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

      testSource = new LineGroupIterator (new FileReader (testFile.value), Pattern.compile ("^\\s*$"), true);
    } else {
      testSource = null;
    }


    InstanceList training = new InstanceList (pipe);
    training.addThruPipe (trainSource);
    InstanceList testing = new InstanceList (pipe);
    testing.addThruPipe (testSource);


    ACRF.Template[] tmpls = parseModelFile (modelFile.value);
    ACRFEvaluator eval = createEvaluator (evalOption.value);


    Inferencer inf = createInferencer (inferencerOption.value);

View Full Code Here


  public void testStateAddWeights() {
    Pipe p = makeSpacePredictionPipe(); // This used to be
    // MEMM.makeSpacePredictionPipe(),
    // but I don't know why -akm 12/2007
    InstanceList training = new InstanceList(p);
    training.addThruPipe(new ArrayIterator(data)); // This used to be
    // MEMM.data, but I
    // don't know why -akm
    // 12/2007


    CRF crf = new CRF(p, null);
    crf.addFullyConnectedStatesForLabels();
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crft.trainIncremental(training);


    // Check that the notstart state is used at test time
    Sequence input = (Sequence) training.get(0).getData();
    Sequence output = new MaxLatticeDefault(crf, input)
        .bestOutputSequence();


    boolean notstartFound = false;
    for (int i = 0; i < output.size(); i++) {

View Full Code Here


            File pageFile = getFileForPage (pageId);
            ObjectInputStream in = null;
            try {
                in = new ObjectInputStream (new FileInputStream (pageFile));
                InstanceList page = deserializePage(in);
                
                this.inMemoryPageIds[bin] = pageId;
                this.inMemoryPages[bin] = page;
            } catch (Exception e) {
                System.err.println (e);

View Full Code Here

            long startTime = System.currentTimeMillis ();
            File pageFile = getFileForPage (pageId);
            ObjectOutputStream out = null;
            try {
                out = new ObjectOutputStream (new FileOutputStream (pageFile));
                InstanceList page = this.inMemoryPages[bin];
                this.inMemoryPageIds[bin] = -1;
                this.inMemoryPages[bin] = null;


                serializePage(out, page);

View Full Code Here

     * the Instance has already been allocated, no check is made to
     * catch OutOfMemoryError.
     * @return <code>true</code> if successful
     */
    public boolean add (Instance instance) {
        InstanceList page;
        if (this.size % this.instancesPerPage == 0) {
            // this is the start of a new page, swap out the one in this pages
            // spot and create a new one
            int pageId = this.size / this.instancesPerPage;
            int bin = pageId % this.inMemoryPages.length;
            swapOut (this.inMemoryPageIds[bin]);
            page = new InstanceList (this.noopPipe);
            this.inMemoryPageIds[bin] = pageId;
            this.inMemoryPages[bin] = page;
        } else {
            page = getPageForIndex (this.size, true);
        }
        boolean ret = page.add (instance);
        if (ret) {
            this.size++;
        }
        return ret;
    }

View Full Code Here

   * This method assumes the input instance contains FeatureVectorSequence as data  
   */
  public Instance pipe(Instance carrier) 
  {
    FeatureVectorSequence fvs = (FeatureVectorSequence) carrier.getData();
    InstanceList ilist = convert(carrier, (Noop) m_tokenClassifiers.getInstancePipe());
    assert (fvs.size() == ilist.size());


    // For passing instances to the token classifier, each instance's data alphabet needs to 
    // match that used by the token classifier at training time.  For the resulting piped 
    // instance, each instance's data alphabet needs to contain token classifier's prediction 
    // as features 
    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,

View Full Code Here

  public static InstanceList convert(InstanceList ilist, Noop alphabetsPipe)
  {
    if (ilist == null) return null;
    
    // This monstrosity is necessary b/c Classifiers obtain the data/target alphabets via pipes
    InstanceList ret = new InstanceList(alphabetsPipe);


    for (Instance inst : ilist)
      ret.add(inst);
    //for (int i = 0; i < ilist.size(); i++) ret.add(convert(ilist.get(i), alphabetsPipe));


    return ret;
  }

View Full Code Here

   * the resulting InstanceList and AugmentableFeatureVectors
   * @return list of instances, each with one AugmentableFeatureVector as data
   */
  public static InstanceList convert(Instance inst, Noop alphabetsPipe)
  {
    InstanceList ret = new InstanceList(alphabetsPipe);
    Object obj = inst.getData();
    assert(obj instanceof FeatureVectorSequence);


    FeatureVectorSequence fvs = (FeatureVectorSequence) obj;
    LabelSequence ls = (LabelSequence) inst.getTarget();
    assert(fvs.size() == ls.size());


    Object instName = (inst.getName() == null ? "NONAME" : inst.getName());
    
    for (int j = 0; j < fvs.size(); j++) {
      FeatureVector fv = fvs.getFeatureVector(j);
      int[] indices = fv.getIndices();
      FeatureVector data = new AugmentableFeatureVector (alphabetsPipe.getDataAlphabet(),
          indices, fv.getValues(), indices.length); 
      Labeling target = ls.getLabelAtPosition(j);
      String name = instName.toString() + "_@_POS_" + (j + 1);
      Object source = inst.getSource();
      Instance toAdd = alphabetsPipe.pipe(new Instance(data, target, name, source));


      ret.add(toAdd);
    }


    return ret;
  }

View Full Code Here

    for (int i = 0; i < numStates; i++)
      stateNames[i] = "state" + i;
    crf.addFullyConnectedStates(stateNames);
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    Optimizable.ByGradientValue mcrf = crft
        .getOptimizableCRF(new InstanceList(null));
    TestOptimizable.testGetSetParameters(mcrf);
  }

View Full Code Here

                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);


    crf.addFullyConnectedStates(stateNames);
    CRFTrainerByLabelLikelihood crft = new CRFTrainerByLabelLikelihood(crf);
    crft.setUseSparseWeights(false);

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.