svm.cpp

orange源码 数据挖掘技术

					if(nonzero[sj+k])
						model->sv_coef[i][q++] = f[p].alpha[ci+k];
				++p;
			}
		
		free(label);
		free(probA);
		free(probB);
		free(count);
		free(perm);
		free(start);
		free(x);
		free(weighted_C);
		free(nonzero);
		for(i=0;i<nr_class*(nr_class-1)/2;i++)
			free(f[i].alpha);
		free(f);
		free(nz_count);
		free(nz_start);
	}
	return model;
}

// Stratified cross validation
void svm_cross_validation(const svm_problem *prob, const svm_parameter *param, int nr_fold, double *target)
{
	int i;
	int *fold_start = Malloc(int,nr_fold+1);
	int l = prob->l;
	int *perm = Malloc(int,l);
	int nr_class;

	// stratified cv may not give leave-one-out rate
	// Each class to l folds -> some folds may have zero elements
	if((param->svm_type == C_SVC ||
	    param->svm_type == NU_SVC) && nr_fold < l)
	{
		int *start = NULL;
		int *label = NULL;
		int *count = NULL;
		svm_group_classes(prob,&nr_class,&label,&start,&count,perm);

		// random shuffle and then data grouped by fold using the array perm
		int *fold_count = Malloc(int,nr_fold);
		int c;
		int *index = Malloc(int,l);
		for(i=0;i<l;i++)
			index[i]=perm[i];
		for (c=0; c<nr_class; c++) 
			for(i=0;i<count[c];i++)
			{
				int j = i+rand()%(count[c]-i);
				swap(index[start[c]+j],index[start[c]+i]);
			}
		for(i=0;i<nr_fold;i++)
		{
			fold_count[i] = 0;
			for (c=0; c<nr_class;c++)
				fold_count[i]+=(i+1)*count[c]/nr_fold-i*count[c]/nr_fold;
		}
		fold_start[0]=0;
		for (i=1;i<=nr_fold;i++)
			fold_start[i] = fold_start[i-1]+fold_count[i-1];
		for (c=0; c<nr_class;c++)
			for(i=0;i<nr_fold;i++)
			{
				int begin = start[c]+i*count[c]/nr_fold;
				int end = start[c]+(i+1)*count[c]/nr_fold;
				for(int j=begin;j<end;j++)
				{
					perm[fold_start[i]] = index[j];
					fold_start[i]++;
				}
			}
		fold_start[0]=0;
		for (i=1;i<=nr_fold;i++)
			fold_start[i] = fold_start[i-1]+fold_count[i-1];
		free(start);	
		free(label);
		free(count);	
		free(index);
		free(fold_count);
	}
	else
	{
		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 svm_problem subprob;

		subprob.l = l-(end-begin);
		subprob.x = Malloc(struct svm_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 svm_model *submodel = svm_train(&subprob,param);
		if(param->probability && 
		   (param->svm_type == C_SVC || param->svm_type == NU_SVC))
		{
			double *prob_estimates=Malloc(double,svm_get_nr_class(submodel));
			for(j=begin;j<end;j++)
				target[perm[j]] = svm_predict_probability(submodel,prob->x[perm[j]],prob_estimates);
			free(prob_estimates);			
		}
		else
			for(j=begin;j<end;j++)
				target[perm[j]] = svm_predict(submodel,prob->x[perm[j]]);
		svm_destroy_model(submodel);
		free(subprob.x);
		free(subprob.y);
	}		
	free(fold_start);
	free(perm);	
}


int svm_get_svm_type(const svm_model *model)
{
	return model->param.svm_type;
}

int svm_get_nr_class(const svm_model *model)
{
	return model->nr_class;
}

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

double svm_get_svr_probability(const svm_model *model)
{
	if ((model->param.svm_type == EPSILON_SVR || model->param.svm_type == NU_SVR) &&
	    model->probA!=NULL)
		return model->probA[0];
	else
	{
		info("Model doesn't contain information for SVR probability inference\n");
		return 0;
	}
}

