int main(int argc, char* argv[])
{
/* Start the timer */
uglyTime(NULL);
printf("\nQUBIC %.1f: greedy biclustering (compiled "__DATE__" "__TIME__")\n\n", VER);
rows = cols = 0;
/* get the program options defined in get_options.c */
get_options(argc, argv);
/*get the size of input expression matrix*/
get_matrix_size(po->FP);
progress("File %s contains %d genes by %d conditions", po -> FN, rows, cols);
if (rows < 3 || cols < 3)
{
/*neither rows number nor cols number can be too small*/
errAbort("Not enough genes or conditions to make inference");
}
genes = alloc2c(rows, LABEL_LEN);
conds = alloc2c(cols, LABEL_LEN);
/* Read in the gene names and condition names */
read_labels(po -> FP);
/* Read in the expression data */
if (po->IS_DISCRETE)
read_discrete(po -> FP);
else
{
read_continuous(po -> FP);
/* formatting rules */
discretize(addSuffix(po->FN, ".rules"));
}
fclose(po->FP);
/*we can do expansion by activate po->IS_SWITCH*/
if (po->IS_SWITCH)
{
read_and_solve_blocks(po->FB, addSuffix(po->BN, ".expansion"));
}
else
{
/* formatted file */
write_imported(addSuffix(po->FN, ".chars"));
/* the file that stores all blocks */
make_graph(addSuffix(po->FN, ".blocks"));
}/* end of main else */
free(po);
return 0;
}
/*** MAIN FUNCTION ***/
int main (int argc, char **argv) {
// process the command line
process_args (argc, argv);
determine_limits();
// check if there is something wrong in the command
if (n_nodes <= 0 || n_edges <= 0) {
fprintf (stderr, "Incorrect or missing node numbers\n");
exit (1);
}
fprintf (stderr, "allocating edges..\n");
edges = (edge_t *) malloc(n_edges * sizeof(edge_t));
read_edges();
fprintf (stderr, "allocating nodes..\n");
nodes = (node_t *) malloc(n_nodes * sizeof(node_t));
memset (nodes, 0, n_nodes * sizeof(node_t));
for (unsigned int i=0; i < n_nodes; i++) {
nodes[i].old_values = (float *) malloc (n_classes * sizeof(float));
nodes[i].new_values = (float *) malloc (n_classes * sizeof(float));
}
read_labels();
for (unsigned int i=0; i < n_nodes; i++) {
for (short j=0; j < n_classes; j++) {
if (!nodes[i].labeled)
nodes[i].old_values[j] = 1.0 / n_classes;
nodes[i].new_values[j] = 0;
}
}
// compute the influx (weighted degree) of each node
for (unsigned int i=0; i < n_edges; i++) {
nodes[edges[i].ids[0]].influx += edges[i].weight;
nodes[edges[i].ids[1]].influx += edges[i].weight;
}
float max_error;
do {
max_error = propagate_labels();
fprintf (stderr, "error: %f\n", max_error);
} while (max_error > 0.0002);
output_labels();
return 0;
}
void execute(DBN& dbn, task& task, const std::vector<std::string>& actions) {
print_title("Network");
dbn.display();
using dbn_t = std::decay_t<DBN>;
//Execute all the actions sequentially
for (auto& action : actions) {
if (action == "pretrain") {
print_title("Pretraining");
if (task.pretraining.samples.empty()) {
std::cout << "dllp: error: pretrain is not possible without a pretraining input" << std::endl;
return;
}
std::vector<Container> pt_samples;
//Try to read the samples
if (!read_samples<Three>(task.pretraining.samples, pt_samples)) {
std::cout << "dllp: error: failed to read the pretraining samples" << std::endl;
return;
}
if (task.pt_desc.denoising) {
std::vector<Container> clean_samples;
//Try to read the samples
if (!read_samples<Three>(task.pretraining_clean.samples, clean_samples)) {
std::cout << "dllp: error: failed to read the clean samples" << std::endl;
return;
}
//Pretrain the network
cpp::static_if<dbn_t::layers_t::is_denoising>([&](auto f) {
f(dbn).pretrain_denoising(pt_samples.begin(), pt_samples.end(), clean_samples.begin(), clean_samples.end(), task.pt_desc.epochs);
});
} else {
//Pretrain the network
dbn.pretrain(pt_samples.begin(), pt_samples.end(), task.pt_desc.epochs);
