void do_predict(FILE *input, FILE *output)
{
std::vector<double> pred_values; //store decision values
std::vector<double> true_values; //store true values
int total = 0;
int nr_class = get_nr_class(model_);
int * labels = Malloc(int, nr_class);
get_labels(model_, labels);
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;
// not yet support multiclass
assert(nr_class==2);
//print out header...
if(output_option ==2) {
prob_estimates = Malloc(double, nr_class);
fprintf(output,"labels");
for(j=0;j<nr_class;j++)
fprintf(output," %d",labels[j]);
fprintf(output,"\n");
}
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;
}
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 do_predict(mxArray *plhs[], const mxArray *prhs[], struct model *model_, const int predict_probability_flag)
{
int label_vector_row_num, label_vector_col_num;
int feature_number, testing_instance_number;
int instance_index;
double *ptr_label, *ptr_predict_label;
double *ptr_prob_estimates, *ptr_dec_values, *ptr;
struct feature_node *x;
mxArray *pplhs[1]; // instance sparse matrix in row format
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_);
int nr_w;
double *prob_estimates=NULL;
if(nr_class==2 && model_->param.solver_type!=MCSVM_CS)
nr_w=1;
else
nr_w=nr_class;
// prhs[1] = testing instance matrix
feature_number = get_nr_feature(model_);
testing_instance_number = (int) mxGetM(prhs[1]);
if(col_format_flag)
{
feature_number = (int) mxGetM(prhs[1]);
testing_instance_number = (int) mxGetN(prhs[1]);
}
label_vector_row_num = (int) mxGetM(prhs[0]);
label_vector_col_num = (int) mxGetN(prhs[0]);
if(label_vector_row_num!=testing_instance_number)
{
mexPrintf("Length of label vector does not match # of instances.\n");
fake_answer(plhs);
return;
}
if(label_vector_col_num!=1)
{
mexPrintf("label (1st argument) should be a vector (# of column is 1).\n");
fake_answer(plhs);
return;
}
ptr_label = mxGetPr(prhs[0]);
// transpose instance matrix
if(col_format_flag)
pplhs[0] = (mxArray *)prhs[1];
else
{
mxArray *pprhs[1];
pprhs[0] = mxDuplicateArray(prhs[1]);
if(mexCallMATLAB(1, pplhs, 1, pprhs, "transpose"))
{
mexPrintf("Error: cannot transpose testing instance matrix\n");
fake_answer(plhs);
return;
}
}
prob_estimates = Malloc(double, nr_class);
plhs[0] = mxCreateDoubleMatrix(testing_instance_number, 1, mxREAL);
if(predict_probability_flag)
plhs[2] = mxCreateDoubleMatrix(testing_instance_number, nr_class, mxREAL);
else
plhs[2] = mxCreateDoubleMatrix(testing_instance_number, nr_w, mxREAL);
ptr_predict_label = mxGetPr(plhs[0]);
ptr_prob_estimates = mxGetPr(plhs[2]);
ptr_dec_values = mxGetPr(plhs[2]);
x = Malloc(struct feature_node, feature_number+2);
for(instance_index=0;instance_index<testing_instance_number;instance_index++)
{
int i;
double target_label, predict_label;
target_label = ptr_label[instance_index];
// prhs[1] and prhs[1]^T are sparse
read_sparse_instance(pplhs[0], instance_index, x, feature_number, model_->bias);
if(predict_probability_flag)
{
predict_label = predict_probability(model_, x, prob_estimates);
ptr_predict_label[instance_index] = predict_label;
for(i=0;i<nr_class;i++)
ptr_prob_estimates[instance_index + i * testing_instance_number] = prob_estimates[i];
}
else
{
double *dec_values = Malloc(double, nr_class);
predict_label = predict_values(model_, x, dec_values);
ptr_predict_label[instance_index] = predict_label;
for(i=0;i<nr_w;i++)
ptr_dec_values[instance_index + i * testing_instance_number] = dec_values[i];
