This class implements a generic decision tree learner. More...

#include <decision_tree.hpp>

Inheritance diagram for mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >:

[legend]

Collaboration diagram for mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >:

[legend]

Public Types
typedef NumericSplitType< FitnessFunction >	NumericSplit
	Allow access to the numeric split type.

typedef CategoricalSplitType< FitnessFunction >	CategoricalSplit
	Allow access to the categorical split type.

typedef DimensionSelectionType	DimensionSelection
	Allow access to the dimension selection type.

Public Member Functions
template<typename MatType , typename LabelsType >
	DecisionTree (MatType data, const data::DatasetInfo &datasetInfo, LabelsType labels, const size_t numClasses, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType())
	Construct the decision tree on the given data and labels, where the data can be both numeric and categorical. More...

template<typename MatType , typename LabelsType >
	DecisionTree (MatType data, LabelsType labels, const size_t numClasses, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType())
	Construct the decision tree on the given data and labels, assuming that the data is all of the numeric type. More...

template<typename MatType , typename LabelsType , typename WeightsType >
	DecisionTree (MatType data, const data::DatasetInfo &datasetInfo, LabelsType labels, const size_t numClasses, WeightsType weights, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType(), const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *=0)
	Construct the decision tree on the given data and labels with weights, where the data can be both numeric and categorical. More...

template<typename MatType , typename LabelsType , typename WeightsType >
	DecisionTree (const DecisionTree &other, MatType data, const data::DatasetInfo &datasetInfo, LabelsType labels, const size_t numClasses, WeightsType weights, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *=0)
	Take ownership of another decision tree and train on the given data and labels with weights, where the data can be both numeric and categorical. More...

template<typename MatType , typename LabelsType , typename WeightsType >
	DecisionTree (MatType data, LabelsType labels, const size_t numClasses, WeightsType weights, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType(), const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *=0)
	Construct the decision tree on the given data and labels with weights, assuming that the data is all of the numeric type. More...

template<typename MatType , typename LabelsType , typename WeightsType >
	DecisionTree (const DecisionTree &other, MatType data, LabelsType labels, const size_t numClasses, WeightsType weights, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType(), const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *=0)
	Take ownership of another decision tree and train on the given data and labels with weights, assuming that the data is all of the numeric type. More...

	DecisionTree (const size_t numClasses=1)
	Construct a decision tree without training it. More...

	DecisionTree (const DecisionTree &other)
	Copy another tree. More...

	DecisionTree (DecisionTree &&other)
	Take ownership of another tree. More...

DecisionTree &	operator= (const DecisionTree &other)
	Copy another tree. More...

DecisionTree &	operator= (DecisionTree &&other)
	Take ownership of another tree. More...

	~DecisionTree ()
	Clean up memory.

template<typename MatType , typename LabelsType >
double	Train (MatType data, const data::DatasetInfo &datasetInfo, LabelsType labels, const size_t numClasses, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType())
	Train the decision tree on the given data. More...

template<typename MatType , typename LabelsType >
double	Train (MatType data, LabelsType labels, const size_t numClasses, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType())
	Train the decision tree on the given data, assuming that all dimensions are numeric. More...

template<typename MatType , typename LabelsType , typename WeightsType >
double	Train (MatType data, const data::DatasetInfo &datasetInfo, LabelsType labels, const size_t numClasses, WeightsType weights, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType(), const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *=0)
	Train the decision tree on the given weighted data. More...

template<typename MatType , typename LabelsType , typename WeightsType >
double	Train (MatType data, LabelsType labels, const size_t numClasses, WeightsType weights, const size_t minimumLeafSize=10, const double minimumGainSplit=1e-7, const size_t maximumDepth=0, DimensionSelectionType dimensionSelector=DimensionSelectionType(), const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *=0)
	Train the decision tree on the given weighted data, assuming that all dimensions are numeric. More...

template<typename VecType >
size_t	Classify (const VecType &point) const
	Classify the given point, using the entire tree. More...

template<typename VecType >
void	Classify (const VecType &point, size_t &prediction, arma::vec &probabilities) const
	Classify the given point and also return estimates of the probability for each class in the given vector. More...

template<typename MatType >
void	Classify (const MatType &data, arma::Row< size_t > &predictions) const
	Classify the given points, using the entire tree. More...

template<typename MatType >
void	Classify (const MatType &data, arma::Row< size_t > &predictions, arma::mat &probabilities) const
	Classify the given points and also return estimates of the probabilities for each class in the given matrix. More...

template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the tree.

size_t	NumChildren () const
	Get the number of children.

const DecisionTree &	Child (const size_t i) const
	Get the child of the given index.

DecisionTree &	Child (const size_t i)
	Modify the child of the given index (be careful!).

size_t	SplitDimension () const
	Get the split dimension (only meaningful if this is a non-leaf in a trained tree). More...

template<typename VecType >
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 would go towards. More...

size_t	NumClasses () const
	Get the number of classes in the tree.

