13 #ifndef MLPACK_METHODS_HOEFFDING_TREES_HOEFFDING_TREE_HPP 14 #define MLPACK_METHODS_HOEFFDING_TREES_HOEFFDING_TREE_HPP 55 template<
typename FitnessFunction = GiniImpurity,
56 template<
typename>
class NumericSplitType =
58 template<
typename>
class CategoricalSplitType =
59 HoeffdingCategoricalSplit
93 template<
typename MatType>
96 const arma::Row<size_t>& labels,
97 const size_t numClasses,
98 const bool batchTraining =
true,
99 const double successProbability = 0.95,
100 const size_t maxSamples = 0,
101 const size_t checkInterval = 100,
102 const size_t minSamples = 100,
103 const CategoricalSplitType<FitnessFunction>& categoricalSplitIn
104 = CategoricalSplitType<FitnessFunction>(0, 0),
105 const NumericSplitType<FitnessFunction>& numericSplitIn =
106 NumericSplitType<FitnessFunction>(0));
131 const size_t numClasses,
132 const double successProbability = 0.95,
133 const size_t maxSamples = 0,
134 const size_t checkInterval = 100,
135 const size_t minSamples = 100,
136 const CategoricalSplitType<FitnessFunction>& categoricalSplitIn
137 = CategoricalSplitType<FitnessFunction>(0, 0),
138 const NumericSplitType<FitnessFunction>& numericSplitIn =
139 NumericSplitType<FitnessFunction>(0),
140 std::unordered_map<
size_t, std::pair<size_t, size_t>>*
141 dimensionMappings = NULL,
142 const bool copyDatasetInfo =
true);
192 template<
typename MatType>
193 void Train(
const MatType& data,
194 const arma::Row<size_t>& labels,
195 const bool batchTraining =
true);
201 template<
typename MatType>
202 void Train(
const MatType& data,
204 const arma::Row<size_t>& labels,
205 const bool batchTraining =
true);
213 template<
typename VecType>
214 void Train(
const VecType& point,
const size_t label);
271 template<
typename VecType>
281 template<
typename VecType>
282 size_t Classify(
const VecType& point)
const;
298 template<
typename VecType>
299 void Classify(
const VecType& point,
size_t& prediction,
double& probability)
309 template<
typename MatType>
310 void Classify(
const MatType& data, arma::Row<size_t>& predictions)
const;
323 template<
typename MatType>
325 arma::Row<size_t>& predictions,
326 arma::rowvec& probabilities)
const;
334 template<
typename Archive>
335 void serialize(Archive& ar,
const uint32_t );
341 std::vector<NumericSplitType<FitnessFunction>> numericSplits;
343 std::vector<CategoricalSplitType<FitnessFunction>> categoricalSplits;
346 std::unordered_map<size_t, std::pair<size_t, size_t>>* dimensionMappings;
357 size_t checkInterval;
365 double successProbability;
370 size_t splitDimension;
372 size_t majorityClass;
375 double majorityProbability;
377 typename CategoricalSplitType<FitnessFunction>::SplitInfo categoricalSplit;
379 typename NumericSplitType<FitnessFunction>::SplitInfo numericSplit;
381 std::vector<HoeffdingTree*> children;
387 #include "hoeffding_tree_impl.hpp" HoeffdingTree()
Construct a Hoeffding tree with no data and no information.
const HoeffdingTree & Child(const size_t i) const
Get a child.
size_t NumChildren() const
Get the number of children.
Auxiliary information for a dataset, including mappings to/from strings (or other types) and the data...
~HoeffdingTree()
Clean up memory.
The HoeffdingTree object represents all of the necessary information for a Hoeffding-bound-based deci...
size_t CheckInterval() const
Get the number of samples before a split check is performed.
Linear algebra utility functions, generally performed on matrices or vectors.
The core includes that mlpack expects; standard C++ includes and Armadillo.
void Train(const MatType &data, const arma::Row< size_t > &labels, const bool batchTraining=true)
Train on a set of points, either in streaming mode or in batch mode, with the given labels...
size_t CalculateDirection(const VecType &point) const
Given a point and that this node is not a leaf, calculate the index of the child node this point woul...
size_t Classify(const VecType &point) const
Classify the given point, using this node and the entire (sub)tree beneath it.
size_t MaxSamples() const
Get the maximum number of samples before a split is forced.
double SuccessProbability() const
Get the confidence required for a split.
void serialize(Archive &ar, const uint32_t)
Serialize the split.
void CreateChildren()
Given that this node should split, create the children.
CategoricalSplitType< FitnessFunction > CategoricalSplit
Allow access to the categorical split type.
HoeffdingTree & operator=(const HoeffdingTree &other)
Copy assignment operator.
double MajorityProbability() const
Get the probability of the majority class (based on training samples).
size_t NumDescendants() const
Get the size of the Hoeffding Tree.
HoeffdingNumericSplit< FitnessFunction, double > HoeffdingDoubleNumericSplit
Convenience typedef.
size_t & MajorityClass()
Modify the majority class.
size_t SplitDimension() const
Get the splitting dimension (size_t(-1) if no split).
size_t MinSamples() const
Get the minimum number of samples for a split.
size_t SplitCheck()
Check if a split would satisfy the conditions of the Hoeffding bound with the node's specified succes...
HoeffdingTree & Child(const size_t i)
Modify a child.
size_t MajorityClass() const
Get the majority class.
NumericSplitType< FitnessFunction > NumericSplit
Allow access to the numeric split type.
double & MajorityProbability()
Modify the probability of the majority class.