Java Code Examples for cc.mallet.classify.Classifier#classify()

@Override
public List<ModelApplication> applyModel(
        AnnotationSet instanceAS, AnnotationSet inputAS, AnnotationSet sequenceAS, String parms) {
  // NOTE: the crm should be of type CorpusRepresentationMalletClass for this to work!
  if(!(corpusRepresentation instanceof CorpusRepresentationMalletTarget)) {
    throw new GateRuntimeException("Cannot perform classification with data from "+corpusRepresentation.getClass());
  }
  CorpusRepresentationMalletTarget data = (CorpusRepresentationMalletTarget)corpusRepresentation;
  data.stopGrowth();
  List<ModelApplication> gcs = new ArrayList<>();
  LFPipe pipe = (LFPipe)data.getRepresentationMallet().getPipe();
  Classifier classifier = (Classifier)model;
  // iterate over the instance annotations and create mallet instances 
  for(Annotation instAnn : instanceAS.inDocumentOrder()) {
    Instance inst = data.extractIndependentFeatures(instAnn, inputAS);
    inst = pipe.instanceFrom(inst);
    Classification classification = classifier.classify(inst);
    Labeling labeling = classification.getLabeling();
    LabelVector labelvec = labeling.toLabelVector();
    List<String> classes = new ArrayList<>(labelvec.numLocations());
    List<Double> confidences = new ArrayList<>(labelvec.numLocations());
    for(int i=0; i<labelvec.numLocations(); i++) {
      classes.add(labelvec.getLabelAtRank(i).toString());
      confidences.add(labelvec.getValueAtRank(i));
    }      
    ModelApplication gc = new ModelApplication(instAnn, labeling.getBestLabel().toString(), 
            labeling.getBestValue(), classes, confidences);
    //System.err.println("ADDING GC "+gc);
    // now save the class in our special class feature on the instance as well
    instAnn.getFeatures().put("gate.LF.target",labeling.getBestLabel().toString());
    gcs.add(gc);
  }
  data.startGrowth();
  return gcs;
}
 

@Override
protected void execute(JobSettings settings) throws AnalysisEngineProcessException {

  Pipe pipe = new MaxEntClassifierPipe(labelsAndFeatures.keySet(), stopwords);

  InstanceList instances = new InstanceList(pipe);
  instances.addThruPipe(getDocumentsFromMongoWithRandonLabelAssignement());

  Alphabet targetAlphabet = instances.getTargetAlphabet();
  HashMap<Integer, ArrayList<Integer>> featuresAndLabels =
      mapFeaturesToLabels(instances.getDataAlphabet(), targetAlphabet);

  int numLabels = targetAlphabet.size();
  HashMap<Integer, double[]> constraintsMap =
      FeatureConstraintUtil.setTargetsUsingHeuristic(featuresAndLabels, numLabels, 0.9);

  MaxEntKLFLGEConstraints geConstraints =
      new MaxEntKLFLGEConstraints(instances.getDataAlphabet().size(), numLabels, false);
  constraintsMap
      .entrySet()
      .forEach(e -> geConstraints.addConstraint(e.getKey(), e.getValue(), 1));
  ArrayList<MaxEntGEConstraint> constraints = new ArrayList<>();
  constraints.add(geConstraints);

  // Create a classifier trainer, and use it to create a classifier
  MaxEntGETrainer trainer = new MaxEntGETrainer(constraints);
  trainer.setMaxIterations(numIterations);
  trainer.setGaussianPriorVariance(variance);

  instances.forEach(
      i -> {
        i.unLock();
        i.setTarget(null);
        i.lock();
      });

  Classifier classifier = trainer.train(instances);

  List<Classification> classify = classifier.classify(instances);

  writeClassificationToMongo(classify);
  new ObjectFile(classifier, modelFile).write();
}
 

public static void main(String[] args) {

        // pipe instances
        InstanceList instanceList = new InstanceList(
                new SerialPipes(getPipes()));
        FileIterator iterator = new FileIterator(new File[] { CORPUS },
                new TxtFilter(), LAST_DIRECTORY);
        instanceList.addThruPipe(iterator);

        // ////////////////////////////////////////////////////////////////
        // cross-validate
        System.out.println("trial\tprec\trecall\tF-score");
        double f1s = 0;
        for (int i = 0; i < trials; i++) {
            Trial trial = testTrainSplit(instanceList);
            System.out.println(join(new Object[] {//
                    i, trial.getPrecision(TESTING), trial.getRecall(TESTING),
                            trial.getF1(TESTING) }, "\t"));
            f1s += trial.getF1(TESTING);
        }
        System.out.println("mean F1 = " + (f1s / (trials + 0d)));

        // ////////////////////////////////////////////////////////////////
        // train
        ClassifierTrainer trainer = new MaxEntTrainer();
        Classifier c = trainer.train(instanceList);

        String txt = "in the entorhinal cortex of the rat\n"
                + "II: phase relations between unit discharges and theta field potentials.\n"
                + "J. Comp. Neurol. 67, 502–509.\n"
                + "Alonso, A., and Klink, R. (1993).\n"
                + "Differential electroresponsiveness of\n"
                + "stellate and pyramidal-like cells of\n"
                + "medial entorhinal cortex layer II.\n"
                + "J. Neurophysiol. 70, 128–143.\n"
                + "Alonso, A., and Köhler, C. (1984).\n"
                + "A study of the reciprocal connections between the septum and the\n"
                + "entorhinal area using anterograde\n"
                + "and retrograde axonal transport\n"
                + "methods in the rat brain. J. Comp.\n"
                + "Neurol. 225, 327–343.\n"
                + "Alonso, A., and Llinás, R. (1989).\n"
                + "Subthreshold sodium-dependent\n"
                + "theta-like rhythmicity in stellate\n"
                + "cells of entorhinal cortex layer II.\n"
                + "Nature 342, 175–177.\n"
                + "Amaral, D. G., and Kurz, J. (1985).\n"
                + "An analysis of the origins of\n" + "";
        Classification classification = c.classify(c.getInstancePipe()
                .instanceFrom(new Instance(txt, null, null, null)));
        System.out.println("LABELL " + classification.getLabeling());
        c.print();

        try {
            ObjectOutputStream oos = new ObjectOutputStream(
                    new FileOutputStream("target/classifier_"
                            + currentTimeMillis() + ".model"));
            oos.writeObject(c);
            oos.close();
        } catch (Exception e) {
            e.fillInStackTrace();
        }

        // //////////////////////////////////////////////////////////////////
        // train test
        for (String goldLabel : new String[] { "I", "O" }) {
            ClassifierTrainer trainer2 = new MaxEntTrainer();
            Classifier c2 = trainer2.train(instanceList);

            FileIterator iteratorI = new FileIterator(new File[] { new File(
                    CORPUS, "../annots1/" + goldLabel + "/") },
                    new TxtFilter(), LAST_DIRECTORY);
            Iterator<Instance> instancesI = c2.getInstancePipe()
                    .newIteratorFrom(iteratorI);

            Histogram<String> h = new Histogram<String>();
            while (instancesI.hasNext()) {
                Instance inst = instancesI.next();
                Labeling labeling = c2.classify(inst).getLabeling();
                Label bestLabel = labeling.getBestLabel();
                h.add(bestLabel.toString());

                // if (!bestLabel.toString().equals(goldLabel)) {
                // LOG.debug(
                // "\n\n\nMISSCLASSIFIED as {} but gold:{} :: "
                // + inst.getSource(), bestLabel, goldLabel);
                // }
            }
            System.out.println("\nlabel " + goldLabel + "\n" + h);
        }
    }