Method BaggingHelper

src/boosting/goss.hpp:91–139

  }

  data_size_t BaggingHelper(Random* cur_rand, data_size_t start, data_size_t cnt, data_size_t* buffer, data_size_t* buffer_right) {
    if (cnt <= 0) {
      return 0;
    }
    std::vector<score_t> tmp_gradients(cnt, 0.0f);
    for (data_size_t i = 0; i < cnt; ++i) {
      for (int cur_tree_id = 0; cur_tree_id < num_tree_per_iteration_; ++cur_tree_id) {
        size_t idx = static_cast<size_t>(cur_tree_id) * num_data_ + start + i;
        tmp_gradients[i] += std::fabs(gradients_[idx] * hessians_[idx]);
      }
    }
    data_size_t top_k = static_cast<data_size_t>(cnt * config_->top_rate);
    data_size_t other_k = static_cast<data_size_t>(cnt * config_->other_rate);
    top_k = std::max(1, top_k);
    ArrayArgs<score_t>::ArgMaxAtK(&tmp_gradients, 0, static_cast<int>(tmp_gradients.size()), top_k - 1);
    score_t threshold = tmp_gradients[top_k - 1];

    score_t multiply = static_cast<score_t>(cnt - top_k) / other_k;
    data_size_t cur_left_cnt = 0;
    data_size_t cur_right_cnt = 0;
    data_size_t big_weight_cnt = 0;
    for (data_size_t i = 0; i < cnt; ++i) {
      score_t grad = 0.0f;
      for (int cur_tree_id = 0; cur_tree_id < num_tree_per_iteration_; ++cur_tree_id) {
        size_t idx = static_cast<size_t>(cur_tree_id) * num_data_ + start + i;
        grad += std::fabs(gradients_[idx] * hessians_[idx]);
      }
      if (grad >= threshold) {
        buffer[cur_left_cnt++] = start + i;
        ++big_weight_cnt;
      } else {
        data_size_t sampled = cur_left_cnt - big_weight_cnt;
        data_size_t rest_need = other_k - sampled;
        data_size_t rest_all = (cnt - i) - (top_k - big_weight_cnt);
        double prob = (rest_need) / static_cast<double>(rest_all);
        if (cur_rand->NextFloat() < prob) {
          buffer[cur_left_cnt++] = start + i;
          for (int cur_tree_id = 0; cur_tree_id < num_tree_per_iteration_; ++cur_tree_id) {
            size_t idx = static_cast<size_t>(cur_tree_id) * num_data_ + start + i;
            gradients_[idx] *= multiply;
            hessians_[idx] *= multiply;
          }
        } else {
          buffer_right[cur_right_cnt++] = start + i;
        }
      }
    }
    return cur_left_cnt;
  }

  void Bagging(int iter) override {
    bag_data_cnt_ = num_data_;