int cLibsvmLiveSink::myFinaliseInstance()
{
int ap=0;
int ret = cDataSink::myFinaliseInstance();
if (ret==0) return 0;
// TODO: binary model files...
// load model
SMILE_MSG(2,"loading LibSVM model for instance '%s' ...",getInstName());
if((model=svm_load_model(modelfile))==0) {
COMP_ERR("can't open libSVM model file '%s'",modelfile);
}
nClasses = svm_get_nr_class(model);
svmType = svm_get_svm_type(model);
if(predictProbability) {
if ((svmType==NU_SVR) || (svmType==EPSILON_SVR)) {
nClasses = 0;
SMILE_MSG(2,"LibSVM prob. model (regression) for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g",svm_get_svr_probability(model));
} else {
labels=(int *) malloc(nClasses*sizeof(int));
svm_get_labels(model,labels);
SMILE_MSG(3,"LibSVM %i labels in model '%s':",nClasses,modelfile);
int j;
for(j=0;j<nClasses;j++)
SMILE_MSG(3," Label[%i] : '%d'",j,labels[j]);
}
}
//?? move this in front of above if() block ?
if ((predictProbability)&&(nClasses>0))
probEstimates = (double *) malloc(nClasses*sizeof(double));
// load scale
if((scale=svm_load_scale(scalefile))==0) {
COMP_ERR("can't open libSVM scale file '%s'",scalefile);
}
// load selection
loadSelection(fselection);
//TODO: check compatibility of getLevelN() (possibly after selection), number of features in model, and scale
if (nClasses>0) {
// load class mapping
loadClasses(classes);
} else {
if (classes != NULL) SMILE_IWRN(2,"not loading given class mapping file for regression SVR model (there are no classes...)!");
}
return ret;
}
int predict(double **values, int **indices, int rowNum, int *arrayNcol, int *labels, double **prob_estimates, int isProb)
{
int svm_type=svm_get_svm_type(model);
int nr_class=svm_get_nr_class(model);
int j;
LOGD("isProb:%d", isProb);
if(isProb)
{
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
LOGD("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model));
else
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model,labels);
// fprintf(output,"labels");
// for(j=0;j<nr_class;j++)
// fprintf(output," %d",labels[j]);
// fprintf(output,"\n");
// free(labels);
}
}
// each record will receive
// a predicted label and a [nClass]-D probability estimate array
for (int i = 0; i < rowNum; i++)
{
int nCol = arrayNcol[i];
double target_label = 0;
int predict_label=0;
x = (struct svm_node *) realloc(x,(nCol+1)*sizeof(struct svm_node));
for (int j = 0; j < nCol; j++)
{
x[j].index = indices[i][j];
x[j].value = values[i][j];
}
x[nCol].index = -1;
// Probability prediction
if (isProb && (svm_type==C_SVC || svm_type==NU_SVC))
{
// prob_estimate[rowNum][nClass]
labels[i] = svm_predict_probability(model,x,prob_estimates[i]);
}
// without probability
else
{
labels[i] = svm_predict(model,x);
}
} // For
return 0;
}
int predict(float **values, int **indices, int rowNum, int colNum, int *labels, double *prob_estimates, int isProb)
{
int svm_type=svm_get_svm_type(model);
int nr_class=svm_get_nr_class(model);
int j;
if(isProb)
{
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
LOGD("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model));
else
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model,labels);
// fprintf(output,"labels");
// for(j=0;j<nr_class;j++)
// fprintf(output," %d",labels[j]);
// fprintf(output,"\n");
// free(labels);
}
}
for (int i = 0; i < rowNum; i++)
{
double target_label, predict_label=0;
x = (struct svm_node *) realloc(x,(colNum+1)*sizeof(struct svm_node));
for (int j = 0; j < colNum; j++)
{
x[j].index = indices[i][j];
x[j].value = values[i][j];
}
x[colNum].index = -1;
// Probability prediction
if (isProb && (svm_type==C_SVC || svm_type==NU_SVC))
{
predict_label = svm_predict_probability(model,x,prob_estimates);
labels[0]=predict_label;
}
else { labels[i] = svm_predict(model,x); }
} // For
return 0;
}
HandTranslating::HandTranslating(QObject *parent) :
QThread(parent)
{
databaseFolderPath = "../Database/Main";
modelFile = "databaseMain.model";
string model_file_name = databaseFolderPath + "/" + modelFile;
if((model=svm_load_model(model_file_name.c_str()))==0)
{
STOP = true;
cout << "ko mo duoc model\n";
} else {
svm_type = svm_get_svm_type(model);
nr_class = svm_get_nr_class(model);
labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model,labels);
prob_estimates = (double *) malloc(nr_class * sizeof(double));
STOP = false;
enableToTranslate = false;
}
}
void predict(FILE *input, FILE *output)
{
int correct = 0;
int total = 0;
double error = 0;
double sump = 0, sumt = 0, sumpp = 0, sumtt = 0, sumpt = 0;
int svm_type=svm_get_svm_type(model);
int nr_class=svm_get_nr_class(model);
double *prob_estimates=NULL;
