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;
}
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;
}
@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;
}