This class implements a decision stump. More...

Public Member Functions
	DecisionStump (const MatType &data, const arma::Row< size_t > &labels, const size_t classes, size_t inpBucketSize)
	Constructor. More...

	DecisionStump (const DecisionStump<> &other, const MatType &data, const arma::rowvec &weights, const arma::Row< size_t > &labels)
	Alternate constructor which copies parameters bucketSize and numClass from an already initiated decision stump, other. More...

const arma::Col< size_t >	BinLabels () const
	Access the labels for each split bin. More...

arma::Col< size_t > &	BinLabels ()
	Modify the labels for each split bin (be careful!). More...

void	Classify (const MatType &test, arma::Row< size_t > &predictedLabels)
	Classification function. More...

const arma::vec &	Split () const
	Access the splitting values. More...

arma::vec &	Split ()
	Modify the splitting values (be careful!). More...

int	SplitAttribute () const
	Access the splitting attribute. More...

int &	SplitAttribute ()
	Modify the splitting attribute (be careful!). More...

Private Member Functions
template<typename LabelType , bool isWeight>
double	CalculateEntropy (arma::subview_row< LabelType > labels, int begin, const arma::rowvec &tempD)
	Calculate the entropy of the given attribute. More...

template<typename rType >
rType	CountMostFreq (const arma::Row< rType > &subCols)
	Count the most frequently occurring element in subCols. More...

template<typename rType >
int	IsDistinct (const arma::Row< rType > &featureRow)
	Returns 1 if all the values of featureRow are not same. More...

void	MergeRanges ()
	After the "split" matrix has been set up, merge ranges with identical class labels. More...

template<bool isWeight>
double	SetupSplitAttribute (const arma::rowvec &attribute, const arma::Row< size_t > &labels, const arma::rowvec &weightD)
	Sets up attribute as if it were splitting on it and finds entropy when splitting on attribute. More...

template<bool isWeight>
void	Train (const MatType &data, const arma::Row< size_t > &labels, const arma::rowvec &weightD)
	Train the decision stump on the given data and labels. More...

template<typename rType >
void	TrainOnAtt (const arma::rowvec &attribute, const arma::Row< size_t > &labels)
	After having decided the attribute on which to split, train on that attribute. More...

Private Attributes
arma::Col< size_t >	binLabels
	Stores the labels for each splitting bin. More...

size_t	bucketSize
	Size of bucket while determining splitting criterion. More...

size_t	numClass
	Stores the number of classes. More...

arma::vec	split
	Stores the splitting values after training. More...

int	splitAttribute
	Stores the value of the attribute on which to split. More...

Detailed Description

template<typename MatType = arma::mat>
class mlpack::decision_stump::DecisionStump< MatType >

This class implements a decision stump.

It constructs a single level decision tree, i.e., a decision stump. It uses entropy to decide splitting ranges.

The stump is parameterized by a splitting attribute (the dimension on which points are split), a vector of bin split values, and a vector of labels for each bin. Bin i is specified by the range [split[i], split[i + 1]). The last bin has range up to (split[i + 1] does not exist in that case). Points that are below the first bin will take the label of the first bin.

Template Parameters

MatType Type of matrix that is being used (sparse or dense).

Definition at line 44 of file decision_stump.hpp.

Constructor & Destructor Documentation

template<typename MatType = arma::mat>

mlpack::decision_stump::DecisionStump< MatType >::DecisionStump	(	const MatType &	data,
		const arma::Row< size_t > &	labels,
		const size_t	classes,
		size_t	inpBucketSize
	)

Constructor.

Train on the provided data. Generate a decision stump from data.

Parameters

data	Input, training data.
labels	Labels of training data.
classes	Number of distinct classes in labels.
inpBucketSize	Minimum size of bucket when splitting.

template<typename MatType = arma::mat>

mlpack::decision_stump::DecisionStump< MatType >::DecisionStump	(	const DecisionStump<> &	other,
		const MatType &	data,
		const arma::rowvec &	weights,
		const arma::Row< size_t > &	labels
	)

Alternate constructor which copies parameters bucketSize and numClass from an already initiated decision stump, other.

