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;
}
float classifier_base::squared_norm(const common::sfv_t& fv) {
float ret = 0.f;
for (size_t i = 0; i < fv.size(); ++i) {
ret += fv[i].second * fv[i].second;
}
return ret;
}
float classifier_base::calc_margin_and_variance(
const common::sfv_t& sfv,
const string& label,
string& incorrect_label,
float& var) const {
float margin = calc_margin(sfv, label, incorrect_label);
var = 0.f;
for (size_t i = 0; i < sfv.size(); ++i) {
const string& feature = sfv[i].first;
const float val = sfv[i].second;
feature_val2_t weight_covars;
storage_->get2(feature, weight_covars);
float label_covar = 1.f;
float incorrect_label_covar = 1.f;
for (size_t j = 0; j < weight_covars.size(); ++j) {
if (weight_covars[j].first == label) {
label_covar = weight_covars[j].second.v2;
} else if (weight_covars[j].first == incorrect_label) {
incorrect_label_covar = weight_covars[j].second.v2;
}
}
var += (label_covar + incorrect_label_covar) * val * val;
}
return margin;
}
static float squared_norm(const common::sfv_t& fv) {
float norm = 0.f;
for (size_t i = 0; i < fv.size(); ++i) {
norm += fv[i].second * fv[i].second;
}
return norm;
}
void recommender_base::complete_row(const common::sfv_t& query,
common::sfv_t& ret) const {
ret.clear();
vector<pair<string, float> > ids;
similar_row(query, ids, complete_row_similar_num_);
if (ids.size() == 0) {
return;
}
size_t exist_row_num = 0;
for (size_t i = 0; i < ids.size(); ++i) {
common::sfv_t row;
orig_.get_row(ids[i].first, row);
if (row.size() == 0) {
continue;
} else {
++exist_row_num;
}
float ratio = ids[i].second;
for (size_t j = 0; j < row.size(); ++j) {
ret.push_back(make_pair(row[j].first, row[j].second * ratio));
}
}
if (exist_row_num == 0) {
return;
}
common::sort_and_merge(ret);
for (size_t i = 0; i < ret.size(); ++i) {
ret[i].second /= exist_row_num;
}
}
float recommender_base::calc_l2norm(const common::sfv_t& query) {
float ret = 0.f;
for (size_t i = 0; i < query.size(); ++i) {
ret += query[i].second * query[i].second;
}
return sqrt(ret);
}
float inverted_index_storage::calc_l2norm(const common::sfv_t& sfv) {
float ret = 0.f;
for (size_t i = 0; i < sfv.size(); ++i) {
ret += sfv[i].second * sfv[i].second;
}
return std::sqrt(ret);
}
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));
}
}
void revert_feature(const common::sfv_t& fv, fv_converter::datum& data) {
for (size_t i = 0; i < fv.size(); ++i) {
std::pair<std::string, double> num_value;
std::pair<std::string, std::string> string_value;
if (revert_num_value(fv[i], num_value)) {
data.num_values_.push_back(num_value);
} else if (revert_string_value(fv[i], string_value)) {
data.string_values_.push_back(string_value);
}
}
}
vector<float> random_projection(const common::sfv_t& sfv, uint32_t hash_num) {
vector<float> proj(hash_num);
for (size_t i = 0; i < sfv.size(); ++i) {
const uint32_t seed = common::hash_util::calc_string_hash(sfv[i].first);
jubatus::util::math::random::mtrand rnd(seed);
for (uint32_t j = 0; j < hash_num; ++j) {
proj[j] += sfv[i].second * rnd.next_gaussian();
}
}
return proj;
}
vector<float> euclid_lsh::calculate_lsh(const common::sfv_t& query) const {
vector<float> hash(mixable_storage_->get_model()->all_lsh_num());
for (size_t i = 0; i < query.size(); ++i) {
const uint32_t seed = common::hash_util::calc_string_hash(query[i].first);
const vector<float> proj = get_projection(seed);
for (size_t j = 0; j < hash.size(); ++j) {
hash[j] += query[i].second * proj[j];
}
}
for (size_t j = 0; j < hash.size(); ++j) {
hash[j] /= bin_width_;
}
return hash;
}
void inverted_index_classifier::train(
const common::sfv_t& fv,
const std::string& label) {
std::string id;
{
util::concurrent::scoped_lock lk(rand_mutex_);
id = make_id_from_label(label, rand_);
}
{
util::concurrent::scoped_wlock lk(storage_mutex_);
storage::inverted_index_storage& inv = *mixable_storage_->get_model();
for (size_t i = 0; i < fv.size(); ++i) {
inv.set(fv[i].first, id, fv[i].second);
}
}
set_label(label);
labels_.get_model()->increment(label);
}
void lsh::generate_column_bases(const common::sfv_t& sfv) {
for (size_t i = 0; i < sfv.size(); ++i) {
generate_column_base(sfv[i].first);
}
}
void feature_hasher::hash_feature_keys(common::sfv_t& fv) const {
for (size_t i = 0, size = fv.size(); i < size; ++i) {
uint64_t id = common::hash_util::calc_string_hash(fv[i].first) % max_size_;
fv[i].first = jubatus::util::lang::lexical_cast<std::string>(id);
}
}