/**
* Fast computation of ln(n!) for non-negative ints
*
* <p>negative ints are passed on to the general gamma-function based version in
* weka.core.SpecialFunctions
*
* <p>if the current n value is higher than any previous one, the cache is extended and filled to
* cover it
*
* <p>the common case is reduced to a simple array lookup
*
* @param n the integer
* @return ln(n!)
*/
public double lnFactorial(int n) {
if (n < 0) return weka.core.SpecialFunctions.lnFactorial(n);
if (m_lnFactorialCache.length <= n) {
double[] tmp = new double[n + 1];
System.arraycopy(m_lnFactorialCache, 0, tmp, 0, m_lnFactorialCache.length);
for (int i = m_lnFactorialCache.length; i < tmp.length; i++)
tmp[i] = tmp[i - 1] + Math.log(i);
m_lnFactorialCache = tmp;
}
return m_lnFactorialCache[n];
}
/**
* Test using Kononenko's MDL criterion.
*
* @param priorCounts
* @param bestCounts
* @param numInstances
* @param numCutPoints
* @return true if the split is acceptable
*/
private boolean KononenkosMDL(
double[] priorCounts, double[][] bestCounts, double numInstances, int numCutPoints) {
double distPrior, instPrior, distAfter = 0, sum, instAfter = 0;
double before, after;
int numClassesTotal;
// Number of classes occuring in the set
numClassesTotal = 0;
for (double priorCount : priorCounts) {
if (priorCount > 0) {
numClassesTotal++;
}
}
// Encode distribution prior to split
distPrior =
SpecialFunctions.log2Binomial(numInstances + numClassesTotal - 1, numClassesTotal - 1);
// Encode instances prior to split.
instPrior = SpecialFunctions.log2Multinomial(numInstances, priorCounts);
before = instPrior + distPrior;
// Encode distributions and instances after split.
for (double[] bestCount : bestCounts) {
sum = Utils.sum(bestCount);
distAfter += SpecialFunctions.log2Binomial(sum + numClassesTotal - 1, numClassesTotal - 1);
instAfter += SpecialFunctions.log2Multinomial(sum, bestCount);
}
// Coding cost after split
after = Utils.log2(numCutPoints) + distAfter + instAfter;
// Check if split is to be accepted
return (before > after);
}
