#include <eqpalg/distribution/nd_test.h>
namespace distribution {

std::tuple<int, std::string> nd_test(std::vector<double> data,
                                     dlib::running_stats<double> rs) {
  std::stringstream sstream;
  // 验证数据正态分布性，AD测试
  std::sort(data.begin(), data.end());
  double ad_value =
      boost::math::statistics::anderson_darling_normality_statistic(
          data, rs.mean(), rs.stddev()) /
      data.size();
  int test_result = 0;
  if (ad_value > 2) {
    sstream << "错误，该算法不属于正态分布,anderson_darling正态测试值为:"
            << ad_value << std::endl;
    test_result = 2;
  }
  auto [test_result_2, erro_msg] = nd_test(rs);
  sstream << erro_msg;
  return std::make_tuple(test_result + test_result_2, sstream.str());
}

std::tuple<int, std::string> nd_test(dlib::running_stats<double> rs) {
  std::stringstream sstream;
  int test_result = 0;
  // 对小范围数据正态分布进行估计
  if (std::abs(rs.skewness()) > 1) {
    sstream << "错误，偏态系数过大!请检查是否符合正态分布" << std::endl;
    test_result = 5;
  } else if (std::abs(rs.skewness()) > 0.6) {
    sstream << "警告，偏态系数偏大!" << std::endl;
    test_result = 3;
  }
  if (rs.ex_kurtosis() < -1) {
    sstream << "警告，数据分布过于分散，可能导致中心数据数据异常" << std::endl;
    test_result = test_result + 2;
  } else if (rs.ex_kurtosis() > 1) {
    sstream << "警告，数据分布过于集中，可能导致边缘数据报警异常" << std::endl;
    test_result = test_result + 1;
  }
  return std::make_tuple(test_result, sstream.str());
}

}  // namespace distribution