Trainer for decision trees. More...

#include <pcl/ml/dt/decision_tree_trainer.h>

Public Member Functions
	DecisionTreeTrainer ()
	Constructor.

virtual	~DecisionTreeTrainer ()
	Destructor.

void	setFeatureHandler (pcl::FeatureHandler< FeatureType, DataSet, ExampleIndex > &feature_handler)
	Sets the feature handler used to create and evaluate features.

void	setStatsEstimator (pcl::StatsEstimator< LabelType, NodeType, DataSet, ExampleIndex > &stats_estimator)
	Sets the object for estimating the statistics for tree nodes.

void	setMaxTreeDepth (const std::size_t max_tree_depth)
	Sets the maximum depth of the learned tree.

void	setNumOfFeatures (const std::size_t num_of_features)
	Sets the number of features used to find optimal decision features.

void	setNumOfThresholds (const std::size_t num_of_threshold)
	Sets the number of thresholds tested for finding the optimal decision threshold on the feature responses.

void	setTrainingDataSet (DataSet &data_set)
	Sets the input data set used for training.

void	setExamples (std::vector< ExampleIndex > &examples)
	Example indices that specify the data used for training.

void	setLabelData (std::vector< LabelType > &label_data)
	Sets the label data corresponding to the example data.

void	setMinExamplesForSplit (std::size_t n)
	Sets the minimum number of examples to continue growing a tree.

void	setThresholds (std::vector< float > &thres)
	Specify the thresholds to be used when evaluating features.

void	setDecisionTreeDataProvider (typename pcl::DecisionTreeTrainerDataProvider< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::Ptr &dtdp)
	Specify the data provider.

void	setRandomFeaturesAtSplitNode (bool b)
	Specify if the features are randomly generated at each split node.

void	train (DecisionTree< NodeType > &tree)
	Trains a decision tree using the set training data and settings.

Protected Member Functions
void	trainDecisionTreeNode (std::vector< FeatureType > &features, std::vector< ExampleIndex > &examples, std::vector< LabelType > &label_data, std::size_t max_depth, NodeType &node)
	Trains a decision tree node from the specified features, label data, and examples.

Static Protected Member Functions
static void	createThresholdsUniform (const std::size_t num_of_thresholds, std::vector< float > &values, std::vector< float > &thresholds)
	Creates uniformly distributed thresholds over the range of the supplied values.

Detailed Description

template<class FeatureType, class DataSet, class LabelType, class ExampleIndex, class NodeType>
class pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >

Trainer for decision trees.

Definition at line 56 of file decision_tree_trainer.h.

Constructor & Destructor Documentation

◆ DecisionTreeTrainer()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::DecisionTreeTrainer ( )

default

Constructor.

◆ ~DecisionTreeTrainer()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::~DecisionTreeTrainer ( )

virtualdefault

Destructor.

Member Function Documentation

◆ createThresholdsUniform()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::createThresholdsUniform	(	const std::size_t	num_of_thresholds,
		std::vector< float > &	values,
		std::vector< float > &	thresholds
	)

staticprotected

Creates uniformly distributed thresholds over the range of the supplied values.

Parameters

[in]	num_of_thresholds	the number of thresholds to create
[in]	values	the values for estimating the expected value range
[out]	thresholds	the resulting thresholds

Definition at line 259 of file decision_tree_trainer.hpp.

◆ setDecisionTreeDataProvider()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setDecisionTreeDataProvider ( typename pcl::DecisionTreeTrainerDataProvider< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::Ptr & dtdp )

inline

Specify the data provider.

Parameters

[in] dtdp the data provider that should implement getDatasetAndLabels() function

Definition at line 174 of file decision_tree_trainer.h.

◆ setExamples()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setExamples ( std::vector< ExampleIndex > & examples )

inline

Example indices that specify the data used for training.

Parameters

[in] examples the examples

Definition at line 133 of file decision_tree_trainer.h.

◆ setFeatureHandler()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setFeatureHandler ( pcl::FeatureHandler< FeatureType, DataSet, ExampleIndex > & feature_handler )

inline

Sets the feature handler used to create and evaluate features.

Parameters

[in] feature_handler the feature handler

Definition at line 70 of file decision_tree_trainer.h.

◆ setLabelData()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setLabelData ( std::vector< LabelType > & label_data )

inline

Sets the label data corresponding to the example data.