int j;
if(predict_probability)
{
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
printf("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model));
else
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
free(labels);
}
}
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
while(readline(input) != NULL)
{
int i = 0;
double target_label, predict_label;
char *idx, *val, *label, *endptr;
int inst_max_index = -1; // strtol gives 0 if wrong format, and precomputed kernel has <index> start from 0
label = strtok(line," \t");
target_label = strtod(label,&endptr);
if(endptr == label)
exit_input_error(total+1);
while(1)
{
if(i>=max_nr_attr-1) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
}
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
break;
errno = 0;
x[i].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x[i].index <= inst_max_index)
exit_input_error(total+1);
else
inst_max_index = x[i].index;
errno = 0;
x[i].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
exit_input_error(total+1);
++i;
}
x[i].index = -1;
if (predict_probability && (svm_type==C_SVC || svm_type==NU_SVC))
{
predict_label = svm_predict_probability(model,x,prob_estimates);
fprintf(output,"%g",predict_label);
for(j=0;j<nr_class;j++)
fprintf(output," %g",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
predict_label = svm_predict(model,x);
fprintf(output,"%g\n",predict_label);
}
if(predict_label == target_label)
++correct;
error += (predict_label-target_label)*(predict_label-target_label);
sump += predict_label;
sumt += target_label;
sumpp += predict_label*predict_label;
sumtt += target_label*target_label;
sumpt += predict_label*target_label;
++total;
}
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
{
printf("Mean squared error = %g (regression)\n",error/total);
printf("Squared correlation coefficient = %g (regression)\n",
((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
);
}
else
printf("Accuracy = %g%% (%d/%d) (classification)\n",
(double)correct/total*100,correct,total);
if(predict_probability)
free(prob_estimates);
}
double binary_class_cross_validation(const svm_problem *prob, const svm_parameter *param, int nr_fold)
{
dvec_t dec_values;
ivec_t ty;
int *labels;
if (nr_fold > 1)
{
int i;
int *fold_start = Malloc(int,nr_fold+1);
int l = prob->l;
int *perm = Malloc(int,l);
for(i=0;i<l;i++) perm[i]=i;
for(i=0;i<l;i++)
{
int j = i+rand()%(l-i);
std::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);
int svm_type = svm_get_svm_type(submodel);
if(svm_type == NU_SVR || svm_type == EPSILON_SVR){
fprintf(stderr, "wrong svm type");
exit(1);
}
labels = Malloc(int, svm_get_nr_class(submodel));
svm_get_labels(submodel, labels);
if(svm_get_nr_class(submodel) > 2)
{
fprintf(stderr,"Error: the number of class is not equal to 2\n");
exit(-1);
}
dec_values.resize(end);
ty.resize(end);
for(j=begin;j<end;j++) {
svm_predict_values(submodel,prob->x[perm[j]], &dec_values[j]);
ty[j] = (prob->y[perm[j]] > 0)? 1: -1;
}
if(labels[0] <= 0) {
for(j=begin;j<end;j++)
dec_values[j] *= -1;
}
svm_free_and_destroy_model(&submodel);
free(subprob.x);
free(subprob.y);
free(labels);
}
free(perm);
free(fold_start);
}
void binary_class_predict(FILE *input, FILE *output){
int total = 0;
int *labels;
int max_nr_attr = 64;
struct svm_node *x = Malloc(struct svm_node, max_nr_attr);
dvec_t dec_values;
ivec_t true_labels;
int svm_type=svm_get_svm_type(model);
if (svm_type==NU_SVR || svm_type==EPSILON_SVR){
fprintf(stderr, "wrong svm type.");
exit(1);
}
labels = Malloc(int, svm_get_nr_class(model));
svm_get_labels(model, labels);
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
while(readline(input) != NULL)
{
int i = 0;
double target_label, predict_label;
char *idx, *val, *label, *endptr;
int inst_max_index = -1; // strtol gives 0 if wrong format, and precomputed kernel has <index> start from 0
label = strtok(line," \t");
target_label = strtod(label,&endptr);
if(endptr == label)
exit_input_error(total+1);
while(1)
{
if(i>=max_nr_attr - 2) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
}
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
break;
errno = 0;
x[i].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x[i].index <= inst_max_index)
exit_input_error(total+1);
else
inst_max_index = x[i].index;
errno = 0;
x[i].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
exit_input_error(total+1);
++i;
}
x[i].index = -1;
predict_label = svm_predict(model,x);
fprintf(output,"%g\n",predict_label);
double dec_value;
svm_predict_values(model, x, &dec_value);
true_labels.push_back((target_label > 0)? 1: -1);
