diff --git a/src/Platform/GridSearch.cc b/src/Platform/GridSearch.cc index 8ace92d..7cb36df 100644 --- a/src/Platform/GridSearch.cc +++ b/src/Platform/GridSearch.cc @@ -36,7 +36,7 @@ namespace platform { GridSearch::GridSearch(struct ConfigGrid& config) : config(config) { } - json GridSearch::getResults() + json GridSearch::loadResults() { std::ifstream file(Paths::grid_output(config.model)); if (file.is_open()) { @@ -44,7 +44,7 @@ namespace platform { } return json(); } - vector GridSearch::processDatasets(Datasets& datasets) const + vector GridSearch::filterDatasets(Datasets& datasets) const { // Load datasets auto datasets_names = datasets.getNames(); @@ -108,9 +108,9 @@ namespace platform { auto grid = GridData(Paths::grid_input(config.model)); auto datasets = Datasets(false, Paths::datasets()); auto all_datasets = datasets.getNames(); - auto datasets_names = processDatasets(datasets); + auto datasets_names = filterDatasets(datasets); for (int idx_dataset = 0; idx_dataset < datasets_names.size(); ++idx_dataset) { - auto dataset = all_datasets[idx_dataset]; + auto dataset = datasets_names[idx_dataset]; for (const auto& seed : config.seeds) { auto combinations = grid.getGrid(dataset); for (int n_fold = 0; n_fold < config.n_folds; n_fold++) { @@ -226,25 +226,25 @@ namespace platform { // Update progress bar std::cout << get_color_rank(config_mpi.rank) << "*" << std::flush; } - std::pair GridSearch::part_range_mpi(int n_tasks, int nprocs, int rank) - { - int assigned = 0; - int remainder = n_tasks % nprocs; - int start = 0; - if (rank < remainder) { - assigned = n_tasks / nprocs + 1; - } else { - assigned = n_tasks / nprocs; - start = remainder; - } - start += rank * assigned; - int end = start + assigned; - if (rank == nprocs - 1) { - end = n_tasks; - } - return { start, end }; - } - void store_result(std::vector& names, Task_Result& result, json& results) + // std::pair GridSearch::part_range_mpi(int n_tasks, int nprocs, int rank) + // { + // int assigned = 0; + // int remainder = n_tasks % nprocs; + // int start = 0; + // if (rank < remainder) { + // assigned = n_tasks / nprocs + 1; + // } else { + // assigned = n_tasks / nprocs; + // start = remainder; + // } + // start += rank * assigned; + // int end = start + assigned; + // if (rank == nprocs - 1) { + // end = n_tasks; + // } + // return { start, end }; + // } + json store_result(std::vector& names, Task_Result& result, json& results) { json json_result = { { "score", result.score }, @@ -253,11 +253,16 @@ namespace platform { { "time", result.time }, { "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]; if (!results.contains(name)) { results[name] = json::array(); } results[name].push_back(json_result); + std::cout << results.dump() << std::endl; + return results; } json producer(json& tasks, struct ConfigMPI& config_mpi, MPI_Datatype& MPI_Result) { @@ -268,21 +273,27 @@ namespace platform { auto names = datasets.getNames(); for (int i = 0; i < num_tasks; ++i) { 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); if (status.MPI_TAG == TAG_RESULT) { //Store result + std::cout << "+ Producer received result from " << status.MPI_SOURCE << std::endl; 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); } - // Send end message to all workers - for (int i = 0; i < config_mpi.n_procs; ++i) { + // Send end message to all workers but the manager + for (int i = 0; i < config_mpi.n_procs - 1; ++i) { 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); if (status.MPI_TAG == TAG_RESULT) { //Store result + std::cout << "+ Producer received result from " << status.MPI_SOURCE << " (closing)" << std::endl; 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); } return results; @@ -295,10 +306,13 @@ namespace platform { // // Select the best result of the computed outer folds // - for (const auto& result : results.items()) { + 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()) { // each result has the results of all the outer folds as each one were a different task double best_score = 0.0; json best; + std::cout << " Processing " << result.key() << std::endl; for (const auto& result_fold : result.value()) { double score = result_fold["score"].get(); if (score > best_score) { @@ -327,14 +341,17 @@ namespace platform { int task; while (true) { 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); if (status.MPI_TAG == TAG_END) { break; } // 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); // Send result to producer 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) @@ -409,419 +426,419 @@ namespace platform { // auto datasets = Datasets(config.discretize, Paths::datasets()); if (config_mpi.rank == config_mpi.manager) { - auto all_results = producer(tasks, config_mpi, MPI_Result); - auto results = select_best_results_folds(all_results, config.model); + json all_results = producer(tasks, config_mpi, MPI_Result); + json results = select_best_results_folds(all_results, config.model); save(results); } else { consumer(datasets, tasks, config, config_mpi, MPI_Result); } } - void GridSearch::go_mpi(struct ConfigMPI& config_mpi) - { - /* - * Each task is a json object with the following structure: - * { - * "dataset": "dataset_name", - * "idx_dataset": idx_dataset, - * "seed": # of seed to use, - * "Fold": # of fold to process - * } - * - * The overall process consists in these steps: - * 1. Manager will broadcast the tasks to all the processes - * 1.1 Broadcast the number of tasks - * 1.2 Broadcast the length of the following string - * 1.2 Broadcast the tasks as a char* string - * 2. Workers will receive the tasks and start the process - * 2.1 A method will tell each worker the range of tasks to process - * 2.2 Each worker will process the tasks and generate the best score for each task - * 3. Manager gather the scores from all the workers and find out the best hyperparameters for each dataset - * 3.1 Obtain the maximum size of the results message of all the workers - * 3.2 Gather all the results from the workers into the manager - * 3.3 Compile the results from all the workers - * 3.4 Filter the best hyperparameters for each dataset - */ - char* msg; - int tasks_size; - if (config_mpi.rank == config_mpi.manager) { - timer.start(); - auto tasks = build_tasks_mpi(); - auto tasks_str = tasks.dump(); - tasks_size = tasks_str.size(); - msg = new char[tasks_size + 1]; - strcpy(msg, tasks_str.c_str()); - } - // - // 1. Manager will broadcast the tasks to all the processes - // - MPI_Bcast(&tasks_size, 1, MPI_INT, config_mpi.manager, MPI_COMM_WORLD); - if (config_mpi.rank != config_mpi.manager) { - msg = new char[tasks_size + 1]; - } - MPI_Bcast(msg, tasks_size + 1, MPI_CHAR, config_mpi.manager, MPI_COMM_WORLD); - json tasks = json::parse(msg); - delete[] msg; - // - // 2. All Workers will receive the tasks and start the process - // - int num_tasks = tasks.size(); - // 2.1 A method will tell each worker the range of tasks to process - auto [start, end] = part_range_mpi(num_tasks, config_mpi.n_procs, config_mpi.rank); - // 2.2 Each worker will process the tasks and return the best scores obtained - auto datasets = Datasets(config.discretize, Paths::datasets()); - json results; - for (int i = start; i < end; ++i) { - // Process task - process_task_mpi(config_mpi, tasks[i], datasets, results); - } - int size = results.dump().size() + 1; - int max_size = 0; - // - // 3. Manager gather the scores from all the workers and find out the best hyperparameters for each dataset - // - //3.1 Obtain the maximum size of the results message of all the workers - MPI_Allreduce(&size, &max_size, 1, MPI_INT, MPI_MAX, MPI_COMM_WORLD); - // Assign the memory to the message and initialize it to 0s - char* total = NULL; - msg = new char[max_size]; - strncpy(msg, results.dump().c_str(), size); - if (config_mpi.rank == config_mpi.manager) { - total = new char[max_size * config_mpi.n_procs]; - } - // 3.2 Gather all the results from the workers into the manager - MPI_Gather(msg, max_size, MPI_CHAR, total, max_size, MPI_CHAR, config_mpi.manager, MPI_COMM_WORLD); - delete[] msg; - if (config_mpi.rank == config_mpi.manager) { - std::cout << Colors::RESET() << "|" << std::endl; - json total_results; - json best_results; - // 3.3 Compile the results from all the workers - for (int i = 0; i < config_mpi.n_procs; ++i) { - json partial_results = json::parse(total + i * max_size); - for (auto& [dataset, folds] : partial_results.items()) { - for (auto& [fold, result] : folds.items()) { - total_results[dataset][fold] = result; - } - } - } - delete[] total; - // 3.4 Filter the best hyperparameters for each dataset - auto grid = GridData(Paths::grid_input(config.model)); - for (auto& [dataset, folds] : total_results.items()) { - double best_score = 0.0; - double duration = 0.0; - json best_hyper; - for (auto& [fold, result] : folds.items()) { - duration += result["duration"].get(); - if (result["score"] > best_score) { - best_score = result["score"]; - best_hyper = result["hyperparameters"]; - } - } - auto timer = Timer(); - json result = { - { "score", best_score }, - { "hyperparameters", best_hyper }, - { "date", get_date() + " " + get_time() }, - { "grid", grid.getInputGrid(dataset) }, - { "duration", timer.translate2String(duration) } - }; - best_results[dataset] = result; - } - save(best_results); - } - } - void GridSearch::go() - { - timer.start(); - auto grid_type = config.nested == 0 ? "Single" : "Nested"; - auto datasets = Datasets(config.discretize, Paths::datasets()); - auto datasets_names = processDatasets(datasets); - json results = initializeResults(); - std::cout << "***************** Starting " << grid_type << " Gridsearch *****************" << std::endl; - std::cout << "input file=" << Paths::grid_input(config.model) << std::endl; - auto grid = GridData(Paths::grid_input(config.model)); - Timer timer_dataset; - double bestScore = 0; - json bestHyperparameters; - for (const auto& dataset : datasets_names) { - if (!config.quiet) - std::cout << "- " << setw(20) << left << dataset << " " << right << flush; - auto combinations = grid.getGrid(dataset); - timer_dataset.start(); - if (config.nested == 0) - // for dataset // for hyperparameters // for seed // for fold - tie(bestScore, bestHyperparameters) = processFileSingle(dataset, datasets, combinations); - else - // for dataset // for seed // for fold // for hyperparameters // for nested fold - tie(bestScore, bestHyperparameters) = processFileNested(dataset, datasets, combinations); - if (!config.quiet) { - std::cout << "end." << " Score: " << Colors::IBLUE() << setw(9) << setprecision(7) << fixed - << bestScore << Colors::BLUE() << " [" << bestHyperparameters.dump() << "]" - << Colors::RESET() << ::endl; - } - json result = { - { "score", bestScore }, - { "hyperparameters", bestHyperparameters }, - { "date", get_date() + " " + get_time() }, - { "grid", grid.getInputGrid(dataset) }, - { "duration", timer_dataset.getDurationString() } - }; - results[dataset] = result; - // Save partial results - save(results); - } - // Save final results - save(results); - std::cout << "***************** Ending " << grid_type << " Gridsearch *******************" << std::endl; - } - pair GridSearch::processFileSingle(std::string fileName, Datasets& datasets, vector& combinations) - { - int num = 0; - double bestScore = 0.0; - json bestHyperparameters; - auto totalComb = combinations.size(); - for (const auto& hyperparam_line : combinations) { - if (!config.quiet) - showProgressComb(++num, config.n_folds, totalComb, Colors::CYAN()); - auto hyperparameters = platform::HyperParameters(datasets.getNames(), hyperparam_line); - // Get dataset - auto [X, y] = datasets.getTensors(fileName); - auto states = datasets.getStates(fileName); - auto features = datasets.getFeatures(fileName); - auto className = datasets.getClassName(fileName); - double totalScore = 0.0; - int numItems = 0; - for (const auto& seed : config.seeds) { - if (!config.quiet) - std::cout << "(" << seed << ") doing Fold: " << flush; - Fold* fold; - if (config.stratified) - fold = new StratifiedKFold(config.n_folds, y, seed); - else - fold = new KFold(config.n_folds, y.size(0), seed); - for (int nfold = 0; nfold < config.n_folds; nfold++) { - auto clf = Models::instance()->create(config.model); - auto valid = clf->getValidHyperparameters(); - hyperparameters.check(valid, fileName); - clf->setHyperparameters(hyperparameters.get(fileName)); - auto [train, test] = fold->getFold(nfold); - auto train_t = torch::tensor(train); - auto test_t = torch::tensor(test); - auto X_train = X.index({ "...", train_t }); - auto y_train = y.index({ train_t }); - auto X_test = X.index({ "...", test_t }); - auto y_test = y.index({ test_t }); - // Train model - if (!config.quiet) - showProgressFold(nfold + 1, getColor(clf->getStatus()), "a"); - clf->fit(X_train, y_train, features, className, states); - // Test model - if (!config.quiet) - showProgressFold(nfold + 1, getColor(clf->getStatus()), "b"); - totalScore += clf->score(X_test, y_test); - numItems++; - if (!config.quiet) - std::cout << "\b\b\b, \b" << flush; - } - delete fold; - } - double score = numItems == 0 ? 