The HoeffdingTree object represents all of the necessary information for a Hoeffding-bound-based decision tree. More...

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

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

Public Member Functions
template<typename MatType >
	HoeffdingTree (const MatType &data, const data::DatasetInfo &datasetInfo, const arma::Row< size_t > &labels, const size_t numClasses, const bool batchTraining=true, const double successProbability=0.95, const size_t maxSamples=0, const size_t checkInterval=100, const size_t minSamples=100, const CategoricalSplitType< FitnessFunction > &categoricalSplitIn=CategoricalSplitType< FitnessFunction >(0, 0), const NumericSplitType< FitnessFunction > &numericSplitIn=NumericSplitType< FitnessFunction >(0))
	Construct the Hoeffding tree with the given parameters and given training data. More...

	HoeffdingTree (const data::DatasetInfo &datasetInfo, const size_t numClasses, const double successProbability=0.95, const size_t maxSamples=0, const size_t checkInterval=100, const size_t minSamples=100, const CategoricalSplitType< FitnessFunction > &categoricalSplitIn=CategoricalSplitType< FitnessFunction >(0, 0), const NumericSplitType< FitnessFunction > &numericSplitIn=NumericSplitType< FitnessFunction >(0), std::unordered_map< size_t, std::pair< size_t, size_t >> *dimensionMappings=NULL)
	Construct the Hoeffding tree with the given parameters, but training on no data. More...

	HoeffdingTree (const HoeffdingTree &other)
	Copy another tree (warning: this will duplicate the tree entirely, and may use a lot of memory. More...

	~HoeffdingTree ()
	Clean up memory. 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	CheckInterval () const
	Get the number of samples before a split check is performed. More...

void	CheckInterval (const size_t checkInterval)
	Modify the number of samples before a split check is performed. More...

const HoeffdingTree &	Child (const size_t i) const
	Get a child. More...

HoeffdingTree &	Child (const size_t i)
	Modify a child. More...

template<typename VecType >
size_t	Classify (const VecType &point) const
	Classify the given point, using this node and the entire (sub)tree beneath it. More...

template<typename VecType >
void	Classify (const VecType &point, size_t &prediction, double &probability) const
	Classify the given point and also return an estimate of the probability that the prediction is correct. More...

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

template<typename MatType >
void	Classify (const MatType &data, arma::Row< size_t > &predictions, arma::rowvec &probabilities) const
	Classify the given points, using this node and the entire (sub)tree beneath it. More...

void	CreateChildren ()
	Given that this node should split, create the children. More...

size_t	MajorityClass () const
	Get the majority class. More...

size_t &	MajorityClass ()
	Modify the majority class. More...

double	MajorityProbability () const
	Get the probability of the majority class (based on training samples). More...

double &	MajorityProbability ()
	Modify the probability of the majority class. More...

size_t	MaxSamples () const
	Get the maximum number of samples before a split is forced. More...

void	MaxSamples (const size_t maxSamples)
	Modify the maximum number of samples before a split is forced. More...

size_t	MinSamples () const
	Get the minimum number of samples for a split. More...

void	MinSamples (const size_t minSamples)
	Modify the minimum number of samples for a split. More...

size_t	NumChildren () const
	Get the number of children. More...

template<typename Archive >
void	Serialize (Archive &ar, const unsigned int)
	Serialize the split. More...

size_t	SplitCheck ()
	Check if a split would satisfy the conditions of the Hoeffding bound with the node's specified success probability. More...

size_t	SplitDimension () const
	Get the splitting dimension (size_t(-1) if no split). More...

double	SuccessProbability () const
	Get the confidence required for a split. More...

void	SuccessProbability (const double successProbability)
	Modify the confidence required for a split. More...

template<typename MatType >
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. More...

template<typename VecType >
void	Train (const VecType &point, const size_t label)
	Train on a single point in streaming mode, with the given label. More...