if(labels[0] <= 0) dec_value *= -1;
dec_values.push_back(dec_value);
}
// validation_function(dec_values, true_labels);
accuracy(dec_values, true_labels);
bac(dec_values, true_labels);
free(labels);
free(x);
}
void predict(FILE *input, FILE *output, FILE *output_w2, FILE *output_prob,int predict_probability, FILE *addr, int Ncol, int Nlig, long Npolar)
{
int svm_type=svm_get_svm_type(model);
int nr_class=svm_get_nr_class(model);
double *prob_estimates=NULL;
int i,j,k,l,num_block,p,n,count;
int Nband[Npolar];
long n_addr = 0,m=0, n_total_band, offset=0;
long max_num_pixel, num_rest_pixel, n_img_pixel = (long)Ncol * (long)Nlig;
float buff_float, zero = 0;
float **V_pol_rest, **V_pol_block, *v_pol_buff;
long int *tab_addr, buff_long_int;
float *output_label;
double *w2_predict;
float **w2_predict_out, *mean_dist, *max_prob, **prob_estimates_out;
max_num_pixel = (long)floor(memory_pixel /((long)4 * Npolar));
for(i=0; i< n_img_pixel; i++){// We initiaite the output classification file with '0' value
fwrite(&zero, sizeof(float), 1, output);
}
rewind(output);
/* for(i=0; i< n_img_pixel*(nr_class*(nr_class-1)/2 +1) ; i++){// We initiaite the output classification file with '0' value
fwrite(&zero, sizeof(float), 1, output_w2);
}
rewind(output_w2);
*/
if(predict_probability)
{
printf("Predict prob!!!!\n");
for(i=0; i< n_img_pixel*(nr_class + 1) ; i++){// We initiaite the output classification file with '0' value
fwrite(&zero, sizeof(float), 1, output_prob);
}
rewind(output_prob);
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
printf("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model));
else
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
//fprintf(output,"labels");
//for(j=0;j<nr_class;j++)
// printf(" %d\n",labels[j]);
//fprintf(output," %d",labels[j]);
//fprintf(output,"\n");
free(labels);
}
}
while(fread(&buff_long_int, sizeof(long int), 1, addr)!=0){ // We read the addr file to know the number of pixel to be classified
n_addr++;
}
n_addr = n_addr - Npolar;
rewind(addr);
tab_addr = (long int *) malloc((long int) (n_addr) * sizeof(long int));
for(i=0; i<Npolar;i++){
fread(&buff_long_int, sizeof(long int), 1, addr);
Nband[i] = (int)buff_long_int;
}
i=0;
while(fread(&tab_addr[i], sizeof(long int), 1, addr)!=0){ // We read the addr of each classified pixel
//hde
//printf("tab_addr[%d]:%d\n",i,tab_addr[i]);
i++;
}
//hde
int min,max;
min=tab_addr[0];
max=min;
for (i=0;i<n_addr;i++)
{
if (tab_addr[i]>max) {max=tab_addr[i];}
if (tab_addr[i]<min) {min=tab_addr[i];}
}
printf("min:%d; max:%d\n",min,max);
// fin HDE
// We compute the necessary number of block and remaining pixel
num_block = (int)floor(n_addr /max_num_pixel);
num_rest_pixel = n_addr - num_block * max_num_pixel;
printf("num_block: %i\n",num_block);
/////////////////////////////////////////////////Ajouter boucle de lecture des float input pour ensuite calculer le
//nb de bande total initial pour faire une lecutre par bloc de bande puis extraire celle qui sont interessante
while(fread(&buff_float, sizeof(float), 1, input)!=0){
m++;
}
rewind(input);
if(num_block > 0){//Loop on the block
V_pol_block = matrix_float((int)max_num_pixel,(int)Npolar);
output_label = vector_float((int)max_num_pixel);
// mean_dist = vector_float((int)max_num_pixel);
// w2_predict_out = matrix_float((int)max_num_pixel,nr_class*(nr_class-1)/2);
prob_estimates_out = matrix_float((int)max_num_pixel,nr_class);
max_prob = vector_float((int)max_num_pixel);
for (i=0; i<num_block; i++){ // blocs pour l'optimisation accès disque
for (j=0; j< max_num_pixel; j++){
for (k=0; k<Npolar; k++){
// pointe sur le pixel col,lig, k(bande), selon la bande
offset = (long)(sizeof(float)) * (Nband[k] * n_img_pixel + tab_addr[i*max_num_pixel + j]);
fseek(input, offset, SEEK_SET); //place le pointeur à l'offset calculé avant qui s'appelle offset !
fread(&V_pol_block[j][k], sizeof(float), 1, input);
}
}
for (j=0; j< max_num_pixel; j++){
for (k=0; k<Npolar; k++){
if(k>=max_nr_attr-1) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
}
x[k].index = k+1;
x[k].value = scale(k, (double)V_pol_block[j][k]);
}
x[k].index = -1;
double predict_label;
if (predict_probability && (svm_type==C_SVC || svm_type==NU_SVC))
{
//printf("Predict prob if block!!!!\n");
predict_label = svm_predict_probability(model,x,prob_estimates);
w2_predict = svm_w2(model,x);
output_label[j] = (float)predict_label;
// mean_dist[j] = 0.;
count = 0;
l=0;
max_prob[j] = 0.;
for(p=0;p<nr_class;p++){
for(n=p+1;n<nr_class;n++){
// w2_predict_out[j][l] =(float)w2_predict[l];
// printf("w2_predict[%i] : %g\n",w2_predict[l]);
