Class BinaryLogloss

src/objective/binary_objective.hpp:21–210

! * \brief Objective function for binary classification */

* \brief Objective function for binary classification
*/
class BinaryLogloss: public ObjectiveFunction {
 public:
  explicit BinaryLogloss(const Config& config, std::function<bool(label_t)> is_pos = nullptr) {
    sigmoid_ = static_cast<double>(config.sigmoid);
    if (sigmoid_ <= 0.0) {
      Log::Fatal("Sigmoid parameter %f should be greater than zero", sigmoid_);
    }
    is_unbalance_ = config.is_unbalance;
    scale_pos_weight_ = static_cast<double>(config.scale_pos_weight);
    if (is_unbalance_ && std::fabs(scale_pos_weight_ - 1.0f) > 1e-6) {
      Log::Fatal("Cannot set is_unbalance and scale_pos_weight at the same time");
    }
    is_pos_ = is_pos;
    if (is_pos_ == nullptr) {
      is_pos_ = [](label_t label) {return label > 0; };
    }
  }

  explicit BinaryLogloss(const std::vector<std::string>& strs) {
    sigmoid_ = -1;
    for (auto str : strs) {
      auto tokens = Common::Split(str.c_str(), ':');
      if (tokens.size() == 2) {
        if (tokens[0] == std::string("sigmoid")) {
          Common::Atof(tokens[1].c_str(), &sigmoid_);
        }
      }
    }
    if (sigmoid_ <= 0.0) {
      Log::Fatal("Sigmoid parameter %f should be greater than zero", sigmoid_);
    }
  }

  ~BinaryLogloss() {}

  void Init(const Metadata& metadata, data_size_t num_data) override {
    num_data_ = num_data;
    label_ = metadata.label();
    weights_ = metadata.weights();
    data_size_t cnt_positive = 0;
    data_size_t cnt_negative = 0;
    // REMOVEME: remove the warning after 2.4 version release
    Log::Warning("Starting from the 2.1.2 version, default value for "
                 "the \"boost_from_average\" parameter in \"binary\" objective is true.\n"
                 "This may cause significantly different results comparing to the previous versions of LightGBM.\n"
                 "Try to set boost_from_average=false, if your old models produce bad results");
    // count for positive and negative samples
    #pragma omp parallel for schedule(static) reduction(+:cnt_positive, cnt_negative)
    for (data_size_t i = 0; i < num_data_; ++i) {
      if (is_pos_(label_[i])) {
        ++cnt_positive;
      } else {
        ++cnt_negative;
      }
    }
    num_pos_data_ = cnt_positive;
    if (Network::num_machines() > 1) {
      cnt_positive = Network::GlobalSyncUpBySum(cnt_positive);