//
// 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 bool allExamplesHaveSameClassification(DataSet ds)
{
String classification = ds.getExample(0).targetValue();
List<Example>.Enumerator iter = ds.iterator();
while (iter.MoveNext())
{
Example element = iter.Current;
if (!(element.targetValue().Equals(classification)))
{
return false;
}
}
return true;
}
private ConstantDecisonTree majorityValue(DataSet ds)
{
Learner learner = new MajorityLearner();
learner.train(ds);
return new ConstantDecisonTree(learner.predict(ds.getExample(0)));
}
private void adjustExampleWeights(DataSet ds, Learner l, double error)
{
double epsilon = error / (1.0 - error);
for (int j = 0; j < ds.examples.Count; j++)
{
Example e = ds.getExample(j);
if ((l.predict(e).Equals(e.targetValue())))
{
exampleWeights[j] = exampleWeights[j] * epsilon;
}
}
exampleWeights = Util.normalize(exampleWeights);
}
private double calculateError(DataSet ds, Learner l)
{
double error = 0.0;
for (int i = 0; i < ds.examples.Count; i++)
{
Example e = ds.getExample(i);
if (!(l.predict(e).Equals(e.targetValue())))
{
error = error + exampleWeights[i];
}
}
return error;
}
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;
}
private bool allExamplesHaveSameTargetValue(DataSet matched) {
// assumes at least i example in dataset
String targetValue = matched.getExample(0).targetValue();
foreach (Example e in matched.examples) {
if (!(e.targetValue().Equals(targetValue))) {
return false;
}
}
return true;
}
