stderr results from the CPAN

stderr

Algorithm-LibLinear

view release on metacpan or search on metacpan

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

			break;
		}
		case L1R_LR:
		{
			problem prob_col;
			feature_node *x_space = NULL;
			transpose(prob, &x_space ,&prob_col);
			solve_l1r_lr(&prob_col, param, w, Cp, Cn, primal_solver_tol);
			delete [] prob_col.y;
			delete [] prob_col.x;
			delete [] x_space;
			break;
		}
		case L2R_LR_DUAL:
		{
			iter = solve_l2r_lr_dual(prob, param, w, Cp, Cn, dual_solver_max_iter);
			if(iter >= dual_solver_max_iter)
			{
				info("\nWARNING: reaching max number of iterations\nSwitching to use -s 0\n\n");
				// primal_solver_tol obtained from eps for dual may be too loose
				primal_solver_tol *= 0.1;
				l2r_lr_fun fun_obj(prob, param, C);
				NEWTON newton_obj(&fun_obj, primal_solver_tol);
				newton_obj.set_print_string(liblinear_print_string);
				newton_obj.newton(w);
			}
			break;
		}
		case L2R_L2LOSS_SVR:
		{
			l2r_l2_svr_fun fun_obj(prob, param, C);
			NEWTON newton_obj(&fun_obj, primal_solver_tol);
			newton_obj.set_print_string(liblinear_print_string);
			newton_obj.newton(w);
			break;
		}
		case L2R_L1LOSS_SVR_DUAL:
		{
			iter = solve_l2r_l1l2_svr(prob, param, w, dual_solver_max_iter);
			if(iter >= dual_solver_max_iter)
				info("\nWARNING: reaching max number of iterations\nUsing -s 11 may be faster (also see FAQ)\n\n");			

			break;
		}
		case L2R_L2LOSS_SVR_DUAL:
		{
			iter = solve_l2r_l1l2_svr(prob, param, w, dual_solver_max_iter);
			if(iter >= dual_solver_max_iter)
			{
				info("\nWARNING: reaching max number of iterations\nSwitching to use -s 11\n\n");
				// primal_solver_tol obtained from eps for dual may be too loose
				primal_solver_tol *= 0.001;
				l2r_l2_svr_fun fun_obj(prob, param, C);
				NEWTON newton_obj(&fun_obj, primal_solver_tol);
				newton_obj.set_print_string(liblinear_print_string);
				newton_obj.newton(w);
			}
			break;
		}
		default:
			fprintf(stderr, "ERROR: unknown solver_type\n");
			break;
	}

	delete[] C;
}

// Calculate the initial C for parameter selection
static double calc_start_C(const problem *prob, const parameter *param)
{
	int i;
	double xTx, max_xTx;
	max_xTx = 0;
	for(i=0; i<prob->l; i++)
	{
		xTx = 0;
		feature_node *xi=prob->x[i];
		while(xi->index != -1)
		{
			double val = xi->value;
			xTx += val*val;
			xi++;
		}
		if(xTx > max_xTx)
			max_xTx = xTx;
	}

	double min_C = 1.0;
	if(param->solver_type == L2R_LR)
		min_C = 1.0 / (prob->l * max_xTx);
	else if(param->solver_type == L2R_L2LOSS_SVC)
		min_C = 1.0 / (2 * prob->l * max_xTx);
	else if(param->solver_type == L2R_L2LOSS_SVR)
	{
		double sum_y, loss, y_abs;
		double delta2 = 0.1;
		sum_y = 0, loss = 0;
		for(i=0; i<prob->l; i++)
		{
			y_abs = fabs(prob->y[i]);
			sum_y += y_abs;
			loss += max(y_abs - param->p, 0.0) * max(y_abs - param->p, 0.0);
		}
		if(loss > 0)
			min_C = delta2 * delta2 * loss / (8 * sum_y * sum_y * max_xTx);
		else
			min_C = INF;
	}