void svm_predict_values(const svm_model *model, const svm_node *x, double* dec_values)
{
	if(model->param.svm_type == ONE_CLASS ||
	   model->param.svm_type == EPSILON_SVR ||
	   model->param.svm_type == NU_SVR)
	{
		double *sv_coef = model->sv_coef[0];
		double sum = 0;
		for(int i=0;i<model->l;i++)
			sum += sv_coef[i] * Kernel::k_function(x,model->SV[i],model->param);
		sum -= model->rho[0];
		*dec_values = sum;
	}
	else
	{
		int i;
		int nr_class = model->nr_class;
		int l = model->l;
		
		double *kvalue = Malloc(double,l);
		for(i=0;i<l;i++)
			kvalue[i] = Kernel::k_function(x,model->SV[i],model->param);

		int *start = Malloc(int,nr_class);
		start[0] = 0;
		for(i=1;i<nr_class;i++)
			start[i] = start[i-1]+model->nSV[i-1];

		int p=0;
		int pos=0;
		for(i=0;i<nr_class;i++)
			for(int j=i+1;j<nr_class;j++)
			{
				double sum = 0;
				int si = start[i];
				int sj = start[j];
				int ci = model->nSV[i];
				int cj = model->nSV[j];
				
				int k;
				double *coef1 = model->sv_coef[j-1];
				double *coef2 = model->sv_coef[i];
				for(k=0;k<ci;k++)
					sum += coef1[si+k] * kvalue[si+k];
				for(k=0;k<cj;k++)
					sum += coef2[sj+k] * kvalue[sj+k];
				sum -= model->rho[p++];
				dec_values[pos++] = sum;
			}

		free(kvalue);
		free(start);
	}
}

double svm_predict(const svm_model *model, const svm_node *x)
{
	if(model->param.svm_type == ONE_CLASS ||
	   model->param.svm_type == EPSILON_SVR ||
	   model->param.svm_type == NU_SVR)
	{
		double res;
		svm_predict_values(model, x, &res);
		
		if(model->param.svm_type == ONE_CLASS)
			return (res>0)?1:-1;
		else
			return res;
	}
	else
	{
		int i;
		int nr_class = model->nr_class;
		double *dec_values = Malloc(double, nr_class*(nr_class-1)/2);
		svm_predict_values(model, x, dec_values);

		int *vote = Malloc(int,nr_class);
		for(i=0;i<nr_class;i++)
			vote[i] = 0;
		int pos=0;
		for(i=0;i<nr_class;i++)
			for(int j=i+1;j<nr_class;j++)
			{
				if(dec_values[pos++] > 0)
					++vote[i];
				else
					++vote[j];
			}

		int vote_max_idx = 0;
		for(i=1;i<nr_class;i++)
			if(vote[i] > vote[vote_max_idx])
				vote_max_idx = i;
		free(vote);
		free(dec_values);
		return model->label[vote_max_idx];
	}
}

double svm_predict_probability(
	const svm_model *model, const svm_node *x, double *prob_estimates)
{
	if ((model->param.svm_type == C_SVC || model->param.svm_type == NU_SVC) &&
	    model->probA!=NULL && model->probB!=NULL)
	{
		int i;
		int nr_class = model->nr_class;
		double *dec_values = Malloc(double, nr_class*(nr_class-1)/2);
		svm_predict_values(model, x, dec_values);

		double min_prob=1e-7;
		double **pairwise_prob=Malloc(double *,nr_class);
		for(i=0;i<nr_class;i++)
			pairwise_prob[i]=Malloc(double,nr_class);
		int k=0;
		for(i=0;i<nr_class;i++)
			for(int j=i+1;j<nr_class;j++)
			{
				pairwise_prob[i][j]=min(max(sigmoid_predict(dec_values[k],model->probA[k],model->probB[k]),min_prob),1-min_prob);
				pairwise_prob[j][i]=1-pairwise_prob[i][j];
				k++;
			}
		multiclass_probability(nr_class,pairwise_prob,prob_estimates);

		int prob_max_idx = 0;
		for(i=1;i<nr_class;i++)
			if(prob_estimates[i] > prob_estimates[prob_max_idx])
				prob_max_idx = i;
		for(i=0;i<nr_class;i++)
			free(pairwise_prob[i]);
		free(dec_values);
                free(pairwise_prob);	     
		return model->label[prob_max_idx];
	}
	else 
		return svm_predict(model, x);
}

