view release on metacpan or  search on metacpan

src/liblinear/linear.cpp  view on Meta::CPAN

#include <math.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdarg.h>
#include <locale.h>
#include "linear.h"
#include "newton.h"
int liblinear_version = LIBLINEAR_VERSION;
typedef signed char schar;
template <class T> static inline void swap(T& x, T& y) { T t=x; x=y; y=t; }
#ifndef min
template <class T> static inline T min(T x,T y) { return (x<y)?x:y; }
#endif
#ifndef max
template <class T> static inline T max(T x,T y) { return (x>y)?x:y; }
#endif
template <class S, class T> static inline void clone(T*& dst, S* src, int n)
{
	dst = new T[n];
	memcpy((void *)dst,(void *)src,sizeof(T)*n);
}
#define INF HUGE_VAL
#define Malloc(type,n) (type *)malloc((n)*sizeof(type))

static void print_string_stdout(const char *s)
{
	fputs(s,stdout);
	fflush(stdout);
}
static void print_null(const char *s) {}

static void (*liblinear_print_string) (const char *) = &print_string_stdout;

#if 1
static void info(const char *fmt,...)
{
	char buf[BUFSIZ];
	va_list ap;
	va_start(ap,fmt);
	vsprintf(buf,fmt,ap);
	va_end(ap);
	(*liblinear_print_string)(buf);
}
#else
static void info(const char *fmt,...) {}
#endif
class sparse_operator
{
public:
	static double nrm2_sq(const feature_node *x)
	{
		double ret = 0;
		while(x->index != -1)
		{
			ret += x->value*x->value;
			x++;
		}
		return ret;
	}

	static double dot(const double *s, const feature_node *x)
	{
		double ret = 0;
		while(x->index != -1)
		{

src/liblinear/linear.cpp  view on Meta::CPAN

double predict_probability(const struct model *model_, const struct feature_node *x, double* prob_estimates)
{
	if(check_probability_model(model_))
	{
		int i;
		int nr_class=model_->nr_class;
		int nr_w;
		if(nr_class==2)
			nr_w = 1;
		else
			nr_w = nr_class;

		double label=predict_values(model_, x, prob_estimates);
		for(i=0;i<nr_w;i++)
			prob_estimates[i]=1/(1+exp(-prob_estimates[i]));

		if(nr_class==2) // for binary classification
			prob_estimates[1]=1.-prob_estimates[0];
		else
		{
			double sum=0;
			for(i=0; i<nr_class; i++)
				sum+=prob_estimates[i];

			for(i=0; i<nr_class; i++)
				prob_estimates[i]=prob_estimates[i]/sum;
		}

		return label;
	}
	else
		return 0;
}

static const char *solver_type_table[]=
{
	"L2R_LR", "L2R_L2LOSS_SVC_DUAL", "L2R_L2LOSS_SVC", "L2R_L1LOSS_SVC_DUAL", "MCSVM_CS",
	"L1R_L2LOSS_SVC", "L1R_LR", "L2R_LR_DUAL",
	"", "", "",
	"L2R_L2LOSS_SVR", "L2R_L2LOSS_SVR_DUAL", "L2R_L1LOSS_SVR_DUAL",
	"", "", "", "", "", "", "",
	"ONECLASS_SVM", NULL
};

int save_model(const char *model_file_name, const struct model *model_)
{
	int i;
	int nr_feature=model_->nr_feature;
	int n;
	const parameter& param = model_->param;

	if(model_->bias>=0)
		n=nr_feature+1;
	else
		n=nr_feature;
	int w_size = n;
	FILE *fp = fopen(model_file_name,"w");
	if(fp==NULL) return -1;

	char *old_locale = setlocale(LC_ALL, NULL);
	if (old_locale)
	{
		old_locale = strdup(old_locale);
	}
	setlocale(LC_ALL, "C");

	int nr_w;
	if(model_->nr_class==2 && model_->param.solver_type != MCSVM_CS)
		nr_w=1;
	else
		nr_w=model_->nr_class;

	fprintf(fp, "solver_type %s\n", solver_type_table[param.solver_type]);
	fprintf(fp, "nr_class %d\n", model_->nr_class);

	if(model_->label)
	{
		fprintf(fp, "label");
		for(i=0; i<model_->nr_class; i++)
			fprintf(fp, " %d", model_->label[i]);
		fprintf(fp, "\n");
	}

	fprintf(fp, "nr_feature %d\n", nr_feature);

	fprintf(fp, "bias %.17g\n", model_->bias);

	if(check_oneclass_model(model_))
		fprintf(fp, "rho %.17g\n", model_->rho);

	fprintf(fp, "w\n");
	for(i=0; i<w_size; i++)
	{
		int j;
		for(j=0; j<nr_w; j++)
			fprintf(fp, "%.17g ", model_->w[i*nr_w+j]);
		fprintf(fp, "\n");
	}

	setlocale(LC_ALL, old_locale);
	free(old_locale);