	return pow( 2, floor(log(min_C) / log(2.0)) );
}

static double calc_max_p(const problem *prob)
{
	int i;
	double max_p = 0.0;
	for(i = 0; i < prob->l; i++)
		max_p = max(max_p, fabs(prob->y[i]));

	return max_p;
}

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

	int l = prob->l;
	int n = prob->n;
	int w_size = prob->n;
	model *model_ = Malloc(model,1);

	if(prob->bias>=0)
		model_->nr_feature=n-1;
	else
		model_->nr_feature=n;
	model_->param = *param;
	model_->bias = prob->bias;

	if(check_regression_model(model_))
	{
		model_->w = Malloc(double, w_size);

		if(param->init_sol != NULL)
			for(i=0;i<w_size;i++)
				model_->w[i] = param->init_sol[i];
		else
			for(i=0;i<w_size;i++)
				model_->w[i] = 0;

		model_->nr_class = 2;
		model_->label = NULL;
		train_one(prob, param, model_->w, 0, 0);
	}
	else if(check_oneclass_model(model_))
	{
		model_->w = Malloc(double, w_size);
		model_->nr_class = 2;
		model_->label = NULL;
		solve_oneclass_svm(prob, param, model_->w, &(model_->rho));
	}
	else
	{
		int nr_class;
		int *label = NULL;
		int *start = NULL;
		int *count = NULL;
		int *perm = Malloc(int,l);

		// group training data of the same class
		group_classes(prob,&nr_class,&label,&start,&count,perm);

		model_->nr_class=nr_class;
		model_->label = Malloc(int,nr_class);
		for(i=0;i<nr_class;i++)
			model_->label[i] = label[i];

		// calculate weighted C
		double *weighted_C = Malloc(double, nr_class);
		for(i=0;i<nr_class;i++)
			weighted_C[i] = param->C;
		for(i=0;i<param->nr_weight;i++)
		{
			for(j=0;j<nr_class;j++)
				if(param->weight_label[i] == label[j])
					break;
			if(j == nr_class)
				fprintf(stderr,"WARNING: class label %d specified in weight is not found\n", param->weight_label[i]);
			else
				weighted_C[j] *= param->weight[i];
		}

		// constructing the subproblem
		feature_node **x = Malloc(feature_node *,l);
		for(i=0;i<l;i++)
			x[i] = prob->x[perm[i]];

		int k;
		problem sub_prob;
		sub_prob.l = l;
		sub_prob.n = n;
		sub_prob.x = Malloc(feature_node *,sub_prob.l);
		sub_prob.y = Malloc(double,sub_prob.l);

		for(k=0; k<sub_prob.l; k++)
			sub_prob.x[k] = x[k];

		// multi-class svm by Crammer and Singer
		if(param->solver_type == MCSVM_CS)
		{
			model_->w=Malloc(double, n*nr_class);
			for(i=0;i<nr_class;i++)
				for(j=start[i];j<start[i]+count[i];j++)
					sub_prob.y[j] = i;
			Solver_MCSVM_CS Solver(&sub_prob, nr_class, weighted_C, param->eps);
			Solver.Solve(model_->w);
		}
		else
		{
			if(nr_class == 2)
			{
				model_->w=Malloc(double, w_size);

				int e0 = start[0]+count[0];
				k=0;
				for(; k<e0; k++)
					sub_prob.y[k] = +1;
				for(; k<sub_prob.l; k++)
					sub_prob.y[k] = -1;

				if(param->init_sol != NULL)
					for(i=0;i<w_size;i++)
						model_->w[i] = param->init_sol[i];
				else
					for(i=0;i<w_size;i++)
						model_->w[i] = 0;

				train_one(&sub_prob, param, model_->w, weighted_C[0], weighted_C[1]);
			}
			else
			{
				model_->w=Malloc(double, w_size*nr_class);
				double *w=Malloc(double, w_size);
				for(i=0;i<nr_class;i++)
				{
					int si = start[i];
					int ei = si+count[i];

