private double predictUsingCurtailment(Example example, ExtendedTree node) {
double dPrediction = 0;
if (node.isLeaf()) {
dPrediction = predictAsLeaf(example, node);
} else {
boolean bEdgeConditionFound = false;
Iterator<Edge> childIterator = node.childIterator();
while ((childIterator.hasNext()) && (bEdgeConditionFound == false)) {
Edge edge = childIterator.next();
SplitCondition condition = edge.getCondition();
if (condition.test(example)) {
bEdgeConditionFound = true;
ExtendedTree childTree = (ExtendedTree) edge.getChild();
if (childTree.getTotalExamples() >= dCurtailmentThreshold)
dPrediction = (predictUsingCurtailment(example, childTree));
else dPrediction = predictAsLeaf(example, node);
}
}
if (bEdgeConditionFound == false) {
dPrediction = predictAsLeaf(example, node);
}
}
return dPrediction;
}
@Override
public String getEdgeName(String object) {
SplitCondition condition = edgeMap.get(object);
if (condition != null) {
return condition.getRelation() + " " + condition.getValueString();
} else {
return null;
}
}
@Override
public String getVertexName(String object) {
Tree node = vertexMap.get(object);
String name = "";
if (node != null) {
if (node.isLeaf()) {
name = node.getLabel();
} else {
Iterator<Edge> e = node.childIterator();
while (e.hasNext()) {
SplitCondition condition = e.next().getCondition();
name = condition.getAttributeName();
break;
}
}
}
return name;
}
@Override
public Model learn(ExampleSet exampleSet) throws OperatorException {
Attribute label = exampleSet.getAttributes().getLabel();
RuleModel ruleModel = new RuleModel(exampleSet);
double pureness = getParameterAsDouble(PARAMETER_PURENESS);
TermDetermination termDetermination = new TermDetermination(new AccuracyCriterion(), 0.5d);
ExampleSet trainingSet = (ExampleSet) exampleSet.clone();
for (String labelName : label.getMapping().getValues()) {
trainingSet.recalculateAttributeStatistics(label);
int oldSize = -1;
while (trainingSet.size() > 0
&& trainingSet.size() != oldSize
&& trainingSet.getStatistics(label, Statistics.COUNT, labelName) > 0) {
Rule rule = new Rule(labelName);
ExampleSet oldTrainingSet = (ExampleSet) trainingSet.clone();
// grow rule
int growOldSize = -1;
ExampleSet growSet = (ExampleSet) trainingSet.clone();
while (growSet.size() > 0
&& growSet.size() != growOldSize
&& !rule.isPure(growSet, pureness)
&& growSet.getAttributes().size() > 0) {
SplitCondition term = termDetermination.getBestTerm(growSet, labelName);
if (term == null) {
break;
}
rule.addTerm(term);
Attribute splitAttribute = growSet.getAttributes().get(term.getAttributeName());
growSet.getAttributes().remove(splitAttribute);
growOldSize = growSet.size();
growSet = rule.getCovered(growSet);
}
// add rule if not empty
if (rule.getTerms().size() > 0) {
growSet = rule.getCovered(trainingSet);
growSet.recalculateAttributeStatistics(label);
int[] frequencies = new int[label.getMapping().size()];
int counter = 0;
for (String value : label.getMapping().getValues()) {
frequencies[counter++] = (int) growSet.getStatistics(label, Statistics.COUNT, value);
}
rule.setFrequencies(frequencies);
ruleModel.addRule(rule);
oldSize = trainingSet.size();
trainingSet = rule.removeCovered(oldTrainingSet);
} else {
break; // no other terms found for this class --> next class
}
trainingSet.recalculateAttributeStatistics(label);
}
checkForStop();
}
// training set not empty? add default rule
if (trainingSet.size() > 0) {
trainingSet.recalculateAttributeStatistics(label);
int index = (int) trainingSet.getStatistics(label, Statistics.MODE);
String defaultLabel = label.getMapping().mapIndex(index);
Rule defaultRule = new Rule(defaultLabel);
int[] frequencies = new int[label.getMapping().size()];
int counter = 0;
for (String value : label.getMapping().getValues()) {
frequencies[counter++] = (int) trainingSet.getStatistics(label, Statistics.COUNT, value);
}
defaultRule.setFrequencies(frequencies);
ruleModel.addRule(defaultRule);
}
return ruleModel;
}