Java Code Examples for weka.core.Instances#equalHeadersMsg()

/**
 * Compare two datasets to see if they differ.
 *
 * @param data1 one set of instances
 * @param data2 the other set of instances
 * @throws Exception if the datasets differ
 */
protected void compareDatasets(Instances data1, Instances data2)
throws Exception {
  if (!data2.equalHeaders(data1)) {
    throw new Exception("header has been modified\n" + data2.equalHeadersMsg(data1));
  }
  if (!(data2.numInstances() == data1.numInstances())) {
    throw new Exception("number of instances has changed");
  }
  for (int i = 0; i < data2.numInstances(); i++) {
    Instance orig = data1.instance(i);
    Instance copy = data2.instance(i);
    for (int j = 0; j < orig.numAttributes(); j++) {
      if (orig.isMissing(j)) {
        if (!copy.isMissing(j)) {
          throw new Exception("instances have changed");
        }
      } else if (orig.value(j) != copy.value(j)) {
        throw new Exception("instances have changed");
      }
      if (orig.weight() != copy.weight()) {
        throw new Exception("instance weights have changed");
      }	  
    }
  }
}
 

/**
 * Loads test data, if required.
 *
 * @param data	the current training data
 * @throws Exception	if test sets are not compatible with training data
 */
protected void loadTestData(Instances data) throws Exception {
	String		msg;

	m_InitialSpaceTestInst = null;
	if (m_InitialSpaceTestSet.exists() && !m_InitialSpaceTestSet.isDirectory()) {
		m_InitialSpaceTestInst = DataSource.read(m_InitialSpaceTestSet.getAbsolutePath());
		m_InitialSpaceTestInst.setClassIndex(data.classIndex());
		msg = data.equalHeadersMsg(m_InitialSpaceTestInst);
		if (msg != null)
			throw new IllegalArgumentException("Test set for initial space not compatible with training dta:\n" +  msg);
		m_InitialSpaceTestInst.deleteWithMissingClass();
		log("Using test set for initial space: " + m_InitialSpaceTestSet);
	}

	m_SubsequentSpaceTestInst = null;
	if (m_SubsequentSpaceTestSet.exists() && !m_SubsequentSpaceTestSet.isDirectory()) {
		m_SubsequentSpaceTestInst = DataSource.read(m_SubsequentSpaceTestSet.getAbsolutePath());
		m_SubsequentSpaceTestInst.setClassIndex(data.classIndex());
		msg = data.equalHeadersMsg(m_SubsequentSpaceTestInst);
		if (msg != null)
			throw new IllegalArgumentException("Test set for subsequent sub-spaces not compatible with training dta:\n" +  msg);
		m_SubsequentSpaceTestInst.deleteWithMissingClass();
		log("Using test set for subsequent sub-spaces: " + m_InitialSpaceTestSet);
	}
}
 

/**
  * Evaluates the classifier on a test set.
  *
  * @param classifier the classifier to evaluate
  * @param output for collecting the test results
  * @param outBuff the buffer for the output
  * @return the generated evaluation
  * @throws Execption if evaluation fails
  */
 protected CollectiveEvaluation evalTestSet(CollectiveClassifier classifier, AbstractOutput output, StringBuffer outBuff) throws Exception {
   CollectiveEvaluation eval;

   if (m_UnlabeledSet == null)
     throw new IllegalStateException("No unlabeled dataset set!");
   Instances train = new Instances(m_Instances);
   train.setClassIndex(m_ClassCombo.getSelectedIndex());
   Instances unlabeled = new Instances(m_UnlabeledSet);
   unlabeled.setClassIndex(m_ClassCombo.getSelectedIndex());
   if (!train.equalHeaders(unlabeled))
     throw new IllegalStateException(train.equalHeadersMsg(unlabeled));
   eval = new CollectiveEvaluation(train);
   classifier.buildClassifier(train, unlabeled);
   if (m_TestSet != null) {
     Instances test = new Instances(m_TestSet);
     test.setClassIndex(m_ClassCombo.getSelectedIndex());
     if (!train.equalHeaders(test))
       throw new IllegalStateException(train.equalHeadersMsg(test));
     if (output != null) {
       printPredictionsHeader(outBuff, output, "test set");
       output.printHeader();
       eval.evaluateModel(classifier, test, output);
output.printFooter();
     }
     else {
       eval.evaluateModel(classifier, test);
     }
   }

   return eval;
 }
 

public static void main(String[] args) throws Exception {
  if (args.length != 3)
    throw new IllegalArgumentException("Required arguments: <train> <test> <output>");

  System.out.println("Loading train: " + args[0]);
  Instances train = DataSource.read(args[0]);
  MLUtils.prepareData(train);

  System.out.println("Loading test: " + args[1]);
  Instances test = DataSource.read(args[1]);
  MLUtils.prepareData(test);

  // compatible?
  String msg = train.equalHeadersMsg(test);
  if (msg != null)
    throw new IllegalStateException(msg);

  System.out.println("Build BR classifier on " + args[0]);
  BR classifier = new BR();
  // further configuration of classifier
  classifier.buildClassifier(train);

  System.out.println("Evaluate BR classifier on " + args[1]);
  String top = "PCut1";
  String vop = "3";
  Result result = Evaluation.evaluateModel(classifier, train, test, top, vop);

  System.out.println(result);

  System.out.println("Saving predictions test set to " + args[2]);
  Instances performance = Result.getPredictionsAsInstances(result);
  DataSink.write(args[2], performance);
}
 

public static void main(String[] args) throws Exception {
  if (args.length != 2)
    throw new IllegalArgumentException("Required arguments: <train> <test>");

  System.out.println("Loading train: " + args[0]);
  Instances train = DataSource.read(args[0]);
  MLUtils.prepareData(train);

  System.out.println("Loading test: " + args[1]);
  Instances test = DataSource.read(args[1]);
  MLUtils.prepareData(test);

  // compatible?
  String msg = train.equalHeadersMsg(test);
  if (msg != null)
    throw new IllegalStateException(msg);

  System.out.println("Build BR classifier on " + args[0]);
  BR classifier = new BR();
  // further configuration of classifier
  classifier.buildClassifier(train);

  System.out.println("Evaluate BR classifier on " + args[1]);
  String top = "PCut1";
  String vop = "3";
  Result result = Evaluation.evaluateModel(classifier, train, test, top, vop);

  System.out.println(result);
}
 

public static void main(String[] args) throws Exception {
  if (args.length != 2)
    throw new IllegalArgumentException("Required arguments: <train> <predict>");

  System.out.println("Loading train: " + args[0]);
  Instances train = DataSource.read(args[0]);
  MLUtils.prepareData(train);

  System.out.println("Loading predict: " + args[1]);
  Instances predict = DataSource.read(args[1]);
  MLUtils.prepareData(predict);

  // compatible?
  String msg = train.equalHeadersMsg(predict);
  if (msg != null)
    throw new IllegalStateException(msg);

  System.out.println("Build BR classifier on " + args[0]);
  BR classifier = new BR();
  // further configuration of classifier
  classifier.buildClassifier(train);

  System.out.println("Use BR classifier on " + args[1]);
  for (int i = 0; i < predict.numInstances(); i++) {
    double[] dist = classifier.distributionForInstance(predict.instance(i));
    System.out.println((i+1) + ": " + Utils.arrayToString(dist));
  }
}