It appropriately sets the weight vector.

Parameters

other	The other initiated Decision Stump object from which we copy the values.
data	The data on which to train this object on.
D	Weight vector to use while training. For boosting purposes.
labels	The labels of data.
isWeight	Whether we need to run a weighted Decision Stump.

Member Function Documentation

template<typename MatType = arma::mat>

const arma::Col<size_t> mlpack::decision_stump::DecisionStump< MatType >::BinLabels ( ) const

inline

Access the labels for each split bin.

Definition at line 99 of file decision_stump.hpp.

References mlpack::decision_stump::DecisionStump< MatType >::binLabels.

template<typename MatType = arma::mat>

arma::Col<size_t>& mlpack::decision_stump::DecisionStump< MatType >::BinLabels ( )

inline

Modify the labels for each split bin (be careful!).

Definition at line 101 of file decision_stump.hpp.

References mlpack::decision_stump::DecisionStump< MatType >::binLabels.

template<typename MatType = arma::mat>

template<typename LabelType , bool isWeight>

double mlpack::decision_stump::DecisionStump< MatType >::CalculateEntropy	(	arma::subview_row< LabelType >	labels,
		int	begin,
		const arma::rowvec &	tempD
	)

private

Calculate the entropy of the given attribute.

Parameters

attribute	The attribute of which we calculate the entropy.
labels	Corresponding labels of the attribute.
isWeight	Whether we need to run a weighted Decision Stump.

template<typename MatType = arma::mat>

void mlpack::decision_stump::DecisionStump< MatType >::Classify	(	const MatType &	test,
		arma::Row< size_t > &	predictedLabels
	)

Classification function.

After training, classify test, and put the predicted classes in predictedLabels.

Parameters

test	Testing data or data to classify.
predictedLabels	Vector to store the predicted classes after classifying test data.

template<typename MatType = arma::mat>

template<typename rType >

rType mlpack::decision_stump::DecisionStump< MatType >::CountMostFreq ( const arma::Row< rType > & subCols )

private

Count the most frequently occurring element in subCols.

Parameters

subCols The vector in which to find the most frequently occurring element.

template<typename MatType = arma::mat>

template<typename rType >

int mlpack::decision_stump::DecisionStump< MatType >::IsDistinct ( const arma::Row< rType > & featureRow )

private

Returns 1 if all the values of featureRow are not same.

Parameters

featureRow The attribute which is checked for identical values.

template<typename MatType = arma::mat>

void mlpack::decision_stump::DecisionStump< MatType >::MergeRanges ( )

private

After the "split" matrix has been set up, merge ranges with identical class labels.

template<typename MatType = arma::mat>

template<bool isWeight>

double mlpack::decision_stump::DecisionStump< MatType >::SetupSplitAttribute	(	const arma::rowvec &	attribute,
		const arma::Row< size_t > &	labels,
		const arma::rowvec &	weightD
	)

private

Sets up attribute as if it were splitting on it and finds entropy when splitting on attribute.

Parameters

attribute	A row from the training data, which might be a candidate for the splitting attribute.
isWeight	Whether we need to run a weighted Decision Stump.

template<typename MatType = arma::mat>

const arma::vec& mlpack::decision_stump::DecisionStump< MatType >::Split ( ) const

inline

Access the splitting values.

Definition at line 94 of file decision_stump.hpp.

References mlpack::decision_stump::DecisionStump< MatType >::split.

template<typename MatType = arma::mat>

arma::vec& mlpack::decision_stump::DecisionStump< MatType >::Split ( )

inline

Modify the splitting values (be careful!).

Definition at line 96 of file decision_stump.hpp.

References mlpack::decision_stump::DecisionStump< MatType >::split.