// return classification error and the normalized difference between predicted and true sentiment
std::pair<double, double> do_predict(const struct problem *test_prob, struct model* model_)
{
double acc = 0;
double clse=0;
int total = 0;
double *prob_estimates=NULL;
int *labels=NULL;
int nr_class=get_nr_class(model_);
if(flag_predict_probability)
{
if(!check_probability_model(model_))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
labels=(int *) malloc(nr_class*sizeof(int));
get_labels(model_,labels);
prob_estimates = (double *) malloc(nr_class*sizeof(double));
}
int l = test_prob->l;
int i = 0;
for(i=0; i<l; i++)
{
int predict_label = 0;
int target_label=test_prob->y[i];
feature_node *xi = test_prob->x[i];
if(flag_predict_probability)
{
int j;
predict_label = predict_probability(model_,xi,prob_estimates);
double predict_score=0;
for(j=0;j<model_->nr_class;j++)
predict_score+=prob_estimates[j]*labels[j];
//double acc_max= fabs(target_label-3)+2;
//acc+=(acc_max-sqrt((predict_score - target_label)*(predict_score - target_label)))/acc_max;
acc += (predict_score - target_label) * (predict_score - target_label);
if (predict_label!=target_label)
clse++;
}
else
{
predict_label = predict(model_,xi);
//double acc_max= fabs(target_label-3)+2;
//acc+=(acc_max-sqrt((predict_label - target_label)*(predict_label - target_label)))/acc_max;
acc += (predict_label - target_label) * (predict_label - target_label);
if (predict_label!=target_label)
clse++;
}
++total;
}
if(flag_predict_probability)
{
free(prob_estimates);
free(labels);
}
//printf("Error = %g%% (%d/%d)\n",(double) (total-correct)/total*100,total-correct,total);
return std::make_pair(clse/total,acc/total) ;
}
bool QPredictLinearLearner::predict(QPredictDocument &doc)
{
QPredictFeatureList &feature_list = doc.feature_list;
int num_space = feature_list.size();
num_space++;
num_space++; // for bias
struct feature_node *x_space = new struct feature_node[num_space];
int nr_feature = get_nr_feature(m_model);
int n;
if (m_model->bias >= 0)
n = nr_feature + 1;
else
n = nr_feature;
sort(feature_list.begin(), feature_list.end(), QPredictFeature::feature_compare);
const QPredictFeatureListIter &feature_end_it = feature_list.end();
int j = 0;
for (QPredictFeatureListIter feature_it = feature_list.begin(); feature_it != feature_end_it; ++feature_it) {
x_space[j].index = feature_it->id;
x_space[j].value = feature_it->value;
++j;
}
if(m_model->bias >= 0) {
x_space[j].index = n;
x_space[j].value = m_model->bias;
++j;
}
x_space[j].index = -1;
x_space[j].value = -1;
if (check_probability_model(m_model)) {
doc.predict_class_index = static_cast<uint32_t>(
::predict_probability(m_model, x_space, doc.predict_class_probs)
);
} else {
doc.predict_class_index = static_cast<uint32_t>(
::predict(m_model, x_space)
);
}
delete []x_space;
return true;
}
double LVlinear_predict_probability(lvError *lvErr, const LVlinear_model *model_in, const LVArray_Hdl<LVlinear_node> x_in, LVArray_Hdl<double> prob_estimates_out){
try{
// Input validation: Uninitialized model
if (model_in == nullptr || model_in->w == nullptr || (*model_in->w)->dimSize == 0)
throw LVException(__FILE__, __LINE__, "Uninitialized model passed to liblinear_predict_probability.");
// Input validation: Empty feature vector
if (x_in == nullptr || (*x_in)->dimSize == 0)
throw LVException(__FILE__, __LINE__, "Empty feature vector passed to liblinear_predict_probability.");
// Input validation: Final index -1?
