Package cc.mallet.types

Examples of cc.mallet.types.InstanceList

73
74
75
76
77
78
79
80
81
82
83
                if (this.i.hasNext ()) {
                    return this.i.next ();
                }
               
                for (this.index++; this.index < lists.length; this.index++) {
                    final InstanceList list = lists[this.index];
                    if (list != null && lists[this.index].size () > 0) {
                        this.i = lists[this.index].iterator ();
                        return this.i.next ();
                    }
                }
View Full Code Here
177
178
179
180
181
182
183
184
185
186
187
    timing.tick ("Training");

    FileUtils.writeGzippedObject (new File (outputPrefix.value, "extor.ser.gz"), extor);
    timing.tick ("Serializing");

    InstanceList testing = trainer.getTestingData ();
    if (testing != null) {
      eval.test (extor.getAcrf (), testing, "Final results");
    }

    if ((extractionEval != null) && (testing != null)) {
View Full Code Here
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
  }

  protected void setupData ()
  {
    Timing timing = new Timing ();
    training = new InstanceList (featurePipe);
    training.addThruPipe (new PipedIterator (trainIterator, tokPipe));
    if (trainingPct > 0) training = subsetData (training, trainingPct);

    if (testIterator != null) {
      testing = new InstanceList (featurePipe);
      testing.addThruPipe (new PipedIterator (testIterator, tokPipe));
      if (testingPct > 0) testing = subsetData (testing, trainingPct);
    }

    timing.tick ("Data loading");
View Full Code Here
54
55
56
57
58
59
60
61
62
    Pipe p = new SerialPipes (new Pipe[]  {
      new TokenSequence2FeatureSequence (),
      new FeatureSequence2FeatureVector (),
      new Target2Label()});

    double testAcc1 = testRandomTrainedOn (new InstanceList (p));
    double testAcc2 = testRandomTrainedOn (new PagedInstanceList (p, 700, 200, new File(".")));
    assertEquals (testAcc1, testAcc2, 0.01);
  }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
    Randoms r = new Randoms (1);
    Iterator<Instance> iter = new RandomTokenSequenceIterator (r,  new Dirichlet(fd, 2.0),
          30, 0, 10, 200, classNames);
    training.addThruPipe (iter);

    InstanceList testing = new InstanceList (training.getPipe ());
    testing.addThruPipe (new RandomTokenSequenceIterator (r,  new Dirichlet(fd, 2.0),
          30, 0, 10, 200, classNames));

    System.out.println ("Training set size = "+training.size());
    System.out.println ("Testing set size = "+testing.size());

    Classifier classifier = trainer.train (training);

    System.out.println ("Accuracy on training set:");
    System.out.println (classifier.getClass().getName()
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
  {
    Pipe pipe = TestMEMM.makeSpacePredictionPipe ();
    String[] data0 = { TestCRF.data[0] };
    String[] data1 = TestCRF.data;

    InstanceList training = new InstanceList (pipe);
    training.addThruPipe (new ArrayIterator (data0));
    InstanceList testing = new InstanceList (pipe);
    testing.addThruPipe (new ArrayIterator (data1));

    CRF crf = new CRF (pipe, null);
    crf.addFullyConnectedStatesForLabels ();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood (crf);
    TokenAccuracyEvaluator eval = new TokenAccuracyEvaluator (new InstanceList[] {training, testing}, new String[] {"Training", "Testing"});
    for (int i = 0; i < 5; i++) {
      crft.train (training, 1);
      eval.evaluate(crft);
    }

    CRFExtractor extor = hackCrfExtor (crf);
    Extraction e1 = extor.extract (new ArrayIterator (data1));

    Pipe pipe2 = TestMEMM.makeSpacePredictionPipe ();
    InstanceList training2 = new InstanceList (pipe2);
    training2.addThruPipe (new ArrayIterator (data0));
    InstanceList testing2 = new InstanceList (pipe2);
    testing2.addThruPipe (new ArrayIterator (data1));

