Method GetUsedFeatures

src/treelearner/serial_tree_learner2.cpp:332–380

}

std::vector<int8_t> SerialTreeLearner2::GetUsedFeatures(bool is_tree_level) {
  std::vector<int8_t> ret(num_features_, 1);
  if (config_->feature_fraction >= 1.0f && is_tree_level) {
    return ret;
  }
  if (config_->feature_fraction_bynode >= 1.0f && !is_tree_level) {
    return ret;
  }
  std::memset(ret.data(), 0, sizeof(int8_t) * num_features_);
  const int min_used_features = std::min(2, static_cast<int>(valid_feature_indices_.size()));
  if (is_tree_level) {
    int used_feature_cnt = static_cast<int>(std::round(valid_feature_indices_.size() * config_->feature_fraction));
    used_feature_cnt = std::max(used_feature_cnt, min_used_features);
    used_feature_indices_ = random_.Sample(static_cast<int>(valid_feature_indices_.size()), used_feature_cnt);
    int omp_loop_size = static_cast<int>(used_feature_indices_.size());
    #pragma omp parallel for schedule(static, 512) if (omp_loop_size >= 1024)
    for (int i = 0; i < omp_loop_size; ++i) {
      int used_feature = valid_feature_indices_[used_feature_indices_[i]];
      int inner_feature_index = train_data_->InnerFeatureIndex(used_feature);
      CHECK(inner_feature_index >= 0);
      ret[inner_feature_index] = 1;
    }
  } else if (used_feature_indices_.size() <= 0) {
    int used_feature_cnt = static_cast<int>(std::round(valid_feature_indices_.size() * config_->feature_fraction_bynode));
    used_feature_cnt = std::max(used_feature_cnt, min_used_features);
    auto sampled_indices = random_.Sample(static_cast<int>(valid_feature_indices_.size()), used_feature_cnt);
    int omp_loop_size = static_cast<int>(sampled_indices.size());
    #pragma omp parallel for schedule(static, 512) if (omp_loop_size >= 1024)
    for (int i = 0; i < omp_loop_size; ++i) {
      int used_feature = valid_feature_indices_[sampled_indices[i]];
      int inner_feature_index = train_data_->InnerFeatureIndex(used_feature);
      CHECK(inner_feature_index >= 0);
      ret[inner_feature_index] = 1;
    }
  } else {
    int used_feature_cnt = static_cast<int>(std::round(used_feature_indices_.size() * config_->feature_fraction_bynode));
    used_feature_cnt = std::max(used_feature_cnt, min_used_features);
    auto sampled_indices = random_.Sample(static_cast<int>(used_feature_indices_.size()), used_feature_cnt);
    int omp_loop_size = static_cast<int>(sampled_indices.size());
    #pragma omp parallel for schedule(static, 512) if (omp_loop_size >= 1024)
    for (int i = 0; i < omp_loop_size; ++i) {
      int used_feature = valid_feature_indices_[used_feature_indices_[sampled_indices[i]]];
      int inner_feature_index = train_data_->InnerFeatureIndex(used_feature);
      CHECK(inner_feature_index >= 0);
      ret[inner_feature_index] = 1;
    }
  }
  return ret;
}

void SerialTreeLearner2::BeforeTrain() {
  // reset histogram pool