Parameters

[in] label_data the label data

Definition at line 143 of file decision_tree_trainer.h.

◆ setMaxTreeDepth()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setMaxTreeDepth ( const std::size_t max_tree_depth )

inline

Sets the maximum depth of the learned tree.

Parameters

[in] max_tree_depth maximum depth of the learned tree

Definition at line 92 of file decision_tree_trainer.h.

◆ setMinExamplesForSplit()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setMinExamplesForSplit ( std::size_t n )

inline

Sets the minimum number of examples to continue growing a tree.

Parameters

[in] n number of examples

Definition at line 153 of file decision_tree_trainer.h.

◆ setNumOfFeatures()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setNumOfFeatures ( const std::size_t num_of_features )

inline

Sets the number of features used to find optimal decision features.

Parameters

[in] num_of_features the number of features

Definition at line 102 of file decision_tree_trainer.h.

◆ setNumOfThresholds()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setNumOfThresholds ( const std::size_t num_of_threshold )

inline

Sets the number of thresholds tested for finding the optimal decision threshold on the feature responses.

Parameters

[in] num_of_threshold the number of thresholds

Definition at line 113 of file decision_tree_trainer.h.

◆ setRandomFeaturesAtSplitNode()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setRandomFeaturesAtSplitNode ( bool b )

inline

Specify if the features are randomly generated at each split node.

Parameters

[in] b do it or not

Definition at line 189 of file decision_tree_trainer.h.

◆ setStatsEstimator()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setStatsEstimator ( pcl::StatsEstimator< LabelType, NodeType, DataSet, ExampleIndex > & stats_estimator )

inline

Sets the object for estimating the statistics for tree nodes.

Parameters

[in] stats_estimator the statistics estimator

Definition at line 81 of file decision_tree_trainer.h.

◆ setThresholds()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setThresholds ( std::vector< float > & thres )

inline

Specify the thresholds to be used when evaluating features.

Parameters

[in] thres the threshold values

Definition at line 163 of file decision_tree_trainer.h.

◆ setTrainingDataSet()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::setTrainingDataSet ( DataSet & data_set )

inline

Sets the input data set used for training.

Parameters

[in] data_set the data set used for training

Definition at line 123 of file decision_tree_trainer.h.

◆ train()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::train ( pcl::DecisionTree< NodeType > & tree )

Trains a decision tree using the set training data and settings.

Parameters

[out] tree destination for the trained tree

Definition at line 64 of file decision_tree_trainer.hpp.

References pcl::DecisionTree< NodeType >::getRoot(), and pcl::DecisionTree< NodeType >::setRoot().

◆ trainDecisionTreeNode()

template<class FeatureType , class DataSet , class LabelType , class ExampleIndex , class NodeType >

void pcl::DecisionTreeTrainer< FeatureType, DataSet, LabelType, ExampleIndex, NodeType >::trainDecisionTreeNode	(	std::vector< FeatureType > &	features,
		std::vector< ExampleIndex > &	examples,
		std::vector< LabelType > &	label_data,
		std::size_t	max_depth,
		NodeType &	node
	)

protected

Trains a decision tree node from the specified features, label data, and examples.

Parameters

[in]	features	the feature pool used for training
[in]	examples	the examples used for training
[in]	label_data	the label data corresponding to the examples
[in]	max_depth	the maximum depth of the remaining tree
[out]	node	the resulting node

Definition at line 100 of file decision_tree_trainer.hpp.

The documentation for this class was generated from the following files:

pcl/ml/dt/decision_tree_trainer.h
pcl/ml/impl/dt/decision_tree_trainer.hpp

Public Member Functions

Protected Member Functions

Static Protected Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ DecisionTreeTrainer()

◆ ~DecisionTreeTrainer()

Member Function Documentation

◆ createThresholdsUniform()

◆ setDecisionTreeDataProvider()

◆ setExamples()

◆ setFeatureHandler()

◆ setLabelData()

◆ setMaxTreeDepth()

◆ setMinExamplesForSplit()

◆ setNumOfFeatures()

◆ setNumOfThresholds()

◆ setRandomFeaturesAtSplitNode()

◆ setStatsEstimator()

◆ setThresholds()

◆ setTrainingDataSet()

◆ train()

◆ trainDecisionTreeNode()