Examples of cc.mallet.types.InstanceList

cc.mallet.types.InstanceList
A list of machine learning instances, typically used for training or testing of a machine learning algorithm.
All of the instances in the list will have been passed through the same {@link cc.mallet.pipe.Pipe}, and thus must also share the same data and target Alphabets. InstanceList keeps a reference to the pipe and the two alphabets.
The most common way of adding instances to an InstanceList is through the add(PipeInputIterator) method. PipeInputIterators are a way of mapping general data sources into instances suitable for processing through a pipe. As each {@link cc.mallet.types.Instance} is pulled from the PipeInputIterator, the InstanceListcopies the instance and runs the copy through its pipe (with resultant destructive modifications) before saving the modified instance on its list. This is the usual way in which instances are transformed by pipes.
InstanceList also contains methods for randomly generating lists of feature vectors; splitting lists into non-overlapping subsets (useful for test/train splits), and iterators for cross validation. @see Instance @see Pipe @author Andrew McCallum mccallum@cs.umass.edu

      new FeatureVector(crf.getInputAlphabet(), new int[]{1, 2, 3}, new double[]{1, 1, 1}),
      new FeatureVector(crf.getInputAlphabet(), new int[]{1, 2, 3}, new double[]{1, 1, 1}),
      new FeatureVector(crf.getInputAlphabet(), new int[]{1, 2, 3}, new double[]{1, 1, 1}),
    });
    FeatureSequence ss = new FeatureSequence(crf.getOutputAlphabet(), new int[]{0, 1, 2, 3});
    InstanceList ilist = new InstanceList(null);
    ilist.add(fvs, ss, null, null);


    crf.addFullyConnectedStates(stateNames);


    try {
      ObjectOutputStream oos = new ObjectOutputStream(new FileOutputStream(f));

View Full Code Here

  public void doTestSpacePrediction(boolean testValueAndGradient)
  {
    Pipe p = makeSpacePredictionPipe ();
    Pipe p2 = new TestMEMM2String();


    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new double[]{.5, .5});
    MEMM memm = new MEMM(p, p2);
    memm.addFullyConnectedStatesForLabels();
    memm.setWeightsDimensionAsIn(lists[0]);
    
    MEMMTrainer memmt = new MEMMTrainer (memm);

View Full Code Here

  {
    Pipe p = makeSpacePredictionPipe ();


    MEMM savedCRF;
    File f = new File("TestObject.obj");
    InstanceList instances = new InstanceList(p);
    instances.addThruPipe(new ArrayIterator(data));
    InstanceList[] lists = instances.split(new double[]{.5, .5});
    MEMM crf = new MEMM(p.getDataAlphabet(), p.getTargetAlphabet());
    crf.addFullyConnectedStatesForLabels();
    if (useSparseWeights)
      crf.setWeightsDimensionAsIn(lists[0]);
    else

View Full Code Here


  public void disabledtestAddOrderNStates ()
  {
    Pipe p = makeSpacePredictionPipe ();


    InstanceList instances = new InstanceList (p);
    instances.addThruPipe (new ArrayIterator(data));
    InstanceList[] lists = instances.split (new java.util.Random (678), new double[]{.5, .5});


    // Compare 3 CRFs trained with addOrderNStates, and make sure
    // that having more features leads to a higher likelihood


    MEMM crf1 = new MEMM(p.getDataAlphabet(), p.getTargetAlphabet());

View Full Code Here

       new TokenText(),
       new TestMEMM.TestMEMMTokenSequenceRemoveSpaces(),
       new TokenSequence2FeatureVectorSequence(),
       new PrintInputAndTarget(),
    });
    InstanceList one = new InstanceList (p);
    String[] data = new String[] { "ABCDE", };
    one.addThruPipe (new ArrayIterator (data));
    MEMM crf = new MEMM (p, null);
    crf.addFullyConnectedStatesForLabels();
    crf.setWeightsDimensionAsIn (one);
    MEMMTrainer memmt = new MEMMTrainer (crf);
    MEMMTrainer.MEMMOptimizableByLabelLikelihood mcrf = memmt.getOptimizableMEMM(one);

