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

  }


  //printRank, added by Limin Yao
  public void printRank (PrintWriter out)
  {
    final Alphabet dict = getAlphabet();
    final LabelAlphabet labelDict = getLabelAlphabet();


    int numFeatures = dict.size() + 1;
    int numLabels = labelDict.size();
  // Include the feature weights according to each label
    RankedFeatureVector rfv;
    double[] weights = new double[numFeatures-1]; // do not deal with the default feature
    for (int li = 0; li < numLabels; li++) {

View Full Code Here

    }
  }


  public void printExtremeFeatures (PrintWriter out,int num)
  {
    final Alphabet dict = getAlphabet();
    final LabelAlphabet labelDict = getLabelAlphabet();


    int numFeatures = dict.size() + 1;
    int numLabels = labelDict.size();


    // Include the feature weights according to each label
    RankedFeatureVector rfv;
    double[] weights = new double[numFeatures-1]; // do not deal with the default feature
    for (int li = 0; li < numLabels; li++) {
      out.print ("FEATURES FOR CLASS "+labelDict.lookupObject (li) + " ");
      for (int i = 0; i < defaultFeatureIndex; i++) {
        Object name = dict.lookupObject (i);
        double weight = parameters [li*numFeatures + i];
        weights[i] = weight;
      }
      rfv = new RankedFeatureVector(dict,weights);
      rfv.printTopK(out,num);

View Full Code Here

          sortedTypes[type] = new IDSorter(type, nkt.get(k)[type]);
        }
        
        Arrays.sort(sortedTypes);
      
        Alphabet alphabet = instances.getDataAlphabet();
        StringBuffer out = new StringBuffer();
        out.append("topic"+k + ": ");
        out.append("word:"+ count + ", ");
        if(k< kactive.size()){
          out.append("matched topic "+kactive.get(k) + ", ");
        }
        double prop = (double)count/totalWord;
        out.append(String.format("prop:%2.4f, ", prop));
      
        for (int i=0; i<numWords; i++) {
          out.append(alphabet.lookupObject(sortedTypes[i].getID()) + " ");
        }
        System.out.println(out);
      }
      else{
        if(k < kactive.size() )

View Full Code Here

            sortedTypes[type] = new IDSorter(type, nkt.get(k)[type]);
          }
          
          Arrays.sort(sortedTypes);
        
          Alphabet alphabet = instances.getDataAlphabet();
          StringBuffer out = new StringBuffer();
          out.append("topic"+k + ": ");
          if(k< kactive.size()){
            out.append("matched topic "+kactive.get(k) + ", ");
          }
          out.append("word:"+ nk.get(k) + ", ");
          double prop = (double)nk.get(k)/totalWord;
          out.append(String.format("prop:%2.4f, ", prop));
        
          for (int i=0; i<numWords; i++) {
            out.append(alphabet.lookupObject(sortedTypes[i].getID()) + " ");
          }
          System.out.println(out);
        }
        else{
          if(k < kactive.size() )

View Full Code Here

    
    
    
    if (p.isTargetProcessing())
    {
      Alphabet targets = p.getTargetAlphabet();
      StringBuffer buf = new StringBuffer("Labels:");
      for (int i = 0; i < targets.size(); i++)
        buf.append(" ").append(targets.lookupObject(i).toString());
      logger.info(buf.toString());
    }
    if (trainOption.value)
    {
      crf = train(trainingData, testData, eval,

View Full Code Here

    print(System.out);
  }


  public void print (PrintStream out)
  {
    final Alphabet dict = getAlphabet();
    final LabelAlphabet labelDict = getLabelAlphabet();


    int numFeatures = dict.size() + 1;
    int numLabels = labelDict.size();


    // Include the feature weights according to each label
    for (int li = 0; li < numLabels; li++) {
      out.println ("FEATURES FOR CLASS "+labelDict.lookupObject (li));
      out.println (" <default> "+parameters [li*numFeatures + defaultFeatureIndex]);
      for (int i = 0; i < defaultFeatureIndex; i++) {
        Object name = dict.lookupObject (i);
        double weight = parameters [li*numFeatures + i];
        out.println (" "+name+" "+weight);
      }
    }
  }

View Full Code Here

  }


  //printRank, added by Limin Yao
  public void printRank (PrintWriter out)
  {
    final Alphabet dict = getAlphabet();
    final LabelAlphabet labelDict = getLabelAlphabet();


    int numFeatures = dict.size() + 1;
    int numLabels = labelDict.size();
  // Include the feature weights according to each label
    RankedFeatureVector rfv;
    double[] weights = new double[numFeatures-1]; // do not deal with the default feature
    for (int li = 0; li < numLabels; li++) {

View Full Code Here

    }
  }


  public void printExtremeFeatures (PrintWriter out,int num)
  {
    final Alphabet dict = getAlphabet();
    final LabelAlphabet labelDict = getLabelAlphabet();


    int numFeatures = dict.size() + 1;
    int numLabels = labelDict.size();


    // Include the feature weights according to each label
    RankedFeatureVector rfv;
    double[] weights = new double[numFeatures-1]; // do not deal with the default feature
    for (int li = 0; li < numLabels; li++) {
      out.print ("FEATURES FOR CLASS "+labelDict.lookupObject (li) + " ");
      for (int i = 0; i < defaultFeatureIndex; i++) {
        Object name = dict.lookupObject (i);
        double weight = parameters [li*numFeatures + i];
        weights[i] = weight;
      }
      rfv = new RankedFeatureVector(dict,weights);
      rfv.printTopK(out,num);

View Full Code Here

     * Creates a new
     * <code>SimpleTaggerSentence2FeatureVectorSequence</code> instance.
     */
    public SimpleTaggerSentence2FeatureVectorSequence ()
    {
      super (new Alphabet(), new LabelAlphabet());
    }

View Full Code Here

    }


    public Instance pipe (Instance carrier)
    {
      Object inputData = carrier.getData();
      Alphabet features = getDataAlphabet();
      LabelAlphabet labels;
      LabelSequence target = null;
      String [][] tokens;
      if (inputData instanceof String)
        tokens = parseSentence((String)inputData);
      else if (inputData instanceof String[][])
        tokens = (String[][])inputData;
      else
        throw new IllegalArgumentException("Not a String or String[][]; got "+inputData);
      FeatureVector[] fvs = new FeatureVector[tokens.length];
      if (isTargetProcessing())
      {
        labels = (LabelAlphabet)getTargetAlphabet();
        target = new LabelSequence (labels, tokens.length);
      }
      for (int l = 0; l < tokens.length; l++) {
        int nFeatures;
        if (isTargetProcessing())
        {
          if (tokens[l].length < 1)
            throw new IllegalStateException ("Missing label at line " + l + " instance "+carrier.getName ());
          nFeatures = tokens[l].length - 1;
          target.add(tokens[l][nFeatures]);
        }
        else nFeatures = tokens[l].length;
        ArrayList<Integer> featureIndices = new ArrayList<Integer>();
        for (int f = 0; f < nFeatures; f++) {
          int featureIndex = features.lookupIndex(tokens[l][f]);
          // gdruck
          // If the data alphabet's growth is stopped, featureIndex
          // will be -1.  Ignore these features.
          if (featureIndex >= 0) {
            featureIndices.add(featureIndex);

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.