/**
* Returns index of subset instance is assigned to. Returns -1 if instance is assigned to more
* than one subset.
*
* @exception Exception if something goes wrong
*/
public final int whichSubset(Instance instance) throws Exception {
if (instance.isMissing(m_attIndex)) return -1;
else {
if (instance.attribute(m_attIndex).isNominal()) {
if ((int) m_splitPoint == (int) instance.value(m_attIndex)) return 0;
else return 1;
} else if (Utils.smOrEq(instance.value(m_attIndex), m_splitPoint)) return 0;
else return 1;
}
}
/**
* Prunes a tree using C4.5's pruning procedure.
*
* @throws Exception if something goes wrong
*/
public void prune() throws Exception {
double errorsLargestBranch;
double errorsLeaf;
double errorsTree;
int indexOfLargestBranch;
myJ48ClassifierTree largestBranch;
int i;
if (!m_isLeaf) {
// Prune all subtrees.
for (i = 0; i < m_sons.length; i++) m_sons[i].prune();
// Compute error for largest branch
indexOfLargestBranch = m_localModel.distribution().maxBag();
errorsLargestBranch = Double.MAX_VALUE;
// Compute error if this Tree would be leaf
errorsLeaf = getEstimatedErrorsForDistribution(m_localModel.distribution());
// Compute error for the whole subtree
errorsTree = getEstimatedErrors();
// Decide if leaf is best choice.
if (Utils.smOrEq(errorsLeaf, errorsTree + 0.1)
&& Utils.smOrEq(errorsLeaf, errorsLargestBranch + 0.1)) {
// Free son Trees
m_sons = null;
m_isLeaf = true;
// Get NoSplit Model for node.
m_localModel = new myJ48NoSplit(m_localModel.distribution());
return;
}
// Decide if largest branch is better choice
// than whole subtree.
if (Utils.smOrEq(errorsLargestBranch, errorsTree + 0.1)) {
largestBranch = m_sons[indexOfLargestBranch];
m_sons = largestBranch.m_sons;
m_localModel = largestBranch.m_localModel;
m_isLeaf = largestBranch.m_isLeaf;
newDistribution(m_train);
prune();
}
}
}
/**
* Sets split point to greatest value in given data smaller or equal to old split point. (C4.5
* does this for some strange reason).
*/
public final void setSplitPoint(Instances allInstances) {
double newSplitPoint = -Double.MAX_VALUE;
double tempValue;
Instance instance;
if ((!allInstances.attribute(m_attIndex).isNominal()) && (m_numSubsets > 1)) {
Enumeration enu = allInstances.enumerateInstances();
while (enu.hasMoreElements()) {
instance = (Instance) enu.nextElement();
if (!instance.isMissing(m_attIndex)) {
tempValue = instance.value(m_attIndex);
if (Utils.gr(tempValue, newSplitPoint) && Utils.smOrEq(tempValue, m_splitPoint))
newSplitPoint = tempValue;
}
}
m_splitPoint = newSplitPoint;
}
}
/**
* Creates split on numeric attribute.
*
* @exception Exception if something goes wrong
*/
private void handleNumericAttribute(Instances trainInstances) throws Exception {
int firstMiss;
int next = 1;
int last = 0;
int index = 0;
int splitIndex = -1;
double currentInfoGain;
double defaultEnt;
double minSplit;
Instance instance;
int i;
// Current attribute is a numeric attribute.
m_distribution = new Distribution(2, trainInstances.numClasses());
// Only Instances with known values are relevant.
Enumeration enu = trainInstances.enumerateInstances();
i = 0;
while (enu.hasMoreElements()) {
instance = (Instance) enu.nextElement();
if (instance.isMissing(m_attIndex)) break;
m_distribution.add(1, instance);
i++;
}
firstMiss = i;
// Compute minimum number of Instances required in each
// subset.
minSplit = 0.1 * (m_distribution.total()) / ((double) trainInstances.numClasses());
if (Utils.smOrEq(minSplit, m_minNoObj)) minSplit = m_minNoObj;
else if (Utils.gr(minSplit, 25)) minSplit = 25;
// Enough Instances with known values?
if (Utils.sm((double) firstMiss, 2 * minSplit)) return;
// Compute values of criteria for all possible split
// indices.
defaultEnt = m_infoGainCrit.oldEnt(m_distribution);
while (next < firstMiss) {
if (trainInstances.instance(next - 1).value(m_attIndex) + 1e-5
< trainInstances.instance(next).value(m_attIndex)) {
// Move class values for all Instances up to next
// possible split point.
m_distribution.shiftRange(1, 0, trainInstances, last, next);
// Check if enough Instances in each subset and compute
// values for criteria.
if (Utils.grOrEq(m_distribution.perBag(0), minSplit)
&& Utils.grOrEq(m_distribution.perBag(1), minSplit)) {
currentInfoGain =
m_infoGainCrit.splitCritValue(m_distribution, m_sumOfWeights, defaultEnt);
if (Utils.gr(currentInfoGain, m_infoGain)) {
m_infoGain = currentInfoGain;
splitIndex = next - 1;
}
index++;
}
last = next;
}
next++;
}
// Was there any useful split?
if (index == 0) return;
// Compute modified information gain for best split.
if (m_useMDLcorrection) {
m_infoGain = m_infoGain - (Utils.log2(index) / m_sumOfWeights);
}
if (Utils.smOrEq(m_infoGain, 0)) return;
// Set instance variables' values to values for
// best split.
m_numSubsets = 2;
m_splitPoint =
(trainInstances.instance(splitIndex + 1).value(m_attIndex)
+ trainInstances.instance(splitIndex).value(m_attIndex))
/ 2;
// In case we have a numerical precision problem we need to choose the
// smaller value
if (m_splitPoint == trainInstances.instance(splitIndex + 1).value(m_attIndex)) {
m_splitPoint = trainInstances.instance(splitIndex).value(m_attIndex);
}
// Restore distributioN for best split.
m_distribution = new Distribution(2, trainInstances.numClasses());
m_distribution.addRange(0, trainInstances, 0, splitIndex + 1);
m_distribution.addRange(1, trainInstances, splitIndex + 1, firstMiss);
// Compute modified gain ratio for best split.
m_gainRatio = m_gainRatioCrit.splitCritValue(m_distribution, m_sumOfWeights, m_infoGain);
}
