//
// PRIVATE METHODS
//
private DecisionTree decisionTreeLearning(DataSet ds,
List<String> attributeNames, ConstantDecisonTree defaultTree)
{
if (ds.size() == 0)
{
return defaultTree;
}
if (allExamplesHaveSameClassification(ds))
{
return new ConstantDecisonTree(ds.getExample(0).targetValue());
}
if (attributeNames.Count == 0)
{
return majorityValue(ds);
}
String chosenAttribute = chooseAttribute(ds, attributeNames);
DecisionTree tree = new DecisionTree(chosenAttribute);
ConstantDecisonTree m = majorityValue(ds);
List<String> values = ds.getPossibleAttributeValues(chosenAttribute);
foreach (String v in values)
{
DataSet filtered = ds.matchingDataSet(chosenAttribute, v);
List<String> newAttribs = Util.removeFrom(attributeNames,
chosenAttribute);
DecisionTree subTree = decisionTreeLearning(filtered, newAttribs, m);
tree.addNode(v, subTree);
}
return tree;
}
//
// PRIVATE METHODS
//
private DecisionList decisionListLearning(DataSet ds)
{
if (ds.size() == 0)
{
return new DecisionList(positive, negative);
}
List<DLTest> possibleTests = testFactory
.createDLTestsWithAttributeCount(ds, 1);
DLTest test = getValidTest(possibleTests, ds);
if (test == null)
{
return new DecisionList(null, FAILURE);
}
// at this point there is a test that classifies some subset of examples
// with the same target value
DataSet matched = test.matchedExamples(ds);
DecisionList list = new DecisionList(positive, negative);
list.add(test, matched.getExample(0).targetValue());
return list.mergeWith(decisionListLearning(test.unmatchedExamples(ds)));
}
private List<List<Double>> rawExamplesFromDataSet(DataSet ds,
Numerizer numerizer) {
// assumes all values for inout and target are doubles
List<List<Double>> rds = new List<List<Double>>();
for (int i = 0; i < ds.size(); i++) {
List<Double> rexample = new List<Double>();
Example e = ds.getExample(i);
Pair<List<Double>, List<Double>> p = numerizer.numerize(e);
List<Double> attributes = p.getFirst();
foreach (Double d in attributes) {
rexample.Add(d);
}
List<Double> targets = p.getSecond();
foreach (Double d in targets) {
rexample.Add(d);
}
rds.Add(rexample);
}
return rds;
}
