@Override
public void trainC(ClassificationDataSet dataSet, ExecutorService threadPool) {
final int models = baseClassifiers.size();
final int C = dataSet.getClassSize();
weightsPerModel = C == 2 ? 1 : C;
ClassificationDataSet metaSet =
new ClassificationDataSet(
weightsPerModel * models, new CategoricalData[0], dataSet.getPredicting());
List<ClassificationDataSet> dataFolds = dataSet.cvSet(folds);
// iterate in the order of the folds so we get the right dataum weights
for (ClassificationDataSet cds : dataFolds)
for (int i = 0; i < cds.getSampleSize(); i++)
metaSet.addDataPoint(
new DenseVector(weightsPerModel * models),
cds.getDataPointCategory(i),
cds.getDataPoint(i).getWeight());
// create the meta training set
for (int c = 0; c < baseClassifiers.size(); c++) {
Classifier cl = baseClassifiers.get(c);
int pos = 0;
for (int f = 0; f < dataFolds.size(); f++) {
ClassificationDataSet train = ClassificationDataSet.comineAllBut(dataFolds, f);
ClassificationDataSet test = dataFolds.get(f);
if (threadPool == null) cl.trainC(train);
else cl.trainC(train, threadPool);
for (int i = 0;
i < test.getSampleSize();
i++) // evaluate and mark each point in the held out fold.
{
CategoricalResults pred = cl.classify(test.getDataPoint(i));
if (C == 2)
metaSet.getDataPoint(pos).getNumericalValues().set(c, pred.getProb(0) * 2 - 1);
else {
Vec toSet = metaSet.getDataPoint(pos).getNumericalValues();
for (int j = weightsPerModel * c; j < weightsPerModel * (c + 1); j++)
toSet.set(j, pred.getProb(j - weightsPerModel * c));
}
pos++;
}
}
}
// train the meta model
if (threadPool == null) aggregatingClassifier.trainC(metaSet);
else aggregatingClassifier.trainC(metaSet, threadPool);
// train the final classifiers, unless folds=1. In that case they are already trained
if (folds != 1) {
for (Classifier cl : baseClassifiers)
if (threadPool == null) cl.trainC(dataSet);
else cl.trainC(dataSet, threadPool);
}
}
public CategoricalResults classify(DataPoint data) {
if (coefficents == null) throw new UntrainedModelException("Model has not yet been trained");
else if (shift != 0 || scale != 1)
throw new UntrainedModelException("Model was trained for regression, not classifiaction");
CategoricalResults results = new CategoricalResults(2);
// It looks a little backwards. But if the true class is 0, and we are accurate, then we expect
// regress to return a value near zero.
results.setProb(1, regress(data));
results.setProb(0, 1.0 - results.getProb(1));
return results;
}
@Override
public CategoricalResults classify(DataPoint data) {
Vec w = new DenseVector(weightsPerModel * baseClassifiers.size());
if (weightsPerModel == 1)
for (int i = 0; i < baseClassifiers.size(); i++)
w.set(i, baseClassifiers.get(i).classify(data).getProb(0) * 2 - 1);
else {
for (int i = 0; i < baseClassifiers.size(); i++) {
CategoricalResults pred = baseClassifiers.get(i).classify(data);
for (int j = 0; j < weightsPerModel; j++) w.set(i * weightsPerModel + j, pred.getProb(j));
}
}
return aggregatingClassifier.classify(new DataPoint(w));
}