if(p+1 == output_label[j] || n+1 == output_label[j]){
// mean_dist[j] = mean_dist[j] + w2_predict_out[j][l];
count = count + 1;
}
l++;
}
prob_estimates_out[j][p] = (float)prob_estimates[p];
if(max_prob[j] < prob_estimates_out[j][p] ){
max_prob[j] = prob_estimates_out[j][p];
}
}
// mean_dist[j] = mean_dist[j] / (float)count;
}
else
{
predict_label = svm_predict(model,x);
w2_predict = svm_w2(model,x);
output_label[j] = (float)predict_label;
// mean_dist[j] = 0.;
count = 0;
l=0;
for(p=0;p<nr_class;p++){
for(n=p+1;n<nr_class;n++){
// w2_predict_out[j][l] =(float)w2_predict[l];
if(p+1 == output_label[j] || n+1 == output_label[j]){
// mean_dist[j] = mean_dist[j] + w2_predict_out[j][l];
count = count + 1;
}
l++;
}
}
// mean_dist[j] = mean_dist[j] / (float)count;
}
}/* pixels block */
for (j=0; j< max_num_pixel; j++){ // On ecrit le fichier de classif
offset = (long)(sizeof(float)) * tab_addr[i*max_num_pixel + j];
fseek (output, offset, SEEK_SET);
fwrite(&output_label[j], sizeof(float), 1, output);
}
/* for (l=0; l< nr_class*(nr_class-1)/2; l++){ // On ecrit les cartes de distances
for (j=0; j< max_num_pixel; j++){
offset = (long)(sizeof(float)) * tab_addr[i*max_num_pixel + j];
fseek(output_w2, offset + n_img_pixel * sizeof(float) * l, SEEK_SET);
fwrite(&w2_predict_out[j][l], sizeof(float), 1, output_w2);
}
}
for (j=0; j< max_num_pixel; j++){ // On ecrit la distance moyenne
offset = (long)(sizeof(float)) * tab_addr[i*max_num_pixel + j];
fseek(output_w2, offset + n_img_pixel * sizeof(float) * (nr_class*(nr_class-1)/2), SEEK_SET);// on ecrit la distance moyenne parmi les classif bianaire renvoyant le label final
fwrite(&mean_dist[j], sizeof(float), 1, output_w2);
}
*/
if(predict_probability){
//printf("Predict prob fin if block ecriture!!!!\n");
for (l=0; l< nr_class; l++){ // On ecrit les cartes de probabilité
for (j=0; j< max_num_pixel; j++){
offset = (long)(sizeof(float)) * tab_addr[i*max_num_pixel + j];
fseek(output_prob, offset + n_img_pixel * sizeof(float) * l, SEEK_SET);
fwrite(&prob_estimates_out[j][l], sizeof(float), 1, output_prob);
}
}
for (j=0; j< max_num_pixel; j++){
offset = (long)(sizeof(float)) * tab_addr[i*max_num_pixel + j];
fseek(output_prob, offset + n_img_pixel * sizeof(float) * nr_class, SEEK_SET);
fwrite(&max_prob[j], sizeof(float), 1, output_prob);
}
}
}/* Loop over the blocks*/
free_matrix_float(V_pol_block, max_num_pixel);
// free_matrix_float(w2_predict_out, max_num_pixel);
free_matrix_float(prob_estimates_out, max_num_pixel);
free_vector_float(output_label);
// free_vector_float(mean_dist);
free(w2_predict);
free_vector_float(max_prob);
printf("FREE block: %i\n",num_block);
}else{
printf("PAS DE BLOCK\n");
}
if(num_rest_pixel > 0){// Loop on the remaining pixel
V_pol_rest = matrix_float((int)num_rest_pixel,(int)Npolar);/* Vector of polarimetrics indicators for the remaining pixel */
output_label = vector_float((int)num_rest_pixel);
// w2_predict_out = matrix_float((int)num_rest_pixel,nr_class*(nr_class-1)/2);
// mean_dist = vector_float((int)num_rest_pixel);
prob_estimates_out = matrix_float((int)num_rest_pixel,nr_class);
max_prob = vector_float((int)max_num_pixel);
for (j=0; j< num_rest_pixel;j++){
for (k=0; k<Npolar; k++){
offset = (long)(sizeof(float)) * (Nband[k] * n_img_pixel + tab_addr[num_block*max_num_pixel + j]);
fseek (input, offset , SEEK_SET);
fread(&V_pol_rest[j][k], sizeof(float), 1, input);
//hde
//printf("valeur pixel a adresse %d et pour bande %d: %d\n", tab_addr[num_block*max_num_pixel + j],k,V_pol_rest[j][k]);
}
}
for (j=0; j< num_rest_pixel;j++){
for (k=0; k<Npolar; k++){
if(k>=max_nr_attr-1) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
}
x[k].index = k+1;
x[k].value = scale(k, (double)V_pol_rest[j][k]);
}
x[k].index = -1;
double predict_label;
if (predict_probability && (svm_type==C_SVC || svm_type==NU_SVC))
{
//printf("Predict prob if fin apres block!!!!\n");
predict_label = svm_predict_probability(model,x,prob_estimates);
w2_predict = svm_w2(model,x);
output_label[j] = (float)predict_label;
// mean_dist[j] = 0.;
count = 0;
l=0;
max_prob[j] = 0.;
for(p=0;p<nr_class;p++){
for(n=p+1;n<nr_class;n++){
// w2_predict_out[j][l] =(float)w2_predict[l];
// printf("w2_predict[%i] : %g\n",l,w2_predict[l]);
// printf("w2_predict_out[%i][%i] : %g\n",j,l,w2_predict_out[j][l]);
if(p+1 == output_label[j] || n+1 == output_label[j]){
// mean_dist[j] = mean_dist[j] + w2_predict_out[j][l];
count = count + 1;
}
l++;
}
prob_estimates_out[j][p] = (float)prob_estimates[p];
if(max_prob[j] < prob_estimates_out[j][p] ){
max_prob[j] = prob_estimates_out[j][p];
}
}
// mean_dist[j] = mean_dist[j] / (float)count;
