@Override
public Model learn(ExampleSet exampleSet) throws OperatorException {
Kernel kernel = getKernel();
kernel.init(exampleSet);
double initLearnRate = getParameterAsDouble(PARAMETER_LEARNING_RATE);
NominalMapping labelMapping = exampleSet.getAttributes().getLabel().getMapping();
String classNeg = labelMapping.getNegativeString();
String classPos = labelMapping.getPositiveString();
double classValueNeg = labelMapping.getNegativeIndex();
int numberOfAttributes = exampleSet.getAttributes().size();
HyperplaneModel model = new HyperplaneModel(exampleSet, classNeg, classPos, kernel);
model.init(new double[numberOfAttributes], 0);
for (int round = 0; round <= getParameterAsInt(PARAMETER_ROUNDS); round++) {
double learnRate = getLearnRate(round, getParameterAsInt(PARAMETER_ROUNDS), initLearnRate);
Attributes attributes = exampleSet.getAttributes();
for (Example example : exampleSet) {
double prediction = model.predict(example);
if (prediction != example.getLabel()) {
double direction = (example.getLabel() == classValueNeg) ? -1 : 1;
// adapting intercept
model.setIntercept(model.getIntercept() + learnRate * direction);
// adapting coefficients
double coefficients[] = model.getCoefficients();
int i = 0;
for (Attribute attribute : attributes) {
coefficients[i] += learnRate * direction * example.getValue(attribute);
i++;
}
}
}
}
return model;
}
@Override
public ExampleSet apply(ExampleSet exampleSet) throws OperatorException {
// searching confidence attributes
Attributes attributes = exampleSet.getAttributes();
Attribute predictedLabel = attributes.getPredictedLabel();
if (predictedLabel == null) {
throw new UserError(this, 107);
}
NominalMapping mapping = predictedLabel.getMapping();
int numberOfLabels = mapping.size();
Attribute[] confidences = new Attribute[numberOfLabels];
String[] labelValue = new String[numberOfLabels];
int i = 0;
for (String value : mapping.getValues()) {
labelValue[i] = value;
confidences[i] = attributes.getConfidence(value);
if (confidences[i] == null) {
throw new UserError(this, 154, value);
}
i++;
}
// generating new prediction attributes
int k = Math.min(numberOfLabels, getParameterAsInt(PARAMETER_NUMBER_OF_RANKS));
Attribute[] kthPredictions = new Attribute[k];
Attribute[] kthConfidences = new Attribute[k];
for (i = 0; i < k; i++) {
kthPredictions[i] = AttributeFactory.createAttribute(predictedLabel.getValueType());
kthPredictions[i].setName(predictedLabel.getName() + "_" + (i + 1));
kthPredictions[i].setMapping((NominalMapping) predictedLabel.getMapping().clone());
kthConfidences[i] = AttributeFactory.createAttribute(Ontology.REAL);
kthConfidences[i].setName(Attributes.CONFIDENCE_NAME + "_" + (i + 1));
attributes.addRegular(kthPredictions[i]);
attributes.addRegular(kthConfidences[i]);
attributes.setSpecialAttribute(kthPredictions[i], Attributes.PREDICTION_NAME + "_" + (i + 1));
attributes.setSpecialAttribute(kthConfidences[i], Attributes.CONFIDENCE_NAME + "_" + (i + 1));
}
exampleSet.getExampleTable().addAttributes(Arrays.asList(kthConfidences));
exampleSet.getExampleTable().addAttributes(Arrays.asList(kthPredictions));
// now setting values
for (Example example : exampleSet) {
ArrayList<Tupel<Double, Integer>> labelConfidences =
new ArrayList<Tupel<Double, Integer>>(numberOfLabels);
for (i = 0; i < numberOfLabels; i++) {
labelConfidences.add(new Tupel<Double, Integer>(example.getValue(confidences[i]), i));
}
Collections.sort(labelConfidences);
for (i = 0; i < k; i++) {
Tupel<Double, Integer> tupel = labelConfidences.get(numberOfLabels - i - 1);
example.setValue(
kthPredictions[i],
tupel.getSecond()); // Can use index since mapping has been cloned from above
example.setValue(kthConfidences[i], tupel.getFirst());
}
}
// deleting old prediction / confidences
attributes.remove(predictedLabel);
if (getParameterAsBoolean(PARAMETER_REMOVE_OLD_PREDICTIONS)) {
for (i = 0; i < confidences.length; i++) {
attributes.remove(confidences[i]);
}
}
return exampleSet;
}
@Override
public void doWork() throws OperatorException {
// sanity checks
ExampleSet exampleSet = exampleSetInput.getData(ExampleSet.class);
// checking preconditions
Attribute label = exampleSet.getAttributes().getLabel();
if (label == null) {
throw new UserError(this, 105);
}
if (!label.isNominal()) {
throw new UserError(this, 101, label, "threshold finding");
}
exampleSet.recalculateAttributeStatistics(label);
NominalMapping mapping = label.getMapping();
if (mapping.size() != 2) {
throw new UserError(
this,
118,
new Object[] {label, Integer.valueOf(mapping.getValues().size()), Integer.valueOf(2)});
}
if (exampleSet.getAttributes().getPredictedLabel() == null) {
throw new UserError(this, 107);
}
boolean useExplictLabels = getParameterAsBoolean(PARAMETER_DEFINE_LABELS);
double secondCost = getParameterAsDouble(PARAMETER_MISCLASSIFICATION_COSTS_SECOND);
double firstCost = getParameterAsDouble(PARAMETER_MISCLASSIFICATION_COSTS_FIRST);
if (useExplictLabels) {
String firstLabel = getParameterAsString(PARAMETER_FIRST_LABEL);
String secondLabel = getParameterAsString(PARAMETER_SECOND_LABEL);
if (mapping.getIndex(firstLabel) == -1) {
throw new UserError(this, 143, firstLabel, label.getName());
}
if (mapping.getIndex(secondLabel) == -1) {
throw new UserError(this, 143, secondLabel, label.getName());
}
// if explicit order differs from order in data: internally swap costs.
if (mapping.getIndex(firstLabel) > mapping.getIndex(secondLabel)) {
double temp = firstCost;
firstCost = secondCost;
secondCost = temp;
}
}
// check whether the confidence attributes are available
if (exampleSet.getAttributes().getConfidence(mapping.getPositiveString()) == null) {
throw new UserError(
this, 113, Attributes.CONFIDENCE_NAME + "_" + mapping.getPositiveString());
}
if (exampleSet.getAttributes().getConfidence(mapping.getNegativeString()) == null) {
throw new UserError(
this, 113, Attributes.CONFIDENCE_NAME + "_" + mapping.getNegativeString());
}
// create ROC data
ROCDataGenerator rocDataGenerator = new ROCDataGenerator(firstCost, secondCost);
ROCData rocData =
rocDataGenerator.createROCData(
exampleSet,
getParameterAsBoolean(PARAMETER_USE_EXAMPLE_WEIGHTS),
ROCBias.getROCBiasParameter(this));
// create plotter
if (getParameterAsBoolean(PARAMETER_SHOW_ROC_PLOT)) {
rocDataGenerator.createROCPlotDialog(rocData, true, true);
}
// create and return output
exampleSetOutput.deliver(exampleSet);
thresholdOutput.deliver(
new Threshold(
rocDataGenerator.getBestThreshold(),
mapping.getNegativeString(),
mapping.getPositiveString()));
}