svm.h

Language, Script, and Encoding Identification with String Kernel Classifiers

#ifndef _LIBSVM_H
#define _LIBSVM_H

#ifdef __cplusplus
extern "C" {
#include "text.h"
#endif

struct svm_node
{
	int index;
	double value;
};

struct svm_problem
{
	int l;
	double *y;
	struct svm_node **x;
};

enum { C_SVC, NU_SVC, ONE_CLASS, EPSILON_SVR, NU_SVR };	/* svm_type */
enum { LINEAR, POLY, RBF, SIGMOID, /* Canasai's addition begin */ STRING /* Canasai's addition end */ };	/* kernel_type */
/* Canasai's addition begin */
enum { ONE_AGAINST_ONE, DAGSVM };	
/* Canasai's addition end */
struct svm_parameter
{
	int svm_type;
	int kernel_type;
	double degree;	/* for poly */
	double gamma;	/* for poly/rbf/sigmoid */
	double coef0;	/* for poly/sigmoid */

	/* these are for training only */
	double cache_size; /* in MB */
	double eps;	/* stopping criteria */
	double C;	/* for C_SVC, EPSILON_SVR and NU_SVR */
	int nr_weight;		/* for C_SVC */
	int *weight_label;	/* for C_SVC */
	double* weight;		/* for C_SVC */
	double nu;	/* for NU_SVC, ONE_CLASS, and NU_SVR */
	double p;	/* for EPSILON_SVR */
	int shrinking;	/* use the shrinking heuristics */
	int probability; /* do probability estimates */

	/* Canasai's addition begin */
	char *tagged_file;
	char *model_file;
	char *label_file;
	char *cv_result_file;
	int mc_method;
	int cross_validation;
	int nr_fold;
	/* Canasai's addition end */
};

struct svm_model *svm_train(const struct svm_problem *prob, const struct svm_parameter *param);
void svm_cross_validation(const struct svm_problem *prob, const struct svm_parameter *param, int nr_fold, double *target);

int svm_save_model(const char *model_file_name, const struct svm_model *model);
struct svm_model *svm_load_model(const char *model_file_name);

int svm_get_svm_type(const struct svm_model *model);
int svm_get_nr_class(const struct svm_model *model);
void svm_get_labels(const struct svm_model *model, int *label);
double svm_get_svr_probability(const struct svm_model *model);

void svm_predict_values(const struct svm_model *model, const struct svm_node *x, double* dec_values);
double svm_predict(const struct svm_model *model, const struct svm_node *x);
double svm_predict_probability(const struct svm_model *model, const struct svm_node *x, double* prob_estimates);

void svm_destroy_model(struct svm_model *model);
void svm_destroy_param(struct svm_parameter *param);

const char *svm_check_parameter(const struct svm_problem *prob, const struct svm_parameter *param);
int svm_check_probability_model(const struct svm_model *model);

// Canasai's addition begin
double brute_force_full_substring( const struct svm_node *px, const struct svm_node *py, int n, double lambda );
double brute_force_substring( const struct svm_node *px, const struct svm_node *py, int n, double lambda );
double suffix_tree_full_substring( const struct svm_node *px, const struct svm_node *py, int n, double lambda );
double suffix_tree_substring( const struct svm_node *px, const struct svm_node *py, int n, double lambda );
double string( const struct svm_node *px, const struct svm_node *py, double degree, double gamma, double coef0 );
void sk_svm_cross_validation( const struct svm_problem *prob, const struct svm_parameter *param, double *target, char **label, int max_classname_length, int *nr_class_ );
double dagsvm_predict( const struct svm_model *model, const struct svm_node *x );
char **load_label( char *label_file, int *max_classname_length );
// Canasai's addition end

#ifdef __cplusplus
}
#endif

#endif /* _LIBSVM_H */