z_score_normalization.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_CF_NORMALIZATION_Z_SCORE_NORMALIZATION_HPP
#define MLPACK_METHODS_CF_NORMALIZATION_Z_SCORE_NORMALIZATION_HPP

#include <mlpack/prereqs.hpp>

namespace mlpack {
namespace cf {

class ZScoreNormalization
{
 public:
  // Empty constructor.
  ZScoreNormalization() : mean(0), stddev(1) { }

  void Normalize(arma::mat& data)
  {
    mean = arma::mean(data.row(2));
    stddev = arma::stddev(data.row(2));

    if (std::fabs(stddev) < 1e-14)
    {
      Log::Fatal << "Standard deviation of all existing ratings is 0! "
          << "This may indicate that all existing ratings are the same."
          << std::endl;
    }

    data.row(2) = (data.row(2) - mean) / stddev;
    // The algorithm omits rating of zero. If normalized rating equals zero,
    // it is set to the smallest positive double value.
    data.row(2).for_each([](double& x)
    {
      if (x == 0)
        x = std::numeric_limits<double>::min();
    });
  }

  void Normalize(arma::sp_mat& cleanedData)
  {
    // Caculate mean and stdev of all non zero ratings.
    arma::vec ratings = arma::nonzeros(cleanedData);
    mean = arma::mean(ratings);
    stddev = arma::stddev(ratings);

    if (std::fabs(stddev) < 1e-14)
    {
      Log::Fatal << "Standard deviation of all existing ratings is 0! "
          << "This may indicate that all existing ratings are the same."
          << std::endl;
    }

    // Subtract mean from existing rating and divide it by stddev.
    arma::sp_mat::iterator it = cleanedData.begin();
    arma::sp_mat::iterator it_end = cleanedData.end();
    for (; it != it_end; ++it)
    {
      *it = (*it - mean) / stddev;
      // The algorithm omits rating of zero. If normalized rating equals zero,
      // it is set to the smallest positive double value.
      if (*it == 0)
        *it = std::numeric_limits<double>::min();
    }
  }

  double Denormalize(const size_t /* user */,
                     const size_t /* item */,
                     const double rating) const
  {
    return rating * stddev + mean;
  }

  void Denormalize(const arma::Mat<size_t>& /* combinations */,
                   arma::vec& predictions) const
  {
    predictions = predictions * stddev + mean;
  }

  double Mean() const
  {
    return mean;
  }

  double Stddev() const
  {
    return stddev;
  }

  template<typename Archive>
  void serialize(Archive& ar, const unsigned int /* version */)
  {
    ar & BOOST_SERIALIZATION_NVP(mean);
    ar & BOOST_SERIALIZATION_NVP(stddev);
  }

 private:
  double mean;
  double stddev;
};

} // namespace cf
} // namespace mlpack

#endif