liblinear-ruby 1.0.1 → 1.0.2

data/liblinear-2.1/train.c

@@ -1,449 +0,0 @@
-#include <stdio.h>
-#include <math.h>
-#include <stdlib.h>
-#include <string.h>
-#include <ctype.h>
-#include <errno.h>
-#include "linear.h"
-#define Malloc(type,n) (type *)malloc((n)*sizeof(type))
-#define INF HUGE_VAL
-
-void print_null(const char *s) {}
-
-void exit_with_help()
-{
-	printf(
-	"Usage: train [options] training_set_file [model_file]\n"
-	"options:\n"
-	"-s type : set type of solver (default 1)\n"
-	"  for multi-class classification\n"
-	"	 0 -- L2-regularized logistic regression (primal)\n"
-	"	 1 -- L2-regularized L2-loss support vector classification (dual)\n"
-	"	 2 -- L2-regularized L2-loss support vector classification (primal)\n"
-	"	 3 -- L2-regularized L1-loss support vector classification (dual)\n"
-	"	 4 -- support vector classification by Crammer and Singer\n"
-	"	 5 -- L1-regularized L2-loss support vector classification\n"
-	"	 6 -- L1-regularized logistic regression\n"
-	"	 7 -- L2-regularized logistic regression (dual)\n"
-	"  for regression\n"
-	"	11 -- L2-regularized L2-loss support vector regression (primal)\n"
-	"	12 -- L2-regularized L2-loss support vector regression (dual)\n"
-	"	13 -- L2-regularized L1-loss support vector regression (dual)\n"
-	"-c cost : set the parameter C (default 1)\n"
-	"-p epsilon : set the epsilon in loss function of SVR (default 0.1)\n"
-	"-e epsilon : set tolerance of termination criterion\n"
-	"	-s 0 and 2\n"
-	"		|f'(w)|_2 <= eps*min(pos,neg)/l*|f'(w0)|_2,\n"
-	"		where f is the primal function and pos/neg are # of\n"
-	"		positive/negative data (default 0.01)\n"
-	"	-s 11\n"
-	"		|f'(w)|_2 <= eps*|f'(w0)|_2 (default 0.001)\n"
-	"	-s 1, 3, 4, and 7\n"
-	"		Dual maximal violation <= eps; similar to libsvm (default 0.1)\n"
-	"	-s 5 and 6\n"
-	"		|f'(w)|_1 <= eps*min(pos,neg)/l*|f'(w0)|_1,\n"
-	"		where f is the primal function (default 0.01)\n"
-	"	-s 12 and 13\n"
-	"		|f'(alpha)|_1 <= eps |f'(alpha0)|,\n"
-	"		where f is the dual function (default 0.1)\n"
-	"-B bias : if bias >= 0, instance x becomes [x; bias]; if < 0, no bias term added (default -1)\n"
-	"-wi weight: weights adjust the parameter C of different classes (see README for details)\n"
-	"-v n: n-fold cross validation mode\n"
-	"-C : find parameter C (only for -s 0 and 2)\n"
-	"-q : quiet mode (no outputs)\n"
-	);
-	exit(1);
-}
-
-void exit_input_error(int line_num)
-{
-	fprintf(stderr,"Wrong input format at line %d\n", line_num);
-	exit(1);
-}
-
-static char *line = NULL;
-static int max_line_len;
-
-static char* readline(FILE *input)
-{
-	int len;
-
-	if(fgets(line,max_line_len,input) == NULL)
-		return NULL;
-
-	while(strrchr(line,'\n') == NULL)
-	{
-		max_line_len *= 2;
-		line = (char *) realloc(line,max_line_len);
-		len = (int) strlen(line);
-		if(fgets(line+len,max_line_len-len,input) == NULL)
-			break;
-	}
-	return line;
-}
-
-void parse_command_line(int argc, char **argv, char *input_file_name, char *model_file_name);
-void read_problem(const char *filename);
-void do_cross_validation();
-void do_find_parameter_C();
-
-struct feature_node *x_space;
-struct parameter param;
-struct problem prob;
-struct model* model_;
-int flag_cross_validation;
-int flag_find_C;
-int flag_C_specified;
-int flag_solver_specified;
-int nr_fold;
-double bias;
-
-int main(int argc, char **argv)
-{
-	char input_file_name[1024];