Detailed Description

template<typename FitnessFunction = GiniGain, template< typename > class NumericSplitType = BestBinaryNumericSplit, template< typename > class CategoricalSplitType = AllCategoricalSplit, typename DimensionSelectionType = AllDimensionSelect, bool NoRecursion = false>
class mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >

This class implements a generic decision tree learner.

Its behavior can be controlled via its template arguments.

The class inherits from the auxiliary split information in order to prevent an empty auxiliary split information struct from taking any extra size.

Constructor & Destructor Documentation

◆ DecisionTree() [1/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType >

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree	(	MatType	data,
		const data::DatasetInfo &	datasetInfo,
		LabelsType	labels,
		const size_t	numClasses,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`
	)

Construct the decision tree on the given data and labels, where the data can be both numeric and categorical.

Construct and train without weight.

Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data or labels are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
datasetInfo	Type information for each dimension of the dataset.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

◆ DecisionTree() [2/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType >

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree	(	MatType	data,
		LabelsType	labels,
		const size_t	numClasses,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`
	)

Construct the decision tree on the given data and labels, assuming that the data is all of the numeric type.

Construct and train.

Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data or labels are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

◆ DecisionTree() [3/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType , typename WeightsType >

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree	(	MatType	data,
		const data::DatasetInfo &	datasetInfo,
		LabelsType	labels,
		const size_t	numClasses,
		WeightsType	weights,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`,
		const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *	= `0`
	)

Construct the decision tree on the given data and labels with weights, where the data can be both numeric and categorical.

Construct and train with weights.

Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data, labels or weights are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
datasetInfo	Type information for each dimension of the dataset.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
weights	The weight list of given label.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

◆ DecisionTree() [4/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType , typename WeightsType >

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree	(	const DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > &	other,
		MatType	data,
		const data::DatasetInfo &	datasetInfo,
		LabelsType	labels,
		const size_t	numClasses,
		WeightsType	weights,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *	= `0`
	)

Take ownership of another decision tree and train on the given data and labels with weights, where the data can be both numeric and categorical.

Construct and train with weights.

Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data, labels or weights are no longer needed to avoid copies.

Parameters

other	Tree to take ownership of.
data	Dataset to train on.
datasetInfo	Type information for each dimension of the dataset.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
weights	The weight list of given label.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.

◆ DecisionTree() [5/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType , typename WeightsType >

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree	(	MatType	data,
		LabelsType	labels,
		const size_t	numClasses,
		WeightsType	weights,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`,
		const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *	= `0`
	)

Construct the decision tree on the given data and labels with weights, assuming that the data is all of the numeric type.

Construct and train with weights.

Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data, labels or weights are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
weights	The Weight list of given labels.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

◆ DecisionTree() [6/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType , typename WeightsType >

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree	(	const DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > &	other,
		MatType	data,
		LabelsType	labels,
		const size_t	numClasses,
		WeightsType	weights,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`,
		const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *	= `0`
	)

Take ownership of another decision tree and train on the given data and labels with weights, assuming that the data is all of the numeric type.

Construct and train with weights.

Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data, labels or weights are no longer needed to avoid copies.

Parameters

other	Tree to take ownership of.
data	Dataset to train on.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
weights	The Weight list of given labels.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

◆ DecisionTree() [7/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree ( const size_t numClasses = 1 )

Construct a decision tree without training it.

Construct, don't train.

It will be a leaf node with equal probabilities for each class.

Parameters

numClasses Number of classes in the dataset.

◆ DecisionTree() [8/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree ( const DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > & other )

Copy another tree.

This may use a lot of memory—be sure that it's what you want to do.

Parameters

other Tree to copy.

◆ DecisionTree() [9/9]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::DecisionTree ( DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > && other )

Take ownership of another tree.

Parameters

other Tree to take ownership of.

Member Function Documentation

◆ CalculateDirection()

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename VecType >

size_t mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::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 would go towards.

This method is primarily used by the Classify() function, but it can be used in a standalone sense too.

Parameters

point Point to classify.

◆ Classify() [1/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename VecType >

size_t mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Classify ( const VecType & point ) const

Classify the given point, using the entire tree.

Return the class.

The predicted label is returned.

Parameters

point Point to classify.

◆ Classify() [2/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename VecType >

void mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Classify	(	const VecType &	point,
		size_t &	prediction,
		arma::vec &	probabilities
	)		const

Classify the given point and also return estimates of the probability for each class in the given vector.

Return class probabilities for a given point.

Parameters

point	Point to classify.
prediction	This will be set to the predicted class of the point.
probabilities	This will be filled with class probabilities for the point.

◆ Classify() [3/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType >

void mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Classify	(	const MatType &	data,
		arma::Row< size_t > &	predictions
	)		const

Classify the given points, using the entire tree.

Return the class for a set of points.

The predicted labels for each point are stored in the given vector.

Parameters

data	Set of points to classify.
predictions	This will be filled with predictions for each point.

