cf.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_CF_CF_HPP
#define MLPACK_METHODS_CF_CF_HPP

#include <mlpack/prereqs.hpp>
#include <mlpack/methods/neighbor_search/neighbor_search.hpp>
#include <mlpack/methods/amf/amf.hpp>
#include <mlpack/methods/amf/update_rules/nmf_als.hpp>
#include <mlpack/methods/amf/termination_policies/simple_residue_termination.hpp>
#include <set>
#include <map>
#include <iostream>

namespace mlpack {
namespace cf  {

template<typename FactorizerType>
struct FactorizerTraits
{
  static const bool UsesCoordinateList = false;
};

class CF
{
 public:
  CF(const size_t numUsersForSimilarity = 5,
     const size_t rank = 0);

  template<typename FactorizerType = amf::NMFALSFactorizer>
  CF(const arma::mat& data,
     FactorizerType factorizer = FactorizerType(),
     const size_t numUsersForSimilarity = 5,
     const size_t rank = 0);

  template<typename FactorizerType = amf::NMFALSFactorizer>
  CF(const arma::sp_mat& data,
     FactorizerType factorizer = FactorizerType(),
     const size_t numUsersForSimilarity = 5,
     const size_t rank = 0,
     const typename std::enable_if_t<
         !FactorizerTraits<FactorizerType>::UsesCoordinateList>* = 0);

  template<typename FactorizerType = amf::NMFALSFactorizer>
  void Train(const arma::mat& data,
             FactorizerType factorizer = FactorizerType());

  template<typename FactorizerType = amf::NMFALSFactorizer>
  void Train(const arma::sp_mat& data,
             FactorizerType factorizer = FactorizerType(),
             const typename std::enable_if_t<
                 !FactorizerTraits<FactorizerType>::UsesCoordinateList>* = 0);

  void NumUsersForSimilarity(const size_t num)
  {
    if (num < 1)
    {
      Log::Warn << "CF::NumUsersForSimilarity(): invalid value (< 1) "
          "ignored." << std::endl;
      return;
    }
    this->numUsersForSimilarity = num;
  }

  size_t NumUsersForSimilarity() const
  {
    return numUsersForSimilarity;
  }

  void Rank(const size_t rankValue)
  {
    this->rank = rankValue;
  }

  size_t Rank() const
  {
    return rank;
  }

  const arma::mat& W() const { return w; }
  const arma::mat& H() const { return h; }
  const arma::sp_mat& CleanedData() const { return cleanedData; }

  void GetRecommendations(const size_t numRecs,
                          arma::Mat<size_t>& recommendations);

  void GetRecommendations(const size_t numRecs,
                          arma::Mat<size_t>& recommendations,
                          const arma::Col<size_t>& users);

  static void CleanData(const arma::mat& data, arma::sp_mat& cleanedData);

  double Predict(const size_t user, const size_t item) const;

  void Predict(const arma::Mat<size_t>& combinations,
               arma::vec& predictions) const;

  template<typename Archive>
  void Serialize(Archive& ar, const unsigned int /* version */);

 private:
  size_t numUsersForSimilarity;
  size_t rank;
  arma::mat w;
  arma::mat h;
  arma::sp_mat cleanedData;

  typedef std::pair<double, size_t> Candidate;

  struct CandidateCmp {
    bool operator()(const Candidate& c1, const Candidate& c2)
    {
      return c1.first > c2.first;
    };
  };
}; // class CF

} // namespace cf
} // namespace mlpack

// Include implementation of templated functions.
#include "cf_impl.hpp"

#endif