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

    }
    public boolean hasNext () { 
      return doesHaveNext;
    }
    public Instance next() { 
      Instance ret = nextInstance;
      doesHaveNext = false;
      while (source.hasNext()) {
          nextInstance = source.next();
          if (((FeatureVector)nextInstance.getData()).numLocations() > 0) {
            doesHaveNext = true;

View Full Code Here

  }


  public Void call() throws Exception {
    for (int ii = start; ii < end; ii++) {
      if (instancesWithConstraints.get(ii)) {
        Instance instance = data.get(ii);
        SumLatticeDefault lattice = new SumLatticeDefault(
          this.crf, (FeatureVectorSequence)instance.getData(),
          null, null, true);
        lattices.add(lattice);
      }
      else {
        lattices.add(null);

View Full Code Here

      memmt.train(lists[0], 1);
      System.out.println("Training Accuracy after training = " + memm.averageTokenAccuracy(lists[0]));
      System.out.println("Testing  Accuracy after training = " + memm.averageTokenAccuracy(lists[1]));
      System.out.println("Training results:");
      for (int i = 0; i < lists[0].size(); i++) {
        Instance inst = lists[0].get(i);
        Sequence input = (Sequence) inst.getData ();
        Sequence output = memm.transduce (input);
        System.out.println (output);
      }
      System.out.println ("Testing results:");
      for (int i = 0; i < lists[1].size(); i++) {
        Instance inst = lists[1].get(i);
        Sequence input = (Sequence) inst.getData ();
        Sequence output = memm.transduce (input);
        System.out.println (output);
      }
    }
  }

View Full Code Here

    int numInfWeight = 0;


    double value = 0;
    double unlabeledWeight, labeledWeight, weight;
    for (int ii = batchAssignments[0]; ii < batchAssignments[1]; ii++) {
      Instance instance = trainingSet.get(ii);
      double instanceWeight = trainingSet.getInstanceWeight(instance);
      FeatureVectorSequence input = (FeatureVectorSequence) instance.getData();
      FeatureSequence output = (FeatureSequence) instance.getTarget();


      labeledWeight = new SumLatticeDefault (this.crf, input, output, null).getTotalWeight();
      if (Double.isInfinite (labeledWeight)) {
        ++numInfLabeledWeight;
      }

View Full Code Here

        nextInstance = next();
      return nextInstance; 
    }
    public Instance next () {
      if (nextInstance != null) {
        Instance tmp = nextInstance;
        nextInstance = null;
        return tmp;
      } else {
        return source.next(); 
      }

View Full Code Here

      for (Pipe p : pipes)
        iterators.add (new GateKeepingInstanceIterator (source, p));
    }
    public boolean hasNext () { return source.hasNext(); }
    public Instance next() {
      Instance input = source.peekNext();
      for (int i = 0; i < pipes.size(); i++) {
        if (pipes.get(i).precondition(input)) {
          return iterators.get(i).next();
        }
      }

View Full Code Here

    int numInfWeight = 0;
    
    // Calculate the value of each instance, and also fill in expectations
    double unlabeledWeight, labeledWeight, weight;
    for (int ii = 0; ii < trainingSet.size(); ii++) {
      Instance instance = trainingSet.get(ii);
      double instanceWeight = trainingSet.getInstanceWeight(instance);
      FeatureVectorSequence input = (FeatureVectorSequence) instance.getData();
      FeatureSequence output = (FeatureSequence) instance.getTarget();
      labeledWeight = new SumLatticeDefault (this.crf, input, output, (Transducer.Incrementor)null).getTotalWeight();
      String instanceName = instance.getName() == null ? "instance#"+ii : instance.getName().toString();
      //System.out.println ("labeledWeight = "+labeledWeight);
      if (Double.isInfinite (labeledWeight)) {
        ++numInfLabeledWeight;
        logger.warning (instanceName + " has -infinite labeled weight.\n"+(instance.getSource() != null ? instance.getSource() : ""));
      }
      
      Transducer.Incrementor incrementor = instanceWeight == 1.0 ? expectations.new Incrementor() : expectations.new WeightedIncrementor (instanceWeight);
      unlabeledWeight = new SumLatticeDefault (this.crf, input, null, incrementor).getTotalWeight();
      //System.out.println ("unlabeledWeight = "+unlabeledWeight);
      if (Double.isInfinite (unlabeledWeight)) {
        ++numInfUnlabeledWeight;
        logger.warning (instance.getName().toString() + " has -infinite unlabeled weight.\n"+(instance.getSource() != null ? instance.getSource() : ""));
      }
      
      // Here weight is log(conditional probability correct label sequence)
      weight = labeledWeight - unlabeledWeight;
      //System.out.println ("Instance "+ii+" CRF.MaximizableCRF.getWeight = "+weight);

View Full Code Here

    totalTokens = numCorrectTokens = 0;
    numTrueSegments = numPredictedSegments = numCorrectSegments = 0;
    numCorrectSegmentsInAlphabet = numCorrectSegmentsOOV = 0;
    numIncorrectSegmentsInAlphabet = numIncorrectSegmentsOOV = 0;
    for (int i = 0; i < data.size(); i++) {
      Instance instance = data.get(i);
      Sequence input = (Sequence) instance.getData();
      //String tokens = null;
      //if (instance.getSource() != null)
      //tokens = (String) instance.getSource().toString();
      Sequence trueOutput = (Sequence) instance.getTarget();
      assert (input.size() == trueOutput.size());
      Sequence predOutput = model.transduce (input);
      assert (predOutput.size() == trueOutput.size());
      boolean trueStart, predStart;
      for (int j = 0; j < trueOutput.size(); j++) {

View Full Code Here

    constraints = new CRF.Factors(crf.getParameters());
    expectations = new CRF.Factors(crf.getParameters());


    constraints.zero();
    for (int ii = 0; ii < trainingSet.size(); ii++) {
      Instance inst = trainingSet.get(ii);
      Sequence input = (Sequence) inst.getData();


      SumLatticePR geLatt = 
        new SumLatticePR(crf, ii, input, null, auxModel, cachedDots[ii], false, null, null, true);
      double gammas[][] = geLatt.getGammas();

View Full Code Here

    
    public Double call() throws Exception {
      double value = 0;
      
      for (int ii = start; ii < end; ii++) {
        Instance inst = trainingSet.get(ii);
        Sequence input = (Sequence) inst.getData();
        double initProbs[] = initialProbList.get(ii);
        double finalProbs[] = finalProbList.get(ii);
        double transProbs[][][] = transitionProbList.get(ii);


        double[][][] cachedDots = new double[input.size()][crf.numStates()][crf.numStates()];

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.