//printf("mean_dist[%i],%f\n",j,mean_dist[j]);
}
else
{
predict_label = svm_predict(model,x);
w2_predict = svm_w2(model,x);
output_label[j] = (float)predict_label;
// mean_dist[j] = 0.;
count = 0;
l=0;
for(p=0;p<nr_class;p++){
for(n=p+1;n<nr_class;n++){
// w2_predict_out[j][l] =(float)w2_predict[l];
if(p+1 == output_label[j] || n+1 == output_label[j]){
// mean_dist[j] = mean_dist[j] + w2_predict_out[j][l];
count = count + 1;
}
l++;
}
}
// mean_dist[j] = mean_dist[j] / (float)count;
}
}
for (j=0; j< num_rest_pixel; j++){
offset = (long)(sizeof(float)) * (tab_addr[num_block*max_num_pixel + j]);
fseek (output, offset, SEEK_SET);
fwrite(&output_label[j], sizeof(float), 1, output);
}
/* for (l=0; l< nr_class*(nr_class-1)/2; l++){
for (j=0; j< num_rest_pixel; j++){
offset = (long)(sizeof(float)) * (tab_addr[num_block*max_num_pixel + j]);
fseek(output_w2, offset + n_img_pixel * sizeof(float) * l, SEEK_SET);
fwrite(&w2_predict_out[j][l], sizeof(float), 1, output_w2);
}
}
for (j=0; j< num_rest_pixel; j++){
offset = (long)(sizeof(float)) * (tab_addr[num_block*max_num_pixel + j]);
fseek(output_w2, offset + n_img_pixel * sizeof(float) * (nr_class*(nr_class-1)/2), SEEK_SET);// on ecrit la distance moyenne parmi les classif bianaire renvoyant le label final
fwrite(&mean_dist[j], sizeof(float), 1, output_w2);
}
*/
if(predict_probability){
//printf("Predict prob if fin apres blockeCRITUR!!!!!!!\n");
for (l=0; l< nr_class; l++){ // On ecrit les cartes de probabilité
for (j=0; j< num_rest_pixel; j++){
offset = (long)(sizeof(float)) * (tab_addr[num_block*max_num_pixel + j]);
fseek(output_prob, offset + n_img_pixel * sizeof(float) * l, SEEK_SET);
fwrite(&prob_estimates_out[j][l], sizeof(float), 1, output_prob);
//printf("prob_estimates_out[%i][%i] : %f\n", j, l, prob_estimates_out[j][l]);
}
}
for (j=0; j< num_rest_pixel; j++){
offset = (long)(sizeof(float)) * (tab_addr[num_block*max_num_pixel + j]);
fseek(output_prob, offset + n_img_pixel * sizeof(float) * nr_class, SEEK_SET);
fwrite(&max_prob[j], sizeof(float), 1, output_prob);
}
}
free_matrix_float(V_pol_rest, num_rest_pixel);
// free_matrix_float(w2_predict_out, num_rest_pixel);
free_matrix_float(prob_estimates_out, num_rest_pixel);
free_vector_float(output_label);
free(w2_predict);
// free_vector_float(mean_dist);
free_vector_float(max_prob);
}/* remaning pixel */
free(tab_addr);
if(predict_probability)
free(prob_estimates);
}
JNIEXPORT jint JNICALL Java_LibSVMTest_doClassificationNative
(JNIEnv *env, jobject obj, jobjectArray valuesArr,
jobjectArray indicesArr, jint isProb, jintArray labelsArr, jdoubleArray probsArr) {
int *labels = env->GetIntArrayElements(labelsArr, NULL);
// initiate the arrays
int nRow = env->GetArrayLength(valuesArr);
double **probs = (double **) calloc(nRow, sizeof(double *));
jfloatArray vrows = (jfloatArray) env->GetObjectArrayElement(valuesArr, 0);
jintArray irows = (jintArray) env->GetObjectArrayElement(indicesArr, 0);
jfloat *velement = env->GetFloatArrayElements(vrows, NULL);
jint *ielement = env->GetIntArrayElements(irows, NULL);
int colNum = env->GetArrayLength(vrows);
probs[0] = env->GetDoubleArrayElements(probsArr, NULL);
if(isProb)
{
if(svm_check_probability_model(model_F)==0)
{
fprintf(stderr, "Model does not support probabiliy estimates\n");
exit(1);
}
}
else
{
if(svm_check_probability_model(model_F)!=0)
fprintf(stderr, "Model supports probability estimates, but disabled in prediction.\n");
}
if(isProb)
{
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
fprintf(stderr, "Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model_F));
else
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model_F,labels);
}
}
double predict_label=0;
struct svm_node *x = (struct svm_node *) malloc(64*sizeof(struct svm_node));
x = (struct svm_node *) realloc(x, (colNum+1)*sizeof(struct svm_node));
for (int j = 0; j < colNum; j++)
{
x[j].index = velement[j];
x[j].value = ielement[j];
}
x[colNum].index = -1;
// Probability prediction
if (isProb && (svm_type==C_SVC || svm_type==NU_SVC))
{
predict_label = svm_predict_probability(model_F,x,*probs);
labels[0]=predict_label;
}
else { labels[0] = svm_predict(model_F,x);}
env->ReleaseFloatArrayElements(vrows, velement, JNI_ABORT);
env->ReleaseIntArrayElements(irows, ielement, JNI_ABORT);
//added for fixing : JNI ERROR (app bug): local reference table overflow (max=512)
env->DeleteLocalRef(vrows);
env->DeleteLocalRef(irows);
// release the one-D arrays and strings
env->ReleaseIntArrayElements(labelsArr, labels, 0);
//added for fixing : JNI ERROR (app bug): local reference table overflow (max=512)
