public void split() {
if (m_ilist == null) throw new IllegalStateException("Frozen. Cannot split.");
int numLeftChildren = 0;
boolean[] toLeftChild = new boolean[m_instIndices.length];
for (int i = 0; i < m_instIndices.length; i++) {
Instance instance = m_ilist.get(m_instIndices[i]);
FeatureVector fv = (FeatureVector) instance.getData();
if (fv.value(m_gainRatio.getMaxValuedIndex()) <= m_gainRatio.getMaxValuedThreshold()) {
toLeftChild[i] = true;
numLeftChildren++;
} else toLeftChild[i] = false;
}
logger.info(
"leftChild.size="
+ numLeftChildren
+ " rightChild.size="
+ (m_instIndices.length - numLeftChildren));
int[] leftIndices = new int[numLeftChildren];
int[] rightIndices = new int[m_instIndices.length - numLeftChildren];
int li = 0, ri = 0;
for (int i = 0; i < m_instIndices.length; i++) {
if (toLeftChild[i]) leftIndices[li++] = m_instIndices[i];
else rightIndices[ri++] = m_instIndices[i];
}
m_leftChild = new Node(m_ilist, this, m_minNumInsts, leftIndices);
m_rightChild = new Node(m_ilist, this, m_minNumInsts, rightIndices);
}
public Node(InstanceList ilist, Node parent, int minNumInsts, int[] instIndices) {
if (instIndices == null) {
instIndices = new int[ilist.size()];
for (int ii = 0; ii < instIndices.length; ii++) instIndices[ii] = ii;
}
m_gainRatio = GainRatio.createGainRatio(ilist, instIndices, minNumInsts);
m_ilist = ilist;
m_instIndices = instIndices;
m_dataDict = m_ilist.getDataAlphabet();
m_minNumInsts = minNumInsts;
m_parent = parent;
m_leftChild = m_rightChild = null;
}
public double computeCostAndPrune() {
double costS = getMDL();
if (isLeaf()) return costS + 1;
double minCost1 = getLeftChild().computeCostAndPrune();
double minCost2 = getRightChild().computeCostAndPrune();
double costSplit = Math.log(m_gainRatio.getNumSplitPointsForBestFeature()) / GainRatio.log2;
double minCostN = Math.min(costS + 1, costSplit + 1 + minCost1 + minCost2);
if (Maths.almostEquals(minCostN, costS + 1)) m_leftChild = m_rightChild = null;
return minCostN;
}
public Object getSplitFeature() {
return m_dataDict.lookupObject(m_gainRatio.getMaxValuedIndex());
}