Examples of cc.mallet.types.Instance

cc.mallet.types.Instance
A machine learning "example" to be used in training, testing or performance of various machine learning algorithms.
An instance contains four generic fields of predefined name: "data", "target", "name", and "source". "Data" holds the data represented `by the instance, "target" is often a label associated with the instance, "name" is a short identifying name for the instance (such as a filename), and "source" is human-readable sourceinformation, (such as the original text).
Each field has no predefined type, and may change type as the instance is processed. For example, the data field may start off being a string that represents a file name and then be processed by a {@link cc.mallet.pipe.Pipe} into a CharSequencerepresenting the contents of the file, and eventually to a feature vector holding indices into an {@link cc.mallet.types.Alphabet} holding words found in the file.It is up to each pipe which fields in the Instance it modifies; the most common case is that the pipe modifies the data field.
Generally speaking, there are two modes of operation for Instances. (1) An instance gets created and passed through a Pipe, and the resulting data/target/name/source fields are used. This is generally done for training instances. (2) An instance gets created with raw values in its slots, then different users of the instance call newPipedCopy() with their respective different pipes. This might be done for test instances at "performance" time.
Rather than store an {@link cc.mallet.types.Alphabet} in the Instance,we obtain it through the Pipe instance variable, because the Pipe also indicates where the data came from and how to interpret the Alphabet.
Instances can be made immutable if locked. Although unlocked Instances are mutable, typically the only code that changes the values in the four slots is inside Pipes.
Note that constructing an instance with a pipe argument means "Construct the instance and then run it through the pipe". {@link cc.mallet.types.InstanceList} uses this methodwhen adding instances through a pipeInputIterator. @see Pipe @see Alphabet @see InstanceList @author Andrew McCallum mccallum@cs.umass.edu

      resetExpectations();


      /* Fill in expectations for each instance */
      for (int i = 0; i < numInstances; i++)
      {
        Instance instance = trainData.get(i);


        /* Compute marginals for each clique */
        long unrollStart = System.currentTimeMillis ();
        ACRF.UnrolledGraph unrolled = new ACRF.UnrolledGraph (instance, templates, fixedTmpls);
        long unrollEnd = System.currentTimeMillis ();
        unrollTime += (unrollEnd - unrollStart);


        if (unrolled.numVariables () == 0) continue;   // Happens if all nodes are pruned.


        /* Save the expected value of each feature for when we
           compute the gradient. */
        Assignment observations = unrolled.getAssignment ();
        double value = collectExpectationsAndValue (unrolled, observations);


        if (Double.isInfinite(value))
        {
          if (initializingInfiniteValues) {
            logger.warning ("Instance " + instance.getName() +
                            " has infinite value; skipping.");
            infiniteValues.set (i);
            continue;
          } else if (!infiniteValues.get(i)) {
            logger.warning ("Infinite value on instance "+instance.getName()+
                            "returning -infinity");
            return Double.NEGATIVE_INFINITY;
/*
            printDebugInfo (unrolled);
            throw new IllegalStateException
              ("Instance " + instance.getName()+ " used to have non-infinite"
               + " value, but now it has infinite value.");
*/
          }
        } else if (Double.isNaN (value)) {
          System.out.println("NaN on instance "+i+" : "+instance.getName ());
          printDebugInfo (unrolled);
/*          throw new IllegalStateException
            ("Value is NaN in ACRF.getValue() Instance "+i);
*/
          logger.warning ("Value is NaN in ACRF.getValue() Instance "+i+" : "+

View Full Code Here


    public void collectConstraints (InstanceList ilist)
    {
      for (int inum = 0; inum < ilist.size(); inum++) {
        logger.finest ("*** Collecting constraints for instance "+inum);
        Instance inst = ilist.get (inum);
        ACRF.UnrolledGraph unrolled = new ACRF.UnrolledGraph (inst, templates, null, true);
        Assignment assn = unrolled.getAssignment ();
        collectConstraintsForGraph (unrolled, assn);
      }
    }