env->DeleteLocalRef(labelsArr);
free(x);
return 0;
}
void predict(FILE *input, FILE *output)
{
int correct = 0;
int total = 0;
double error = 0, brier_score = 0, log_likelihood = 0;
double sumv = 0, sumy = 0, sumvv = 0, sumyy = 0, sumvy = 0;
int svm_type=svm_get_svm_type(model);
int nr_class=svm_get_nr_class(model);
int *labels=(int *) malloc(nr_class*sizeof(int));
double *prob_estimates=NULL;
int j;
if(predict_probability)
{
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
printf("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model));
else
{
svm_get_labels(model,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
}
}
while(1)
{
int i = 0;
int c;
double target,v;
if (fscanf(input,"%lf",&target)==EOF)
break;
while(1)
{
if(i>=max_nr_attr-1) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
}
do {
c = getc(input);
if(c=='\n' || c==EOF) goto out2;
} while(isspace(c));
ungetc(c,input);
fscanf(input,"%d:%lf",&x[i].index,&x[i].value);
++i;
}
out2:
x[i++].index = -1;
if (predict_probability && (svm_type==C_SVC || svm_type==NU_SVC))
{
v = svm_predict_probability(model,x,prob_estimates, predict_probability);
fprintf(output,"%g ",v);
for(j=0;j<nr_class;j++)
fprintf(output,"%g ",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
v = svm_predict(model,x);
fprintf(output,"%g\n",v);
}
if(v == target)
++correct;
error += (v-target)*(v-target);
sumv += v;
sumy += target;
sumvv += v*v;
sumyy += target*target;
sumvy += v*target;
++total;
//Brier Score and log likelihood
if (predict_probability && (svm_type==C_SVC || svm_type==NU_SVC))
{
int j;
double bscore=0;
for( j=0; j<nr_class && target != labels[j]; j++)
;
if(j < nr_class)
{
for(int i=0; i<nr_class; i++)
bscore += prob_estimates[i]*prob_estimates[i];
bscore = (bscore - 2 * prob_estimates[j] + 1)/nr_class;
brier_score += bscore;
log_likelihood += log(prob_estimates[j]);
}
}
}
printf("Accuracy = %g%% (%d/%d) (classification)\n",
(double)correct/total*100,correct,total);
printf("Mean squared error = %g (regression)\n",error/total);
printf("Squared correlation coefficient = %g (regression)\n",
((total*sumvy-sumv*sumy)*(total*sumvy-sumv*sumy))/
((total*sumvv-sumv*sumv)*(total*sumyy-sumy*sumy))
);
if(predict_probability)
{
printf("Brier score = %g\n", brier_score/total);
printf("Normalized log likelihood = %g\n", log_likelihood/total);
free(prob_estimates);
free(labels);
}
}
int SVM::test(char* data_filename, char* filename_model, double &dTestError)
{
int correct = 0;
int total = 0;
double error = 0;
double sump = 0, sumt = 0, sumpp = 0, sumtt = 0, sumpt = 0;
struct svm_model* svmModel;
int svm_type;
int nr_class;
double *prob_estimates=NULL;
FILE *fInputTestData = NULL;
int max_line_len = 0;
char *line = NULL;
int max_nr_attr = 64;
struct svm_node *x = NULL;
fInputTestData = fopen(data_filename,"r");
if(fInputTestData == NULL)
{
fprintf(stderr,"can't open input file %s\n",data_filename);
return -1;
}
if((svmModel=svm_load_model(filename_model))==0)
{
fprintf(stderr,"can't open model file %s\n",filename_model);
return -3;
}
svm_type=svm_get_svm_type(svmModel);
nr_class=svm_get_nr_class(svmModel);
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
printf("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(svmModel));
else
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(svmModel,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
//printf("labels");
//for(j=0;j<nr_class;j++)
//printf(" %d",labels[j]);
//printf("\n");
free(labels);
}
max_line_len = 1024;
while((line = this->read_line(fInputTestData, max_line_len)) != NULL)
{
int i = 0;
double target_label, predict_label;
char *idx, *val, *label, *endptr;
int inst_max_index = -1; // strtol gives 0 if wrong format, and precomputed kernel has <index> start from 0
label = strtok(line," \t");
target_label = strtod(label,&endptr);
if(endptr == label)
{
fprintf(stderr,"Wrong input format at line %d\n", total+1);
return -2;
}
x = (struct svm_node *) malloc(max_nr_attr*sizeof(struct svm_node));
while(1)
{
if(i>=max_nr_attr-1) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
}
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
break;
errno = 0;
x[i].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x[i].index <= inst_max_index)
{
fprintf(stderr,"Wrong input format at line %d\n", total+1);
return -2;
}
else
inst_max_index = x[i].index;
errno = 0;
x[i].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
{
fprintf(stderr,"Wrong input format at line %d\n", total+1);
return -2;
}
++i;
}
x[i].index = -1;
if (svm_type==C_SVC || svm_type==NU_SVC)
{
predict_label = svm_predict_probability(svmModel,x,prob_estimates);
