overall_mean_normalization.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_CF_NORMALIZATION_OVERALL_MEAN_NORMALIZATION_HPP
#define MLPACK_METHODS_CF_NORMALIZATION_OVERALL_MEAN_NORMALIZATION_HPP

#include <mlpack/prereqs.hpp>

namespace mlpack {
namespace cf {

class OverallMeanNormalization
{
 public:
  // Empty constructor.
  OverallMeanNormalization() : mean(0) { }

  void Normalize(arma::mat& data)
  {
    mean = arma::mean(data.row(2));
    data.row(2) -= mean;
    // 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 of all non zero ratings.
    if (cleanedData.n_nonzero != 0)
    {
      mean = arma::accu(cleanedData) / cleanedData.n_nonzero;
      // Subtract mean from all non zero ratings.
      arma::sp_mat::iterator it = cleanedData.begin();
      arma::sp_mat::iterator it_end = cleanedData.end();
      for (; it != it_end; ++it)
      {
        *it = *it - mean;
        // 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();
      }
    }
    else
    {
      mean = 0;
      // cleanedData remains the same when mean == 0.
    }
  }

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

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

  double Mean() const
  {
    return mean;
  }

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

 private:
  double mean;
};

} // namespace cf
} // namespace mlpack

#endif