/**
* Set cutpoints for a single attribute using MDL.
*
* @param index the index of the attribute to set cutpoints for
* @param data the data to work with
*/
protected void calculateCutPointsByMDL(int index, Instances data) {
// Sort instances
data.sort(data.attribute(index));
// Find first instances that's missing
int firstMissing = data.numInstances();
for (int i = 0; i < data.numInstances(); i++) {
if (data.instance(i).isMissing(index)) {
firstMissing = i;
break;
}
}
m_CutPoints[index] = cutPointsForSubset(data, index, 0, firstMissing);
}
/**
* Creates a C4.5-type split on the given data.
*
* @exception Exception if something goes wrong
*/
public void buildClassifier(Instances trainInstances) throws Exception {
// Initialize the remaining instance variables.
m_numSubsets = 0;
m_splitPoint = Double.MAX_VALUE;
m_infoGain = 0;
m_gainRatio = 0;
// Different treatment for enumerated and numeric
// attributes.
if (trainInstances.attribute(m_attIndex).isNominal()) {
handleEnumeratedAttribute(trainInstances);
} else {
trainInstances.sort(trainInstances.attribute(m_attIndex));
handleNumericAttribute(trainInstances);
}
}