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");
}
// 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) ;
}
double SVMLinear::predictModel(vector<double> features)
{
if(modelLinearSVM==NULL)
{
fprintf(stdout,"Error, Train Model First \n");
return 0.0;
}
int nr_class=get_nr_class(modelLinearSVM);
int bias=modelLinearSVM->bias;
int sparsity=0.0;
for (int i=0; i<features.size(); i++)
if(features[i]!=0.0)
sparsity++;
feature_node *x=Malloc(struct feature_node,sparsity+bias+1); //bias and -1 index
int cnt=0;
for (int i=0; i<features.size(); i++)
{
if(features[i]!=0.0)
{
x[cnt].index=i+1;
x[cnt].value=features[i];
cnt++;
}
}
if(bias)
{
x[cnt].index=modelLinearSVM->nr_feature+1,
x[cnt].value=1;
cnt++;
}
x[cnt].index=-1;
double val=0;
predict_values(modelLinearSVM,x,&val);
return val;
}
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);
}
void *predictModelWholeGenome(void *arg) {
thread_data_t *data = (thread_data_t *) arg;
printf("data->trainedModel is %s\n", data->trainedModel);
printf("data->coverageFileList is %s\n", data->coverageFileList);
printf("data->trainFile %s\n", data->trainFile);
printf("data->paramFile %s\n", data->paramFile);
printf("data->chr is %d\n", data->chr);
char *trainedModel = data->trainedModel;
char *coverageFileList = data->coverageFileList;
// char *trainFile = data->trainFile;
char *paramFile = data->paramFile;
int chr = data->chr;
// utility var
int i,j,k;
// trainedModel
struct model *mymodel;
if( (mymodel = load_model(trainedModel)) == 0) {
printf("cannot load model from file %s\n", trainedModel);
return EXIT_SUCCESS;
}
// coverageFileList
int totalCoverageFiles;
FILE *coverageFileListFp = NULL;
if( (coverageFileListFp = fopen(coverageFileList, "r") ) == NULL) {
printf("Cannot open file %s\n", coverageFileList);
return EXIT_SUCCESS;
}
char **coverageFiles = (char **)calloc(MAX_BAM_FILES,sizeof(char *));
for(i = 0; i < MAX_BAM_FILES; i++) {
coverageFiles[i] = (char *)calloc(MAX_DIR_LEN, sizeof(char));
}
i = 0;
while (!feof(coverageFileListFp)) {
if (i >= MAX_BAM_FILES) {
printf("Error: the number of input coverages files exceeds the limit %d\n", i);
return EXIT_SUCCESS;
}
if( ( fscanf(coverageFileListFp, "%s\n", coverageFiles[i]) ) != 1) {
printf("Error: reading %dth from %s\n", i, coverageFileList);
return EXIT_SUCCESS;
}
i++;
}
totalCoverageFiles = i;
fclose(coverageFileListFp);
// open coverage Files
FILE *coverageFps[totalCoverageFiles];
for(i = 0; i < totalCoverageFiles; i++) {
if( (coverageFps[i] = fopen(coverageFiles[i], "rb")) == NULL ) {
printf("Error opening coverage file %s\n", coverageFiles[i]);
return EXIT_SUCCESS;
}
}
// paramFile
struct extractFeatureParam *param = (struct extractFeatureParam *)calloc(1, sizeof(struct extractFeatureParam));
parseParam(paramFile, param);
// predict model: by default: predict probability
int nr_class = get_nr_class(mymodel);
double *prob_estimates = (double *)calloc(nr_class, sizeof(double));
// predResult for storing results
int totalBins = 0;
int cumBins[NUM_SEQ];
for (i = 0; i < NUM_SEQ; i++) {
totalBins += (int)(chrlen[i] / param->resolution) + 1;
cumBins[i] = totalBins;
}
// allocate memory for result based on thread data chr
// as we are using one thread for each chr
float *predResult = (float *)calloc( (int)(chrlen[chr] / param->resolution) + 1, sizeof(float));
// read in feature for each bin and do prediction
for(j = 0; j < (int)(chrlen[chr] / param->resolution) + 1; j++) {
if(j % 100000 == 0) {
printf("Predicting chr%d:%dth bin\n", chr,j);
fflush(stdout);
}
int max_nr_feature = 100;
struct feature_node *myX = (struct feature_node *)calloc(max_nr_feature, sizeof(struct feature_node));
int idx = 0;
for(k = 0; k < totalCoverageFiles; k++) {
