int
ME_Model::make_feature_bag(const int cutoff)
{
int max_num_features = 0;
// count the occurrences of features
#ifdef USE_HASH_MAP
#if __cplusplus < 201103L
typedef std::tr1::unordered_map<unsigned int, int> map_type;
#else
typedef std::unordered_map<unsigned int, int> map_type;
#endif
#else
typedef std::map<unsigned int, int> map_type;
#endif
map_type count;
if (cutoff > 0) {
for (std::vector<Sample>::const_iterator i = _vs.begin(); i != _vs.end(); i++) {
for (std::vector<int>::const_iterator j = i->positive_features.begin(); j != i->positive_features.end(); j++) {
count[ME_Feature(i->label, *j).body()]++;
}
for (std::vector<pair<int, double> >::const_iterator j = i->rvfeatures.begin(); j != i->rvfeatures.end(); j++) {
count[ME_Feature(i->label, j->first).body()]++;
}
}
}
int n = 0;
for (std::vector<Sample>::const_iterator i = _vs.begin(); i != _vs.end(); i++, n++) {
max_num_features = max(max_num_features, (int)(i->positive_features.size()));
for (std::vector<int>::const_iterator j = i->positive_features.begin(); j != i->positive_features.end(); j++) {
const ME_Feature feature(i->label, *j);
// if (cutoff > 0 && count[feature.body()] < cutoff) continue;
if (cutoff > 0 && count[feature.body()] <= cutoff) continue;
_fb.Put(feature);
// cout << i->label << "\t" << *j << "\t" << id << endl;
// feature2sample[id].push_back(n);
}
for (std::vector<pair<int, double> >::const_iterator j = i->rvfeatures.begin(); j != i->rvfeatures.end(); j++) {
const ME_Feature feature(i->label, j->first);
// if (cutoff > 0 && count[feature.body()] < cutoff) continue;
if (cutoff > 0 && count[feature.body()] <= cutoff) continue;
_fb.Put(feature);
}
}
count.clear();
// cerr << "num_classes = " << _num_classes << endl;
// cerr << "max_num_features = " << max_num_features << endl;
init_feature2mef();
return max_num_features;
}
int
ME_Model::make_feature_bag(const int cutoff)
{
int max_label = 0;
int max_num_features = 0;
for (std::vector<Sample>::const_iterator i = _train.begin(); i != _train.end(); i++) {
max_label = max(max_label, i->label);
}
_num_classes = max_label + 1;
// map< int, list<int> > feature2sample;
// count the occurrences of features
#ifdef USE_HASH_MAP
typedef __gnu_cxx::hash_map<unsigned int, int> map_type;
#else
typedef std::map<unsigned int, int> map_type;
#endif
map_type count;
if (cutoff > 0) {
for (std::vector<Sample>::const_iterator i = _train.begin(); i != _train.end(); i++) {
for (std::list<int>::const_iterator j = i->positive_features.begin(); j != i->positive_features.end(); j++) {
count[ME_Feature(i->label, *j).body()]++;
}
}
}
int n = 0;
for (std::vector<Sample>::const_iterator i = _train.begin(); i != _train.end(); i++, n++) {
max_num_features = max(max_num_features, (int)(i->positive_features.size()));
for (std::list<int>::const_iterator j = i->positive_features.begin(); j != i->positive_features.end(); j++) {
const ME_Feature feature(i->label, *j);
if (cutoff > 0 && count[feature.body()] < cutoff) continue;
//int id = _fb.Put(feature);
// cout << i->label << "\t" << *j << "\t" << id << endl;
// feature2sample[id].push_back(n);
}
}
count.clear();
// cerr << "num_classes = " << _num_classes << endl;
// cerr << "max_num_features = " << max_num_features << endl;
int c = 0;
_sample2feature.clear();
_sample2feature.resize(_train.size());
n = 0;
for (std::vector<Sample>::const_iterator i = _train.begin(); i != _train.end(); i++) {
// _sample2feature[n].resize(_num_classes);
for (std::list<int>::const_iterator j = i->positive_features.begin(); j != i->positive_features.end(); j++){
for (int k = 0; k < _num_classes; k++) {
int id = _fb.Id(ME_Feature(k, *j));
if (id >= 0) {
_sample2feature[n].push_back(id);
c++;
}
}
}
n++;
}
// cerr << "c = " << c << endl;
return max_num_features;
}