random_forest.hpp

Go to the documentation of this file.

#ifndef MLPACK_METHODS_RANDOM_FOREST_RANDOM_FOREST_HPP
#define MLPACK_METHODS_RANDOM_FOREST_RANDOM_FOREST_HPP

#include <mlpack/methods/decision_tree/decision_tree.hpp>
#include <mlpack/methods/decision_tree/multiple_random_dimension_select.hpp>
#include "bootstrap.hpp"

namespace mlpack {
namespace tree {

template<typename FitnessFunction = GiniGain,
         typename DimensionSelectionType = MultipleRandomDimensionSelect<>,
         template<typename> class NumericSplitType = BestBinaryNumericSplit,
         template<typename> class CategoricalSplitType = AllCategoricalSplit,
         typename ElemType = double>
class RandomForest
{
 public:
  typedef DecisionTree<FitnessFunction, NumericSplitType, CategoricalSplitType,
      DimensionSelectionType, ElemType> DecisionTreeType;

  RandomForest() { }

  template<typename MatType>
  RandomForest(const MatType& dataset,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename MatType>
  RandomForest(const MatType& dataset,
               const data::DatasetInfo& datasetInfo,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename MatType>
  RandomForest(const MatType& dataset,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const arma::rowvec& weights,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename MatType>
  RandomForest(const MatType& dataset,
               const data::DatasetInfo& datasetInfo,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const arma::rowvec& weights,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename MatType>
  double Train(const MatType& data,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename MatType>
  double Train(const MatType& data,
               const data::DatasetInfo& datasetInfo,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename MatType>
  double Train(const MatType& data,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const arma::rowvec& weights,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename MatType>
  double Train(const MatType& data,
               const data::DatasetInfo& datasetInfo,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const arma::rowvec& weights,
               const size_t numTrees = 50,
               const size_t minimumLeafSize = 20);

  template<typename VecType>
  size_t Classify(const VecType& point) const;

  template<typename VecType>
  void Classify(const VecType& point,
                size_t& prediction,
                arma::vec& probabilities) const;

  template<typename MatType>
  void Classify(const MatType& data,
                arma::Row<size_t>& predictions) const;

  template<typename MatType>
  void Classify(const MatType& data,
                arma::Row<size_t>& predictions,
                arma::mat& probabilities) const;

  const DecisionTreeType& Tree(const size_t i) const { return trees[i]; }
  DecisionTreeType& Tree(const size_t i) { return trees[i]; }

  size_t NumTrees() const { return trees.size(); }

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

 private:
  template<bool UseWeights, bool UseDatasetInfo, typename MatType>
  double Train(const MatType& data,
               const data::DatasetInfo& datasetInfo,
               const arma::Row<size_t>& labels,
               const size_t numClasses,
               const arma::rowvec& weights,
               const size_t numTrees,
               const size_t minimumLeafSize);

  std::vector<DecisionTreeType> trees;
};

} // namespace tree
} // namespace mlpack

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

#endif