if ((*x_in)->elt[(*x_in)->dimSize - 1].index != -1)
throw LVException(__FILE__, __LINE__, "The index of the last element of the feature vector needs to be -1 (liblinear_predict_probability).");
// Convert LVsvm_model to svm_model
auto mdl = std::make_unique<model>();
LVConvertModel(*model_in, *mdl);
// Check probability model
int valid_probability = check_probability_model(mdl.get());
if (!valid_probability)
throw LVException(__FILE__, __LINE__, "The selected solver type does not support probability output.");
// Allocate room for probability estimates
LVResizeNumericArrayHandle(prob_estimates_out, mdl->nr_class);
(*prob_estimates_out)->dimSize = mdl->nr_class;
double highest_prob_label = predict_probability(mdl.get(), reinterpret_cast<feature_node*>((*x_in)->elt), (*prob_estimates_out)->elt);
return highest_prob_label;
}
catch (LVException &ex) {
ex.returnError(lvErr);
(*prob_estimates_out)->dimSize = 0;
return std::nan("");
}
catch (std::exception &ex) {
LVException::returnStdException(lvErr, __FILE__, __LINE__, ex);
(*prob_estimates_out)->dimSize = 0;
return std::nan("");
}
catch (...) {
LVException ex(__FILE__, __LINE__, "Unknown exception has occurred");
ex.returnError(lvErr);
(*prob_estimates_out)->dimSize = 0;
return std::nan("");
}
}
double LVlinear_predict_probability(lvError *lvErr, const LVlinear_model *model_in, const LVArray_Hdl<LVlinear_node> x_in, LVArray_Hdl<double> prob_estimates_out){
try{
// Convert LVsvm_model to svm_model
std::unique_ptr<model> model(new model);
LVConvertModel(model_in, model.get());
// Check probability model
int valid_probability = check_probability_model(model.get());
if (!valid_probability)
throw LVException(__FILE__, __LINE__, "The model does not support probability output.");
// Allocate room for probability estimates
LVResizeNumericArrayHandle(prob_estimates_out, model->nr_class);
(*prob_estimates_out)->dimSize = model->nr_class;
double highest_prob_label = predict_probability(model.get(), reinterpret_cast<feature_node*>((*x_in)->elt), (*prob_estimates_out)->elt);
return highest_prob_label;
}
catch (LVException &ex) {
ex.returnError(lvErr);
(*prob_estimates_out)->dimSize = 0;
return std::nan("");
}
catch (std::exception &ex) {
LVException::returnStdException(lvErr, __FILE__, __LINE__, ex);
(*prob_estimates_out)->dimSize = 0;
return std::nan("");
}
catch (...) {
LVException ex(__FILE__, __LINE__, "Unknown exception has occurred");
ex.returnError(lvErr);
(*prob_estimates_out)->dimSize = 0;
return std::nan("");
}
}
void do_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 nr_class=get_nr_class(model_);
double *prob_estimates=NULL;
int j, n;
int nr_feature=get_nr_feature(model_);
if(model_->bias>=0)
n=nr_feature+1;
else
n=nr_feature;
if(flag_predict_probability)
{
int *labels;
if(!check_probability_model(model_))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
labels=(int *) malloc(nr_class*sizeof(int));
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 = 0; // strtol gives 0 if wrong format
label = strtok(line," \t\n");
if(label == NULL) // empty line
exit_input_error(total+1);
target_label = strtod(label,&endptr);
if(endptr == label || *endptr != '\0')
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 feature_node *) realloc(x,max_nr_attr*sizeof(struct feature_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);
// feature indices larger than those in training are not used
if(x[i].index <= nr_feature)
++i;
}
if(model_->bias>=0)
{
x[i].index = n;
x[i].value = model_->bias;
i++;
}
x[i].index = -1;
if(model_->normal){
double length = 0;
for(int kk = 0; x[kk].index != -1; kk++)
length += x[kk].value * x[kk].value;
length = sqrt(length);
for(int kk = 0; x[kk].index != -1; kk++)
x[kk].value /= length;
}
if(flag_predict_probability)
{
int j;
predict_label = predict_probability(model_,x,prob_estimates);
fprintf(output,"%g",predict_label);
for(j=0;j<model_->nr_class;j++)
fprintf(output," %g",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
predict_label = 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(model_->param.solver_type==L2R_L2LOSS_SVR ||
