Examples of cc.mallet.types.FeatureVector

cc.mallet.types.FeatureVector
A subset of an {@link cc.mallet.types.Alphabet} in which each element of the subset has an associated value.The subset is represented as a {@link cc.mallet.types.SparseVector}
A SparseVector represents only the non-zero locations of a vector. In the case of a FeatureVector, a location represents the index of an entry in the Alphabet that is contained in the FeatureVector.
To loop over the elements of a feature vector, one loops over the consecutive integers between 0 and the number of locations in the feature vector. From these locations one can cheaply obtain the index of the entry in the underlying Alphabet, the entry itself, and the value in this feature vector associated the entry.
A SparseVector (or FeatureVector) can be sparse or dense depending on whether or not an array if indices is specified at construction time. If the FeatureVector is dense, the mapping from location to index is the identity mapping.
The associated value of an element in a SparseVector (or FeatureVector) can be a double or binary (0.0 or 1.0), depending on whether an array of doubles is specified at contruction time. @see SparseVector @see Alphabet @author Andrew McCallum mccallum@cs.umass.edu

      SumLattice lattice = lattices.get(i);
      FeatureVectorSequence fvs = (FeatureVectorSequence)lattice.getInput();
      gammas = lattice.getGammas();
      for (int ip = 0; ip < fvs.size(); ++ip) {
        cache.resetQuick();
        FeatureVector fv = fvs.getFeatureVector(ip);
        int fi;
        for (int loc = 0; loc < fv.numLocations(); loc++) {
          fi = fv.indexAtLocation(loc);
          // binary constraint features
          if (constraints.containsKey(fi)) {
            cache.add(fi);
          }
        }
        if (constraints.containsKey(fv.getAlphabet().size())) {
          cache.add(fv.getAlphabet().size());
        }
        for (int s = 0; s < map.getNumStates(); ++s) {
          int li = map.getLabelIndex(s);
          if (li != StateLabelMap.START_LABEL) {
            double gammaProb = Math.exp(gammas[ip+1][s]);

View Full Code Here

  // find examples that contain constrained input features
  public BitSet preProcess(InstanceList data) {
    // count
    int ii = 0;
    int fi;
    FeatureVector fv;
    BitSet bitSet = new BitSet(data.size());
    for (Instance instance : data) {
      FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
      for (int ip = 0; ip < fvs.size(); ip++) {
        fv = fvs.get(ip);
        for (int loc = 0; loc < fv.numLocations(); loc++) {
          fi = fv.indexAtLocation(loc);
          if (constraints.containsKey(fi)) {
            constraints.get(fi).count += 1;
            bitSet.set(ii);
          }
        }

View Full Code Here

    // Initialize the constraints


    logger.fine("Number of instances in training list = " + trainingList.size());


    for (Instance instance : trainingList) {
      FeatureVector multinomialValues = (FeatureVector) instance.getTarget();


      if (multinomialValues == null)
        continue;


      FeatureVector features = (FeatureVector) instance.getData();
      assert (features.getAlphabet() == alphabet);


      boolean hasNaN = false;


      for (int i = 0; i < features.numLocations(); i++) {
        if (Double.isNaN(features.valueAtLocation(i))) {
          logger.info("NaN for feature " + alphabet.lookupObject(features.indexAtLocation(i)).toString()); 
          hasNaN = true;
        }
      }


      if (hasNaN) {

View Full Code Here


    int instanceIndex = 0;
    
    for (Instance instance: trainingList) {


      FeatureVector multinomialValues = (FeatureVector) instance.getTarget();
      if (multinomialValues == null) { continue; }


      //System.out.println("L Now "+inputAlphabet.size()+" regular features.");
                
      // Get the predicted probability of each class
      //   under the current model parameters
      this.classifier.getUnnormalizedClassificationScores(instance, scores);


      double sumScores = 0.0;


      // Exponentiate the scores
      for (int i=0; i<scores.length; i++) {
        // Due to underflow, it's very likely that some of these scores will be 0.0.
        scores[i] = Math.exp(scores[i]);
        sumScores += scores[i];
      }


      FeatureVector features = (FeatureVector) instance.getData();


      // This is really an int, but since FeatureVectors are defined as doubles, 
      //  avoid casting.
      double totalLength = 0;

View Full Code Here


    int instanceIndex = 0;


    for (Instance instance: trainingList) {


      FeatureVector multinomialValues = (FeatureVector) instance.getTarget();
      if (multinomialValues == null) { continue; }


