meta::classify::svm_wrapper Class Reference

Wrapper class for liblinear (http://www.csie.ntu.edu.tw/~cjlin/liblinear/) and libsvm (http://www.csie.ntu.edu.tw/~cjlin/libsvm/) implementation of support vector machine classification. More...

#include <svm_wrapper.h>

Inheritance diagram for meta::classify::svm_wrapper:

Public Types
enum	kernel {   None, Quadratic, Cubic, Quartic,   RBF, Sigmoid }
	Selects which kernel to use. More...

Public Member Functions
	svm_wrapper (std::shared_ptr< index::forward_index > idx, const std::string &svm_path, kernel kernel_opt=kernel::None)
	Constructor. More...
class_label	classify (doc_id d_id) override
	Classifies a document into a specific group, as determined by training data. More...
void	train (const std::vector< doc_id > &docs) override
	Creates a classification model based on training documents. More...
confusion_matrix	test (const std::vector< doc_id > &docs) override
	Classifies a collection document into specific groups, as determined by training data; this function will make repeated calls to classify(). More...
void	reset () override
	Clears any learned data from this classifier.
Public Member Functions inherited from meta::classify::classifier
	classifier (std::shared_ptr< index::forward_index > idx)
virtual confusion_matrix	cross_validate (const std::vector< doc_id > &input_docs, size_t k, bool even_split=false, int seed=1)
	Performs k-fold cross-validation on a set of documents. More...

Static Public Attributes
static const std::string	id = "libsvm"
	The identifier for this classifier.

Private Attributes
const std::string	svm_path_
	the path to the liblinear/libsvm library
kernel	kernel_
	which kernel function to use for this SVM
std::string	executable_
	used to select which executable to use (libsvm or liblinear)

Static Private Attributes
static const std::unordered_map< kernel, std::string, std::hash< int > >	options_
	keeps track of which arguments are necessary for which kernel function

Additional Inherited Members
Protected Attributes inherited from meta::classify::classifier
std::shared_ptr< index::forward_index >	idx_
	the index that the classifer is run on

Detailed Description

Wrapper class for liblinear (http://www.csie.ntu.edu.tw/~cjlin/liblinear/) and libsvm (http://www.csie.ntu.edu.tw/~cjlin/libsvm/) implementation of support vector machine classification.

To use this class, make sure that you have checked out the libsvm-modules submodule and have compiled both libsvm and liblinear.

If no kernel is selected, liblinear is used. Otherwise, libsvm is used.

Member Enumeration Documentation

enum meta::classify::svm_wrapper::kernel

Selects which kernel to use.

"None" uses liblinear. Any other kernel uses libsvm.

Constructor & Destructor Documentation

meta::classify::svm_wrapper::svm_wrapper	(	std::shared_ptr< index::forward_index >	idx,
		const std::string &	svm_path,
		kernel	kernel_opt = kernel::None
	)

Constructor.

Parameters

idx	The index to run the classifier on
svm_path	The path to the liblinear/libsvm library
kernel_opt	Which kind of kernel you want to use (default: None)

Member Function Documentation

class_label meta::classify::svm_wrapper::classify ( doc_id  d_id )

overridevirtual

Classifies a document into a specific group, as determined by training data.

Parameters

doc	The document to classify

Returns

the class it belongs to

Implements meta::classify::classifier.

void meta::classify::svm_wrapper::train ( const std::vector< doc_id > &  docs )

overridevirtual

Creates a classification model based on training documents.

Parameters

docs	The training documents

Implements meta::classify::classifier.

confusion_matrix meta::classify::svm_wrapper::test ( const std::vector< doc_id > &  docs )

overridevirtual

Classifies a collection document into specific groups, as determined by training data; this function will make repeated calls to classify().

Parameters

docs	The documents to classify

Returns

a confusion_matrix detailing the performance of the classifier

Reimplemented from meta::classify::classifier.

---

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

• /home/chase/projects/meta/include/classify/classifier/svm_wrapper.h
• /home/chase/projects/meta/src/classify/classifier/svm_wrapper.cpp