float *buffer = (float *)calloc( param->windowSize/param->resolution,sizeof(float));
int offset = j;
offset += -(int)((float)(param->windowSize / 2) / (float)param->resolution + 0.5);
if(offset < 0 || offset + (int)((float)(param->windowSize) / (float)param->resolution + 0.5) > (int)(chrlen[i] / param->resolution) + 1) {
// printf("offset is %d\n", offset);
free(buffer);
continue;
}
if(chr != 0) offset += cumBins[chr-1];
// printf("offset is %d\n", offset);
fseek(coverageFps[k], offset*sizeof(float), SEEK_SET);
fread(buffer, sizeof(float), param->windowSize/param->resolution, coverageFps[k]);
int l;
// printf("buffer[%d] is:",l);
for(l = 0; l < param->windowSize/param->resolution; l++) {
// if(j == 289540) printf("%f,",buffer[l]);
if(buffer[l] != 0) {
myX[idx].index = k*(param->windowSize/param->resolution) + l + 1;
myX[idx].value = buffer[l];
idx++;
}
if(idx >= max_nr_feature -2) { // feature_node is not long enough
max_nr_feature *= 2;
myX = (struct feature_node *)realloc(myX, max_nr_feature*sizeof(struct feature_node));
}
}
free(buffer);
} // end of loop through coverageFiles
// printf("\n");
myX[idx].index = -1; // a flag for end of features
if(idx == 0) {
// printf("idx is %d\n",idx);
predResult[j] = 0.0;
free(myX);
continue;
}
// printf("nr_feature is %d\n", idx);
predict_probability(mymodel, myX, prob_estimates);
// printf("num of feature is %d\n", get_nr_feature(mymodel));
// printf("num of class is %d\n", get_nr_class(mymodel));
int *mylabel = (int *)calloc(10, sizeof(int));
// added, in order to get the correct label
get_labels(mymodel, mylabel);
if(mylabel[0] == 1) {
predResult[j] = prob_estimates[0];
} else {
predResult[j] = prob_estimates[1];
}
free(myX);
free(mylabel);
}
for(i = 0; i < totalCoverageFiles; i++) {
fclose(coverageFps[i]);
}
// free pointers
for(i = 0; i < MAX_BAM_FILES; i++) {
free(coverageFiles[i]);
}
free(coverageFiles);
free(param);
free(prob_estimates);
// give address of pointer to this function, so that the function can free the pointer.
free_and_destroy_model(&mymodel);
pthread_exit((void *) predResult);
}
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_classifier;
double *prob_estimates=NULL;
if(nr_class==2)
nr_classifier=1;
else
nr_classifier=nr_class;
// prhs[1] = testing instance matrix
feature_number = mxGetN(prhs[1]);
testing_instance_number = mxGetM(prhs[1]);
if(col_format_flag)
{
feature_number = mxGetM(prhs[1]);
testing_instance_number = mxGetN(prhs[1]);
}
label_vector_row_num = mxGetM(prhs[0]);
label_vector_col_num = 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_classifier, 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_classifier;i++)
ptr_dec_values[instance_index + i * testing_instance_number] = dec_values[i];
}
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 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);
}
double binary_class_cross_validation(const problem *prob, const 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 problem subprob;
subprob.l = l-(end-begin);
subprob.x = Malloc(struct feature_node*,subprob.l);
subprob.y = Malloc(int,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 model *submodel = train(&subprob,param);
//int svm_type = get_svm_type(submodel);
//if(svm_type == NU_SVR || svm_type == EPSILON_SVR){
// fprintf(stderr, "wrong svm type");
// exit(1);
//}
labels = Malloc(int, get_nr_class(submodel));
get_labels(submodel, labels);
if(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++) {
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;
}
free_and_destroy_model(&submodel);
free(subprob.x);
free(subprob.y);
free(labels);
}
free(perm);
free(fold_start);
}
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);
}