void KNN::train(Examples& exs){
TRACE_V(TAG,"train");
//Maybe we didnt calculate this before...
stats->calculateIDF();
for(int i = 0; i < exs.getNumberOfNumericalAttibutes(); i++){
maxv[i] = numeric_limits<double>::min();
minv[i] = numeric_limits<double>::max();
}
for(ExampleIterator e = exs.getBegin(); e != exs.getEnd(); e++){
vector<string> textTokens = (e)->getTextTokens();
vector<int> textFrequencyTokens = (e)->getTextFrequency();
string exampleClass = (e)->getClass();
string eId = (e)->getId();
double docSize = 0.0;
// cout<<" Tokens categoricos = " << tokens.size() << endl;
for(unsigned int i = 3; i < textTokens.size(); i++){
int tf = textFrequencyTokens[i-3];
string termId = textTokens[i];
double tfidf = tf * stats->getIDF(termId);
docSize += (tfidf * tfidf);
docWeighted dw(eId, tfidf);
termDocWset[termId].insert(dw);
}
vector<double> numTokens = (e)->getNumericalTokens();
for(unsigned int i = 0; i < numTokens.size(); i++){
if(greaterThan(numTokens[i], maxv[i])){
maxv[i] = numTokens[i];
}
if(lesserThan(numTokens[i], minv[i])){
minv[i] = numTokens[i];
}
}
exNumTrain[eId] = numTokens;
exCatTrain[eId] = (e)->getCategoricalTokens();
docTrainSizes[eId] = docSize;
}
}
