C++ sfv_t::size方法代码示例

float recommender_base::calc_similality(sfv_t& q1, 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 recommender_base::complete_row(const sfv_t& query, 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) {
    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;
  }
  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 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);
}

static float calc_norm(const sfv_t& fv) {
  float norm = 0;
  for (size_t i = 0; i < fv.size(); ++i) {
    norm += fv[i].second * fv[i].second;
  }
  return norm;
}

void inverted_index_storage::calc_scores(const 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;
  }
  pfi::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 (pfi::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));
  }
}

float inverted_index_storage::calc_l2norm(const sfv_t& sfv){
  float ret = 0.f;
  for (size_t i = 0; i < sfv.size(); ++i){
    ret +=  sfv[i].second * sfv[i].second;
  }
  return sqrt(ret);
}

void sort_and_merge(sfv_t& sfv){
  if (sfv.size() == 0) return;
  sort(sfv.begin(), sfv.end());
  sfv_t ret_sfv;
  const string* prev = &sfv[0].first;
  float val = sfv[0].second;
  for (size_t i = 1; i < sfv.size(); ++i){
    if (sfv[i].first == *prev){
      val += sfv[i].second;
    } else {
      ret_sfv.push_back(make_pair(*prev, val));
      prev = &sfv[i].first;
      val = sfv[i].second;
    }
  }
  ret_sfv.push_back(make_pair(*prev, val));
  sfv.swap(ret_sfv);
}

void revert_feature(const sfv_t& fv,
                    fv_converter::datum& data) {
  for (size_t i = 0; i < fv.size(); ++i) {
    pair<string, float> num_value;
    pair<string, 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);
    }
  }
}

void sort_and_merge(sfv_t& sfv) {
    if (sfv.size() <= 1) {
        return;
    }
    sort(sfv.begin(), sfv.end());

    typedef sfv_t::iterator iterator;
    iterator cur = sfv.begin();
    iterator end = sfv.end();
    for (iterator iter = cur+1; iter != end; ++iter) {
        if (iter->first == cur->first) {
            cur->second += iter->second;
        } else {
            ++cur;
            *cur = *iter;
        }
    }
    sfv.erase(cur+1, end);
}

void minhash::calc_minhash_values(const sfv_t& sfv, bit_vector& bv) const{
  vector<float> min_values_buffer(hash_num_, FLT_MAX);
  vector<uint64_t> hash_buffer(hash_num_);
  for (size_t i = 0; i < sfv.size(); ++i){
    uint64_t key_hash = hash_util::calc_string_hash(sfv[i].first);
    float val = sfv[i].second;
    for (uint64_t j = 0; j < hash_num_; ++j){
      float hashval = calc_hash(key_hash, j, val);
      if (hashval < min_values_buffer[j]){
        min_values_buffer[j] = hashval;
        hash_buffer[j] = key_hash;
      }
    }
  }

  bv.resize_and_clear(hash_num_);
  for (size_t i = 0; i < hash_buffer.size(); ++i){
    if ((hash_buffer[i] & 1LLU) == 1){
      bv.set_bit(i);
    }
  }
}

void feature_hasher::hash_feature_keys(sfv_t& fv) const {
  for (size_t i = 0, size = fv.size(); i < size; ++i) {
    uint64_t id = hash_util::calc_string_hash(fv[i].first) % max_size_;
    fv[i].first = pfi::lang::lexical_cast<string>(id);
  }
}

void lsh::generate_column_bases(const sfv_t& sfv){
  for (size_t i = 0; i < sfv.size(); ++i){
    generate_column_base(sfv[i].first);
  }
}