Package cc.mallet.types

Examples of cc.mallet.types.FeatureSequence

146
147
148
149
150
151
152
153
154
155
156
157
158
159
  private boolean[][] labelConnectionsIn(InstanceList trainingSet) {
    int numLabels = outputAlphabet.size();
    boolean[][] connections = new boolean[numLabels][numLabels];
    for (Instance instance : trainingSet) {
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      for (int j = 1; j < output.size(); j++) {
        int sourceIndex = outputAlphabet.lookupIndex(output.get(j - 1));
        int destIndex = outputAlphabet.lookupIndex(output.get(j));
        assert (sourceIndex >= 0 && destIndex >= 0);
        connections[sourceIndex][destIndex] = true;
      }
    }
    return connections;
View Full Code Here
652
653
654
655
656
657
658
659
660
661
662
663
      }
      initialEstimator = new Multinomial.LaplaceEstimator(
          transitionAlphabet);
    }
    for (Instance instance : ilist) {
      FeatureSequence input = (FeatureSequence) instance.getData();
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      new SumLatticeDefault(this, input, output, new Incrementor());
    }
    initialMultinomial = initialEstimator.estimate();
    for (int i = 0; i < numStates(); i++) {
      emissionMultinomial[i] = emissionEstimator[i].estimate();
View Full Code Here
710
711
712
713
714
715
716
717
718
719
720
721
722
723
  {
    int numLabels = outputAlphabet.size();
    boolean[][] connections = new boolean[numLabels][numLabels];
    for (int i = 0; i < trainingSet.size(); i++) {
      Instance instance = trainingSet.get(i);
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      for (int j = 1; j < output.size(); j++) {
        int sourceIndex = outputAlphabet.lookupIndex (output.get(j-1));
        int destIndex = outputAlphabet.lookupIndex (output.get(j));
        assert (sourceIndex >= 0 && destIndex >= 0);
        connections[sourceIndex][destIndex] = true;
      }
    }
View Full Code Here
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
        weightsPresent[i].set (parameters.weights[i].indexAtLocation(j));
    // Put in the weights in the training set
    for (int i = 0; i < trainingData.size(); i++) {
      Instance instance = trainingData.get(i);
      FeatureVectorSequence input = (FeatureVectorSequence) instance.getData();
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      // gsc: trainingData can have unlabeled instances as well
      if (output != null && output.size() > 0) {
        // Do it for the paths consistent with the labels...
        sumLatticeFactory.newSumLattice (this, input, output, new Transducer.Incrementor() {
          public void incrementTransition (Transducer.TransitionIterator ti, double count) {
            State source = (CRF.State)ti.getSourceState();
            FeatureVector input = (FeatureVector)ti.getInput();
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
38
39
40
    long start = System.nanoTime();

    try {
      ArrayList<String> tokens = (ArrayList<String>) carrier.getData();
      FeatureSequence featureSequence =
        new FeatureSequence ((Alphabet) getDataAlphabet(), tokens.size());
      for (int i = 0; i < tokens.size(); i++) {
        featureSequence.add (tokens.get(i));
      }
      carrier.setData(featureSequence);
     
      totalNanos += System.nanoTime() - start;
    } catch (ClassCastException cce) {
View Full Code Here
31
32
33
34
35
36
37
38
39
40
41
  FeatureVector fv;
 
  protected void setUp ()
  {
    dict = new Alphabet ();
    fs = new FeatureSequence (dict, 2);
    fs.add (dict.lookupIndex ("a"));
    fs.add (dict.lookupIndex ("n"));
    fs.add (dict.lookupIndex ("d"));
    fs.add (dict.lookupIndex ("r"));
    fs.add (dict.lookupIndex ("e"));
View Full Code Here
279
280
281
282
283
284
285
286
287
288
289
                1, 2, 3 }),
            new FeatureVector(crf.getInputAlphabet(), new int[] {
                1, 2, 3 }),
            new FeatureVector(crf.getInputAlphabet(), new int[] {
                1, 2, 3 }), });
    FeatureSequence ss = new FeatureSequence(crf.getOutputAlphabet(),
        new int[] { 0, 1, 2, 3 });
    InstanceList ilist = new InstanceList(new Noop(inputAlphabet,
        outputAlphabet));
    ilist.add(fvs, ss, null, null);
View Full Code Here
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
  }
 
  public void testNewPutSizeFreeze ()
  {
    Alphabet dict = new Alphabet ();
    FeatureSequence fs = new FeatureSequence (dict, 10);
    fs.add (dict.lookupIndex ("apple"));
    fs.add (dict.lookupIndex ("bear"));
    fs.add (dict.lookupIndex ("car"));
    fs.add (dict.lookupIndex ("door"));
    assertTrue (fs.size() == 4);
    double[] weights = new double[4];
    fs.addFeatureWeightsTo (weights);
    assertTrue (weights[1] == 1.0);

    fs.add (dict.lookupIndex ("bear"));
    int[] feats = fs.toFeatureIndexSequence();
    assertTrue (feats[0] == 0);
    assertTrue (feats[1] == 1);
    assertTrue (feats[2] == 2);
    assertTrue (feats[3] == 3);
    assertTrue (feats[4] == 1);
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
    double logLikelihood = Double.NEGATIVE_INFINITY, prevLogLikelihood;
    for (int iter = 0; iter < numIterations; iter++) {
      prevLogLikelihood = logLikelihood;
      logLikelihood = 0;
      for (Instance inst : trainingSet) {
        FeatureSequence input = (FeatureSequence) inst.getData();
        FeatureSequence output = (FeatureSequence) inst.getTarget();
        double obsLikelihood = new SumLatticeDefault(hmm, input,
            output, hmm.new Incrementor()).getTotalWeight();
        logLikelihood += obsLikelihood;
      }
      logger.info("getValue() (observed log-likelihood) = "
          + logLikelihood);

      if (unlabeledSet != null) {
        int numEx = 0;
        for (Instance inst : unlabeledSet) {
          numEx++;
          if (numEx % 100 == 0) {
            System.err.print(numEx + ". ");
            System.err.flush();
          }
          FeatureSequence input = (FeatureSequence) inst.getData();
          double hiddenLikelihood = new SumLatticeDefault(hmm, input,
              null, hmm.new Incrementor()).getTotalWeight();
          logLikelihood += hiddenLikelihood;
        }
        System.err.println();
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
    trainingGatheredFor = training;
    for (int i = 0; i < training.size(); i++) {
      Instance instance = training.get(i);
      FeatureVectorSequence input = (FeatureVectorSequence) instance.getData();
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      // Do it for the paths consistent with the labels...
      new SumLatticeDefault (memm, input, output, new Transducer.Incrementor() {
        public void incrementFinalState(Transducer.State s, double count) { }
        public void incrementInitialState(Transducer.State s, double count) { }
        public void incrementTransition(Transducer.TransitionIterator ti, double count) {
View Full Code Here
TOP

Related Classes of cc.mallet.types.FeatureSequence

  • cc.mallet.fst.CRF
  • cc.mallet.fst.CRFOptimizableByBatchLabelLikelihood
  • cc.mallet.fst.CRFOptimizableByLabelLikelihood
  • cc.mallet.fst.HMM
  • cc.mallet.fst.HMMTrainerByLikelihood
  • cc.mallet.fst.MEMMTrainer
  • cc.mallet.fst.tests.TestCRF
  • cc.mallet.fst.tests.TestCRF$TestCRFTokenSequenceRemoveSpaces
  • cc.mallet.fst.tests.TestMEMM
  • cc.mallet.pipe.FeatureSequence2FeatureVector
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.