-	char model_file_name[1024];
-	const char *error_msg;
-
-	parse_command_line(argc, argv, input_file_name, model_file_name);
-	read_problem(input_file_name);
-	error_msg = check_parameter(&prob,&param);
-
-	if(error_msg)
-	{
-		fprintf(stderr,"ERROR: %s\n",error_msg);
-		exit(1);
-	}
-
-	if (flag_find_C)
-	{
-		do_find_parameter_C();
-	}
-	else if(flag_cross_validation)
-	{
-		do_cross_validation();
-	}
-	else
-	{
-		model_=train(&prob, &param);
-		if(save_model(model_file_name, model_))
-		{
-			fprintf(stderr,"can't save model to file %s\n",model_file_name);
-			exit(1);
-		}
-		free_and_destroy_model(&model_);
-	}
-	destroy_param(&param);
-	free(prob.y);
-	free(prob.x);
-	free(x_space);
-	free(line);
-
-	return 0;
-}
-
-void do_find_parameter_C()
-{
-	double start_C, best_C, best_rate;
-	double max_C = 1024;
-	if (flag_C_specified)
-		start_C = param.C;
-	else
-		start_C = -1.0;
-	printf("Doing parameter search with %d-fold cross validation.\n", nr_fold);
-	find_parameter_C(&prob, &param, nr_fold, start_C, max_C, &best_C, &best_rate);
-	printf("Best C = %g  CV accuracy = %g%%\n", best_C, 100.0*best_rate);
-}
-
-void do_cross_validation()
-{
-	int i;
-	int total_correct = 0;
-	double total_error = 0;
-	double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
-	double *target = Malloc(double, prob.l);
-
-	cross_validation(&prob,&param,nr_fold,target);
-	if(param.solver_type == L2R_L2LOSS_SVR ||
-	   param.solver_type == L2R_L1LOSS_SVR_DUAL ||
-	   param.solver_type == L2R_L2LOSS_SVR_DUAL)
-	{
-		for(i=0;i<prob.l;i++)
-		{
-			double y = prob.y[i];
-			double v = target[i];
-			total_error += (v-y)*(v-y);
-			sumv += v;
-			sumy += y;
-			sumvv += v*v;
-			sumyy += y*y;
-			sumvy += v*y;
-		}
-		printf("Cross Validation Mean squared error = %g\n",total_error/prob.l);
-		printf("Cross Validation Squared correlation coefficient = %g\n",
-				((prob.l*sumvy-sumv*sumy)*(prob.l*sumvy-sumv*sumy))/
-				((prob.l*sumvv-sumv*sumv)*(prob.l*sumyy-sumy*sumy))
-			  );
-	}
-	else
-	{
-		for(i=0;i<prob.l;i++)
-			if(target[i] == prob.y[i])
-				++total_correct;
-		printf("Cross Validation Accuracy = %g%%\n",100.0*total_correct/prob.l);
-	}
-
-	free(target);
-}
-
-void parse_command_line(int argc, char **argv, char *input_file_name, char *model_file_name)
-{
-	int i;
-	void (*print_func)(const char*) = NULL;	// default printing to stdout
-
-	// default values
-	param.solver_type = L2R_L2LOSS_SVC_DUAL;
-	param.C = 1;
-	param.eps = INF; // see setting below
-	param.p = 0.1;
-	param.nr_weight = 0;
-	param.weight_label = NULL;
-	param.weight = NULL;
-	param.init_sol = NULL;
-	flag_cross_validation = 0;
-	flag_C_specified = 0;
-	flag_solver_specified = 0;
-	flag_find_C = 0;
-	bias = -1;
-
-	// parse options
-	for(i=1;i<argc;i++)
-	{
-		if(argv[i][0] != '-') break;
-		if(++i>=argc)
-			exit_with_help();
-		switch(argv[i-1][1])
-		{
-			case 's':
-				param.solver_type = atoi(argv[i]);
-				flag_solver_specified = 1;
-				break;
-
-			case 'c':
-				param.C = atof(argv[i]);
-				flag_C_specified = 1;
-				break;
-
-			case 'p':
-				param.p = atof(argv[i]);
-				break;
-
-			case 'e':
-				param.eps = atof(argv[i]);
-				break;
-
-			case 'B':
-				bias = atof(argv[i]);
-				break;
-
-			case 'w':
-				++param.nr_weight;
-				param.weight_label = (int *) realloc(param.weight_label,sizeof(int)*param.nr_weight);
-				param.weight = (double *) realloc(param.weight,sizeof(double)*param.nr_weight);
