user_mean_normalization.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_CF_NORMALIZATION_USER_MEAN_NORMALIZATION_HPP
#define MLPACK_METHODS_CF_NORMALIZATION_USER_MEAN_NORMALIZATION_HPP

#include <mlpack/prereqs.hpp>

namespace mlpack {
namespace cf {

class UserMeanNormalization
{
 public:
  // Empty constructor.
  UserMeanNormalization() { }

  void Normalize(arma::mat& data)
  {
    const size_t userNum = arma::max(data.row(0)) + 1;
    userMean = arma::vec(userNum, arma::fill::zeros);
    // Number of ratings for each user.
    arma::Row<size_t> ratingNum(userNum, arma::fill::zeros);

    // Sum ratings for each user.
    data.each_col([&](arma::vec& datapoint)
    {
      const size_t user = (size_t) datapoint(0);
      const double rating = datapoint(2);
      userMean(user) += rating;
      ratingNum(user) += 1;
    });

    // Calculate user mean and subtract user mean from ratings.
    // Set user mean to 0 if the user has no rating.
    for (size_t i = 0; i < userNum; ++i)
    {
      if (ratingNum(i) != 0)
        userMean(i) /= ratingNum(i);
    }

    data.each_col([&](arma::vec& datapoint)
    {
      const size_t user = (size_t) datapoint(0);
      datapoint(2) -= userMean(user);
      // The algorithm omits rating of zero. If normalized rating equals zero,
      // it is set to the smallest positive double value.
      if (datapoint(2) == 0)
        datapoint(2) = std::numeric_limits<double>::min();
    });
  }

  void Normalize(arma::sp_mat& cleanedData)
  {
    // Calculate userMean.
    userMean = arma::vec(cleanedData.n_cols, arma::fill::zeros);
    arma::Col<size_t> ratingNum(cleanedData.n_cols, arma::fill::zeros);
    arma::sp_mat::iterator it = cleanedData.begin();
    arma::sp_mat::iterator it_end = cleanedData.end();
    for (; it != it_end; ++it)
    {
      userMean(it.col()) += *it;
      ratingNum(it.col()) += 1;
    }
    for (size_t i = 0; i < userMean.n_elem; ++i)
    {
      if (ratingNum(i) != 0)
        userMean(i) /= ratingNum(i);
    }

    // Normalize the data.
    it = cleanedData.begin();
    for (; it != cleanedData.end(); ++it)
    {
      double tmp = *it - userMean(it.col());

      // The algorithm omits rating of zero. If normalized rating equals zero,
      // it is set to the smallest positive float value.
      if (tmp == 0)
        tmp = std::numeric_limits<float>::min();

      *it = tmp;
    }
  }

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

  void Denormalize(const arma::Mat<size_t>& combinations,
                   arma::vec& predictions) const
  {
    for (size_t i = 0; i < predictions.n_elem; ++i)
    {
      const size_t user = combinations(0, i);
      predictions(i) += userMean(user);
    }
  }

  const arma::vec& Mean() const { return userMean; }

  template<typename Archive>
  void serialize(Archive& ar, const uint32_t /* version */)
  {
    ar(CEREAL_NVP(userMean));
  }

 private:
  arma::vec userMean;
};

} // namespace cf
} // namespace mlpack

#endif