ParallelTopicModel.read(new File(inferencerFile)); TopicInferencer inferencer = model.getInferencer(); ArrayList<Pipe> pipeList = new ArrayList<Pipe>(); pipeList.add(new CharSequence2TokenSequence(Pattern.compile("\\p{L}\\p{L}+"))); pipeList.add(new TokenSequence2FeatureSequence()); InstanceList instances = new InstanceList(new SerialPipes(pipeList)); Reader fileReader = new InputStreamReader(new FileInputStream(new File(fileName)), "UTF-8"); instances.addThruPipe( new CsvIterator( fileReader, Pattern.compile("^(\\S*)[\\s,]*(\\S*)[\\s,]*(.*)$"), 3, 2, 1)); // data, label, name fields double[] testProbabilities = inferencer.getSampledDistribution(instances.get(1), 10, 1, 5); for (int i = 0; i < 1000; i++) System.out.println(i + ": " + testProbabilities[i]); }