free(dec_values);
}
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)
{
mexPrintf("Mean squared error = %g (regression)\n",error/total);
mexPrintf("Squared correlation coefficient = %g (regression)\n",
((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt))
);
}
//else
//mexPrintf("Accuracy = %g%% (%d/%d)\n", (double) correct/total*100,correct,total);
// return accuracy, mean squared error, squared correlation coefficient
plhs[1] = mxCreateDoubleMatrix(3, 1, mxREAL);
ptr = mxGetPr(plhs[1]);
ptr[0] = (double)correct/total*100;
ptr[1] = error/total;
ptr[2] = ((total*sumpt-sump*sumt)*(total*sumpt-sump*sumt))/
((total*sumpp-sump*sump)*(total*sumtt-sumt*sumt));
free(x);
if(prob_estimates != NULL)
free(prob_estimates);
}
int QPredictLinearLearner::num_of_features()
{
assert(m_model != NULL);
return get_nr_feature(m_model);
}
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(mxArray *plhs[], const mxArray *prhs[], struct model *model_, const int predict_probability_flag)
{
int label_vector_row_num, label_vector_col_num;
int feature_number, testing_instance_number;
int instance_index;
double *ptr_instance, *ptr_label, *ptr_predict_label;
double *ptr_prob_estimates, *ptr_dec_values, *ptr;
struct feature_node *x;
mxArray *pplhs[1]; // instance sparse matrix in row format
int correct = 0;
int total = 0;
int nr_class=get_nr_class(model_);
int nr_w;
double *prob_estimates=NULL;
if(nr_class==2 && model_->param.solver_type!=MCSVM_CS)
nr_w=1;
else
nr_w=nr_class;
// prhs[1] = testing instance matrix
feature_number = get_nr_feature(model_);
testing_instance_number = (int) mxGetM(prhs[1]);
if(col_format_flag)
{
feature_number = (int) mxGetM(prhs[1]);
testing_instance_number = (int) mxGetN(prhs[1]);
}
label_vector_row_num = (int) mxGetM(prhs[0]);
label_vector_col_num = (int) mxGetN(prhs[0]);
if(label_vector_row_num!=testing_instance_number)
{
mexPrintf("Length of label vector does not match # of instances.\n");
fake_answer(plhs);
return;
}
if(label_vector_col_num!=1)
{
mexPrintf("label (1st argument) should be a vector (# of column is 1).\n");
fake_answer(plhs);
return;
}
ptr_instance = mxGetPr(prhs[1]);
ptr_label = mxGetPr(prhs[0]);
// transpose instance matrix
if(mxIsSparse(prhs[1]))
{
if(col_format_flag)
{
pplhs[0] = (mxArray *)prhs[1];
}
else
{
mxArray *pprhs[1];
pprhs[0] = mxDuplicateArray(prhs[1]);
if(mexCallMATLAB(1, pplhs, 1, pprhs, "transpose"))
{
mexPrintf("Error: cannot transpose testing instance matrix\n");
fake_answer(plhs);
return;
}
}
}
else
mexPrintf("Testing_instance_matrix must be sparse\n");
prob_estimates = Malloc(double, nr_class);
plhs[0] = mxCreateDoubleMatrix(testing_instance_number, 1, mxREAL);
if(predict_probability_flag)
plhs[2] = mxCreateDoubleMatrix(testing_instance_number, nr_class, mxREAL);
else
plhs[2] = mxCreateDoubleMatrix(testing_instance_number, nr_w, mxREAL);
ptr_predict_label = mxGetPr(plhs[0]);
ptr_prob_estimates = mxGetPr(plhs[2]);
ptr_dec_values = mxGetPr(plhs[2]);
x = Malloc(struct feature_node, feature_number+2);
for(instance_index=0; instance_index<testing_instance_number; instance_index++)
{
int i;
double target,v;
target = ptr_label[instance_index];
// prhs[1] and prhs[1]^T are sparse
read_sparse_instance(pplhs[0], instance_index, x, feature_number, model_->bias);
if(predict_probability_flag)
{
v = predict_probability(model_, x, prob_estimates);
ptr_predict_label[instance_index] = v;
for(i=0; i<nr_class; i++)