      // Get the predicted probability of each class
      //   under the current model parameters
      this.classifier.getUnnormalizedClassificationScores(instance, scores);


      double sumScores = 0.0;


      // Exponentiate the scores
      for (int i=0; i<scores.length; i++) {
        // Due to underflow, it's very likely that some of these scores will be 0.0.
        scores[i] = Math.exp(scores[i]);
        sumScores += scores[i];
      }


      FeatureVector features = (FeatureVector) instance.getData();


      double totalLength = 0;


      for (double count : multinomialValues.getValues()) {
        totalLength += count;
      }
      
      double digammaDifferenceForSums = 
        Dirichlet.digamma(sumScores + totalLength) -
        Dirichlet.digamma(sumScores);
      
      for (int loc = 0; loc < features.numLocations(); loc++) {
        int index = features.indexAtLocation(loc);
        double value = features.valueAtLocation(loc);
                    
        if (value == 0.0) { continue; }


        // In a FeatureVector, there's no easy way to say "do you know
        //   about this id?" so I've broken this into two for loops,

View Full Code Here

  }


  // "size" is the number of 1.0-weight features in the feature vector
  public FeatureVector randomFeatureVector (Randoms r, int size)
  {
    return new FeatureVector (randomFeatureSequence (r, size));
  }

View Full Code Here

  // find examples that contain constrained input features
  public BitSet preProcess(InstanceList data) {
    // count
    int ii = 0;
    int fi;
    FeatureVector fv;
    BitSet bitSet = new BitSet(data.size());
    for (Instance instance : data) {
      FeatureVectorSequence fvs = (FeatureVectorSequence)instance.getData();
      for (int ip = 0; ip < fvs.size(); ip++) {
        fv = fvs.get(ip);
        for (int loc = 0; loc < fv.numLocations(); loc++) {
          fi = fv.indexAtLocation(loc);
          if (constraints.containsKey(fi)) {
            constraints.get(fi).count += 1;
            bitSet.set(ii);
          }
        }
        if (constraints.containsKey(fv.getAlphabet().size())) {
          bitSet.set(ii);
          constraints.get(fv.getAlphabet().size()).count += 1;
        }
      }


      ii++;
    }

View Full Code Here

      SumLattice lattice = lattices.get(i);
      FeatureVectorSequence fvs = (FeatureVectorSequence)lattice.getInput();
      gammas = lattice.getGammas();
      for (int ip = 0; ip < fvs.size(); ++ip) {
        cache.resetQuick();
        FeatureVector fv = fvs.getFeatureVector(ip);
        int fi;
        for (int loc = 0; loc < fv.numLocations(); loc++) {
          fi = fv.indexAtLocation(loc);
          // binary constraint features
          if (constraints.containsKey(fi)) {
            cache.add(fi);
          }
        }
        if (constraints.containsKey(fv.getAlphabet().size())) {
          cache.add(fv.getAlphabet().size());
        }
        for (int s = 0; s < map.getNumStates(); ++s) {
          int li = map.getLabelIndex(s);
          if (li != StateLabelMap.START_LABEL) {
            double gammaProb = Math.exp(gammas[ip+1][s]);

View Full Code Here

  
  
  public Instance pipe (Instance carrier)
  {
    FeatureSequence fs = (FeatureSequence) carrier.getData();
    carrier.setData(new FeatureVector (fs, binary));
    return carrier;
  }

View Full Code Here

      FeatureVectorSequence fvs = (FeatureVectorSequence)lattices.get(i).getInput();
      SumLattice lattice = lattices.get(i);
      xis = lattice.getXis();
      for (int ip = 1; ip < fvs.size(); ++ip) {
        cache.resetQuick();
        FeatureVector fv = fvs.getFeatureVector(ip);
        int fi;
        for (int loc = 0; loc < fv.numLocations(); loc++) {
          fi = fv.indexAtLocation(loc);
          // binary constraint features
          if (constraintsMap.containsKey(fi)) {
            cache.add(constraintsMap.get(fi));
          }
        }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of cc.mallet.types.FeatureVector

cc.mallet.classify.BalancedWinnow

cc.mallet.classify.BalancedWinnowTrainer

cc.mallet.classify.C45

cc.mallet.classify.C45$Node

cc.mallet.classify.Classification

cc.mallet.classify.constraints.ge.MaxEntFLGEConstraints

cc.mallet.classify.constraints.ge.MaxEntRangeL2FLGEConstraints

cc.mallet.classify.constraints.pr.MaxEntFLPRConstraints

cc.mallet.classify.DecisionTree

cc.mallet.classify.DecisionTree$Node

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.