View Full Code Here

  {
    long startTime = System.currentTimeMillis();
    
    Reader trainingFile = null, testFile = null;
    Reader constraintsFile = null;
    InstanceList trainingData = null, testData = null;
    int restArgs = commandOptions.processOptions(args);
    if (restArgs == args.length)
    {
      commandOptions.printUsage(true);
      throw new IllegalArgumentException("Missing data file(s)");
    }
    if (trainOption.value)
    {
      trainingFile = new FileReader(new File(args[restArgs]));
      if (testOption.value != null) {
        testFile = new FileReader(new File(args[restArgs+1]));
        constraintsFile = new FileReader(new File(args[restArgs+2]));
      }
      else {
        constraintsFile = new FileReader(new File(args[restArgs+1]));
      }
    } else 
      testFile = new FileReader(new File(args[restArgs]));


    Pipe p = null;
    CRF crf = null;
    TransducerEvaluator eval = null;
    if (continueTrainingOption.value || !trainOption.value) {
      if (modelOption.value == null)
      {
        commandOptions.printUsage(true);
        throw new IllegalArgumentException("Missing model file option");
      }
      ObjectInputStream s =
        new ObjectInputStream(new FileInputStream(modelOption.value));
      crf = (CRF) s.readObject();
      s.close();
      p = crf.getInputPipe();
    }
    else {
      p = new SimpleTaggerSentence2FeatureVectorSequence();
      p.getTargetAlphabet().lookupIndex(defaultOption.value);
    }




    if (trainOption.value)
    {
      p.setTargetProcessing(true);
      trainingData = new InstanceList(p);
      trainingData.addThruPipe(
          new LineGroupIterator(trainingFile,
            Pattern.compile("^\\s*$"), true));
      logger.info
        ("Number of features in training data: "+p.getDataAlphabet().size());
      if (testOption.value != null)
      {
        if (testFile != null)
        {
          testData = new InstanceList(p);
          testData.addThruPipe(
              new LineGroupIterator(testFile,
                Pattern.compile("^\\s*$"), true));
        } else
        {
          Random r = new Random (randomSeedOption.value);
          InstanceList[] trainingLists =
            trainingData.split(
                r, new double[] {trainingFractionOption.value,
                  1-trainingFractionOption.value});
          trainingData = trainingLists[0];
          testData = trainingLists[1];
        }
      }
    } else if (testOption.value != null)
    {
      p.setTargetProcessing(true);
      testData = new InstanceList(p);
      testData.addThruPipe(
          new LineGroupIterator(testFile,
            Pattern.compile("^\\s*$"), true));
    } else
    {
      p.setTargetProcessing(false);
      testData = new InstanceList(p);
      testData.addThruPipe(
          new LineGroupIterator(testFile,
            Pattern.compile("^\\s*$"), true));
    }
    logger.info ("Number of predicates: "+p.getDataAlphabet().size());

View Full Code Here


  public static void main(String[] args) {
    String htmldir = args[0];
    Pipe pipe = new SerialPipes(new Pipe[] { new Input2CharSequence(),
        new CharSequenceRemoveHTML() });
    InstanceList list = new InstanceList(pipe);
    list.addThruPipe(new FileIterator(htmldir, FileIterator.STARTING_DIRECTORIES));


    for (int index = 0; index < list.size(); index++) {
      Instance inst = list.get(index);
      System.err.println(inst.getData());
    }


  }

View Full Code Here

   * @exception Exception if an error occurs
   */
  public static void main (String[] args) throws Exception {