ptr_prob_estimates[instance_index + i * testing_instance_number] = prob_estimates[i];
}
else
{
double *dec_values = Malloc(double, nr_class);
v = predict(model_, x);
ptr_predict_label[instance_index] = v;
predict_values(model_, x, dec_values);
for(i=0; i<nr_w; i++)
ptr_dec_values[instance_index + i * testing_instance_number] = dec_values[i];
free(dec_values);
}
if(v == target)
++correct;
++total;
}
mexPrintf("Accuracy = %g%% (%d/%d)\n", (double) correct/total*100,correct,total);
// return accuracy, mean squared error, squared correlation coefficient
plhs[1] = mxCreateDoubleMatrix(1, 1, mxREAL);
ptr = mxGetPr(plhs[1]);
ptr[0] = (double) correct/total*100;
free(x);
if(prob_estimates != NULL)
free(prob_estimates);
}
void binary_class_predict(FILE *input, FILE *output){
int total = 0;
int *labels;
int max_nr_attr = 64;
struct feature_node *x = Malloc(struct feature_node, max_nr_attr);
dvec_t dec_values;
ivec_t true_labels;
int n;
if(model_->bias >= 1)
n = get_nr_feature(model_) + 1;
else
n = get_nr_feature(model_);
labels = Malloc(int, get_nr_class(model_));
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 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);
++i;
}
if(model_->bias >= 0){
x[i].index = n;
x[i].value = model_->bias;
++i;
}
x[i].index = -1;
predict_label = predict(model_,x);
fprintf(output,"%g\n",predict_label);
double dec_value;
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);
free(labels);
free(x);
}
void do_predict(FILE *input, FILE *output)
{
int total=0;
int n;
int nr_feature=get_nr_feature(model_);
double *dvec_t;
double *ivec_t;
int *query;
n=nr_feature;
max_line_len = 1024;
line = (char *)malloc(max_line_len*sizeof(char));
while(readline(input) != NULL)
total++;
rewind(input);
dvec_t = new double[total];
ivec_t = new double[total];
query = new int[total];
total = 0;
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
query[total] = 0;
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);
ivec_t[total] = target_label;
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;
if (strcmp(idx,"qid") == 0)
{
errno = 0;
query[total] = (int) strtol(val,&endptr,10);
if(endptr == val || errno != 0 || *endptr != '\0')
exit_input_error(i+1);
continue;
}
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;
}
x[i].index = -1;
predict_label = predict(model_,x);
fprintf(output,"%.10f\n",predict_label);
dvec_t[total++] = predict_label;
}
double result[3];
eval_list(ivec_t,dvec_t,query,total,result);
info("Pairwise Accuracy = %g%%\n",result[0]*100);
info("MeanNDCG (LETOR) = %g\n",result[1]);
info("NDCG (YAHOO) = %g\n",result[2]);
}
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);
}
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(model_->param.solver_type!=L2_LR)
{
fprintf(stderr, "probability output is only supported for logistic regression\n");
return;
}
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);
}
while(1)
{
int i = 0;
int c;
double target;
int target_label, predict_label;
if (fscanf(input,"%lf",&target)==EOF)
break;
target_label=(int)target;
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));
}
do {
c = getc(input);
if(c=='\n' || c==EOF) goto out2;
} while(isspace(c));
ungetc(c,input);
if (fscanf(input,"%d:%lf",&x[i].index,&x[i].value) < 2)
{
fprintf(stderr,"Wrong input format at line %d\n", total+1);
exit(1);
}
// feature indices larger than those in training are not used
if(x[i].index<=nr_feature)
++i;
}
out2:
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);
}