//printf("%g",predict_label);
//for(j=0;j<nr_class;j++)
// printf(" %g",prob_estimates[j]);
//printf("\n");
}
else
{
predict_label = svm_predict(svmModel,x);
// printf("%g\n",predict_label);
}
if(predict_label == target_label)
++correct;
error += (predict_label-target_label)*(predict_label-target_label);
sump += predict_label;
sumt += target_label;
sumpp += predict_label*predict_label;
sumtt += target_label*target_label;
sumpt += predict_label*target_label;
++total;
free(line);
free(x);
}
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
{
printf("Mean squared error = %g (regression)\n",error/total);
printf("Squared correlation coefficient = %g (regression)\n",
((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
);
}
else
{
printf("Classification Accuracy = %g%% (%d/%d)\n",
(double)correct/total*100,correct,total);
}
dTestError = 1-((double)correct/(double)total);
fclose(fInputTestData);
free(prob_estimates);
svm_destroy_model(svmModel);
return 0;
}
v8::Local<v8::Object> SVMPredict::predict_single (
const struct svm_model* m,
const struct svm_node* p,
v8::Local<v8::Value> id,
int nr) {
#if defined(PROCESS_DEBUG)
log("is called.");
#endif
if (m==NULL) {
std::cerr<<"The model variable is NULL\n";
}
if (p == NULL) {
std::cerr<<"The query vector variable is NULL\n";
}
//
v8::Isolate* isolate = GetIsolate();//v8::Isolate::GetCurrent();
// v8::HandleScope scope(isolate);
// v8::Local<v8::Context> context =
// v8::Local<v8::Context>::New(isolate,context_);
// v8::Context::Scope context_scop(context);
v8::Local<v8::Object> Result = v8::Object::New(isolate);
double dec_values = std::numeric_limits<double>::infinity();
double pred_result = std::numeric_limits<double>::infinity();
double *probab_estimate = (double *) malloc(nr*sizeof(double));
int *labels=(int *) malloc(nr*sizeof(int));
svm_get_labels(this->model,labels);
#if defined(PROCESS_DEBUG)
// CW_ASSERT(m==NULL);
// CW_ASSERT(p==NULL);
log(" Ready to call local function predict");
#endif
//this->predict(m,p,&dec_values,&pred_result);
//this->print_node(p);
pred_result = svm_predict_values(m, p, &dec_values);
Result->Set(v8::String::NewFromUtf8(isolate, "id"),id);
Result->Set(v8::String::NewFromUtf8(isolate, "dec_val"),ToV8<double>(dec_values));
Result->Set(v8::String::NewFromUtf8(isolate, "predict"),ToV8<double>(pred_result));
if (this->predict_probability) {
#if defined(PROCESS_DEBUG)
//CW_ASSERT(m==NULL);
//CW_ASSERT(p==NULL);
log(" Ready to call local function predict_prob");
#endif
this->predict_prob(m, p, &pred_result, probab_estimate);
//pred_result = svm_predict_probability(this->model,p,probab_estimate);
v8::Local<v8::Object> prob = v8::Object::New(isolate);
for(int i=0;i<nr;i++){
std::string cl = _toString<int>(labels[i],std::dec);
prob->Set(v8::String::NewFromUtf8(isolate, cl.c_str()),ToV8<double>(probab_estimate[i]));
}
Result->Set(v8::String::NewFromUtf8(isolate, "probability"),prob);
}
return Result;
}
void predict(FILE *input, FILE *output)
{
int correct = 0;
int total = 0;
double error = 0;
double sump = 0, sumt = 0, sumpp = 0, sumtt = 0, sumpt = 0;
int svm_type=svm_get_svm_type(model);
int nr_class=svm_get_nr_class(model);
double *prob_estimates=NULL;
int j;
// This block by Jianxin Wu, for average accuracy computation
int ii,label_index;
// number of correct predictions in each category
int* correct_sub = (int *)malloc(nr_class*sizeof(int));
for(ii=0;ii<nr_class;ii++) correct_sub[ii] = 0;
// number of testing examples in each category
int* total_sub = (int *)malloc(nr_class*sizeof(int));
for(ii=0;ii<nr_class;ii++) total_sub[ii] = 0;
int* labels_avg = (int*)malloc(nr_class*sizeof(int));
svm_get_labels(model,labels_avg);
if(predict_probability)
{
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
printf("Prob. model for test data: target value = predicted value + z,\nz: Laplace distribution e^(-|z|/sigma)/(2sigma),sigma=%g\n",svm_get_svr_probability(model));
else
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
free(labels);
}
}
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
while(readline(input) != NULL)
{
int i = 0;
double target_label, predict_label;
char *idx, *val, *label, *endptr;
int inst_max_index = -1; // strtol gives 0 if wrong format, and precomputed kernel has <index> start from 0
label = strtok(line," \t");
target_label = strtod(label,&endptr);
if(endptr == label)
exit_input_error(total+1);
while(1)
{
if(i>=max_nr_attr-1) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct svm_node *) realloc(x,max_nr_attr*sizeof(struct svm_node));
}
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