const char *svm_type_table[] =
{
	"c_svc","nu_svc","one_class","epsilon_svr","nu_svr",NULL
};

const char *kernel_type_table[]=
{
	"linear","polynomial","rbf","sigmoid",NULL
};

int svm_save_model(const char *model_file_name, const svm_model *model)
{
	FILE *fp = fopen(model_file_name,"w");
	if(fp==NULL) return -1;

	const svm_parameter& param = model->param;

	fprintf(fp,"svm_type %s\n", svm_type_table[param.svm_type]);
	fprintf(fp,"kernel_type %s\n", kernel_type_table[param.kernel_type]);

	if(param.kernel_type == POLY)
		fprintf(fp,"degree %g\n", param.degree);

	if(param.kernel_type == POLY || param.kernel_type == RBF || param.kernel_type == SIGMOID)
		fprintf(fp,"gamma %g\n", param.gamma);

	if(param.kernel_type == POLY || param.kernel_type == SIGMOID)
		fprintf(fp,"coef0 %g\n", param.coef0);

	int nr_class = model->nr_class;
	int l = model->l;
	fprintf(fp, "nr_class %d\n", nr_class);
	fprintf(fp, "total_sv %d\n",l);
	
	{
		fprintf(fp, "rho");
		for(int i=0;i<nr_class*(nr_class-1)/2;i++)
			fprintf(fp," %g",model->rho[i]);
		fprintf(fp, "\n");
	}
	
	if(model->label)
	{
		fprintf(fp, "label");
		for(int i=0;i<nr_class;i++)
			fprintf(fp," %d",model->label[i]);
		fprintf(fp, "\n");
	}

	if(model->probA) // regression has probA only
	{
		fprintf(fp, "probA");
		for(int i=0;i<nr_class*(nr_class-1)/2;i++)
			fprintf(fp," %g",model->probA[i]);
		fprintf(fp, "\n");
	}
	if(model->probB)
	{
		fprintf(fp, "probB");
		for(int i=0;i<nr_class*(nr_class-1)/2;i++)
			fprintf(fp," %g",model->probB[i]);
		fprintf(fp, "\n");
	}

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

	fprintf(fp, "SV\n");
	const double * const *sv_coef = model->sv_coef;
	const svm_node * const *SV = model->SV;

	for(int i=0;i<l;i++)
	{
		for(int j=0;j<nr_class-1;j++)
			fprintf(fp, "%.16g ",sv_coef[j][i]);

		const svm_node *p = SV[i];
		while(p->index != -1)
		{
			fprintf(fp,"%d:%.8g ",p->index,p->value);
			p++;
		}
		fprintf(fp, "\n");
	}

	fclose(fp);
	return 0;
}

svm_model *svm_load_model(const char *model_file_name)
{
	FILE *fp = fopen(model_file_name,"rb");
	if(fp==NULL) return NULL;
	
	// read parameters

	svm_model *model = Malloc(svm_model,1);
	svm_parameter& param = model->param;
	model->rho = NULL;
	model->probA = NULL;
	model->probB = NULL;
	model->label = NULL;
	model->nSV = NULL;

	char cmd[81];
	while(1)
	{
		fscanf(fp,"%80s",cmd);

