/**
* Calculates the minimum description length of this node, i.e., the length of the binary
* encoding that describes the feature and the split value used at this node
*/
public double getMDL() {
int numClasses = m_ilist.getTargetAlphabet().size();
double mdl = getSize() * getGainRatio().getBaseEntropy();
mdl += ((numClasses - 1) * Math.log(getSize() / 2.0)) / (2 * GainRatio.log2);
double piPow = Math.pow(Math.PI, numClasses / 2.0);
double gammaVal = Maths.gamma(numClasses / 2.0);
mdl += Math.log(piPow / gammaVal) / GainRatio.log2;
return mdl;
}
/**
* Initialize this separate model using a complete list.
*
* @param documents
* @param testStartIndex
*/
public void divideDocuments(InstanceList documents, int testStartIndex) {
Alphabet dataAlpha = documents.getDataAlphabet();
Alphabet targetAlpha = documents.getTargetAlphabet();
this.training = new InstanceList(dataAlpha, targetAlpha);
this.test = new InstanceList(dataAlpha, targetAlpha);
int di = 0;
for (di = 0; di < testStartIndex; di++) {
training.add(documents.get(di));
}
for (di = testStartIndex; di < documents.size(); di++) {
test.add(documents.get(di));
}
}