View Full Code Here

      i++;
      j = i + 1;
    } else {
      j++;
    }
    return new Instance(neighbor, null, null, null);
  }

View Full Code Here

        new SGML2TokenSequence()
//        new SGML2TokenSequence (new CharSequenceLexer (Pattern.compile (".")), "O")
        });


      for (int i = 0; i < args.length; i++) {
        Instance carrier = p.instanceFrom(new Instance (new File(args[i]), null, null, null));
        TokenSequence data = (TokenSequence) carrier.getData();
        TokenSequence target = (TokenSequence) carrier.getTarget();
        logger.finer ("===");
        logger.info (args[i]);
        for (int j = 0; j < data.size(); j++)
          logger.info (target.get(j).getText()+" "+data.get(j).getText());
      }

View Full Code Here

  public Instance[] instancesFrom (Iterator<Instance> source)
  {
    source = this.newIteratorFrom(source);
    if (!source.hasNext())
      return new Instance[0];
    Instance inst = source.next();
    if (!source.hasNext())
      return new Instance[] {inst};
    ArrayList<Instance> ret = new ArrayList<Instance>();
    ret.add(inst);
    while (source.hasNext())

View Full Code Here

    public SimplePipeInstanceIterator (Iterator<Instance> source) {
      this.source = source;
    }
    public boolean hasNext () { return source.hasNext(); }
    public Instance next() { 
      Instance input = source.next();
      if (!precondition(input))
        return input;
      else
        return pipe (input); 
      }

View Full Code Here

  private boolean[][] labelConnectionsIn (InstanceList trainingSet, String start)
  {
    int numLabels = outputAlphabet.size();
    boolean[][] connections = new boolean[numLabels][numLabels];
    for (int i = 0; i < trainingSet.size(); i++) {
      Instance instance = trainingSet.get(i);
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      for (int j = 1; j < output.size(); j++) {
        int sourceIndex = outputAlphabet.lookupIndex (output.get(j-1));
        int destIndex = outputAlphabet.lookupIndex (output.get(j));
        assert (sourceIndex >= 0 && destIndex >= 0);
        connections[sourceIndex][destIndex] = true;

View Full Code Here

            Object data = deserializeObject (in);
            Object target = deserializeObject (in);
            Object name = in.readObject ();
            Object source = in.readObject ();
            double weight = in.readDouble ();
            page.add (new Instance (data, target, name, source), weight);
        }
        
        return page;
    }

View Full Code Here

    for (int i = 0; i < parameters.weights.length; i++) 
      for (int j = parameters.weights[i].numLocations()-1; j >= 0; j--)
        weightsPresent[i].set (parameters.weights[i].indexAtLocation(j));
    // Put in the weights in the training set
    for (int i = 0; i < trainingData.size(); i++) {
      Instance instance = trainingData.get(i);
      FeatureVectorSequence input = (FeatureVectorSequence) instance.getData();
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      // gsc: trainingData can have unlabeled instances as well
      if (output != null && output.size() > 0) {
        // Do it for the paths consistent with the labels...
        sumLatticeFactory.newSumLattice (this, input, output, new Transducer.Incrementor() {
          public void incrementTransition (Transducer.TransitionIterator ti, double count) {

View Full Code Here

    // 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, 
          indices, afv1.getValues(), indices.length + m_predRanks2add.length);


      for (int j = 0; j < m_predRanks2add.length; j++) {

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of cc.mallet.types.Instance

cc.mallet.classify.BalancedWinnowTrainer

cc.mallet.classify.C45$Node

cc.mallet.classify.Classification

cc.mallet.classify.Classifier

cc.mallet.classify.DecisionTree$Node

cc.mallet.classify.evaluate.ConfusionMatrix

cc.mallet.classify.FeatureConstraintUtil

cc.mallet.classify.MaxEntOptimizableByGE

cc.mallet.classify.MaxEntOptimizableByLabelDistribution

cc.mallet.classify.MaxEntOptimizableByLabelLikelihood

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.