Private Attributes
CategoricalSplitType< FitnessFunction >::SplitInfo	categoricalSplit
	If the split is categorical, this holds the splitting information. More...

std::vector< CategoricalSplitType< FitnessFunction > >	categoricalSplits
	Information for splitting of categorical features (used before split). More...

size_t	checkInterval
	The number of samples that should be seen before checking for a split. More...

std::vector< HoeffdingTree * >	children
	If the split has occurred, these are the children. More...

const data::DatasetInfo *	datasetInfo
	The dataset information. More...

std::unordered_map< size_t, std::pair< size_t, size_t > > *	dimensionMappings
	This structure is owned by this node only if it is the root of the tree. More...

size_t	majorityClass
	The majority class of this node. More...

double	majorityProbability
	The empirical probability of a point this node saw having the majority class. More...

size_t	maxSamples
	The maximum number of samples we can see before splitting. More...

size_t	minSamples
	The minimum number of samples for splitting. More...

size_t	numClasses
	The number of classes this node is trained on. More...

NumericSplitType< FitnessFunction >::SplitInfo	numericSplit
	If the split is numeric, this holds the splitting information. More...

std::vector< NumericSplitType< FitnessFunction > >	numericSplits
	Information for splitting of numeric features (used before split). More...

size_t	numSamples
	The number of samples seen so far by this node. More...

bool	ownsInfo
	Whether or not we own the dataset information. More...

bool	ownsMappings
	Indicates whether or not we own the mappings. More...

size_t	splitDimension
	The dimension that this node has split on. More...

double	successProbability
	The required probability of success for a split to be performed. More...

Detailed Description

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>
class mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >

The HoeffdingTree object represents all of the necessary information for a Hoeffding-bound-based decision tree.

This class is able to train on samples in streaming settings and batch settings, and perform splits based on the Hoeffding bound. The Hoeffding tree (also known as the "very fast decision tree" – VFDT) is described in the following paper:

@inproceedings{domingos2000mining,
    title={{Mining High-Speed Data Streams}},
    author={Domingos, P. and Hulten, G.},
    year={2000},
    booktitle={Proceedings of the Sixth ACM SIGKDD International Conference
        on Knowledge Discovery and Data Mining (KDD '00)},
    pages={71--80}
}

The class is modular, and takes three template parameters. The first, FitnessFunction, is the fitness function that should be used to determine whether a split is beneficial; examples might be GiniImpurity or InformationGain. The NumericSplitType determines how numeric attributes are handled, and the CategoricalSplitType determines how categorical attributes are handled. As far as the actual splitting goes, the meat of the splitting procedure will be contained in those two classes.

Template Parameters

FitnessFunction	Fitness function to use.
NumericSplitType	Technique for splitting numeric features.
CategoricalSplitType	Technique for splitting categorical features.

Definition at line 61 of file hoeffding_tree.hpp.

Member Typedef Documentation

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

typedef CategoricalSplitType<FitnessFunction> mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CategoricalSplit

Allow access to the categorical split type.

Definition at line 67 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

typedef NumericSplitType<FitnessFunction> mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::NumericSplit

Allow access to the numeric split type.

Definition at line 65 of file hoeffding_tree.hpp.

Constructor & Destructor Documentation

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename MatType >

mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::HoeffdingTree	(	const MatType &	data,
		const data::DatasetInfo &	datasetInfo,
		const arma::Row< size_t > &	labels,
		const size_t	numClasses,
		const bool	batchTraining = `true`,
		const double	successProbability = `0.95`,
		const size_t	maxSamples = `0`,
		const size_t	checkInterval = `100`,
		const size_t	minSamples = `100`,
		const CategoricalSplitType< FitnessFunction > &	categoricalSplitIn = `CategoricalSplitType< FitnessFunction >(0, 0)`,
		const NumericSplitType< FitnessFunction > &	numericSplitIn = `NumericSplitType< FitnessFunction >(0)`
	)

Construct the Hoeffding tree with the given parameters and given training data.

The tree may be trained either in batch mode (which looks at all points before splitting, and propagates these points to the created children for further training), or in streaming mode, where each point is only considered once. (In general, batch mode will give better-performing trees, but will have higher memory and runtime costs for the same dataset.)

