PProbabilityEstimator TProbabilityEstimatorConstructor_m::operator()(PDistribution frequencies, PDistribution apriori, PExampleGenerator, const long &weightID, const int &) const
{ TProbabilityEstimator_FromDistribution *pefd = mlnew TProbabilityEstimator_FromDistribution(CLONE(TDistribution, frequencies));
PProbabilityEstimator estimator = pefd;
TDiscDistribution *ddist = pefd->probabilities.AS(TDiscDistribution);
if (ddist && (ddist->cases > 1e-20) && apriori) {
TDiscDistribution *dapriori = apriori.AS(TDiscDistribution);
if (!dapriori || (dapriori->abs < 1e-20))
raiseError("invalid apriori distribution");
float mabs = m/dapriori->abs;
const float &abs = ddist->abs;
const float &cases = ddist->cases;
const float div = cases + m;
if ((abs==cases) || !renormalize) {
int i = 0;
for(TDiscDistribution::iterator di(ddist->begin()), de(ddist->end()), ai(dapriori->begin());
di != de;
di++, ai++, i++)
ddist->setint(i, (*di+*ai*mabs)/div);
}
else {
int i = 0;
for(TDiscDistribution::iterator di(ddist->begin()), de(ddist->end()), ai(dapriori->begin());
di != de;
di++, ai++, i++)
ddist->setint(i, (*di / abs * cases + *ai*mabs)/div);
}
}
else
pefd->probabilities->normalize();
return estimator;
}
// rejects the split if there are less than two non-empty branches
// or there is a non-empty branch with less then minSubset examples
bool checkDistribution(const TDiscDistribution &dist, const float &minSubset)
{
int nonzero = 0;
for(TDiscDistribution::const_iterator dvi(dist.begin()), dve(dist.end()); dvi!=dve; dvi++)
if (*dvi > 0) {
if (*dvi < minSubset)
return false;
nonzero++;
}
return nonzero >= 2;
}