-				param.weight_label[param.nr_weight-1] = atoi(&argv[i-1][2]);
-				param.weight[param.nr_weight-1] = atof(argv[i]);
-				break;
-
-			case 'v':
-				flag_cross_validation = 1;
-				nr_fold = atoi(argv[i]);
-				if(nr_fold < 2)
-				{
-					fprintf(stderr,"n-fold cross validation: n must >= 2\n");
-					exit_with_help();
-				}
-				break;
-
-			case 'q':
-				print_func = &print_null;
-				i--;
-				break;
-
-			case 'C':
-				flag_find_C = 1;
-				i--;
-				break;
-
-			default:
-				fprintf(stderr,"unknown option: -%c\n", argv[i-1][1]);
-				exit_with_help();
-				break;
-		}
-	}
-
-	set_print_string_function(print_func);
-
-	// determine filenames
-	if(i>=argc)
-		exit_with_help();
-
-	strcpy(input_file_name, argv[i]);
-
-	if(i<argc-1)
-		strcpy(model_file_name,argv[i+1]);
-	else
-	{
-		char *p = strrchr(argv[i],'/');
-		if(p==NULL)
-			p = argv[i];
-		else
-			++p;
-		sprintf(model_file_name,"%s.model",p);
-	}
-
-	// default solver for parameter selection is L2R_L2LOSS_SVC
-	if(flag_find_C)
-	{
-		if(!flag_cross_validation)
-			nr_fold = 5;
-		if(!flag_solver_specified)
-		{
-			fprintf(stderr, "Solver not specified. Using -s 2\n");
-			param.solver_type = L2R_L2LOSS_SVC;
-		}
-		else if(param.solver_type != L2R_LR && param.solver_type != L2R_L2LOSS_SVC)
-		{
-			fprintf(stderr, "Warm-start parameter search only available for -s 0 and -s 2\n");
-			exit_with_help();
-		}
-	}
-
-	if(param.eps == INF)
-	{
-		switch(param.solver_type)
-		{
-			case L2R_LR:
-			case L2R_L2LOSS_SVC:
-				param.eps = 0.01;
-				break;
-			case L2R_L2LOSS_SVR:
-				param.eps = 0.001;
-				break;
-			case L2R_L2LOSS_SVC_DUAL:
-			case L2R_L1LOSS_SVC_DUAL:
-			case MCSVM_CS:
-			case L2R_LR_DUAL:
-				param.eps = 0.1;
-				break;
-			case L1R_L2LOSS_SVC:
-			case L1R_LR:
-				param.eps = 0.01;
-				break;
-			case L2R_L1LOSS_SVR_DUAL:
-			case L2R_L2LOSS_SVR_DUAL:
-				param.eps = 0.1;
-				break;
-		}
-	}
-}
-
-// read in a problem (in libsvm format)
-void read_problem(const char *filename)
-{
-	int max_index, inst_max_index, i;
-	size_t elements, j;
-	FILE *fp = fopen(filename,"r");
-	char *endptr;
-	char *idx, *val, *label;
-
-	if(fp == NULL)
-	{
-		fprintf(stderr,"can't open input file %s\n",filename);
-		exit(1);
-	}
-
-	prob.l = 0;
-	elements = 0;
-	max_line_len = 1024;
-	line = Malloc(char,max_line_len);
-	while(readline(fp)!=NULL)
-	{
-		char *p = strtok(line," \t"); // label
-
-		// features
-		while(1)
-		{
-			p = strtok(NULL," \t");
-			if(p == NULL || *p == '\n') // check '\n' as ' ' may be after the last feature
-				break;
-			elements++;
-		}
-		elements++; // for bias term
-		prob.l++;
-	}
-	rewind(fp);
-
-	prob.bias=bias;
-
-	prob.y = Malloc(double,prob.l);
-	prob.x = Malloc(struct feature_node *,prob.l);
-	x_space = Malloc(struct feature_node,elements+prob.l);
-
-	max_index = 0;
-	j=0;
-	for(i=0;i<prob.l;i++)
-	{
-		inst_max_index = 0; // strtol gives 0 if wrong format
-		readline(fp);
-		prob.x[i] = &x_space[j];
-		label = strtok(line," \t\n");
-		if(label == NULL) // empty line
-			exit_input_error(i+1);
-
-		prob.y[i] = strtod(label,&endptr);
-		if(endptr == label || *endptr != '\0')
-			exit_input_error(i+1);
-
-		while(1)
-		{
-			idx = strtok(NULL,":");
-			val = strtok(NULL," \t");
-
-			if(val == NULL)
-				break;
-
-			errno = 0;
-			x_space[j].index = (int) strtol(idx,&endptr,10);
