Algorithm-SVM
view release on metacpan or search on metacpan
if(param->probability &&
(param->svm_type == EPSILON_SVR ||
param->svm_type == NU_SVR))
{
model->probA = Malloc(double,1);
model->probA[0] = svm_svr_probability(prob,param);
}
decision_function f = svm_train_one(prob,param,0,0);
model->rho = Malloc(double,1);
model->rho[0] = f.rho;
int nSV = 0;
int i;
for(i=0;i<prob->l;i++)
if(fabs(f.alpha[i]) > 0) ++nSV;
model->l = nSV;
model->SV = Malloc(svm_node *,nSV);
model->sv_coef[0] = Malloc(double,nSV);
int j = 0;
for(i=0;i<prob->l;i++)
if(fabs(f.alpha[i]) > 0)
{
model->SV[j] = prob->x[i];
model->sv_coef[0][j] = f.alpha[i];
++j;
}
free(f.alpha);
}
else
{
// classification
int l = prob->l;
int nr_class;
int *label = NULL;
int *start = NULL;
int *count = NULL;
int *perm = Malloc(int,l);
// group training data of the same class
svm_group_classes(prob,&nr_class,&label,&start,&count,perm);
svm_node **x = Malloc(svm_node *,l);
int i;
for(i=0;i<l;i++)
x[i] = prob->x[perm[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++)
{
int j;
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];
}
// train k*(k-1)/2 models
bool *nonzero = Malloc(bool,l);
for(i=0;i<l;i++)
nonzero[i] = false;
decision_function *f = Malloc(decision_function,nr_class*(nr_class-1)/2);
double *probA=NULL,*probB=NULL;
if (param->probability)
{
probA=Malloc(double,nr_class*(nr_class-1)/2);
probB=Malloc(double,nr_class*(nr_class-1)/2);
}
int p = 0;
for(i=0;i<nr_class;i++)
for(int j=i+1;j<nr_class;j++)
{
svm_problem sub_prob;
int si = start[i], sj = start[j];
int ci = count[i], cj = count[j];
sub_prob.l = ci+cj;
sub_prob.x = Malloc(svm_node *,sub_prob.l);
sub_prob.y = Malloc(double,sub_prob.l);
int k;
for(k=0;k<ci;k++)
{
sub_prob.x[k] = x[si+k];
sub_prob.y[k] = +1;
}
for(k=0;k<cj;k++)
{
sub_prob.x[ci+k] = x[sj+k];
sub_prob.y[ci+k] = -1;
}
if(param->probability)
svm_binary_svc_probability(&sub_prob,param,weighted_C[i],weighted_C[j],probA[p],probB[p]);
f[p] = svm_train_one(&sub_prob,param,weighted_C[i],weighted_C[j]);
for(k=0;k<ci;k++)
if(!nonzero[si+k] && fabs(f[p].alpha[k]) > 0)
nonzero[si+k] = true;
for(k=0;k<cj;k++)
if(!nonzero[sj+k] && fabs(f[p].alpha[ci+k]) > 0)
nonzero[sj+k] = true;
free(sub_prob.x);
free(sub_prob.y);
++p;
}
// build output
model->nr_class = nr_class;
model->label = Malloc(int,nr_class);
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];
if(param.kernel_type == PRECOMPUTED)
fprintf(fp,"0:%d ",(int)(p->value));
else
while(p->index != -1)
{
fprintf(fp,"%d:%.8g ",p->index,p->value);
p++;
}
fprintf(fp, "\n");
}
if (ferror(fp) != 0 || fclose(fp) != 0) return -1;
else return 0;
}
svm_model *svm_load_model(const char *model_file_name)
{
FILE *fp = fopen(model_file_name,"r");
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,"%d",¶m.degree);
else if(strcmp(cmd,"gamma")==0)
fscanf(fp,"%lf",¶m.gamma);
else if(strcmp(cmd,"coef0")==0)
fscanf(fp,"%lf",¶m.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: [%s]\n",cmd);
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:
( run in 0.745 second using v1.01-cache-2.11-cpan-39bf76dae61 )