0.0 : totalScore / numItems; - if (score > bestScore) { - bestScore = score; - bestHyperparameters = hyperparam_line; - } - } - return { bestScore, bestHyperparameters }; - } - pair GridSearch::processFileNested(std::string fileName, Datasets& datasets, vector& combinations) - { - // Get dataset - auto [X, y] = datasets.getTensors(fileName); - auto states = datasets.getStates(fileName); - auto features = datasets.getFeatures(fileName); - auto className = datasets.getClassName(fileName); - int spcs_combinations = int(log(combinations.size()) / log(10)) + 1; - double goatScore = 0.0; - json goatHyperparameters; - // for dataset // for seed // for fold // for hyperparameters // for nested fold - for (const auto& seed : config.seeds) { - Fold* fold; - if (config.stratified) - fold = new StratifiedKFold(config.n_folds, y, seed); - else - fold = new KFold(config.n_folds, y.size(0), seed); - double bestScore = 0.0; - json bestHyperparameters; - std::cout << "(" << seed << ") doing Fold: " << flush; - for (int nfold = 0; nfold < config.n_folds; nfold++) { - if (!config.quiet) - std::cout << Colors::GREEN() << nfold + 1 << " " << flush; - // First level fold - auto [train, test] = fold->getFold(nfold); - auto train_t = torch::tensor(train); - auto test_t = torch::tensor(test); - auto X_train = X.index({ "...", train_t }); - auto y_train = y.index({ train_t }); - auto X_test = X.index({ "...", test_t }); - auto y_test = y.index({ test_t }); - auto num = 0; - json result_fold; - double hypScore = 0.0; - double bestHypScore = 0.0; - json bestHypHyperparameters; - for (const auto& hyperparam_line : combinations) { - std::cout << "[" << setw(spcs_combinations) << ++num << "/" << setw(spcs_combinations) - << combinations.size() << "] " << std::flush; - Fold* nested_fold; - if (config.stratified) - nested_fold = new StratifiedKFold(config.nested, y_train, seed); - else - nested_fold = new KFold(config.nested, y_train.size(0), seed); - for (int n_nested_fold = 0; n_nested_fold < config.nested; n_nested_fold++) { - // Nested level fold - auto [train_nested, test_nested] = nested_fold->getFold(n_nested_fold); - auto train_nested_t = torch::tensor(train_nested); - auto test_nested_t = torch::tensor(test_nested); - auto X_nexted_train = X_train.index({ "...", train_nested_t }); - auto y_nested_train = y_train.index({ train_nested_t }); - auto X_nested_test = X_train.index({ "...", test_nested_t }); - auto y_nested_test = y_train.index({ test_nested_t }); - // Build Classifier with selected hyperparameters - auto hyperparameters = platform::HyperParameters(datasets.getNames(), hyperparam_line); - auto clf = Models::instance()->create(config.model); - auto valid = clf->getValidHyperparameters(); - hyperparameters.check(valid, fileName); - clf->setHyperparameters(hyperparameters.get(fileName)); - // Train model - if (!config.quiet) - showProgressFold(n_nested_fold + 1, getColor(clf->getStatus()), "a"); - clf->fit(X_nexted_train, y_nested_train, features, className, states); - // Test model - if (!config.quiet) - showProgressFold(n_nested_fold + 1, getColor(clf->getStatus()), "b"); - hypScore += clf->score(X_nested_test, y_nested_test); - if (!config.quiet) - std::cout << "\b\b\b, \b" << flush; - } - int magic = 3 * config.nested + 2 * spcs_combinations + 4; - std::cout << string(magic, '\b') << string(magic, ' ') << string(magic, '\b') << flush; - delete nested_fold; - hypScore /= config.nested; - if (hypScore > bestHypScore) { - bestHypScore = hypScore; - bestHypHyperparameters = hyperparam_line; - } - } - // Build Classifier with selected hyperparameters - auto clf = Models::instance()->create(config.model); - clf->setHyperparameters(bestHypHyperparameters); - // Train model - if (!config.quiet) - showProgressFold(nfold + 1, getColor(clf->getStatus()), "a"); - clf->fit(X_train, y_train, features, className, states); - // Test model - if (!config.quiet) - showProgressFold(nfold + 1, getColor(clf->getStatus()), "b"); - double score = clf->score(X_test, y_test); - if (!config.quiet) - std::cout << string(2 * config.nested - 1, '\b') << "," << string(2 * config.nested, ' ') << string(2 * config.nested - 1, '\b') << flush; - if (score > bestScore) { - bestScore = score; - bestHyperparameters = bestHypHyperparameters; - } - } - if (bestScore > goatScore) { - goatScore = bestScore; - goatHyperparameters = bestHyperparameters; - } - delete fold; - } - return { goatScore, goatHyperparameters }; - } - void GridSearch::process_task_mpi(struct ConfigMPI& config_mpi, json& task, Datasets& datasets, json& results) - { - // Process the task and store the result in the results json - Timer timer; - timer.start(); - auto grid = GridData(Paths::grid_input(config.model)); - auto dataset = task["dataset"].get(); - auto seed = task["seed"].get(); - auto n_fold = task["fold"].get(); - // Generate the hyperparamters combinations - auto combinations = grid.getGrid(dataset); - auto [X, y] = datasets.getTensors(dataset); - auto states = datasets.getStates(dataset); - auto features = datasets.getFeatures(dataset); - auto className = datasets.getClassName(dataset); - // - // Start working on task - // - Fold* fold; - if (config.stratified) - fold = new StratifiedKFold(config.n_folds, y, seed); - else - fold = new KFold(config.n_folds, y.size(0), seed); - auto [train, test] = fold->getFold(n_fold); - auto train_t = torch::tensor(train); - auto test_t = torch::tensor(test); - auto X_train = X.index({ "...", train_t }); - auto y_train = y.index({ train_t }); - auto X_test = X.index({ "...", test_t }); - auto y_test = y.index({ test_t }); - auto num = 0; - double best_fold_score = 0.0; - json best_fold_hyper; - for (const auto& hyperparam_line : combinations) { - auto hyperparameters = platform::HyperParameters(datasets.getNames(), hyperparam_line); - Fold* nested_fold; - if (config.stratified) - nested_fold = new StratifiedKFold(config.nested, y_train, seed); - else - nested_fold = new KFold(config.nested, y_train.size(0), seed); - double score = 0.0; - for (int n_nested_fold = 0; n_nested_fold < config.nested; n_nested_fold++) { - // Nested level fold - auto [train_nested, test_nested] = nested_fold->getFold(n_nested_fold); - auto train_nested_t = torch::tensor(train_nested); - auto test_nested_t = torch::tensor(test_nested); - auto X_nested_train = X_train.index({ "...", train_nested_t }); - auto y_nested_train = y_train.index({ train_nested_t }); - auto X_nested_test = X_train.index({ "...", test_nested_t }); - auto y_nested_test = y_train.index({ test_nested_t }); - // Build Classifier with selected hyperparameters - auto clf = Models::instance()->create(config.model); - auto valid = clf->getValidHyperparameters(); - hyperparameters.check(valid, dataset); - clf->setHyperparameters(hyperparameters.get(dataset)); - // Train model - clf->fit(X_nested_train, y_nested_train, features, className, states); - // Test model - score += clf->score(X_nested_test, y_nested_test); - } - delete nested_fold; - score /= config.nested; - if (score > best_fold_score) { - best_fold_score = score; - best_fold_hyper = hyperparam_line; - } - } - delete fold; - // Build Classifier with the best hyperparameters to obtain the best score - auto hyperparameters = platform::HyperParameters(datasets.getNames(), best_fold_hyper); - auto clf = Models::instance()->create(config.model); - auto valid = clf->getValidHyperparameters(); - hyperparameters.check(valid, dataset); - clf->setHyperparameters(best_fold_hyper); - clf->fit(X_train, y_train, features, className, states); - best_fold_score = clf->score(X_test, y_test); - // Save results - results[dataset][std::to_string(n_fold)]["score"] = best_fold_score; - results[dataset][std::to_string(n_fold)]["hyperparameters"] = best_fold_hyper; - results[dataset][std::to_string(n_fold)]["seed"] = seed; - results[dataset][std::to_string(n_fold)]["duration"] = timer.getDuration(); - std::cout << get_color_rank(config_mpi.rank) << "*" << std::flush; - } + // void