-			if(endptr == idx || errno != 0 || *endptr != '\0' || x_space[j].index <= inst_max_index)
-				exit_input_error(i+1);
-			else
-				inst_max_index = x_space[j].index;
-
-			errno = 0;
-			x_space[j].value = strtod(val,&endptr);
-			if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
-				exit_input_error(i+1);
-
-			++j;
-		}
-
-		if(inst_max_index > max_index)
-			max_index = inst_max_index;
-
-		if(prob.bias >= 0)
-			x_space[j++].value = prob.bias;
-
-		x_space[j++].index = -1;
-	}
-
-	if(prob.bias >= 0)
-	{
-		prob.n=max_index+1;
-		for(i=1;i<prob.l;i++)
-			(prob.x[i]-2)->index = prob.n;
-		x_space[j-2].index = prob.n;
-	}
-	else
-		prob.n=max_index;
-
-	fclose(fp);
-}

data/liblinear-2.1/tron.cpp

@@ -1,241 +0,0 @@
-#include <math.h>
-#include <stdio.h>
-#include <string.h>
-#include <stdarg.h>
-#include "tron.h"
-
-#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
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-extern double dnrm2_(int *, double *, int *);
-extern double ddot_(int *, double *, int *, double *, int *);
-extern int daxpy_(int *, double *, double *, int *, double *, int *);
-extern int dscal_(int *, double *, double *, int *);
-
-#ifdef __cplusplus
-}
-#endif
-
-static void default_print(const char *buf)
-{
-	fputs(buf,stdout);
-	fflush(stdout);
-}
-
-void TRON::info(const char *fmt,...)
-{
-	char buf[BUFSIZ];
-	va_list ap;
-	va_start(ap,fmt);
-	vsprintf(buf,fmt,ap);
-	va_end(ap);
-	(*tron_print_string)(buf);
-}
-
-TRON::TRON(const function *fun_obj, double eps, double eps_cg, int max_iter)
-{
-	this->fun_obj=const_cast<function *>(fun_obj);
-	this->eps=eps;
-	this->eps_cg=eps_cg;
-	this->max_iter=max_iter;
-	tron_print_string = default_print;
-}
-
-TRON::~TRON()
-{
-}
-
-void TRON::tron(double *w)
-{
-	// Parameters for updating the iterates.
-	double eta0 = 1e-4, eta1 = 0.25, eta2 = 0.75;
-
-	// Parameters for updating the trust region size delta.
-	double sigma1 = 0.25, sigma2 = 0.5, sigma3 = 4;
-
-	int n = fun_obj->get_nr_variable();
-	int i, cg_iter;
-	double delta, snorm, one=1.0;
-	double alpha, f, fnew, prered, actred, gs;
-	int search = 1, iter = 1, inc = 1;
-	double *s = new double[n];
-	double *r = new double[n];
-	double *g = new double[n];
-
-	// calculate gradient norm at w=0 for stopping condition.
-	double *w0 = new double[n];
-	for (i=0; i<n; i++)
-		w0[i] = 0;
-	fun_obj->fun(w0);
-	fun_obj->grad(w0, g);
-	double gnorm0 = dnrm2_(&n, g, &inc);
-	delete [] w0;
-
-	f = fun_obj->fun(w);
-	fun_obj->grad(w, g);
-	delta = dnrm2_(&n, g, &inc);
-	double gnorm = delta;
-
-	if (gnorm <= eps*gnorm0)
-		search = 0;
-
-	iter = 1;
-
-	double *w_new = new double[n];
-	while (iter <= max_iter && search)
-	{
-		cg_iter = trcg(delta, g, s, r);
-
-		memcpy(w_new, w, sizeof(double)*n);
-		daxpy_(&n, &one, s, &inc, w_new, &inc);
-
-		gs = ddot_(&n, g, &inc, s, &inc);
-		prered = -0.5*(gs-ddot_(&n, s, &inc, r, &inc));
-		fnew = fun_obj->fun(w_new);
-
-		// Compute the actual reduction.
-		actred = f - fnew;
-
-		// On the first iteration, adjust the initial step bound.
-		snorm = dnrm2_(&n, s, &inc);
-		if (iter == 1)
-			delta = min(delta, snorm);
-
-		// Compute prediction alpha*snorm of the step.
-		if (fnew - f - gs <= 0)
-			alpha = sigma3;
-		else
-			alpha = max(sigma1, -0.5*(gs/(fnew - f - gs)));
-
-		// Update the trust region bound according to the ratio of actual to predicted reduction.