    Reader trainingFile = null, testFile = null;
    InstanceList trainingData = null, testData = null;
    int numEvaluations = 0;
    int iterationsBetweenEvals = 16;
    int restArgs = commandOptions.processOptions(args);


    if (restArgs == args.length) {
      commandOptions.printUsage(true);
      throw new IllegalArgumentException("Missing data file(s)");
    }


    if (trainOption.value) {
      trainingFile = new FileReader(new File(args[restArgs]));
      if (testOption.value != null && restArgs < args.length - 1) {
        testFile = new FileReader(new File(args[restArgs+1]));
      }
    }
    else {
      testFile = new FileReader(new File(args[restArgs]));
    }


    Pipe p = null;
    CRF crf = null;
    TransducerEvaluator eval = null;


    if (continueTrainingOption.value || !trainOption.value) {
      if (modelOption.value == null) {
        commandOptions.printUsage(true);
        throw new IllegalArgumentException("Missing model file option");
      }
      ObjectInputStream s =
        new ObjectInputStream(new FileInputStream(modelOption.value));
      crf = (CRF) s.readObject();
      s.close();
      p = crf.getInputPipe();
    }
    else {
      p = new SimpleTaggerSentence2FeatureVectorSequence();
      p.getTargetAlphabet().lookupIndex(defaultOption.value);
    }




    if (trainOption.value) {
      p.setTargetProcessing(true);
      trainingData = new InstanceList(p);
      trainingData.addThruPipe(new LineGroupIterator(trainingFile,
                               Pattern.compile("^\\s*$"), true));


      logger.info("Number of features in training data: "+p.getDataAlphabet().size());


      if (testOption.value != null) {
        if (testFile != null) {
          testData = new InstanceList(p);
          testData.addThruPipe(new LineGroupIterator(testFile,
                                 Pattern.compile("^\\s*$"), true));
        }
        else {
          Random r = new Random (randomSeedOption.value);
          InstanceList[] trainingLists =
            trainingData.split(r, new double[] {trainingFractionOption.value,
                              1 - trainingFractionOption.value});
          trainingData = trainingLists[0];
          testData = trainingLists[1];
        }
      }
    }
    else if (testOption.value != null) {
      p.setTargetProcessing(true);
      testData = new InstanceList(p);
      testData.addThruPipe(new LineGroupIterator(testFile,
                             Pattern.compile("^\\s*$"), true));
    }
    else {
        p.setTargetProcessing(false);
        testData = new InstanceList(p);
        testData.addThruPipe(
                   new LineGroupIterator(testFile,
                               Pattern.compile("^\\s*$"), true));
    }
    logger.info ("Number of predicates: "+p.getDataAlphabet().size());

View Full Code Here

            if (tmp.lists.length != this.lists.length) {
                return false;
            }
            
            for (int i = 0; i < this.lists.length; i++) {
                InstanceList thisList = this.lists[i];
                InstanceList tmpList = tmp.lists[i];


                if (thisList == null && tmpList != null) {
                    return false;
                } else if (!thisList.equals (tmpList)) {
                    return false;

View Full Code Here

                if (this.i.hasNext ()) {
                    return true;
                }


                for (int tmpIndex = this.index + 1; tmpIndex < lists.length; tmpIndex++) {
                    final InstanceList list = lists[tmpIndex];
                    if (list != null && lists[tmpIndex].size () > 0) {
                        return true;
                    }
                }
            }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of cc.mallet.types.InstanceList

cc.mallet.classify.C45$Node

cc.mallet.classify.DecisionTree$Node

cc.mallet.classify.MaxEntPRTrainer

cc.mallet.classify.NaiveBayesEMTrainer

cc.mallet.classify.tui.Vectors2FeatureConstraints

cc.mallet.cluster.Clustering

cc.mallet.cluster.evaluate.BCubedEvaluator

cc.mallet.cluster.evaluate.tests.TestClusteringEvaluators

cc.mallet.cluster.examples.FirstOrderClusterExample

cc.mallet.cluster.examples.FirstOrderClusterExample$OverlappingFeaturePipe

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.