◆ Classify() [4/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType >

void mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Classify	(	const MatType &	data,
		arma::Row< size_t > &	predictions,
		arma::mat &	probabilities
	)		const

Classify the given points and also return estimates of the probabilities for each class in the given matrix.

Return the class probabilities for a set of points.

The predicted labels for each point are stored in the given vector.

Parameters

data	Set of points to classify.
predictions	This will be filled with predictions for each point.
probabilities	This will be filled with class probabilities for each point.

◆ operator=() [1/2]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > & mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::operator= ( const DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > & other )

Copy another tree.

This may use a lot of memory—be sure that it's what you want to do.

Parameters

other Tree to copy.

◆ operator=() [2/2]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > & mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::operator= ( DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion > && other )

Take ownership of another tree.

Parameters

other Tree to take ownership of.

◆ SplitDimension()

template<typename FitnessFunction = GiniGain, template< typename > class NumericSplitType = BestBinaryNumericSplit, template< typename > class CategoricalSplitType = AllCategoricalSplit, typename DimensionSelectionType = AllDimensionSelect, bool NoRecursion = false>

size_t mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::SplitDimension ( ) const

inline

Get the split dimension (only meaningful if this is a non-leaf in a trained tree).

◆ Train() [1/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType >

double mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Train	(	MatType	data,
		const data::DatasetInfo &	datasetInfo,
		LabelsType	labels,
		const size_t	numClasses,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`
	)

Train the decision tree on the given data.

Train on the given data.

This will overwrite the existing model. The data may have numeric and categorical types, specified by the datasetInfo parameter. Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data or labels are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
datasetInfo	Type information for each dimension.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

Returns: The final entropy of decision tree.

◆ Train() [2/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType >

double mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Train	(	MatType	data,
		LabelsType	labels,
		const size_t	numClasses,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`
	)

Train the decision tree on the given data, assuming that all dimensions are numeric.

Train on the given data, assuming all dimensions are numeric.

This will overwrite the given model. Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data or labels are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

Returns: The final entropy of decision tree.

◆ Train() [3/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType , typename WeightsType >

double mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Train	(	MatType	data,
		const data::DatasetInfo &	datasetInfo,
		LabelsType	labels,
		const size_t	numClasses,
		WeightsType	weights,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`,
		const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *	= `0`
	)

Train the decision tree on the given weighted data.

Train on the given weighted data.

This will overwrite the existing model. The data may have numeric and categorical types, specified by the datasetInfo parameter. Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data, labels or weights are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
datasetInfo	Type information for each dimension.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
weights	Weights of all the labels
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

Returns: The final entropy of decision tree.

◆ Train() [4/4]

template<typename FitnessFunction , template< typename > class NumericSplitType, template< typename > class CategoricalSplitType, typename DimensionSelectionType , bool NoRecursion>

template<typename MatType , typename LabelsType , typename WeightsType >

double mlpack::tree::DecisionTree< FitnessFunction, NumericSplitType, CategoricalSplitType, DimensionSelectionType, NoRecursion >::Train	(	MatType	data,
		LabelsType	labels,
		const size_t	numClasses,
		WeightsType	weights,
		const size_t	minimumLeafSize = `10`,
		const double	minimumGainSplit = `1e-7`,
		const size_t	maximumDepth = `0`,
		DimensionSelectionType	dimensionSelector = `DimensionSelectionType()`,
		const std::enable_if_t< arma::is_arma_type< typename std::remove_reference< WeightsType >::type >::value > *	= `0`
	)

Train the decision tree on the given weighted data, assuming that all dimensions are numeric.

Train on the given weighted data.

This will overwrite the given model. Setting minimumLeafSize and minimumGainSplit too small may cause the tree to overfit, but setting them too large may cause it to underfit.

Use std::move if data, labels or weights are no longer needed to avoid copies.

Parameters

data	Dataset to train on.
labels	Labels for each training point.
numClasses	Number of classes in the dataset.
weights	Weights of all the labels
minimumLeafSize	Minimum number of points in each leaf node.
minimumGainSplit	Minimum gain for the node to split.
maximumDepth	Maximum depth for the tree.
dimensionSelector	Instantiated dimension selection policy.

Returns: The final entropy of decision tree.

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

src/mlpack/methods/decision_tree/decision_tree.hpp
src/mlpack/methods/decision_tree/decision_tree_impl.hpp

Public Types

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ DecisionTree() [1/9]

◆ DecisionTree() [2/9]

◆ DecisionTree() [3/9]

◆ DecisionTree() [4/9]

◆ DecisionTree() [5/9]

◆ DecisionTree() [6/9]

◆ DecisionTree() [7/9]

◆ DecisionTree() [8/9]

◆ DecisionTree() [9/9]

Member Function Documentation

◆ CalculateDirection()

◆ Classify() [1/4]

◆ Classify() [2/4]

◆ Classify() [3/4]

◆ Classify() [4/4]

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ SplitDimension()

◆ Train() [1/4]

◆ Train() [2/4]

◆ Train() [3/4]

◆ Train() [4/4]