Function LGBM_DatasetCreateFromCSRFunc

src/c_api.cpp:769–839

}

int LGBM_DatasetCreateFromCSRFunc(void* get_row_funptr,
                                  int num_rows,
                                  int64_t num_col,
                                  const char* parameters,
                                  const DatasetHandle reference,
                                  DatasetHandle* out) {
  API_BEGIN();
  if (num_col <= 0) {
    Log::Fatal("The number of columns should be greater than zero.");
  } else if (num_col >= INT32_MAX) {
    Log::Fatal("The number of columns should be smaller than INT32_MAX.");
  }
  auto get_row_fun = *static_cast<std::function<void(int idx, std::vector<std::pair<int, double>>&)>*>(get_row_funptr);
  auto param = Config::Str2Map(parameters);
  Config config;
  config.Set(param);
  if (config.num_threads > 0) {
    omp_set_num_threads(config.num_threads);
  }
  std::unique_ptr<Dataset> ret;
  int32_t nrow = num_rows;
  if (reference == nullptr) {
    // sample data first
    Random rand(config.data_random_seed);
    int sample_cnt = static_cast<int>(nrow < config.bin_construct_sample_cnt ? nrow : config.bin_construct_sample_cnt);
    auto sample_indices = rand.Sample(nrow, sample_cnt);
    sample_cnt = static_cast<int>(sample_indices.size());
    std::vector<std::vector<double>> sample_values(num_col);
    std::vector<std::vector<int>> sample_idx(num_col);
    // local buffer to re-use memory
    std::vector<std::pair<int, double>> buffer;
    for (size_t i = 0; i < sample_indices.size(); ++i) {
      auto idx = sample_indices[i];
      get_row_fun(static_cast<int>(idx), buffer);
      for (std::pair<int, double>& inner_data : buffer) {
        CHECK(inner_data.first < num_col);
        if (std::fabs(inner_data.second) > kZeroThreshold || std::isnan(inner_data.second)) {
          sample_values[inner_data.first].emplace_back(inner_data.second);
          sample_idx[inner_data.first].emplace_back(static_cast<int>(i));
        }
      }
    }
    DatasetLoader loader(config, nullptr, 1, nullptr);
    ret.reset(loader.CostructFromSampleData(Common::Vector2Ptr<double>(&sample_values).data(),
                                            Common::Vector2Ptr<int>(&sample_idx).data(),
                                            static_cast<int>(num_col),
                                            Common::VectorSize<double>(sample_values).data(),
                                            sample_cnt, nrow));
  } else {
    ret.reset(new Dataset(nrow));
    ret->CreateValid(
      reinterpret_cast<const Dataset*>(reference));
  }

  OMP_INIT_EX();
  std::vector<std::pair<int, double>> threadBuffer;
  #pragma omp parallel for schedule(static) private(threadBuffer)
  for (int i = 0; i < num_rows; ++i) {