}
} else if (action == "train") {
print_title("Training");
if (task.training.samples.empty() || task.training.labels.empty()) {
std::cout << "dllp: error: train is not possible without samples and labels" << std::endl;
return;
}
std::vector<Container> ft_samples;
std::vector<std::size_t> ft_labels;
//Try to read the samples
if (!read_samples<Three>(task.training.samples, ft_samples)) {
std::cout << "dllp: error: failed to read the training samples" << std::endl;
return;
}
//Try to read the labels
if (!read_labels(task.training.labels, ft_labels)) {
std::cout << "dllp: error: failed to read the training labels" << std::endl;
return;
}
using last_layer = typename dbn_t::template layer_type<dbn_t::layers - 1>;
//Train the network
cpp::static_if<sgd_possible<last_layer>::value>([&](auto f) {
auto ft_error = f(dbn).fine_tune(ft_samples, ft_labels, task.ft_desc.epochs);
std::cout << "Train Classification Error:" << ft_error << std::endl;
});
} else if (action == "test") {
print_title("Testing");
if (task.testing.samples.empty() || task.testing.labels.empty()) {
std::cout << "dllp: error: test is not possible without samples and labels" << std::endl;
return;
}
std::vector<Container> test_samples;
std::vector<std::size_t> test_labels;
//Try to read the samples
if (!read_samples<Three>(task.testing.samples, test_samples)) {
std::cout << "dllp: error: failed to read the test samples" << std::endl;
return;
}
//Try to read the labels
if (!read_labels(task.testing.labels, test_labels)) {
std::cout << "dllp: error: failed to read the test labels" << std::endl;
return;
}
auto classes = dbn_t::output_size();
etl::dyn_matrix<std::size_t, 2> conf(classes, classes, 0.0);
std::size_t n = test_samples.size();
std::size_t tp = 0;
for (std::size_t i = 0; i < test_samples.size(); ++i) {
auto sample = test_samples[i];
auto label = test_labels[i];
auto predicted = dbn.predict(sample);
if (predicted == label) {
++tp;
}
++conf(label, predicted);
}
double test_error = (n - tp) / double(n);
std::cout << "Error rate: " << test_error << std::endl;
std::cout << "Accuracy: " << (1.0 - test_error) << std::endl
<< std::endl;
std::cout << "Results per class" << std::endl;
double overall = 0.0;
std::cout << " | Accuracy | Error rate |" << std::endl;
for (std::size_t l = 0; l < classes; ++l) {
std::size_t total = etl::sum(conf(l));
double acc = (total - conf(l, l)) / double(total);
std::cout << std::setw(3) << l;
std::cout << "|" << std::setw(10) << (1.0 - acc) << "|" << std::setw(12) << acc << "|" << std::endl;
overall += acc;
}
std::cout << std::endl;
std::cout << "Overall Error rate: " << overall / classes << std::endl;
std::cout << "Overall Accuracy: " << 1.0 - (overall / classes) << std::endl
<< std::endl;
std::cout << "Confusion Matrix (%)" << std::endl
<< std::endl;
std::cout << " ";
for (std::size_t l = 0; l < classes; ++l) {
std::cout << std::setw(5) << l << " ";
}
std::cout << std::endl;
for (std::size_t l = 0; l < classes; ++l) {
std::size_t total = etl::sum(conf(l));
std::cout << std::setw(3) << l << "|";
for (std::size_t p = 0; p < classes; ++p) {
std::cout << std::setw(5) << std::setprecision(2) << 100.0 * (conf(l, p) / double(total)) << "|";
}
std::cout << std::endl;
}
std::cout << std::endl;
} else if (action == "save") {
print_title("Save Weights");
dbn.store(task.w_desc.file);
std::cout << "Weights saved" << std::endl;
} else if (action == "load") {
print_title("Load Weights");
dbn.load(task.w_desc.file);
std::cout << "Weights loaded" << std::endl;
} else {
std::cout << "dllp: error: Invalid action: " << action << std::endl;
}
}
//TODO
}
mnist_labels_t load_labels(uint32_t train)
{
return read_labels(train);
}