model_->param.solver_type==L2R_L1LOSS_SVR_DUAL ||
model_->param.solver_type==L2R_L2LOSS_SVR_DUAL)
{
info("Mean squared error = %g (regression)\n",error/total);
info("Squared correlation coefficient = %g (regression)\n",
((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
);
}
else
info("Accuracy = %g%% (%d/%d)\n",(double) correct/total*100,correct,total);
if(flag_predict_probability)
free(prob_estimates);
}
void mexFunction( int nlhs, mxArray *plhs[],
int nrhs, const mxArray *prhs[] )
{
int prob_estimate_flag = 0;
struct model *model_;
char cmd[CMD_LEN];
col_format_flag = 0;
if(nrhs > 5 || nrhs < 3)
{
exit_with_help();
fake_answer(plhs);
return;
}
if(nrhs == 5)
{
mxGetString(prhs[4], cmd, mxGetN(prhs[4])+1);
if(strcmp(cmd, "col") == 0)
{
col_format_flag = 1;
}
}
if(!mxIsDouble(prhs[0]) || !mxIsDouble(prhs[1])) {
mexPrintf("Error: label vector and instance matrix must be double\n");
fake_answer(plhs);
return;
}
if(mxIsStruct(prhs[2]))
{
const char *error_msg;
// parse options
if(nrhs>=4)
{
int i, argc = 1;
char *argv[CMD_LEN/2];
// put options in argv[]
mxGetString(prhs[3], cmd, mxGetN(prhs[3]) + 1);
if((argv[argc] = strtok(cmd, " ")) != NULL)
while((argv[++argc] = strtok(NULL, " ")) != NULL)
;
for(i=1;i<argc;i++)
{
if(argv[i][0] != '-') break;
if(++i>=argc)
{
exit_with_help();
fake_answer(plhs);
return;
}
switch(argv[i-1][1])
{
case 'b':
prob_estimate_flag = atoi(argv[i]);
break;
default:
mexPrintf("unknown option\n");
exit_with_help();
fake_answer(plhs);
return;
}
}
}
model_ = Malloc(struct model, 1);
error_msg = matlab_matrix_to_model(model_, prhs[2]);
if(error_msg)
{
mexPrintf("Error: can't read model: %s\n", error_msg);
free_and_destroy_model(&model_);
fake_answer(plhs);
return;
}
if(prob_estimate_flag)
{
if(!check_probability_model(model_))
{
mexPrintf("probability output is only supported for logistic regression\n");
prob_estimate_flag=0;
}
}
if(mxIsSparse(prhs[1]))
do_predict(plhs, prhs, model_, prob_estimate_flag);
else
{
mexPrintf("Testing_instance_matrix must be sparse; "
"use sparse(Testing_instance_matrix) first\n");
fake_answer(plhs);
}
// destroy model_
free_and_destroy_model(&model_);
}
else
{
void do_predict(FILE *input, FILE *output, struct model* model_)
{
int correct = 0;
int total = 0;
int nr_class=get_nr_class(model_);
double *prob_estimates=NULL;
int j, n;
int nr_feature=get_nr_feature(model_);
if(model_->bias>=0)
n=nr_feature+1;
else
n=nr_feature;
if(flag_predict_probability)
{
int *labels;
if(!check_probability_model(model_))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
labels=(int *) malloc(nr_class*sizeof(int));
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;
int target_label, predict_label;
char *idx, *val, *label, *endptr;
int inst_max_index = 0; // strtol gives 0 if wrong format
label = strtok(line," \t");
target_label = (int) strtol(label,&endptr,10);
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 feature_node *) realloc(x,max_nr_attr*sizeof(struct feature_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);
// feature indices larger than those in training are not used
if(x[i].index <= nr_feature)
++i;
}
if(model_->bias>=0)
{
x[i].index = n;
x[i].value = model_->bias;
i++;
}
x[i].index = -1;
if(flag_predict_probability)
{
int j;
predict_label = predict_probability(model_,x,prob_estimates);
fprintf(output,"%d",predict_label);
for(j=0;j<model_->nr_class;j++)
fprintf(output," %g",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
predict_label = predict(model_,x);
fprintf(output,"%d\n",predict_label);
}
if(predict_label == target_label)
++correct;
++total;
}
printf("Accuracy = %g%% (%d/%d)\n",(double) correct/total*100,correct,total);
if(flag_predict_probability)
free(prob_estimates);
}
void do_predict(FILE *input, FILE *output)
{
int total = 0;
int nr_class=get_nr_class(model_);
double *prob_estimates=NULL;
int n;
int nr_feature=get_nr_feature(model_);
if(model_->bias>=0)
n=nr_feature+1;
else
n=nr_feature;
if(!check_probability_model(model_))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
