private RuleModel createNumericalRuleModel(ExampleSet trainingSet, Attribute attribute) {
RuleModel model = new RuleModel(trainingSet);
// split by best attribute
int oldSize = -1;
while ((trainingSet.size() > 0) && (trainingSet.size() != oldSize)) {
ExampleSet exampleSet = (ExampleSet) trainingSet.clone();
Split bestSplit = splitter.getBestSplit(exampleSet, attribute, null);
double bestSplitValue = bestSplit.getSplitPoint();
if (!Double.isNaN(bestSplitValue)) {
SplittedExampleSet splittedSet =
SplittedExampleSet.splitByAttribute(exampleSet, attribute, bestSplitValue);
Attribute label = splittedSet.getAttributes().getLabel();
splittedSet.selectSingleSubset(0);
SplitCondition condition = new LessEqualsSplitCondition(attribute, bestSplitValue);
splittedSet.recalculateAttributeStatistics(label);
int labelValue = (int) splittedSet.getStatistics(label, Statistics.MODE);
String labelName = label.getMapping().mapIndex(labelValue);
Rule rule = new Rule(labelName, condition);
int[] frequencies = new int[label.getMapping().size()];
int counter = 0;
for (String value : label.getMapping().getValues())
frequencies[counter++] = (int) splittedSet.getStatistics(label, Statistics.COUNT, value);
rule.setFrequencies(frequencies);
model.addRule(rule);
oldSize = trainingSet.size();
trainingSet = rule.removeCovered(trainingSet);
} else {
break;
}
}
// add default rule if some examples were not yet covered
if (trainingSet.size() > 0) {
Attribute label = trainingSet.getAttributes().getLabel();
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);
model.addRule(defaultRule);
}
return model;
}
@Override
public void estimatePerformance(ExampleSet inputSet) throws OperatorException {
// split by attribute
Attribute batchAttribute = inputSet.getAttributes().getSpecial(Attributes.BATCH_NAME);
if (batchAttribute == null) {
throw new UserError(this, 113, Attributes.BATCH_NAME);
}
SplittedExampleSet splittedES = SplittedExampleSet.splitByAttribute(inputSet, batchAttribute);
// start crossvalidation
for (iteration = 0; iteration < splittedES.getNumberOfSubsets(); iteration++) {
splittedES.selectAllSubsetsBut(iteration);
learn(splittedES);
splittedES.selectSingleSubset(iteration);
evaluate(splittedES);
inApplyLoop();
}
// end crossvalidation
}
private RuleModel createNominalRuleModel(ExampleSet exampleSet, Attribute attribute) {
RuleModel model = new RuleModel(exampleSet);
SplittedExampleSet splittedSet = SplittedExampleSet.splitByAttribute(exampleSet, attribute);
Attribute label = splittedSet.getAttributes().getLabel();
for (int i = 0; i < splittedSet.getNumberOfSubsets(); i++) {
splittedSet.selectSingleSubset(i);
splittedSet.recalculateAttributeStatistics(label);
SplitCondition term =
new NominalSplitCondition(attribute, attribute.getMapping().mapIndex(i));
int labelValue = (int) splittedSet.getStatistics(label, Statistics.MODE);
String labelName = label.getMapping().mapIndex(labelValue);
Rule rule = new Rule(labelName, term);
int[] frequencies = new int[label.getMapping().size()];
int counter = 0;
for (String value : label.getMapping().getValues())
frequencies[counter++] = (int) splittedSet.getStatistics(label, Statistics.COUNT, value);
rule.setFrequencies(frequencies);
model.addRule(rule);
}
return model;
}