Parameters

data	Dataset to train on.
datasetInfo	Information on the dataset (types of each feature).
labels	Labels of each point in the dataset.
numClasses	Number of classes in the dataset.
batchTraining	Whether or not to train in batch.
successProbability	Probability of success required in Hoeffding bounds before a split can happen.
maxSamples	Maximum number of samples before a split is forced (0 never forces a split); ignored in batch training mode.
checkInterval	Number of samples required before each split; ignored in batch training mode.
minSamples	If the node has seen this many points or fewer, no split will be allowed.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::HoeffdingTree	(	const data::DatasetInfo &	datasetInfo,
		const size_t	numClasses,
		const double	successProbability = `0.95`,
		const size_t	maxSamples = `0`,
		const size_t	checkInterval = `100`,
		const size_t	minSamples = `100`,
		const CategoricalSplitType< FitnessFunction > &	categoricalSplitIn = `CategoricalSplitType< FitnessFunction >(0, 0)`,
		const NumericSplitType< FitnessFunction > &	numericSplitIn = `NumericSplitType< FitnessFunction >(0)`,
		std::unordered_map< size_t, std::pair< size_t, size_t >> *	dimensionMappings = `NULL`
	)

Construct the Hoeffding tree with the given parameters, but training on no data.

The dimensionMappings parameter is only used if it is desired that this node does not create its own dimensionMappings object (for instance, if this is a child of another node in the tree).

Parameters

dimensionality	Dimensionality of the dataset.
numClasses	Number of classes in the dataset.
datasetInfo	Information on the dataset (types of each feature).
successProbability	Probability of success required in Hoeffding bound before a split can happen.
maxSamples	Maximum number of samples before a split is forced.
checkInterval	Number of samples required before each split check.
minSamples	If the node has seen this many points or fewer, no split will be allowed.
dimensionMappings	Mappings from dimension indices to positions in numeric and categorical split vectors. If left NULL, a new one will be created.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::HoeffdingTree ( const HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType > & other )

Copy another tree (warning: this will duplicate the tree entirely, and may use a lot of memory.

Make sure it's what you want before you do it).

Parameters

other Tree to copy.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::~HoeffdingTree ( )

Clean up memory.

Member Function Documentation

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename VecType >

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::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.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CheckInterval().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CheckInterval ( ) const

inline

Get the number of samples before a split check is performed.

Definition at line 217 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CalculateDirection(), mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::checkInterval, mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Classify(), mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CreateChildren(), and mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Serialize().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CheckInterval ( const size_t checkInterval )

Modify the number of samples before a split check is performed.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

const HoeffdingTree& mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Child ( const size_t i ) const

inline

Get a child.

Definition at line 197 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::children.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

HoeffdingTree& mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Child ( const size_t i )

inline

Modify a child.

Definition at line 199 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::children.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename VecType >

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

Classify the given point, using this node and the entire (sub)tree beneath it.

The predicted label is returned.

Parameters

point Point to classify.

Returns: Predicted label of point.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CheckInterval().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename VecType >

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Classify	(	const VecType &	point,
		size_t &	prediction,
		double &	probability
	)		const

Classify the given point and also return an estimate of the probability that the prediction is correct.

(This estimate is simply the probability that a training point was from the majority class in the leaf that this point binned to.)

Parameters

point	Point to classify.
prediction	Predicted label of point.
probability	An estimate of the probability that the prediction is correct.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename MatType >

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

Classify the given points, using this node and the entire (sub)tree beneath it.

The predicted labels for each point are returned.

Parameters

data	Points to classify.
predictions	Predicted labels for each point.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename MatType >

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Classify	(	const MatType &	data,
		arma::Row< size_t > &	predictions,
		arma::rowvec &	probabilities
	)		const

Classify the given points, using this node and the entire (sub)tree beneath it.

The predicted labels for each point are returned, as well as an estimate of the probability that the prediction is correct for each point. This estimate is simply the MajorityProbability() for the leaf that each point bins to.

Parameters

data	Points to classify.
predictions	Predicted labels for each point.
probabilities	Probability estimates for each predicted label.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CreateChildren ( )

Given that this node should split, create the children.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CheckInterval().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MajorityClass ( ) const

inline

Get the majority class.

Definition at line 184 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::majorityClass.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t& mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MajorityClass ( )

inline

Modify the majority class.

Definition at line 186 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::majorityClass.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

double mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MajorityProbability ( ) const

inline

Get the probability of the majority class (based on training samples).

Definition at line 189 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::majorityProbability.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

double& mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MajorityProbability ( )

inline

Modify the probability of the majority class.

Definition at line 191 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::majorityProbability.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MaxSamples ( ) const

inline

Get the maximum number of samples before a split is forced.

