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 = 100000000;
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(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(check_regression_model(model_))
{
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(int nlhs, 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
mxArray *tplhs[3]; // temporary storage for plhs[]
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(nlhs, plhs);
return;
}
if(label_vector_col_num!=1)
{
mexPrintf("label (1st argument) should be a vector (# of column is 1).\n");
fake_answer(nlhs, 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(nlhs, plhs);
return;
}
}
prob_estimates = Malloc(double, nr_class);
tplhs[0] = mxCreateDoubleMatrix(testing_instance_number, 1, mxREAL);
if(predict_probability_flag)
tplhs[2] = mxCreateDoubleMatrix(testing_instance_number, nr_class, mxREAL);
else
tplhs[2] = mxCreateDoubleMatrix(testing_instance_number, nr_w, mxREAL);
ptr_predict_label = mxGetPr(tplhs[0]);
ptr_prob_estimates = mxGetPr(tplhs[2]);
ptr_dec_values = mxGetPr(tplhs[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(check_regression_model(model_))
{
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);
// return accuracy, mean squared error, squared correlation coefficient
tplhs[1] = mxCreateDoubleMatrix(3, 1, mxREAL);
ptr = mxGetPr(tplhs[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);
switch(nlhs)
{
case 3:
plhs[2] = tplhs[2];
plhs[1] = tplhs[1];
case 1:
case 0:
plhs[0] = tplhs[0];
}
}