dataset_mapper.hpp

Go to the documentation of this file.

#ifndef MLPACK_CORE_DATA_DATASET_INFO_HPP
#define MLPACK_CORE_DATA_DATASET_INFO_HPP

#include <mlpack/prereqs.hpp>
#include <unordered_map>
#include <boost/bimap.hpp>

#include "map_policies/increment_policy.hpp"

namespace mlpack {
namespace data {
template <typename PolicyType>
class DatasetMapper
{
 public:
  explicit DatasetMapper(const size_t dimensionality = 0);

  explicit DatasetMapper(PolicyType& policy, const size_t dimensionality = 0);

  typename PolicyType::MappedType MapString(const std::string& string,
                                            const size_t dimension);

  const std::string& UnmapString(const size_t value, const size_t dimension);


  typename PolicyType::MappedType UnmapValue(const std::string& string,
                                            const size_t dimension);

  template <typename eT>
  void MapTokens(const std::vector<std::string>& tokens, size_t& row,
      arma::Mat<eT>& matrix);

  Datatype Type(const size_t dimension) const;
  Datatype& Type(const size_t dimension);

  size_t NumMappings(const size_t dimension) const;

  size_t Dimensionality() const;

  template<typename Archive>
  void Serialize(Archive& ar, const unsigned int /* version */)
  {
    ar & data::CreateNVP(types, "types");
    ar & data::CreateNVP(maps, "maps");
  }

  const PolicyType& Policy() const;

  PolicyType& Policy();

  void Policy(PolicyType&& policy);

 private:
  std::vector<Datatype> types;

  // BiMapType definition
  using BiMapType = boost::bimap<std::string, typename PolicyType::MappedType>;

  // Mappings from strings to integers.
  // Map entries will only exist for dimensions that are categorical.
  // MapType = map<dimension, pair<bimap<string, MappedType>, numMappings>>
  using MapType = std::unordered_map<size_t, std::pair<BiMapType, size_t>>;

  MapType maps;

  //  mapped to the maps object. It is used in MapString() and MapTokens().
  PolicyType policy;
};

// Use typedef to provide backward compatibility
using DatasetInfo = DatasetMapper<data::IncrementPolicy>;

} // namespace data
} // namespace mlpack

#include "dataset_mapper_impl.hpp"

#endif