pca.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_PCA_PCA_HPP
#define MLPACK_METHODS_PCA_PCA_HPP

#include <mlpack/prereqs.hpp>
#include <mlpack/methods/pca/decomposition_policies/exact_svd_method.hpp>

namespace mlpack {
namespace pca {

template<typename DecompositionPolicy = ExactSVDPolicy>
class PCAType
{
 public:
  PCAType(const bool scaleData = false,
          const DecompositionPolicy& decomposition = DecompositionPolicy());

  void Apply(const arma::mat& data,
             arma::mat& transformedData,
             arma::vec& eigVal,
             arma::mat& eigvec);

  void Apply(const arma::mat& data,
             arma::mat& transformedData,
             arma::vec& eigVal);

  double Apply(arma::mat& data, const size_t newDimension);

  inline double Apply(arma::mat& data, const int newDimension)
  {
    return Apply(data, size_t(newDimension));
  }

  double Apply(arma::mat& data, const double varRetained);

  bool ScaleData() const { return scaleData; }
  bool& ScaleData() { return scaleData; }

 private:
  void ScaleData(arma::mat& centeredData)
  {
    if (scaleData)
    {
      // Scaling the data is when we reduce the variance of each dimension
      // to 1. We do this by dividing each dimension by its standard
      // deviation.
      arma::vec stdDev = arma::stddev(
          centeredData, 0, 1 /* for each dimension */);

      // If there are any zeroes, make them very small.
      for (size_t i = 0; i < stdDev.n_elem; ++i)
        if (stdDev[i] == 0)
          stdDev[i] = 1e-50;

      centeredData /= arma::repmat(stdDev, 1, centeredData.n_cols);
    }
  }

  bool scaleData;

  DecompositionPolicy decomposition;
}; // class PCA

typedef PCAType<ExactSVDPolicy> PCA;

} // namespace pca
} // namespace mlpack

// Include implementation.
#include "pca_impl.hpp"

#endif