		if(strcmp(cmd,"svm_type")==0)
		{
			fscanf(fp,"%80s",cmd);
			int i;
			for(i=0;svm_type_table[i];i++)
			{
				if(strcmp(svm_type_table[i],cmd)==0)
				{
					param.svm_type=i;
					break;
				}
			}
			if(svm_type_table[i] == NULL)
			{
				fprintf(stderr,"unknown svm type.\n");
				free(model->rho);
				free(model->label);
				free(model->nSV);
				free(model);
				return NULL;
			}
		}
		else if(strcmp(cmd,"kernel_type")==0)
		{		
			fscanf(fp,"%80s",cmd);
			int i;
			for(i=0;kernel_type_table[i];i++)
			{
				if(strcmp(kernel_type_table[i],cmd)==0)
				{
					param.kernel_type=i;
					break;
				}
			}
			if(kernel_type_table[i] == NULL)
			{
				fprintf(stderr,"unknown kernel function.\n");
				free(model->rho);
				free(model->label);
				free(model->nSV);
				free(model);
				return NULL;
			}
		}
		else if(strcmp(cmd,"degree")==0)
			fscanf(fp,"%lf",&param.degree);
		else if(strcmp(cmd,"gamma")==0)
			fscanf(fp,"%lf",&param.gamma);
		else if(strcmp(cmd,"coef0")==0)
			fscanf(fp,"%lf",&param.coef0);
		else if(strcmp(cmd,"nr_class")==0)
			fscanf(fp,"%d",&model->nr_class);
		else if(strcmp(cmd,"total_sv")==0)
			fscanf(fp,"%d",&model->l);
		else if(strcmp(cmd,"rho")==0)
		{
			int n = model->nr_class * (model->nr_class-1)/2;
			model->rho = Malloc(double,n);
			for(int i=0;i<n;i++)
				fscanf(fp,"%lf",&model->rho[i]);
		}
		else if(strcmp(cmd,"label")==0)
		{
			int n = model->nr_class;
			model->label = Malloc(int,n);
			for(int i=0;i<n;i++)
				fscanf(fp,"%d",&model->label[i]);
		}
		else if(strcmp(cmd,"probA")==0)
		{
			int n = model->nr_class * (model->nr_class-1)/2;
			model->probA = Malloc(double,n);
			for(int i=0;i<n;i++)
				fscanf(fp,"%lf",&model->probA[i]);
		}
		else if(strcmp(cmd,"probB")==0)
		{
			int n = model->nr_class * (model->nr_class-1)/2;
			model->probB = Malloc(double,n);
			for(int i=0;i<n;i++)
				fscanf(fp,"%lf",&model->probB[i]);
		}
		else if(strcmp(cmd,"nr_sv")==0)
		{
			int n = model->nr_class;
			model->nSV = Malloc(int,n);
			for(int i=0;i<n;i++)
				fscanf(fp,"%d",&model->nSV[i]);
		}
		else if(strcmp(cmd,"SV")==0)
		{
			while(1)
			{
				int c = getc(fp);
				if(c==EOF || c=='\n') break;	
			}
			break;
		}
		else
		{
			fprintf(stderr,"unknown text in model file\n");
			free(model->rho);
			free(model->label);
			free(model->nSV);
			free(model);
			return NULL;
		}
	}

	// read sv_coef and SV

	int elements = 0;
	long pos = ftell(fp);

	while(1)
	{
		int c = fgetc(fp);
		switch(c)
		{
			case '\n':
				// count the '-1' element
			case ':':
				++elements;
				break;
			case EOF:
				goto out;
			default:
				;
		}
	}
out:
	fseek(fp,pos,SEEK_SET);

	int m = model->nr_class - 1;
	int l = model->l;
	model->sv_coef = Malloc(double *,m);
	int i;
	for(i=0;i<m;i++)
		model->sv_coef[i] = Malloc(double,l);
	model->SV = Malloc(svm_node*,l);
	svm_node *x_space=NULL;
	if(l>0) x_space = Malloc(svm_node,elements);

	int j=0;
	for(i=0;i<l;i++)
	{
		model->SV[i] = &x_space[j];
		for(int k=0;k<m;k++)
			fscanf(fp,"%lf",&model->sv_coef[k][i]);
		while(1)
		{
			int c;
			do {
				c = getc(fp);
				if(c=='\n') goto out2;
			} while(isspace(c));
			ungetc(c,fp);
			fscanf(fp,"%d:%lf",&(x_space[j].index),&(x_space[j].value));
			++j;
		}	
out2:
		x_space[j++].index = -1;
	}

	fclose(fp);

	model->free_sv = 1;	// XXX
	return model;
}

void svm_destroy_model(svm_model* model)
{
	if(model->free_sv && model->l > 0)
		free((void *)(model->SV[0]));
	for(int i=0;i<model->nr_class-1;i++)
		free(model->sv_coef[i]);
	free(model->SV);
	free(model->sv_coef);
	fr