/**
* Similar to prepareBatch, but for extended batches.
*
* @param extendedBatch containing the extended batch
* @return the class priors of the batch
*/
private double[] prepareExtendedBatch(ExampleSet extendedBatch) {
int[] classCount = new int[2];
Iterator<Example> reader = extendedBatch.iterator();
while (reader.hasNext()) {
Example example = reader.next();
example.setWeight(1);
classCount[(int) example.getLabel()]++;
}
double[] classPriors = new double[2];
int sum = classCount[0] + classCount[1];
classPriors[0] = ((double) classCount[0]) / sum;
classPriors[1] = ((double) classCount[1]) / sum;
return classPriors;
}
/**
* Computes the weighted class priors of the boolean target attribute and shifts weights so that
* the priors are equal afterwards.
*/
private void rescalePriors(ExampleSet exampleSet, double[] classPriors) {
// The weights of class i are calculated as
// (1 / #classes) / (#rel_freq_class_i)
double[] weights = new double[2];
for (int i = 0; i < weights.length; i++) {
weights[i] = 1.0d / (weights.length * (classPriors[i]));
}
Iterator<Example> exRead = exampleSet.iterator();
while (exRead.hasNext()) {
Example example = exRead.next();
example.setWeight(weights[(int) (example.getLabel())]);
}
}
protected void prepareWeights(ExampleSet exampleSet) {
Attribute weightAttr = exampleSet.getAttributes().getWeight();
if (weightAttr == null) {
this.oldWeights = null;
com.rapidminer.example.Tools.createWeightAttribute(exampleSet);
} else { // Back up old weights
this.oldWeights = new double[exampleSet.size()];
Iterator<Example> reader = exampleSet.iterator();
for (int i = 0; (reader.hasNext() && i < oldWeights.length); i++) {
Example example = reader.next();
if (example != null) {
this.oldWeights[i] = example.getWeight();
example.setWeight(1);
}
}
}
}
/**
* The preparation part collecting the examples of a batch, computing priors and resetting weights
* to 1.
*
* @param currentBatchNum the batch number to be assigned to the examples
* @param reader the <code>Iterator<Example></code> with the cursor on the current point in the
* stream.
* @param batchAttribute the attribute to write the batch number to
* @return the class priors of the batch
*/
private double[] prepareBatch(
int currentBatchNum, Iterator<Example> reader, Attribute batchAttribute)
throws UndefinedParameterError {
final int batchSize = this.getParameterAsInt(PARAMETER_BATCH_SIZE);
int batchCount = 0;
// Read and classify examples from stream, as long as the buffer (next
// batch)
// is not full. Examples are weighted at this point, in order to
// simulate sampling.
int[] classCount = new int[2];
while ((batchCount++ < batchSize) && reader.hasNext()) {
Example example = reader.next();
example.setValue(batchAttribute, currentBatchNum);
example.setWeight(1);
classCount[(int) example.getLabel()]++;
}
double[] classPriors = new double[2];
classPriors[0] = ((double) classCount[0]) / --batchCount;
classPriors[1] = ((double) classCount[1]) / batchCount;
return classPriors;
}
private BayBoostModel retrainLastWeight(
BayBoostModel ensemble, ExampleSet exampleSet, Vector holdOutSet) throws OperatorException {
this.prepareExtendedBatch(exampleSet); // method fits by chance
int modelNum = ensemble.getNumberOfModels();
Vector<BayBoostBaseModelInfo> modelInfo = new Vector<BayBoostBaseModelInfo>();
double[] priors = ensemble.getPriors();
for (int i = 0; i < modelNum - 1; i++) {
Model model = ensemble.getModel(i);
ContingencyMatrix cm = ensemble.getContingencyMatrix(i);
modelInfo.add(new BayBoostBaseModelInfo(model, cm));
exampleSet = model.apply(exampleSet);
WeightedPerformanceMeasures.reweightExamples(exampleSet, cm, false);
}
Model latestModel = ensemble.getModel(modelNum - 1);
exampleSet = latestModel.apply(exampleSet);
// quite ugly:
double[] weights = new double[holdOutSet.size()];
Iterator it = holdOutSet.iterator();
int index = 0;
while (it.hasNext()) {
Example example = (Example) it.next();
weights[index++] = example.getWeight();
}
Iterator<Example> reader = exampleSet.iterator();
while (reader.hasNext()) {
reader.next().setWeight(0);
}
it = holdOutSet.iterator();
index = 0;
while (it.hasNext()) {
Example example = (Example) it.next();
example.setWeight(weights[index++]);
}
WeightedPerformanceMeasures wp = new WeightedPerformanceMeasures(exampleSet);
modelInfo.add(new BayBoostBaseModelInfo(latestModel, wp.getContingencyMatrix()));
return new BayBoostModel(exampleSet, modelInfo, priors);
}
