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

  public int value (String field) {
    return value(fieldAlph.lookupIndex(field));
  }
  
  public int value (int field) {
    FeatureVector fv = values(field);
    return (fv == null) ? -1 : fv.indexAtLocation(0);
  }

View Full Code Here

  public String toString (boolean oneLine) {
    StringBuffer b = new StringBuffer();
    int[] keys = field2values.keys();
    for (int i = 0; i < keys.length; i++) {
      b.append(fieldAlph.lookupObject(keys[i]) + "=");
      FeatureVector v = (FeatureVector) field2values.get(keys[i]);
      for (int j = 0; j < v.numLocations(); j++)
        b.append(valueAlph.lookupObject(v.indexAtLocation(j)) + ",");
      if (!oneLine) b.append("\n");
    }
    return b.toString();
  }

View Full Code Here

                       new String[]{"foo", "bar"},
                       30).subList(0, 20);
    Clustering singletons = ClusterUtils.createSingletonClustering(instances);
    // Merge instances that both have feature0
    for (int i = 0; i < instances.size(); i++) {
      FeatureVector fvi = (FeatureVector)instances.get(i).getData();
      for (int j = i + 1; j < instances.size(); j++) {
        FeatureVector fvj = (FeatureVector)instances.get(j).getData();
        if (fvi.contains("feature0") && fvj.contains("feature0")) {
          singletons = ClusterUtils.mergeClusters(singletons,
                                                  singletons.getLabel(i),
                                                  singletons.getLabel(j));
        } else if (!(fvi.contains("feature0") || fvj.contains("feature0"))
                   && random.nextUniform() < noise) {
          // Random noise.
          singletons = ClusterUtils.mergeClusters(singletons,
                                                  singletons.getLabel(i),
                                                  singletons.getLabel(j));

View Full Code Here

      assert (input.size() == trueOutput.size());
      Sequence predOutput = transducerTrainer.getTransducer().transduce (input);
      assert (predOutput.size() == trueOutput.size());
      
      for (int j = 0; j < trueOutput.size(); j++) {
        FeatureVector fv = (FeatureVector) input.get(j);
        //viterbiOutputStream.println (tokens.charAt(j)+" "+trueOutput.get(j).toString()+
        //'/'+predOutput.get(j).toString()+"  "+ fv.toString(true));
        if (sourceTokenSequence != null)
          viterbiOutputStream.print (sourceTokenSequence.get(j).getText()+": ");
        viterbiOutputStream.println (trueOutput.get(j).toString()+
            '/'+predOutput.get(j).toString()+"  "+ fv.toString(true));
      }
    }
  }

View Full Code Here

      boolean match = true;
      for (int i = 0; i < mergedIndices.length; i++) {
        for (int j = i + 1; j < mergedIndices.length; j++) {
          if ((original.getLabel(mergedIndices[i]) !=
               original.getLabel(mergedIndices[j])) || mergeFirst) {
            FeatureVector fvi = (FeatureVector)list.get(mergedIndices[i]).getData();
            FeatureVector fvj = (FeatureVector)list.get(mergedIndices[j]).getData();
            if (!(fvi.contains("feature0") && fvj.contains("feature0"))) {
              match = false;
              break;              
            }
          }
        }
      }


      PropertyList pl = null;
      if (match) 
        pl = PropertyList.add("Match", 1.0, pl);
      else
        pl = PropertyList.add("NoMatch", 1.0, pl);
      
      FeatureVector fv = new FeatureVector ((Alphabet)getDataAlphabet(),
                                            pl, true);
      carrier.setData(fv);


      boolean positive = true;
      for (int i = 0; i < mergedIndices.length; i++) {

View Full Code Here


    if ( dataLength > dataAlphabet.size() )
      for (int k=dataAlphabet.size() ; k<dataLength ; k++ )
        dataAlphabet.lookupIndex( new Integer(k) , true ); // 'add'


    FeatureVector fv = new FeatureVector( dataAlphabet, 
        (double[])carrier.getData() );




    // Check if we've set the target alphabet member
    if (targetAlphabet == null) {

View Full Code Here

    dict.lookupIndex ("ZERO");
    dict.lookupIndex ("ONE");
    dict.lookupIndex ("TWO");
    dict.lookupIndex ("THREE");


    FeatureVector fv = new FeatureVector (dict, new int[] { 1,3 });


    AugmentableFeatureVector afv = new AugmentableFeatureVector (new Alphabet (), true);
    afv.add (fv, "O:");


    assertEquals (4, dict.size());

View Full Code Here

    //System.out.println("Init weights to 1.  Theta= "+theta);
    // loop through all instances
    for (int ii = 0; ii < trainingList.size(); ii++){
      Instance inst = (Instance) trainingList.get(ii);
      Labeling labeling = inst.getLabeling ();
      FeatureVector fv = (FeatureVector) inst.getData ();
      double[] results = new double [numLabels]; 
      int fvisize = fv.numLocations();
      int correctIndex = labeling.getBestIndex();
      
      for(int rpos=0; rpos < numLabels; rpos++)
        results[rpos]=0;
      // sum up xi*wi for each class
      for(int fvi=0; fvi < fvisize; fvi++){
        int fi = fv.indexAtLocation(fvi);
        //System.out.println("feature index "+fi);
        for(int lpos=0; lpos < numLabels; lpos++)
          results[lpos] += this.weights[lpos][fi];
      }
      //System.out.println("In instance " + ii);

View Full Code Here

      // skip if labeled
      if (instance.getTarget() != null) {
        continue;
      }
      
      FeatureVector fv = (FeatureVector) instance.getData();
      classifier.getClassificationScoresWithTemperature(instance, temperature, scores[ii]);
      for (MaxEntGEConstraint constraint : constraints) {
        constraint.computeExpectations(fv,scores[ii],instanceWeight);
      }
    }
    
    // compute value
    double value = 0;
    for (MaxEntGEConstraint constraint : constraints) {
      value += constraint.getValue();
    }
    value *= objWeight;


    // pass 2: determine per example gradient
    for (int ii = 0; ii < trainingList.size(); ii++) {
      Instance instance = trainingList.get(ii);
      
      // skip if labeled
      if (instance.getTarget() != null) {
        continue;
      }
      
      Arrays.fill(constraintValue,0);
      double instanceExpectation = 0;
      double instanceWeight = trainingList.getInstanceWeight(instance);
      FeatureVector fv = (FeatureVector) instance.getData();


      for (MaxEntGEConstraint constraint : constraints) {
        constraint.preProcess(fv);
        for (int label = 0; label < numLabels; label++) {
          double val = constraint.getCompositeConstraintFeatureValue(fv, label);

View Full Code Here


  public BitSet preProcess(InstanceList data) {
    // count
    int ii = 0;
    int fi;
    FeatureVector fv;
    BitSet bitSet = new BitSet(data.size());
    for (Instance instance : data) {
      double weight = data.getInstanceWeight(instance);
      fv = (FeatureVector)instance.getData();
      for (int loc = 0; loc < fv.numLocations(); loc++) {
        fi = fv.indexAtLocation(loc);
        if (constraints.containsKey(fi)) {
          if (useValues) {
            constraints.get(fi).count += weight * fv.valueAtLocation(loc);
          }
          else {
            constraints.get(fi).count += weight; 
          }
          bitSet.set(ii);

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.