Examples of cc.mallet.types.InstanceList

cc.mallet.types.InstanceList
A list of machine learning instances, typically used for training or testing of a machine learning algorithm.
All of the instances in the list will have been passed through the same {@link cc.mallet.pipe.Pipe}, and thus must also share the same data and target Alphabets. InstanceList keeps a reference to the pipe and the two alphabets.
The most common way of adding instances to an InstanceList is through the add(PipeInputIterator) method. PipeInputIterators are a way of mapping general data sources into instances suitable for processing through a pipe. As each {@link cc.mallet.types.Instance} is pulled from the PipeInputIterator, the InstanceListcopies the instance and runs the copy through its pipe (with resultant destructive modifications) before saving the modified instance on its list. This is the usual way in which instances are transformed by pipes.
InstanceList also contains methods for randomly generating lists of feature vectors; splitting lists into non-overlapping subsets (useful for test/train splits), and iterators for cross validation. @see Instance @see Pipe @author Andrew McCallum mccallum@cs.umass.edu


  public void doTestSpacePrediction(boolean testValueAndGradient) {
    Pipe p = makeSpacePredictionPipe();
    Pipe p2 = new TestCRF2String();


    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new Random(1), new double[] {
        .5, .5 });
    CRF crf = new CRF(p, p2);
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    if (testValueAndGradient) {

View Full Code Here

      boolean useSaved, boolean useSparseWeights) {
    Pipe p = makeSpacePredictionPipe();


    CRF savedCRF;
    File f = new File("TestObject.obj");
    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new double[] { .5, .5 });
    CRF crf = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crft.setUseSparseWeights(useSparseWeights);
    if (testValueAndGradient) {

View Full Code Here

  }


  public void testAddOrderNStates() {
    Pipe p = makeSpacePredictionPipe();


    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new java.util.Random(678),
        new double[] { .5, .5 });


    // Compare 3 CRFs trained with addOrderNStates, and make sure
    // that having more features leads to a higher likelihood

View Full Code Here

  }


  public void testFrozenWeights() {
    Pipe p = makeSpacePredictionPipe();


    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));


    CRF crf1 = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
    crf1.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft1 = new CRFTrainerByLabelLikelihood(
        crf1);

View Full Code Here


  public void testTrainStochasticGradient() {
    Pipe p = makeSpacePredictionPipe();
    Pipe p2 = new TestCRF2String();


    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new double[] { .5, .5 });
    CRF crf = new CRF(p, p2);
    crf.addFullyConnectedStatesForLabels();
    crf.setWeightsDimensionAsIn(lists[0], false);
    CRFTrainerByStochasticGradient crft = new CRFTrainerByStochasticGradient(
        crf, 0.0001);

View Full Code Here

  public void testSumLatticeImplementations() {
    Pipe p = makeSpacePredictionPipe();
    Pipe p2 = new TestCRF2String();


    // first do normal training for getting weights
    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new double[] { .5, .5 });
    CRF crf = new CRF(p, p2);
    crf.addFullyConnectedStatesForLabels();
    crf.setWeightsDimensionAsIn(lists[0], false);
    CRFTrainerByStochasticGradient crft = new CRFTrainerByStochasticGradient(
        crf, 0.0001);

View Full Code Here

  }


  public void testTokenAccuracy() {
    Pipe p = makeSpacePredictionPipe();


    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new Random(777), new double[] {
        .5, .5 });


    CRF crf = new CRF(p.getDataAlphabet(), p.getTargetAlphabet());
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);

View Full Code Here

    Pipe p = new SerialPipes(new Pipe[] {
        new CharSequence2TokenSequence("."), new TokenText(),
        new TestCRFTokenSequenceRemoveSpaces(),
        new TokenSequence2FeatureVectorSequence(),
        new PrintInputAndTarget(), });
    InstanceList one = new InstanceList(p);
    String[] data = new String[] { "ABCDE", };
    one.addThruPipe(new ArrayIterator(data));
    CRF crf = new CRF(p, null);
    crf.addFullyConnectedStatesForThreeQuarterLabels(one);
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crf.setWeightsDimensionAsIn(one, false);
    Optimizable mcrf = crft.getOptimizableCRF(one);

View Full Code Here

    Pipe p = new SerialPipes(new Pipe[] {
        new CharSequence2TokenSequence("."), new TokenText(),
        new TestCRFTokenSequenceRemoveSpaces(),
        new TokenSequence2FeatureVectorSequence(),
        new PrintInputAndTarget(), });
    InstanceList one = new InstanceList(p);
    String[] data = new String[] { "ABCDE", };
    one.addThruPipe(new ArrayIterator(data));
    CRF crf = new CRF(p, null);
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crf.setWeightsDimensionAsIn(one, false);
    Optimizable.ByGradientValue mcrf = crft.getOptimizableCRF(one);

View Full Code Here

            .compile("^(\\S+) (.*)"), 2, 1),
        new TokenSequenceParseFeatureString(false), new TokenText(),
        new TokenSequence2FeatureVectorSequence(true, false),
        new Target2LabelSequence(), new PrintInputAndTarget(), });


    InstanceList data = new InstanceList(p);
    data.addThruPipe(new LineGroupIterator(new StringReader(toy), Pattern
        .compile("\n"), true));


    CRF crf = new CRF(p, null);
    crf.print();
    crf.addStatesForLabelsConnectedAsIn(data);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

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

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.