					k=0;
					for(; k<si; k++)
						sub_prob.y[k] = -1;
					for(; k<ei; k++)
						sub_prob.y[k] = +1;
					for(; k<sub_prob.l; k++)
						sub_prob.y[k] = -1;

					if(param->init_sol != NULL)
						for(j=0;j<w_size;j++)
							w[j] = param->init_sol[j*nr_class+i];
					else
						for(j=0;j<w_size;j++)
							w[j] = 0;

					train_one(&sub_prob, param, w, weighted_C[i], param->C);

					for(j=0;j<w_size;j++)
						model_->w[j*nr_class+i] = w[j];
				}
				free(w);
			}

		}

		free(x);
		free(label);
		free(start);
		free(count);
		free(perm);
		free(sub_prob.x);
		free(sub_prob.y);
		free(weighted_C);
	}
	return model_;
}

void cross_validation(const problem *prob, const parameter *param, int nr_fold, double *target)
{
	int i;
	int *fold_start;
	int l = prob->l;
	int *perm = Malloc(int,l);
	if (nr_fold > l)
	{
		nr_fold = l;
		fprintf(stderr,"WARNING: # folds > # data. Will use # folds = # data instead (i.e., leave-one-out cross validation)\n");
	}
	fold_start = Malloc(int,nr_fold+1);
	for(i=0;i<l;i++) perm[i]=i;
	for(i=0;i<l;i++)
	{
		int j = i+rand()%(l-i);
		swap(perm[i],perm[j]);
	}
	for(i=0;i<=nr_fold;i++)
		fold_start[i]=i*l/nr_fold;

	for(i=0;i<nr_fold;i++)
	{
		int begin = fold_start[i];
		int end = fold_start[i+1];
		int j,k;
		struct problem subprob;

		subprob.bias = prob->bias;
		subprob.n = prob->n;
		subprob.l = l-(end-begin);
		subprob.x = Malloc(struct feature_node*,subprob.l);
		subprob.y = Malloc(double,subprob.l);

		k=0;
		for(j=0;j<begin;j++)
		{
			subprob.x[k] = prob->x[perm[j]];
			subprob.y[k] = prob->y[perm[j]];
			++k;
		}
		for(j=end;j<l;j++)
		{
			subprob.x[k] = prob->x[perm[j]];
			subprob.y[k] = prob->y[perm[j]];
			++k;
		}
		struct model *submodel = train(&subprob,param);
		for(j=begin;j<end;j++)
			target[perm[j]] = predict(submodel,prob->x[perm[j]]);
		free_and_destroy_model(&submodel);
		free(subprob.x);
		free(subprob.y);
	}
	free(fold_start);
	free(perm);
}


void find_parameters(const problem *prob, const parameter *param, int nr_fold, double start_C, double start_p, double *best_C, double *best_p, double *best_score)
{
	// prepare CV folds

	int i;
	int *fold_start;
	int l = prob->l;
	int *perm = Malloc(int, l);
	struct problem *subprob = Malloc(problem,nr_fold);

	if (nr_fold > l)
	{
		nr_fold = l;
		fprintf(stderr,"WARNING: # folds > # data. Will use # folds = # data instead (i.e., leave-one-out cross validation)\n");
	}
	fold_start = Malloc(int,nr_fold+1);
	for(i=0;i<l;i++) perm[i]=i;
	for(i=0;i<l;i++)
	{
		int j = i+rand()%(l-i);
		swap(perm[i],perm[j]);
	}
	for(i=0;i<=nr_fold;i++)
		fold_start[i]=i*l/nr_fold;

	for(i=0;i<nr_fold;i++)
	{
		int begin = fold_start[i];
		int end = fold_start[i+1];
		int j,k;

		subprob[i].bias = prob->bias;
		subprob[i].n = prob->n;
		subprob[i].l = l-(end-begin);
		subprob[i].x = Malloc(struct feature_node*,subprob[i].l);
		subprob[i].y = Malloc(double,subprob[i].l);

