float TEFMDataDescription::getExampleMatch(const TExample &ex1, const TExample &ex2)
{
if ((ex1.domain != domain) && (ex2.domain != domain))
raiseError("example's domain doesn't match the data descriptor's");
float weight=1.0;
TExample::iterator e1i(ex1.begin()), e2i(ex2.end());
if (domainDistributions) {
if (matchProbabilities.size() != domainDistributions->size())
matchProbabilities = vector<float>(domainDistributions->size(), -1);
vector<float>::iterator mi(matchProbabilities.begin());
TDomainDistributions::const_iterator di(domainDistributions->begin()), de(domainDistributions->end());
for(; di!=de; e1i++, e2i++, di++, mi++) {
if ((*e1i).varType == TValue::INTVAR) {
if ((*e1i).isDK()) {
if ((*e2i).isDK()) {
if (*mi == -1) {
float mp = 0.0;
ITERATE(TDiscDistribution, ddi, ((TDiscDistribution &)((*di).getReference())))
mp += *ddi * *ddi;
*mi = mp;
}
weight *= *mi;
}
else if (!(*e2i).isSpecial())
weight *= (*di)->p(*e2i);
}
else if ((*e2i).isDK() && !(*e1i).isSpecial())
weight *= (*di)->p(*e1i);
}
}
}
else {
TVarList::const_iterator vi(domain->attributes->begin()), vie(domain->attributes->end());
for(; vi!=vie; e1i++, e2i++, vi++)
if (((*e1i).varType == TValue::INTVAR) && ((*e1i).isDK() && !(*e2i).isSpecial() || (*e2i).isDK() && !(*e1i).isSpecial()))
weight /= (*vi)->noOfValues();
}
return weight;
}
PDistribution TLogRegClassifier::classDistribution(const TExample &origexam)
{
checkProperty(domain);
TExample cexample(domain, origexam);
TExample *example2;
if (imputer)
example2 = imputer->call(cexample);
else {
if (dataDescription)
for(TExample::const_iterator ei(cexample.begin()), ee(cexample.end()-1); ei!=ee; ei++)
if ((*ei).isSpecial())
return TClassifier::classDistribution(cexample, dataDescription);
example2 = &cexample;
}
TExample *example = continuizedDomain ? mlnew TExample(continuizedDomain, *example2) : example2;
float prob1;
try {
// multiply example with beta
TAttributedFloatList::const_iterator b(beta->begin()), be(beta->end());
// get beta 0
prob1 = *b;
b++;
// multiply beta with example
TVarList::const_iterator vi(example->domain->attributes->begin());
TExample::const_iterator ei(example->begin()), ee(example->end());
for (; (b!=be) && (ei!=ee); ei++, b++, vi++) {
if ((*ei).isSpecial())
raiseError("unknown value in attribute '%s'", (*vi)->get_name().c_str());
prob1 += (*ei).floatV * (*b);
}
prob1 = exp(prob1)/(1+exp(prob1));
}
catch (...) {
if (imputer)
mldelete example2;
if (continuizedDomain)
mldelete example;
throw;
}
if (imputer)
mldelete example2;
if (continuizedDomain)
mldelete example;
if (classVar->varType == TValue::INTVAR) {
TDiscDistribution *dist = mlnew TDiscDistribution(classVar);
PDistribution res = dist;
dist->addint(0, 1-prob1);
dist->addint(1, prob1);
return res;
}
else {
TContDistribution *dist = mlnew TContDistribution(classVar);
PDistribution res = dist;
dist->addfloat(prob1, 1.0);
return res;
}
}