/**
* Creates split on enumerated attribute.
*
* @exception Exception if something goes wrong
*/
private void handleEnumeratedAttribute(Instances trainInstances) throws Exception {
Distribution newDistribution, secondDistribution;
int numAttValues;
double currIG, currGR;
Instance instance;
int i;
numAttValues = trainInstances.attribute(m_attIndex).numValues();
newDistribution = new Distribution(numAttValues, trainInstances.numClasses());
// Only Instances with known values are relevant.
Enumeration enu = trainInstances.enumerateInstances();
while (enu.hasMoreElements()) {
instance = (Instance) enu.nextElement();
if (!instance.isMissing(m_attIndex))
newDistribution.add((int) instance.value(m_attIndex), instance);
}
m_distribution = newDistribution;
// For all values
for (i = 0; i < numAttValues; i++) {
if (Utils.grOrEq(newDistribution.perBag(i), m_minNoObj)) {
secondDistribution = new Distribution(newDistribution, i);
// Check if minimum number of Instances in the two
// subsets.
if (secondDistribution.check(m_minNoObj)) {
m_numSubsets = 2;
currIG = m_infoGainCrit.splitCritValue(secondDistribution, m_sumOfWeights);
currGR = m_gainRatioCrit.splitCritValue(secondDistribution, m_sumOfWeights, currIG);
if ((i == 0) || Utils.gr(currGR, m_gainRatio)) {
m_gainRatio = currGR;
m_infoGain = currIG;
m_splitPoint = (double) i;
m_distribution = secondDistribution;
}
}
}
}
}
/**
* Creates split on enumerated attribute.
*
* @exception Exception if something goes wrong
*/
private void handleEnumeratedAttribute(Instances trainInstances) throws Exception {
Instance instance;
m_distribution = new Distribution(m_complexityIndex, trainInstances.numClasses());
// Only Instances with known values are relevant.
Enumeration<Instance> enu = trainInstances.enumerateInstances();
while (enu.hasMoreElements()) {
instance = enu.nextElement();
if (!instance.isMissing(m_attIndex)) {
m_distribution.add((int) instance.value(m_attIndex), instance);
}
}
// Check if minimum number of Instances in at least two
// subsets.
if (m_distribution.check(m_minNoObj)) {
m_numSubsets = m_complexityIndex;
m_infoGain = infoGainCrit.splitCritValue(m_distribution, m_sumOfWeights);
m_gainRatio = gainRatioCrit.splitCritValue(m_distribution, m_sumOfWeights, m_infoGain);
}
}
/**
* 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);
}
