em_fit.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_GMM_EM_FIT_HPP
#define MLPACK_METHODS_GMM_EM_FIT_HPP

#include <mlpack/prereqs.hpp>
#include <mlpack/core/dists/gaussian_distribution.hpp>

// Default clustering mechanism.
#include <mlpack/methods/kmeans/kmeans.hpp>
// Default covariance matrix constraint.
#include "positive_definite_constraint.hpp"

namespace mlpack {
namespace gmm {

template<typename InitialClusteringType = kmeans::KMeans<>,
         typename CovarianceConstraintPolicy = PositiveDefiniteConstraint>
class EMFit
{
 public:
  EMFit(const size_t maxIterations = 300,
        const double tolerance = 1e-10,
        InitialClusteringType clusterer = InitialClusteringType(),
        CovarianceConstraintPolicy constraint = CovarianceConstraintPolicy());

  void Estimate(const arma::mat& observations,
                std::vector<distribution::GaussianDistribution>& dists,
                arma::vec& weights,
                const bool useInitialModel = false);

  void Estimate(const arma::mat& observations,
                const arma::vec& probabilities,
                std::vector<distribution::GaussianDistribution>& dists,
                arma::vec& weights,
                const bool useInitialModel = false);

  const InitialClusteringType& Clusterer() const { return clusterer; }
  InitialClusteringType& Clusterer() { return clusterer; }

  const CovarianceConstraintPolicy& Constraint() const { return constraint; }
  CovarianceConstraintPolicy& Constraint() { return constraint; }

  size_t MaxIterations() const { return maxIterations; }
  size_t& MaxIterations() { return maxIterations; }

  double Tolerance() const { return tolerance; }
  double& Tolerance() { return tolerance; }

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

 private:
  void InitialClustering(const arma::mat& observations,
                         std::vector<distribution::GaussianDistribution>& dists,
                         arma::vec& weights);

  double LogLikelihood(const arma::mat& data,
                       const std::vector<distribution::GaussianDistribution>&
                           dists,
                       const arma::vec& weights) const;

  size_t maxIterations;
  double tolerance;
  InitialClusteringType clusterer;
  CovarianceConstraintPolicy constraint;
};

} // namespace gmm
} // namespace mlpack

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

#endif