    MEMM memm = new MEMM (pipe2, null);
    memm.addFullyConnectedStatesForLabels ();
    MEMMTrainer memmt = new MEMMTrainer (memm);
    TransducerEvaluator memmeval = new TokenAccuracyEvaluator (new InstanceList[] {training2, testing2}, new String[] {"Training2", "Testing2"});
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
53
    Reader reader = new StringReader (input);
    ParenGroupIterator it = new ParenGroupIterator (reader);
    Pipe pipe = new Noop();
    pipe.setTargetProcessing (false);

    InstanceList lst = new InstanceList (pipe);
    lst.addThruPipe (it);

    assertEquals (3, lst.size());
    assertEquals ("(a (b c) ((d))  )", lst.get(0).getData());
    assertEquals ("(3\n 4)", lst.get(1).getData());
    assertEquals ("(  6)", lst.get(2).getData());
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
    Pipe pipe = new SerialPipes (new Pipe[] {
        new GenericAcrfData2TokenSequence (2),
        new TokenSequence2FeatureVectorSequence (true, true),
    });

    InstanceList training = new InstanceList (pipe);
    training.addThruPipe (new LineGroupIterator (new FileReader (trainFile),
                                         Pattern.compile ("\\s*"),
                                         true));

    InstanceList testing = new InstanceList (pipe);
    training.addThruPipe (new LineGroupIterator (new FileReader (testFile),
                                         Pattern.compile ("\\s*"),
                                         true));

    ACRF.Template[] tmpls = new ACRF.Template[] {
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
      Pipe pipe = new ClusteringPipe(string2ints(exactMatchFields.value, fieldAlphabet),
                                 string2ints(approxMatchFields.value, fieldAlphabet),
                                 string2ints(substringMatchFields.value, fieldAlphabet));

      InstanceList trainingInstances = new InstanceList(pipe);
      for (int i = 0; i < training.size(); i++) {
        PairSampleIterator iterator = new PairSampleIterator(training
            .get(i), random, 0.5, training.get(i).getNumInstances());
        while(iterator.hasNext()) {
          Instance inst = iterator.next();
          trainingInstances.add(pipe.pipe(inst));
        }
      }
      logger.info("generated " + trainingInstances.size()
          + " training instances");
      Classifier classifier = new MaxEntTrainer().train(trainingInstances);
      logger.info("InfoGain:\n");
      new InfoGain(trainingInstances).printByRank(System.out);
      logger.info("pairwise training accuracy="
View Full Code Here
239
240
241
242
243
244
245
246
247
248
249
      AgglomerativeNeighbor neighbor = (AgglomerativeNeighbor) carrier
          .getData();
      Clustering original = neighbor.getOriginal();
      int[] cluster1 = neighbor.getOldClusters()[0];
      int[] cluster2 = neighbor.getOldClusters()[1];
      InstanceList list = original.getInstances();
      int[] mergedIndices = neighbor.getNewCluster();
      Record[] records = array2Records(mergedIndices, list);
      Alphabet fieldAlph = records[0].fieldAlphabet();
      Alphabet valueAlph = records[0].valueAlphabet();
View Full Code Here
TOP

Related Classes of cc.mallet.types.InstanceList

  • cc.mallet.classify.C45$Node
  • cc.mallet.classify.DecisionTree$Node
  • cc.mallet.classify.MaxEntPRTrainer
  • cc.mallet.classify.NaiveBayesEMTrainer
  • cc.mallet.classify.tui.Vectors2FeatureConstraints
  • cc.mallet.cluster.Clustering
  • cc.mallet.cluster.evaluate.BCubedEvaluator
  • cc.mallet.cluster.evaluate.tests.TestClusteringEvaluators
  • cc.mallet.cluster.examples.FirstOrderClusterExample
  • cc.mallet.cluster.examples.FirstOrderClusterExample$OverlappingFeaturePipe
    • 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.