rmontanana/BayesNet
rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases 3 Wiki Activity

fix dataset name mistakes

Browse Source
This commit is contained in:
Ricardo Montañana Gómez 2024-01-03 17:15:57 +01:00
parent 9ab4fc7d76
commit 41a0bd4ddd
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
2 changed files with 8 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/Platform/GridSearch.cc
View File

@ -44,7 +44,7 @@ namespace platform {
} }
return json(); return json();
} }
vector<std::string> GridSearch::filterDatasets(Datasets& datasets) const std::vector<std::string> GridSearch::filterDatasets(Datasets& datasets) const
{ {
// Load datasets // Load datasets
auto datasets_names = datasets.getNames(); auto datasets_names = datasets.getNames();
@ -54,7 +54,7 @@ namespace platform {
throw std::invalid_argument("Dataset " + config.continue_from + " not found"); throw std::invalid_argument("Dataset " + config.continue_from + " not found");
} }
// Remove datasets already processed // Remove datasets already processed
vector< string >::iterator it = datasets_names.begin(); std::vector<string>::iterator it = datasets_names.begin();
while (it != datasets_names.end()) { while (it != datasets_names.end()) {
if (*it != config.continue_from) { if (*it != config.continue_from) {
it = datasets_names.erase(it); it = datasets_names.erase(it);
@ -253,47 +253,36 @@ namespace platform {
{ "time", result.time }, { "time", result.time },
{ "dataset", result.idx_dataset } { "dataset", result.idx_dataset }
}; };
std::cout << "x Storing result for dataset " << result.idx_dataset << " from " << result.idx_combination << ::endl;
std::cout << json_result.dump() << std::endl;
std::cout << string(80, '-') << std::endl;
auto name = names[result.idx_dataset]; auto name = names[result.idx_dataset];
if (!results.contains(name)) { if (!results.contains(name)) {
results[name] = json::array(); results[name] = json::array();
} }
results[name].push_back(json_result); results[name].push_back(json_result);
std::cout << results.dump() << std::endl;
return results; return results;
} }
json producer(json& tasks, struct ConfigMPI& config_mpi, MPI_Datatype& MPI_Result) json producer(std::vector<std::string>& names, json& tasks, struct ConfigMPI& config_mpi, MPI_Datatype& MPI_Result)
{ {
Task_Result result; Task_Result result;
json results; json results;
int num_tasks = tasks.size(); int num_tasks = tasks.size();
auto datasets = Datasets(false, Paths::datasets());
auto names = datasets.getNames();
for (int i = 0; i < num_tasks; ++i) { for (int i = 0; i < num_tasks; ++i) {
MPI_Status status; MPI_Status status;
std::cout << "+ Producer waiting for result." << std::endl;
MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status); MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
if (status.MPI_TAG == TAG_RESULT) { if (status.MPI_TAG == TAG_RESULT) {
//Store result //Store result
std::cout << "+ Producer received result from " << status.MPI_SOURCE << std::endl;
store_result(names, result, results); store_result(names, result, results);
} }
std::cout << "+ Producer sending task " << i << " to " << status.MPI_SOURCE << std::endl;
MPI_Send(&i, 1, MPI_INT, status.MPI_SOURCE, TAG_TASK, MPI_COMM_WORLD); MPI_Send(&i, 1, MPI_INT, status.MPI_SOURCE, TAG_TASK, MPI_COMM_WORLD);
} }
// Send end message to all workers but the manager // Send end message to all workers but the manager
for (int i = 0; i < config_mpi.n_procs - 1; ++i) { for (int i = 0; i < config_mpi.n_procs - 1; ++i) {
MPI_Status status; MPI_Status status;
std::cout << "+ Producer waiting for result (closing)." << std::endl;
MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status); MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
if (status.MPI_TAG == TAG_RESULT) { if (status.MPI_TAG == TAG_RESULT) {
//Store result //Store result
std::cout << "+ Producer received result from " << status.MPI_SOURCE << " (closing)" << std::endl;
store_result(names, result, results); store_result(names, result, results);
} }