prob_estimates = (double *) malloc(nr_class*sizeof(double));
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
int clicks = 0;
int shows = 0;
while(readline(input) != NULL)
{
int i = 0;
double target_ctr, predict_ctr;
char *idx, *val, *endptr;
int inst_max_index = 0; // strtol gives 0 if wrong format
char *p = strtok(line," \t\n"); //clicks
if(p == NULL) // empty line
exit_input_error(total+1);
clicks = atoi(p);
p = strtok(NULL," \t"); // shows
shows = atoi(p);
p = strtok(NULL," \t"); // qid:1
if (shows <=0 || clicks > shows) {
continue;
}
target_ctr = (double)clicks / shows;
while(1)
{
if(i>=max_nr_attr-2) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct feature_node *) realloc(x,max_nr_attr*sizeof(struct feature_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);
// feature indices larger than those in training are not used
if(x[i].index <= nr_feature)
++i;
}
if(model_->bias>=0)
{
x[i].index = n;
x[i].value = model_->bias;
i++;
}
x[i].index = -1;
predict_probability(model_,x,prob_estimates);
fprintf(output,"%d %d ", clicks, shows);
predict_ctr = prob_estimates[0];
fprintf(output," %g\n", predict_ctr);
}
info("total:%d\n",total);
free(prob_estimates);
}
void do_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 nr_class=get_nr_class(model_[0]);
double *prob_estimates=NULL;
int j, n;
int nr_feature=get_nr_feature(model_[0]);
if(model_[0]->bias>=0)
n=nr_feature+1;
else
n=nr_feature;
if(flag_predict_probability)
{
int *labels;
if(!check_probability_model(model_[0]))
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
exit(1);
}
labels=(int *) malloc(nr_class*sizeof(int));
get_labels(model_[0],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 = 0; // strtol gives 0 if wrong format
label = strtok(line," \t\n");
if(label == NULL) // empty line
exit_input_error(total+1);
// target_label = strtod(label,&endptr);
switch (label[0]) {
case 'A': target_label = 0; break;
case 'B': target_label = 1; break;
case 'C': target_label = 1; break;
case 'D': target_label = 1; break;
}
// if(endptr == label || *endptr != '\0')
// exit_input_error(total+1);
for (int pid = 0; pid < sum_pro; pid++) {
while(1)
{
if(i>=max_nr_attr-2) // need one more for index = -1
{
max_nr_attr *= 2;
x = (struct feature_node *) realloc(x,max_nr_attr*sizeof(struct feature_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);
// feature indices larger than those in training are not used
if(x[i].index <= nr_feature)
++i;
}
if(model_[pid]->bias>=0)
{
x[i].index = n;
x[i].value = model_[pid]->bias;
i++;
}
x[i].index = -1;
if(flag_predict_probability)
{
int j;
predict_label = predict_probability(model_[pid],x,prob_estimates);
fprintf(output,"%g",predict_label);
for(j=0;j<model_[pid]->nr_class;j++)
fprintf(output," %g",prob_estimates[j]);
fprintf(output,"\n");
}
else
{
p_label[pid] = predict(model_[pid],x);
fprintf(output,"%g", p_label[pid]);
// printf("pid%dhas done\n",pid );
}
fprintf(output, "\n" );
}
int count = 0;
predict_label = 0;
// for ( int l = 0; l < BLOCK ; l++) {
// for (int m = 0;m < BLOCK * N; m++) {
// // printf("%f\t", p_label[l * BLOCK + m]);
// if ( p_label[l * BLOCK + m] == 1) {
// // p_label[l] = 1;
// // break;
// p_label[l]++;
// // count++;* 4
// }
// }
// if (p_label[l] < 4) {
// count++;
// }
// // if ( p_label[l] == 1) {
// // predict_label = 1;
// // }
// // else {
// // predict_label = 0;
// // }
// // if (count >0) {
// // predict_label = 1;
// // }
// // else {
// // predict_label = 0;
// // }
// }
// if (count > 0 ) {
// predict_label = 0;
// }
// else {
// predict_label = 1;
// }
// /printf("\n");
// 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(check_regression_model(model_[0]))
// {
// info("Mean squared error = %g (regression)\n",error/total);
// info("Squared correlation coefficient = %g (regression)\n",
// ((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
// ((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
// );
// }
// else
// info("Accuracy = %g%% (%d/%d)\n",(double) correct/total*100,correct,total);
// if(flag_predict_probability)
// free(prob_estimates);
}