/// <summary> Computes entropy after splitting without considering the
/// class values.
/// </summary>
public double splitEnt(Distribution bags)
{
double returnValue = 0;
int i;
for (i = 0; i < bags.numBags(); i++)
returnValue = returnValue + logFunc(bags.perBag(i));
return logFunc(bags.total()) - returnValue;
}
/// <summary> Computes entropy of distribution after splitting.</summary>
public double newEnt(Distribution bags)
{
double returnValue = 0;
int i, j;
for (i = 0; i < bags.numBags(); i++)
{
for (j = 0; j < bags.numClasses(); j++)
returnValue = returnValue + logFunc(bags.perClassPerBag(i, j));
returnValue = returnValue - logFunc(bags.perBag(i));
}
return - returnValue;
}
/// <summary> Computes entropy of test distribution with respect to training distribution.</summary>
public override double splitCritValue(Distribution train, Distribution test)
{
double result = 0;
int numClasses = 0;
int i, j;
// Find out relevant number of classes
for (j = 0; j < test.numClasses(); j++)
if (Utils.gr(train.perClass(j), 0) || Utils.gr(test.perClass(j), 0))
numClasses++;
// Compute entropy of test data with respect to training data
for (i = 0; i < test.numBags(); i++)
if (Utils.gr(test.perBag(i), 0))
{
for (j = 0; j < test.numClasses(); j++)
if (Utils.gr(test.perClassPerBag(i, j), 0))
result -= test.perClassPerBag(i, j) * System.Math.Log(train.perClassPerBag(i, j) + 1);
result += test.perBag(i) * System.Math.Log(train.perBag(i) + numClasses);
}
return result / log2;
}
/// <summary> Help method for computing the split entropy.</summary>
private double splitEnt(Distribution bags, double totalnoInst)
{
double returnValue = 0;
double noUnknown;
int i;
noUnknown = totalnoInst - bags.total();
if (Utils.gr(bags.total(), 0))
{
for (i = 0; i < bags.numBags(); i++)
returnValue = returnValue - logFunc(bags.perBag(i));
returnValue = returnValue - logFunc(noUnknown);
returnValue = returnValue + logFunc(totalnoInst);
}
return returnValue;
}