	if (ferror(fp) != 0 || fclose(fp) != 0) return -1;
	else return 0;
}

//
// FSCANF helps to handle fscanf failures.
// Its do-while block avoids the ambiguity when
// if (...)
//    FSCANF();
// is used
//
#define FSCANF(_stream, _format, _var)do\
{\
	if (fscanf(_stream, _format, _var) != 1)\
	{\
		fprintf(stderr, "ERROR: fscanf failed to read the model\n");\
		EXIT_LOAD_MODEL()\
	}\
}while(0)
// EXIT_LOAD_MODEL should NOT end with a semicolon.
#define EXIT_LOAD_MODEL()\
{\
	setlocale(LC_ALL, old_locale);\
	free(model_->label);\
	free(model_);\
	free(old_locale);\
	return NULL;\
}
struct model *load_model(const char *model_file_name)
{
	FILE *fp = fopen(model_file_name,"r");
	if(fp==NULL) return NULL;

	int i;
	int nr_feature;
	int n;
	int nr_class;
	double bias;
	double rho;
	model *model_ = Malloc(model,1);
	parameter& param = model_->param;
	// parameters for training only won't be assigned, but arrays are assigned as NULL for safety
	param.nr_weight = 0;
	param.weight_label = NULL;
	param.weight = NULL;
	param.init_sol = NULL;

	model_->label = NULL;

	char *old_locale = setlocale(LC_ALL, NULL);
	if (old_locale)
	{
		old_locale = strdup(old_locale);
	}
	setlocale(LC_ALL, "C");

	char cmd[81];
	while(1)
	{
		FSCANF(fp,"%80s",cmd);
		if(strcmp(cmd,"solver_type")==0)
		{
			FSCANF(fp,"%80s",cmd);
			int i;
			for(i=0;solver_type_table[i];i++)
			{
				if(strcmp(solver_type_table[i],cmd)==0)
				{
					param.solver_type=i;
					break;
				}
			}
			if(solver_type_table[i] == NULL)
			{
				fprintf(stderr,"unknown solver type.\n");
				EXIT_LOAD_MODEL()
			}
		}
		else if(strcmp(cmd,"nr_class")==0)
		{
			FSCANF(fp,"%d",&nr_class);
			model_->nr_class=nr_class;
		}
		else if(strcmp(cmd,"nr_feature")==0)
		{
			FSCANF(fp,"%d",&nr_feature);
			model_->nr_feature=nr_feature;
		}
		else if(strcmp(cmd,"bias")==0)
		{
			FSCANF(fp,"%lf",&bias);
			model_->bias=bias;
		}
		else if(strcmp(cmd,"rho")==0)
		{
			FSCANF(fp,"%lf",&rho);
			model_->rho=rho;
		}
		else if(strcmp(cmd,"w")==0)
		{
			break;
		}
		else if(strcmp(cmd,"label")==0)
		{
			int nr_class = model_->nr_class;
			model_->label = Malloc(int,nr_class);
			for(int i=0;i<nr_class;i++)
				FSCANF(fp,"%d",&model_->label[i]);
		}
		else
		{
			fprintf(stderr,"unknown text in model file: [%s]\n",cmd);
			EXIT_LOAD_MODEL()
		}
	}

	nr_feature=model_->nr_feature;
	if(model_->bias>=0)
		n=nr_feature+1;
	else
		n=nr_feature;
	int w_size = n;
	int nr_w;
	if(nr_class==2 && param.solver_type != MCSVM_CS)
		nr_w = 1;
	else
		nr_w = nr_class;

	model_->w=Malloc(double, w_size*nr_w);
	for(i=0; i<w_size; i++)
	{
		int j;
		for(j=0; j<nr_w; j++)
			FSCANF(fp, "%lf ", &model_->w[i*nr_w+j]);
	}

	setlocale(LC_ALL, old_locale);
	free(old_locale);

	if (ferror(fp) != 0 || fclose(fp) != 0) return NULL;

	return model_;
}

int get_nr_feature(const model *model_)
{
	return model_->nr_feature;
}

int get_nr_class(const model *model_)
{
	return model_->nr_class;
}

void get_labels(const model *model_, int* label)
{
	if (model_->label != NULL)
		for(int i=0;i<model_->nr_class;i++)
			label[i] = model_->label[i];
}

// use inline here for better performance (around 20% faster than the non-inline one)
static inline double get_w_value(const struct model *model_, int idx, int label_idx)
{
	int nr_class = model_->nr_class;
	int solver_type = model_->param.solver_type;
	const double *w = model_->w;

	if(idx < 0 || idx > model_->nr_feature)
		return 0;
	if(check_regression_model(model_) || check_oneclass_model(model_))
		return w[idx];
	else
	{
		if(label_idx < 0 || label_idx >= nr_class)
			return 0;
		if(nr_class == 2 && solver_type != MCSVM_CS)
		{
			if(label_idx == 0)
				return w[idx];
			else
				return -w[idx];
		}
		else
			return w[idx*nr_class+label_idx];
	}
}

// feat_idx: starting from 1 to nr_feature
// label_idx: starting from 0 to nr_class-1 for classification models;
//            for regression and one-class SVM models, label_idx is
//            ignored.
double get_decfun_coef(const struct model *model_, int feat_idx, int label_idx)
{
	if(feat_idx > model_->nr_feature)
		return 0;
	return get_w_value(model_, feat_idx-1, label_idx);
}