normalize_labels_impl.hpp

Go to the documentation of this file.

#ifndef MLPACK_CORE_DATA_NORMALIZE_LABELS_IMPL_HPP
#define MLPACK_CORE_DATA_NORMALIZE_LABELS_IMPL_HPP

// In case it hasn't been included yet.
#include "normalize_labels.hpp"

namespace mlpack {
namespace data {

template<typename eT, typename RowType>
void NormalizeLabels(const RowType& labelsIn,
                     arma::Row<size_t>& labels,
                     arma::Col<eT>& mapping)
{
  // Loop over the input labels, and develop the mapping.  We'll first naively
  // resize the mapping to the maximum possible size, and then when we fill it,
  // we'll resize it back down to its actual size.
  mapping.set_size(labelsIn.n_elem);
  labels.set_size(labelsIn.n_elem);
  // Map for mapping labelIn to their label.
  std::unordered_map<eT, size_t> labelMap;
  size_t curLabel = 0;
  for (size_t i = 0; i < labelsIn.n_elem; ++i)
  {
    // If labelsIn[i] is already in the map, use the existing label.
    if (labelMap.count(labelsIn[i]) > 0)
    {
      labels[i] = labelMap[labelsIn[i]];
    }
    else
    {
      // If labelsIn[i] not there then add it to map.
      labelMap[labelsIn[i]] = curLabel;
      labels[i] = curLabel;
      ++curLabel;
    }
  }
  // Resize mapping back down to necessary size.
  mapping.resize(curLabel);
  // Mapping array created with encoded labels.
  for (auto it = labelMap.begin(); it != labelMap.end(); ++it)
  {
    mapping[it->second] = it->first;
  }
}

template<typename eT>
void RevertLabels(const arma::Row<size_t>& labels,
                  const arma::Col<eT>& mapping,
                  arma::Row<eT>& labelsOut)
{
  // We already have the mapping, so we just need to loop over each element.
  labelsOut.set_size(labels.n_elem);

  for (size_t i = 0; i < labels.n_elem; ++i)
    labelsOut[i] = mapping[labels[i]];
}

} // namespace data
} // namespace mlpack

#endif