		k=0;
		for(j=0;j<begin;j++)
		{
			subprob[i].x[k] = prob->x[perm[j]];
			subprob[i].y[k] = prob->y[perm[j]];
			++k;
		}
		for(j=end;j<l;j++)
		{
			subprob[i].x[k] = prob->x[perm[j]];
			subprob[i].y[k] = prob->y[perm[j]];
			++k;
		}
	}

	struct parameter param_tmp = *param;
	*best_p = -1;
	if(param->solver_type == L2R_LR || param->solver_type == L2R_L2LOSS_SVC)
	{
		if(start_C <= 0)
			start_C = calc_start_C(prob, &param_tmp);
		double max_C = 1024;
		start_C = min(start_C, max_C);
		double best_C_tmp, best_score_tmp;

		find_parameter_C(prob, &param_tmp, start_C, max_C, &best_C_tmp, &best_score_tmp, fold_start, perm, subprob, nr_fold);

		*best_C = best_C_tmp;
		*best_score = best_score_tmp;
	}
	else if(param->solver_type == L2R_L2LOSS_SVR)
	{
		double max_p = calc_max_p(prob);
		int num_p_steps = 20;
		double max_C = 1048576;
		*best_score = INF;

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

	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);
}

double get_decfun_bias(const struct model *model_, int label_idx)
{
	if(check_oneclass_model(model_))
	{
		fprintf(stderr, "ERROR: get_decfun_bias can not be called for a one-class SVM model\n");
		return 0;
	}
	int bias_idx = model_->nr_feature;
	double bias = model_->bias;
	if(bias <= 0)
		return 0;
	else
		return bias*get_w_value(model_, bias_idx, label_idx);
}

double get_decfun_rho(const struct model *model_)
{
	if(check_oneclass_model(model_))
		return model_->rho;
	else
	{
		fprintf(stderr, "ERROR: get_decfun_rho can be called only for a one-class SVM model\n");
		return 0;
	}
}

void free_model_content(struct model *model_ptr)
{
	free(model_ptr->w);
	model_ptr->w = NULL;
	free(model_ptr->label);
	model_ptr->label = NULL;
}

void free_and_destroy_model(struct model **model_ptr_ptr)
{
	struct model *model_ptr = *model_ptr_ptr;
	if(model_ptr != NULL)
	{
		free_model_content(model_ptr);
		free(model_ptr);
		*model_ptr_ptr = NULL;
	}
}

void destroy_param(parameter* param)
{
	free(param->weight_label);
	param->weight_label = NULL;
	free(param->weight);
	param->weight = NULL;
	free(param->init_sol);
	param->init_sol = NULL;
}

const char *check_parameter(const problem *prob, const parameter *param)
{
	if(param->eps <= 0)
		return "eps <= 0";

	if(param->C <= 0)
		return "C <= 0";

	if(param->p < 0 && param->solver_type == L2R_L2LOSS_SVR)
		return "p < 0";

	if(prob->bias >= 0 && param->solver_type == ONECLASS_SVM)
		return "prob->bias >=0, but this is ignored in ONECLASS_SVM";

	if(param->regularize_bias == 0)
	{
		if(prob->bias != 1.0)
			return "To not regularize bias, must specify -B 1 along with -R";
		if(param->solver_type != L2R_LR
			&& param->solver_type != L2R_L2LOSS_SVC
			&& param->solver_type != L1R_L2LOSS_SVC
			&& param->solver_type != L1R_LR
			&& param->solver_type != L2R_L2LOSS_SVR)
			return "-R option supported only for solver L2R_LR, L2R_L2LOSS_SVC, L1R_L2LOSS_SVC, L1R_LR, and L2R_L2LOSS_SVR";
	}

	if(param->solver_type != L2R_LR

( run in 1.978 second using v1.01-cache-2.11-cpan-13bb782fe5a )