break;
errno = 0;
x[i].index = (int) strtol(idx,&endptr,10);
if(endptr == idx || errno != 0 || *endptr != '\0' || x[i].index <= inst_max_index)
exit_input_error(total+1);
else
inst_max_index = x[i].index;
errno = 0;
x[i].value = strtod(val,&endptr);
if(endptr == val || errno != 0 || (*endptr != '\0' && !isspace(*endptr)))
exit_input_error(total+1);
++i;
}
x[i].index = -1;
if (predict_probability && (svm_type==C_SVC || svm_type==NU_SVC))
{
predict_label = svm_predict_probability(model,x,prob_estimates);
fprintf(output,"%g",predict_label);
for(j=0;j<nr_class;j++)
fprintf(output," %g",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
predict_label = svm_predict(model,x);
fprintf(output,"%g\n",predict_label);
}
// This block by Jianxin Wu, for average accuracy
label_index = FindLabel((int)target_label,labels_avg);
total_sub[label_index]++;
if(predict_label == target_label) correct_sub[label_index]++;
if(predict_label == target_label)
++correct;
error += (predict_label-target_label)*(predict_label-target_label);
sump += predict_label;
sumt += target_label;
sumpp += predict_label*predict_label;
sumtt += target_label*target_label;
sumpt += predict_label*target_label;
++total;
}
if (svm_type==NU_SVR || svm_type==EPSILON_SVR)
{
printf("Mean squared error = %g (regression)\n",error/total);
printf("Squared correlation coefficient = %g (regression)\n",
((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
);
}
else
printf("Accuracy = %g%% (%d/%d) (classification)\n",
(double)correct/total*100,correct,total);
if(predict_probability)
free(prob_estimates);
// This block (till endo of function) by Jianxin WU
// Print per-category accuracy and average accuracy of categories
double sub_score = 0;
int nonempty_category = 0;
for(ii=0;ii<nr_class;ii++)
{
if(total_sub[ii]>0)
{
sub_score += (correct_sub[ii]*1.0/total_sub[ii]);
nonempty_category++;
}
}
printf("-----------\n");
for(ii=0;ii<nr_class;ii++)
{
printf("%d / %d (Category %d)\n",correct_sub[ii],total_sub[ii],labels_avg[ii]);
}
printf("-----------\n");
printf("Mean Accuray across classes = %g%%\n",sub_score*100.0/nonempty_category);
free(correct_sub);
free(total_sub);
free(labels_avg);
}
int predict(FILE *input , FILE *output)
{
int correct =0;
int total = 0;
int error = 0;
double sump = 0, sumt = 0, sumpt = 0, sumpp = 0, sumtt = 0;
int svm_type=svm_get_svm_type(model);
int nr_class=svm_get_nr_class(model);
double *prob_estimate = NULL;
int j;
if(predict_probability)
{
int *labels=(int *) malloc(nr_class*sizeof(int));
svm_get_labels(model,labels);
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
free(labels);
}
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
while(readline(input) != NULL)
{
int i =0;
double target_label, predict_label,idVal;
char *idx, *val, *label, *endptr;
int inst_max_index = -1;
label = strtok(line, " \t\n");
if(label == NULL)
{
exit_input_error_predict(total+1);
}
target_label = strtod(label, &endptr);
//if(*endptr =='\0')
if(endptr == label|| *endptr !='\0')
{
exit_input_error_predict(total +1);
}
while(1)
{
if(i >= max_nr_attr-1)
{
max_nr_attr *=2;
x =(struct svm_node *) realloc(x, max_nr_attr*sizeof(struct svm_node));
}
//LOGD("line = %s ",line);
//idVal = strtod(line,&endptr);
//LOGD("endptr = %s", endptr);
idx = strtok(NULL,":");
val = strtok(NULL," \t");
if(val == NULL)
{
break;
}
errno = 0;
x[i].index = (int) strtol(idx,&endptr,10);
//if(endptr ==idx ||errno !=0 || *endptr =='\0'||x[i].index <=inst_max_index)
if(endptr ==idx ||errno !=0 || *endptr !='\0'||x[i].index <=inst_max_index)
{
exit_input_error_predict(total +1);
}
else
{
inst_max_index = x[i].index;
}
errno = 0;
x[i].value = strtod(val, &endptr);
//if(endptr == val || errno !=0||(*endptr =='\0'&& !isspace(*endptr)))
if(endptr == val || errno !=0||(*endptr !='\0'&& !isspace(*endptr)))
{
exit_input_error_predict(total +1);
}
++i;
}
x[i].index = -1;
if(predict_probability &&(svm_type == C_SVC || svm_type == NU_SVC))
{
predict_label = svm_predict_probability(model, x, prob_estimate);
fprintf(output,"%g", predict_label);
for (j = 0; j < nr_class; j++)
{
fprintf(output,"%g",prob_estimate[j]);
}
fprintf(output,"\n");
}
else
{
//LOGD(" CAI DECK");
predict_label = svm_predict(model,x);
fprintf(output,"%g\n",predict_label);
}
if(predict_label == target_label)
{
++correct;
}
error +=(predict_label - target_label)*(predict_label - target_label);
sump += predict_label;
sumt +=target_label;
sumpp += predict_label*predict_label;
sumtt += target_label*target_label;
sumpt += predict_label * target_label;
++total;
}
if(predict_probability)
free(prob_estimate);
}