Definition at line 212 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::maxSamples.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MaxSamples ( const size_t maxSamples )

Modify the maximum number of samples before a split is forced.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MinSamples ( ) const

inline

Get the minimum number of samples for a split.

Definition at line 207 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::minSamples.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MinSamples ( const size_t minSamples )

Modify the minimum number of samples for a split.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::NumChildren ( ) const

inline

Get the number of children.

Definition at line 194 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::children.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename Archive >

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Serialize	(	Archive &	ar,
		const unsigned	int
	)

Serialize the split.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CheckInterval().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::SplitCheck ( )

Check if a split would satisfy the conditions of the Hoeffding bound with the node's specified success probability.

If so, the number of children that would be created is returned. If not, 0 is returned.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::SplitDimension ( ) const

inline

Get the splitting dimension (size_t(-1) if no split).

Definition at line 181 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::splitDimension.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

double mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::SuccessProbability ( ) const

inline

Get the confidence required for a split.

Definition at line 202 of file hoeffding_tree.hpp.

References mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::successProbability.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::SuccessProbability ( const double successProbability )

Modify the confidence required for a split.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename MatType >

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::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.

Parameters

data	Data points to train on.
label	Labels of data points.
batchTraining	If true, perform training in batch.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

template<typename VecType >

void mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Train	(	const VecType &	point,
		const size_t	label
	)

Train on a single point in streaming mode, with the given label.

Parameters

point	Point to train on.
label	Label of point to train on.

Member Data Documentation

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

CategoricalSplitType<FitnessFunction>::SplitInfo mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::categoricalSplit

private

If the split is categorical, this holds the splitting information.

Definition at line 331 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

std::vector<CategoricalSplitType<FitnessFunction> > mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::categoricalSplits

private

Information for splitting of categorical features (used before split).

Definition at line 297 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::checkInterval

private

The number of samples that should be seen before checking for a split.

Definition at line 311 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::CheckInterval().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

std::vector<HoeffdingTree*> mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::children

private

If the split has occurred, these are the children.

Definition at line 335 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::Child(), and mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::NumChildren().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

const data::DatasetInfo* mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::datasetInfo

private

The dataset information.

Definition at line 315 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

std::unordered_map<size_t, std::pair<size_t, size_t> >* mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::dimensionMappings

private

This structure is owned by this node only if it is the root of the tree.

Definition at line 300 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::majorityClass

private

The majority class of this node.

Definition at line 326 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MajorityClass().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

double mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::majorityProbability

private

The empirical probability of a point this node saw having the majority class.

Definition at line 329 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MajorityProbability().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::maxSamples

private

The maximum number of samples we can see before splitting.

Definition at line 309 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MaxSamples().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::minSamples

private

The minimum number of samples for splitting.

Definition at line 313 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::MinSamples().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::numClasses

private

The number of classes this node is trained on.

Definition at line 307 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

NumericSplitType<FitnessFunction>::SplitInfo mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::numericSplit

private

If the split is numeric, this holds the splitting information.

Definition at line 333 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

std::vector<NumericSplitType<FitnessFunction> > mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::numericSplits

private

Information for splitting of numeric features (used before split).

Definition at line 295 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::numSamples

private

The number of samples seen so far by this node.

Definition at line 305 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

bool mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::ownsInfo

private

Whether or not we own the dataset information.

Definition at line 317 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

bool mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::ownsMappings

private

Indicates whether or not we own the mappings.

Definition at line 302 of file hoeffding_tree.hpp.

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

size_t mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::splitDimension

private

The dimension that this node has split on.

Definition at line 324 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::SplitDimension().

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>

double mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::successProbability

private

The required probability of success for a split to be performed.

Definition at line 319 of file hoeffding_tree.hpp.

Referenced by mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >::SuccessProbability().

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

src/mlpack/methods/hoeffding_trees/hoeffding_tree.hpp

Public Types

Public Member Functions

Private Attributes

Detailed Description

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit> class mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation

template<typename FitnessFunction = GiniImpurity, template< typename > class NumericSplitType = HoeffdingDoubleNumericSplit, template< typename > class CategoricalSplitType = HoeffdingCategoricalSplit>
class mlpack::tree::HoeffdingTree< FitnessFunction, NumericSplitType, CategoricalSplitType >