Examples of cc.mallet.types.Alphabet

cc.mallet.types.Alphabet
A mapping between integers and objects where the mapping in each direction is efficient. Integers are assigned consecutively, starting at zero, as objects are added to the Alphabet. Objects can not be deleted from the Alphabet and thus the integers are never reused.
The most common use of an alphabet is as a dictionary of feature names associated with a {@link cc.mallet.types.FeatureVector} in an{@link cc.mallet.types.Instance}. In a simple document classification usage, each unique word in a document would be a unique entry in the Alphabet with a unique integer associated with it. FeatureVectors rely on the integer part of the mapping to efficiently represent the subset of the Alphabet present in the FeatureVector. @see FeatureVector @see Instance @see cc.mallet.pipe.Pipe

  }


  public void testMaxLattice() {
    int inputVocabSize = 1;
    int numStates = 2;
    Alphabet inputAlphabet = new Alphabet();
    for (int i = 0; i < inputVocabSize; i++)
      inputAlphabet.lookupIndex("feature" + i);
    Alphabet outputAlphabet = new Alphabet();


    CRF crf = new CRF(inputAlphabet, outputAlphabet);


    String[] stateNames = new String[numStates];
    for (int i = 0; i < numStates; i++)

View Full Code Here

    int inputVocabSize = 4;
    int numStates = 5;
    // Create a file to store the CRF
    File f = new File("TestObject.obj");
    File f2 = new File("TestObject2.obj");
    Alphabet inputAlphabet = new Alphabet();
    for (int i = 0; i < inputVocabSize; i++)
      inputAlphabet.lookupIndex("feature" + i);
    Alphabet outputAlphabet = new Alphabet();
    String[] stateNames = new String[numStates];
    for (int i = 0; i < numStates; i++) {
      stateNames[i] = "state" + i;
      outputAlphabet.lookupIndex(stateNames[i]);
    }


    CRF crf = new CRF(inputAlphabet, outputAlphabet);
    CRF saveCRF = crf;
    // inputAlphabet = (Feature.Alphabet) crf.getInputAlphabet();

View Full Code Here

    super (name);
  }
  
  public void testNewPutSizeFreeze ()
  {
    Alphabet dict = new Alphabet ();
    FeatureSequence fs = new FeatureSequence (dict, 10);
    fs.add (dict.lookupIndex ("apple"));
    fs.add (dict.lookupIndex ("bear"));
    fs.add (dict.lookupIndex ("car"));
    fs.add (dict.lookupIndex ("door"));
    assertTrue (fs.size() == 4);
    double[] weights = new double[4];
    fs.addFeatureWeightsTo (weights);
    assertTrue (weights[1] == 1.0);


    fs.add (dict.lookupIndex ("bear"));
    int[] feats = fs.toFeatureIndexSequence();
    assertTrue (feats[0] == 0);
    assertTrue (feats[1] == 1);
    assertTrue (feats[2] == 2);
    assertTrue (feats[3] == 3);

View Full Code Here

    this (dataDict, false, false);
  }
  
  public TokenSequence2FeatureVectorSequence (boolean binary, boolean augmentable)
  {
    super (new Alphabet(), null);
    this.augmentable = augmentable;
    this.binary = binary;
  }

View Full Code Here


  private static int[] indicesWithConjunctions (FeatureVector fv, Alphabet newVocab, int[] conjunctions)
  {
    assert (fv.values == null);          // Only works on binary feature vectors
    assert (! (fv instanceof AugmentableFeatureVector));
    Alphabet v = fv.getAlphabet();
    // newVocab should be an augmented copy of v
    assert (v.size() <= newVocab.size())
                        : "fv.vocab.size="+v.size()+" newVocab.size="+newVocab.size();
    int[] newIndices = new int[fv.indices.length * conjunctions.length];
    java.util.Arrays.sort (conjunctions);
    System.arraycopy (fv.indices, 0, newIndices, 0, fv.indices.length);
    int size = fv.indices.length;
    int ci = 0;

View Full Code Here

                                                FeatureSelection fsNarrow,
                                                FeatureSelection fsWide)
  {
    assert (fv.values == null);          // Only works on binary feature vectors
    ////assert (! (fv instanceof AugmentableFeatureVector));
    Alphabet v = fv.getAlphabet();
    // newVocab should be an augmented copy of v
    assert (v.size() <= newVocab.size())
                        : "fv.vocab.size="+v.size()+" newVocab.size="+newVocab.size();
    int length;
    if (fv instanceof AugmentableFeatureVector) {
      length = ((AugmentableFeatureVector)fv).size;
      ((AugmentableFeatureVector)fv).sortIndices();
    } else {

View Full Code Here

    return b.toString();
  }


  public static void main (String[] args) {
    Record r =
        new Record(new Alphabet(), new Alphabet(),
                    new String[][] { { "field1", "f1v1", "f1v2" },
                                    { "field2", "f2v1" },
                                    { "field3", "f3v1", "f3v2", "f3v3" } });
    System.out.println(r);
  }

View Full Code Here

    this.random = new Randoms(123456789);
    this.noise = 0.01;
  }
  
  public void run () {
    Alphabet alphabet = dictOfSize(20);
    
    // TRAIN
    Clustering training = sampleClustering(alphabet);    
    Pipe clusterPipe = new OverlappingFeaturePipe();
    System.err.println("Training with " + training);

View Full Code Here

    }
    return singletons;
  }


   private Alphabet dictOfSize (int size) {
    Alphabet ret = new Alphabet ();
    for (int i = 0; i < size; i++)
      ret.lookupIndex ("feature"+i);
     return ret;
  }

View Full Code Here

  private class OverlappingFeaturePipe extends Pipe {


    private static final long serialVersionUID = 1L;


    public OverlappingFeaturePipe () {
      super (new Alphabet(), new LabelAlphabet());      
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of cc.mallet.types.Alphabet

cc.mallet.classify.BalancedWinnowTrainer

cc.mallet.classify.FeatureConstraintUtil

cc.mallet.classify.MaxEnt

cc.mallet.classify.MaxEntOptimizableByLabelDistribution

cc.mallet.classify.MaxEntOptimizableByLabelLikelihood

cc.mallet.classify.MCMaxEnt

cc.mallet.classify.MCMaxEntTrainer$MaximizableTrainer

cc.mallet.classify.RankMaxEnt

cc.mallet.classify.RankMaxEntTrainer$MaximizableTrainer

cc.mallet.classify.WinnowTrainer

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.