Fn_forest_ecoc

Functions
imat	ecocpak::permvec (const ivec &A)
	Creates permutation vectors of input binary vector.
void	ecocpak::append_tree (const vector< ClassData > &classes_vector, const ivec &root, const int criterion_option, const int classifiers_type, imat &M, vector< Classifier * > &classifiers_vector)
	Appends tree structure to coding matrix M.
u32	ecocpak::forest_ecoc (const mat &training_samples, const icolvec &training_labels, const mat &testing_samples, const icolvec &testing_labels, const int decoding_strategy, const int classifiers_type, const int criterion_option, const u32 n_forests, const bool verbose, ofstream &verbose_output, double &elapsed_time)
	Forest ECOC training and testing procedure.
void	append_tree (const vector< ClassData > &classes_vector, const ivec &root, const int criterion_option, const int classifiers_type, imat &M, vector< Classifier * > &classifiers_vector)
	Appends tree structure to coding matrix M.

---

Function Documentation

void ecocpak::append_tree	(	const vector< ClassData > &	classes_vector,
		const ivec &	root,
		const int	criterion_option,
		const int	classifiers_type,
		imat &	M,
		vector< Classifier * > &	classifiers_vector
	)

Appends tree structure to coding matrix M.

• Input Arguments:
  • classes_vector : Vector of ClassData objects.
  • root : Vector with 1s and -1s that corresponds to the first column of tree's coding matrix.
  • criterion_option : Criterion option.
  • classifiers_type : Type of classifier in use.

• Output Arguments:
  • M : New coding matrix.
  • classifiers_vector : New vector of classifiers.

• Return Argument:
  • Void.

void append_tree	(	const vector< ClassData > &	classes_vector,
		const ivec &	root,
		const int	criterion_option,
		const int	classifiers_type,
		imat &	M,
		vector< Classifier * > &	classifiers_vector
	)

Appends tree structure to coding matrix M.

• Input Arguments:
  • classes_vector : Vector of ClassData objects.
  • root : Vector with 1s and -1s that corresponds to the first column of tree's coding matrix.
  • criterion_option : Criterion option.
  • classifiers_type : Type of classifier in use.

• Output Arguments:
  • M : New coding matrix.
  • classifiers_vector : New vector of classifiers.

• Return Argument:
  • Void.

u32 ecocpak::forest_ecoc	(	const mat &	training_samples,
		const icolvec &	training_labels,
		const mat &	testing_samples,
		const icolvec &	testing_labels,
		const int	decoding_strategy,
		const int	classifiers_type,
		const int	criterion_option,
		const u32	n_forests,
		const bool	verbose,
		ofstream &	verbose_output,
		double &	elapsed_time
	)

Forest ECOC training and testing procedure.

• Input Arguments:
  • training_samples : A 2D input matrix where its rows represent the training sample vectors.
  • training_labels : The respective class labels of the training_samples input matrix.
  • testing_samples : A 2D input matrix where its rows represent the testing sample vectors.
  • testing_labels : The respective class labels of the testing_samples input matrix.
  • decoding_strategy : User's option specifying the type of decoding strategy that will be used.
  • classifiers_type : Type of classifier.
  • criterion_option : Criterion option (FQMI, FLDR or Custom).
  • n_matrices : Number of maximum created forests

• Output Arguments:
  • coding_matrix : Coding matrix.
  • classifiers_vector : Vector of classifiers objects.
  • execution_time : Execution time.

• Return Argument:
  • Number of misclassified test samples.

imat ecocpak::permvec

(

const ivec &

A

)

Creates permutation vectors of input binary vector.

• Input Arguments:
  • A : Binary vector of 1s and -1s.

• Output Arguments:
  • Void.

• Return Argument:
  • A matrix with all the valid permutations of A.