std::cout << "+ Producer sending end signal to " << status.MPI_SOURCE << std::endl;
MPI_Send(&i, 1, MPI_INT, status.MPI_SOURCE, TAG_END, MPI_COMM_WORLD); MPI_Send(&i, 1, MPI_INT, status.MPI_SOURCE, TAG_END, MPI_COMM_WORLD);
} }
return results; return results;
@ -306,13 +295,10 @@ namespace platform {
// //
// Select the best result of the computed outer folds // Select the best result of the computed outer folds
// //
std::cout << "--- Selecting best results of the outer folds ---" << std::endl;
std::cout << all_results.dump() << std::endl;
for (const auto& result : all_results.items()) { for (const auto& result : all_results.items()) {
// each result has the results of all the outer folds as each one were a different task // each result has the results of all the outer folds as each one were a different task
double best_score = 0.0; double best_score = 0.0;
json best; json best;
std::cout << " Processing " << result.key() << std::endl;
for (const auto& result_fold : result.value()) { for (const auto& result_fold : result.value()) {
double score = result_fold["score"].get<double>(); double score = result_fold["score"].get<double>();
if (score > best_score) { if (score > best_score) {
@ -341,17 +327,14 @@ namespace platform {
int task; int task;
while (true) { while (true) {
MPI_Status status; MPI_Status status;
std::cout << "- Consumer nº " << config_mpi.rank << " waiting for task." << std::endl;
MPI_Recv(&task, 1, MPI_INT, config_mpi.manager, MPI_ANY_TAG, MPI_COMM_WORLD, &status); MPI_Recv(&task, 1, MPI_INT, config_mpi.manager, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
if (status.MPI_TAG == TAG_END) { if (status.MPI_TAG == TAG_END) {
break; break;
} }
// Process task // Process task
std::cout << " - Consumer nº " << config_mpi.rank << " processing task " << task << std::endl;
process_task_mpi_consumer(config, config_mpi, tasks, task, datasets, &result); process_task_mpi_consumer(config, config_mpi, tasks, task, datasets, &result);
// Send result to producer // Send result to producer
MPI_Send(&result, 1, MPI_Result, config_mpi.manager, TAG_RESULT, MPI_COMM_WORLD); MPI_Send(&result, 1, MPI_Result, config_mpi.manager, TAG_RESULT, MPI_COMM_WORLD);
std::cout << " - Consumer nº " << config_mpi.rank << " sent task " << task << std::endl;
} }
} }
void GridSearch::go_producer_consumer(struct ConfigMPI& config_mpi) void GridSearch::go_producer_consumer(struct ConfigMPI& config_mpi)
@ -426,9 +409,11 @@ namespace platform {
// //
auto datasets = Datasets(config.discretize, Paths::datasets()); auto datasets = Datasets(config.discretize, Paths::datasets());
if (config_mpi.rank == config_mpi.manager) { if (config_mpi.rank == config_mpi.manager) {
json all_results = producer(tasks, config_mpi, MPI_Result); auto datasets_names = filterDatasets(datasets);
json all_results = producer(datasets_names, tasks, config_mpi, MPI_Result);
json results = select_best_results_folds(all_results, config.model); json results = select_best_results_folds(all_results, config.model);
save(results); save(results);
std::cout << "|" << std::endl;
} else { } else {
consumer(datasets, tasks, config, config_mpi, MPI_Result); consumer(datasets, tasks, config, config_mpi, MPI_Result);
} }

2
src/Platform/GridSearch.h
View File

@ -53,7 +53,7 @@ namespace platform {
private: private:
void save(json& results); void save(json& results);
json initializeResults(); json initializeResults();
vector<std::string> filterDatasets(Datasets& datasets) const; std::vector<std::string> filterDatasets(Datasets& datasets) const;
// pair<double, json> processFileSingle(std::string fileName, Datasets& datasets, std::vector<json>& combinations); // pair<double, json> processFileSingle(std::string fileName, Datasets& datasets, std::vector<json>& combinations);
// pair<double, json> processFileNested(std::string fileName, Datasets& datasets, std::vector<json>& combinations); // pair<double, json> processFileNested(std::string fileName, Datasets& datasets, std::vector<json>& combinations);
struct ConfigGrid config; struct ConfigGrid config;