-		if (actred < eta0*prered)
-			delta = min(max(alpha, sigma1)*snorm, sigma2*delta);
-		else if (actred < eta1*prered)
-			delta = max(sigma1*delta, min(alpha*snorm, sigma2*delta));
-		else if (actred < eta2*prered)
-			delta = max(sigma1*delta, min(alpha*snorm, sigma3*delta));
-		else
-			delta = max(delta, min(alpha*snorm, sigma3*delta));
-
-		info("iter %2d act %5.3e pre %5.3e delta %5.3e f %5.3e |g| %5.3e CG %3d\n", iter, actred, prered, delta, f, gnorm, cg_iter);
-
-		if (actred > eta0*prered)
-		{
-			iter++;
-			memcpy(w, w_new, sizeof(double)*n);
-			f = fnew;
-			fun_obj->grad(w, g);
-
-			gnorm = dnrm2_(&n, g, &inc);
-			if (gnorm <= eps*gnorm0)
-				break;
-		}
-		if (f < -1.0e+32)
-		{
-			info("WARNING: f < -1.0e+32\n");
-			break;
-		}
-		if (fabs(actred) <= 0 && prered <= 0)
-		{
-			info("WARNING: actred and prered <= 0\n");
-			break;
-		}
-		if (fabs(actred) <= 1.0e-12*fabs(f) &&
-		    fabs(prered) <= 1.0e-12*fabs(f))
-		{
-			info("WARNING: actred and prered too small\n");
-			break;
-		}
-	}
-
-	delete[] g;
-	delete[] r;
-	delete[] w_new;
-	delete[] s;
-}
-
-int TRON::trcg(double delta, double *g, double *s, double *r)
-{
-	int i, inc = 1;
-	int n = fun_obj->get_nr_variable();
-	double one = 1;
-	double *d = new double[n];
-	double *Hd = new double[n];
-	double rTr, rnewTrnew, alpha, beta, cgtol;
-
-	for (i=0; i<n; i++)
-	{
-		s[i] = 0;
-		r[i] = -g[i];
-		d[i] = r[i];
-	}
-	cgtol = eps_cg*dnrm2_(&n, g, &inc);
-
-	int cg_iter = 0;
-	rTr = ddot_(&n, r, &inc, r, &inc);
-	while (1)
-	{
-		if (dnrm2_(&n, r, &inc) <= cgtol)
-			break;
-		cg_iter++;
-		fun_obj->Hv(d, Hd);
-
-		alpha = rTr/ddot_(&n, d, &inc, Hd, &inc);
-		daxpy_(&n, &alpha, d, &inc, s, &inc);
-		if (dnrm2_(&n, s, &inc) > delta)
-		{
-			info("cg reaches trust region boundary\n");
-			alpha = -alpha;
-			daxpy_(&n, &alpha, d, &inc, s, &inc);
-
-			double std = ddot_(&n, s, &inc, d, &inc);
-			double sts = ddot_(&n, s, &inc, s, &inc);
-			double dtd = ddot_(&n, d, &inc, d, &inc);
-			double dsq = delta*delta;
-			double rad = sqrt(std*std + dtd*(dsq-sts));
-			if (std >= 0)
-				alpha = (dsq - sts)/(std + rad);
-			else
-				alpha = (rad - std)/dtd;
-			daxpy_(&n, &alpha, d, &inc, s, &inc);
-			alpha = -alpha;
-			daxpy_(&n, &alpha, Hd, &inc, r, &inc);
-			break;
-		}
-		alpha = -alpha;
-		daxpy_(&n, &alpha, Hd, &inc, r, &inc);
-		rnewTrnew = ddot_(&n, r, &inc, r, &inc);
-		beta = rnewTrnew/rTr;
-		dscal_(&n, &beta, d, &inc);
-		daxpy_(&n, &one, r, &inc, d, &inc);
-		rTr = rnewTrnew;
-	}
-
-	delete[] d;
-	delete[] Hd;
-
-	return(cg_iter);
-}
-
-double TRON::norm_inf(int n, double *x)
-{
-	double dmax = fabs(x[0]);
-	for (int i=1; i<n; i++)
-		if (fabs(x[i]) >= dmax)
-			dmax = fabs(x[i]);
-	return(dmax);
-}
-
-void TRON::set_print_string(void (*print_string) (const char *buf))
-{
-	tron_print_string = print_string;
-}