float recommender_base::calc_similality(common::sfv_t& q1, common::sfv_t& q2) {
float q1_norm = calc_l2norm(q1);
float q2_norm = calc_l2norm(q2);
if (q1_norm == 0.f || q2_norm == 0.f) {
return 0.f;
}
sort(q1.begin(), q1.end());
sort(q2.begin(), q2.end());
size_t i1 = 0;
size_t i2 = 0;
float ret = 0.f;
while (i1 < q1.size() && i2 < q2.size()) {
const string& ind1 = q1[i1].first;
const string& ind2 = q2[i2].first;
if (ind1 < ind2) {
++i1;
} else if (ind1 > ind2) {
++i2;
} else {
ret += q1[i1].second * q2[i2].second;
++i1;
++i2;
}
}
return ret / q1_norm / q2_norm;
}
void inverted_index_storage::calc_scores(
const common::sfv_t& query,
vector<pair<string, float> >& scores,
size_t ret_num) const {
float query_norm = calc_l2norm(query);
if (query_norm == 0.f) {
return;
}
jubatus::util::data::unordered_map<uint64_t, float> i_scores;
for (size_t i = 0; i < query.size(); ++i) {
const string& fid = query[i].first;
float val = query[i].second;
add_inp_scores(fid, val, i_scores);
}
vector<pair<float, uint64_t> > sorted_scores;
for (jubatus::util::data::unordered_map<uint64_t, float>::
const_iterator it = i_scores.begin(); it != i_scores.end(); ++it) {
float norm = calc_columnl2norm(it->first);
float normed_score = (norm != 0.f) ? it->second / norm / query_norm : 0.f;
sorted_scores.push_back(make_pair(normed_score, it->first));
}
sort(sorted_scores.rbegin(), sorted_scores.rend());
for (size_t i = 0; i < sorted_scores.size() && i < ret_num; ++i) {
scores.push_back(
make_pair(column2id_.get_key(sorted_scores[i].second),
sorted_scores[i].first));
}
}
