Package cc.mallet.types

Examples of cc.mallet.types.LabelVector

68
69
70
71
72
73
74
75
76
77
78
79
     *
     * @param trial Trial results to add to ROC data
     */
    public void add(Classification classification) {
        int correctIndex = classification.getInstance().getLabeling().getBestIndex();
        LabelVector lv = classification.getLabelVector();
        double[] values = lv.getValues();
       
        if (!Alphabet.alphabetsMatch(this, lv)) {
            throw new IllegalArgumentException ("Alphabets do not match");
        }
       
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
   * @param neighbors
   * @return An array containing a score for each of the elements of <code>neighbors</code>.
   */
  public double[] evaluate (Neighbor[] neighbors) {
    double[] scores = new double[neighbors.length];
    LabelVector ranks = classifier.classify(neighbors).getLabelVector();
    for (int i = 0; i < ranks.numLocations(); i++) {
      int idx = ((Integer)ranks.getLabelAtRank(i).getEntry()).intValue();
      scores[idx] = ranks.getValueAtRank(i);
    }
    return scores;
  }
View Full Code Here
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
    FeatureVector[] fva = new FeatureVector[fvs.size()];

    for (int i = 0; i < ilist.size(); i++) {
      Instance inst = ilist.get(i);
      Classification c = m_tokenClassifiers.classify(inst, ! m_inProduction);
      LabelVector lv = c.getLabelVector();
      AugmentableFeatureVector afv1 = (AugmentableFeatureVector) inst.getData();
      int[] indices = afv1.getIndices();
      AugmentableFeatureVector afv2 = new AugmentableFeatureVector(m_dataAlphabet,
          indices, afv1.getValues(), indices.length + m_predRanks2add.length);

      for (int j = 0; j < m_predRanks2add.length; j++) {
        Label label = lv.getLabelAtRank(m_predRanks2add[j]);
        int idx = m_dataAlphabet.lookupIndex("TOK_PRED=" + label.toString() + "_@_RANK_" + m_predRanks2add[j]);

        assert(idx >= 0);
        afv2.add(idx, 1);
      }
View Full Code Here
30
31
32
33
34
35
36
37
38
39
40
  private LabelVector lv;

  protected void setUp ()
  {
    ld = new LabelAlphabet ();
    lv = new LabelVector (ld,
                          new int[] {
                            ld.lookupIndex ("a"),
                            ld.lookupIndex ("b"),
                            ld.lookupIndex ("c"),
                            ld.lookupIndex ("d")},
View Full Code Here
331
332
333
334
335
336
337
338
339
      }
    if (outputAlphabet != null) {
      labelings = new LabelVector[latticeLength];
      for (int ip = latticeLength-2; ip >= 0; ip--) {
        assert (Math.abs(1.0-MatrixOps.sum (outputCounts[ip])) < 0.000001);;
        labelings[ip] = new LabelVector (outputAlphabet, outputCounts[ip]);
      }
    }
  }
View Full Code Here
252
253
254
255
256
257
258
259
260
261
262
263
264
  }
  public class ClassificationComparator implements Comparator
  {
    public final int compare (Object a, Object b)
    {
      LabelVector x = (LabelVector) (((Classification)a).getLabelVector());
      LabelVector y = (LabelVector) (((Classification)b).getLabelVector());
      double difference = x.getBestValue() - y.getBestValue();
      int toReturn = 0;
      if(difference > 0)
        toReturn = 1;
      else if (difference < 0)
        toReturn = -1;
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
85
86
      ((Classification)classifications.get(0)).getLabeling();
    this.numClasses = tempLabeling.getLabelAlphabet().size();
    values = new int[numClasses][numClasses];
    for(int i=0; i < classifications.size(); i++)
    {
      LabelVector lv =
        ((Classification)classifications.get(i)).getLabelVector();
      Instance inst = ((Classification)classifications.get(i)).getInstance();
      int bestIndex = lv.getBestIndex();
      int correctIndex = inst.getLabeling().getBestIndex();
      assert(correctIndex != -1);
      //System.out.println("Best index="+bestIndex+". Correct="+correctIndex);
      values[correctIndex][bestIndex]++;
    }     
View Full Code Here
75
76
77
78
79
80
81
82
    }
   
   
    // Create and return a Classification object
    return new Classification (instance, this,
                               new LabelVector (getLabelAlphabet(),
                                                scores));
  }   
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
  public Classification classify (Instance instance)
  {
    Classification c = underlyingClassifier.classify (instance);
    Classification cpc = confidencePredictingClassifier.classify (c);
    LabelVector lv = c.getLabelVector();
    int bestIndex = lv.getBestIndex();
    double [] values = new double[lv.numLocations()];
    //// Put score of "correct" into score of the winning class...
    // xxx Can't set lv - it's immutable.
    //     Must create copy and new classification object
    // lv.set (bestIndex, cpc.getLabelVector().value("correct"));
    //for (int i = 0; i < lv.numLocations(); i++)
    //  if (i != bestIndex)
    //    lv.set (i, 0.0);

    // Put score of "correct" in winning class and
    // set rest to 0
    for (int i = 0; i < lv.numLocations(); i++) {
      if (i != bestIndex)
        values[i] = 0.0;
      else values[i] = cpc.getLabelVector().value("correct");
    }
    //return c;
   
    if(c.bestLabelIsCorrect()){
      numCorrectInstances++;
      totalCorrect+=cpc.getLabelVector().value("correct");
      totalIncorrectCorrect+=cpc.getLabelVector().value("incorrect");
      String correct = new String("correct");
      if(correct.equals(cpc.getLabelVector().getBestLabel().toString()))
        numConfidenceCorrect++;
      else numFalseNegative++;
    }
   
    else{
      numIncorrectInstances++;
      totalIncorrect+=cpc.getLabelVector().value("correct");
      totalIncorrectIncorrect+=cpc.getLabelVector().value("incorrect");
      if((new String("incorrect")).equals(cpc.getLabelVector().getBestLabel().toString()))
        numConfidenceCorrect++;
      else numFalsePositive++;
    }
   
    return new Classification(instance, this, new LabelVector(lv.getLabelAlphabet(), values));
//    return cpc;
  }
View Full Code Here
46
47
48
49
50
51
52
      Classification c = ensemble[i].classify(instance);
      c.getLabelVector().addTo(scores, weights[i]);
    }
    // Exponentiate and normalize scores
    expNormalize (scores);
    return new Classification (instance, this, new LabelVector (ensemble[0].getLabelAlphabet(), scores));
  }
View Full Code Here
TOP

Related Classes of cc.mallet.types.LabelVector

  • cc.mallet.classify.BalancedWinnow
  • cc.mallet.classify.Classification
  • cc.mallet.classify.ClassifierEnsemble
  • cc.mallet.classify.ConfidencePredictingClassifier
  • cc.mallet.classify.evaluate.AccuracyCoverage$ClassificationComparator
  • cc.mallet.classify.evaluate.ConfusionMatrix
  • cc.mallet.classify.MaxEnt
  • cc.mallet.classify.MaxEntPRTrainer
  • cc.mallet.classify.MCMaxEnt
  • cc.mallet.classify.PRAuxClassifier
    • 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.