GridSearch::go_mpi(struct ConfigMPI& config_mpi) + // { + // /* + // * Each task is a json object with the following structure: + // * { + // * "dataset": "dataset_name", + // * "seed": # of seed to use, + // * "model": "model_name", + // * "Fold": # of fold to process + // * } + // * + // * The overall process consists in these steps: + // * 1. Manager will broadcast the tasks to all the processes + // * 1.1 Broadcast the number of tasks + // * 1.2 Broadcast the length of the following string + // * 1.2 Broadcast the tasks as a char* string + // * 2. Workers will receive the tasks and start the process + // * 2.1 A method will tell each worker the range of tasks to process + // * 2.2 Each worker will process the tasks and generate the best score for each task + // * 3. Manager gather the scores from all the workers and find out the best hyperparameters for each dataset + // * 3.1 Obtain the maximum size of the results message of all the workers + // * 3.2 Gather all the results from the workers into the manager + // * 3.3 Compile the results from all the workers + // * 3.4 Filter the best hyperparameters for each dataset + // */ + // char* msg; + // int tasks_size; + // if (config_mpi.rank == config_mpi.manager) { + // timer.start(); + // auto tasks = build_tasks_mpi(); + // auto tasks_str = tasks.dump(); + // tasks_size = tasks_str.size(); + // msg = new char[tasks_size + 1]; + // strcpy(msg, tasks_str.c_str()); + // } + // // + // // 1. Manager will broadcast the tasks to all the processes + // // + // MPI_Bcast(&tasks_size, 1, MPI_INT, config_mpi.manager, MPI_COMM_WORLD); + // if (config_mpi.rank != config_mpi.manager) { + // msg = new char[tasks_size + 1]; + // } + // MPI_Bcast(msg, tasks_size + 1, MPI_CHAR, config_mpi.manager, MPI_COMM_WORLD); + // json tasks = json::parse(msg); + // delete[] msg; + // // + // // 2. All Workers will receive the tasks and start the process + // // + // int num_tasks = tasks.size(); + // // 2.1 A method will tell each worker the range of tasks to process + // auto [start, end] = part_range_mpi(num_tasks, config_mpi.n_procs, config_mpi.rank); + // // 2.2 Each worker will process the tasks and return the best scores obtained + // auto datasets = Datasets(config.discretize, Paths::datasets()); + // json results; + // for (int i = start; i < end; ++i) { + // // Process task + // process_task_mpi(config_mpi, tasks[i], datasets, results); + // } + // int size = results.dump().size() + 1; + // int max_size = 0; + // // + // // 3. Manager gather the scores from all the workers and find out the best hyperparameters for each dataset + // // + // //3.1 Obtain the maximum size of the results message of all the workers + // MPI_Allreduce(&size, &max_size, 1, MPI_INT, MPI_MAX, MPI_COMM_WORLD); + // // Assign the memory to the message and initialize it to 0s + // char* total = NULL; + // msg = new char[max_size]; + // strncpy(msg, results.dump().c_str(), size); + // if (config_mpi.rank == config_mpi.manager) { + // total = new char[max_size * config_mpi.n_procs]; + // } + // // 3.2 Gather all the results from the workers into the manager + // MPI_Gather(msg, max_size, MPI_CHAR, total, max_size, MPI_CHAR, config_mpi.manager, MPI_COMM_WORLD); + // delete[] msg; + // if (config_mpi.rank == config_mpi.manager) { + // std::cout << Colors::RESET() << "|" << std::endl; + // json total_results; + // json best_results; + // // 3.3 Compile the results from all the workers + // for (int i = 0; i < config_mpi.n_procs; ++i) { + // json partial_results = json::parse(total + i * max_size); + // for (auto& [dataset, folds] : partial_results.items()) { + // for (auto& [fold, result] : folds.items()) { + // total_results[dataset][fold] = result; + // } + // } + // } + // delete[] total; + // // 3.4 Filter the best hyperparameters for each dataset + // auto grid = GridData(Paths::grid_input(config.model)); + // for (auto& [dataset, folds] : total_results.items()) { + // double best_score = 0.0; + // double duration = 0.0; + // json best_hyper; + // for (auto& [fold, result] : folds.items()) { + // duration += result["duration"].get(); + // if (result["score"] > best_score) { + // best_score = result["score"]; + // best_hyper = result["hyperparameters"]; + // } + // } + // auto timer = Timer(); + // json result = { + // { "score", best_score }, + // { "hyperparameters", best_hyper }, + // { "date", get_date() + " " + get_time() }, + // { "grid", grid.getInputGrid(dataset) }, + // { "duration", timer.translate2String(duration) } + // }; + // best_results[dataset] = result; + // } + // save(best_results); + // } + // } + // void GridSearch::go() + // { + // timer.start(); + // auto grid_type = config.nested == 0 ? "Single" : "Nested"; + // auto datasets = Datasets(config.discretize, Paths::datasets()); + // auto datasets_names = processDatasets(datasets); + // json results = initializeResults(); + // std::cout << "***************** Starting " << grid_type << " Gridsearch *****************" << std::endl; + // std::cout << "input file=" << Paths::grid_input(config.model) << std::endl; + // auto grid = GridData(Paths::grid_input(config.model)); + // Timer timer_dataset; + // double bestScore = 0; + // json bestHyperparameters; + // for (const auto& dataset : datasets_names) { + // if (!config.quiet) + // std::cout << "- " << setw(20) << left << dataset << " " << right << flush; + // auto combinations = grid.getGrid(dataset); + // timer_dataset.start(); + // if (config.nested == 0) + // // for dataset // for hyperparameters // for seed // for fold + // tie(bestScore, bestHyperparameters) = processFileSingle(dataset, datasets, combinations); + // else + // // for dataset // for seed // for fold // for hyperparameters // for nested fold + // tie(bestScore, bestHyperparameters) = processFileNested(dataset, datasets, combinations); + // if (!config.quiet) { + // std::cout << "end." << " Score: " << Colors::IBLUE() << setw(9) << setprecision(7) << fixed + // << bestScore << Colors::BLUE() << " [" << bestHyperparameters.dump() << "]" + // << Colors::RESET() << ::endl; + // } + // json result = { + // { "score", bestScore }, + // { "hyperparameters", bestHyperparameters }, + // { "date", get_date() + " " + get_time() }, + // { "grid", grid.getInputGrid(dataset) }, + // { "duration", timer_dataset.getDurationString() } + // }; + // results[dataset] = result; + // // Save partial results + // save(results); + // } + // // Save final results + // save(results); + // std::cout << "***************** Ending " << grid_type << " Gridsearch *******************" << std::endl; + // } + // pair GridSearch::processFileSingle(std::string fileName, Datasets& datasets, vector& combinations) + // { + // int num = 0; + // double bestScore = 0.0; + // json bestHyperparameters; + // auto totalComb = combinations.size(); + // for (const auto& hyperparam_line : combinations) { + // if (!config.quiet) + // showProgressComb(++num, config.n_folds, totalComb, Colors::CYAN()); + // auto hyperparameters = platform::HyperParameters(datasets.getNames(), hyperparam_line); + // // Get dataset + // auto [X, y] = datasets.getTensors(fileName); + // auto states = datasets.getStates(fileName); + // auto features = datasets.getFeatures(fileName); + // auto className = datasets.getClassName(fileName); + // double totalScore = 0.0; + // int numItems = 0; + // for (const auto& seed : config.seeds) { + // if (!config.quiet) + // std::cout << "(" << seed << ") doing Fold: " << flush; + // Fold* fold; + // if (config.stratified) + // fold = new StratifiedKFold(config.n_folds, y, seed); + // else + // fold = new KFold(config.n_folds, y.size(0), seed); + // for (int nfold = 0; nfold < config.n_folds; nfold++) { + // auto clf = Models::instance()->create(config.model); + // auto valid = clf->getValidHyperparameters(); + // hyperparameters.check(valid, fileName); + // clf->setHyperparameters(hyperparameters.get(fileName)); + // auto [train, test] = fold->getFold(nfold); + // auto train_t = torch::tensor(train); + // auto test_t = torch::tensor(test); + // auto X_train = X.index({ "...", train_t }); + // auto y_train = y.index({ train_t }); + // auto X_test = X.index({ "...", test_t }); + // auto y_test = y.index({ test_t }); + // // Train model + // if (!config.quiet) + // showProgressFold(nfold + 1, getColor(clf->getStatus()), "a"); + // clf->fit(X_train, y_train, features, className, states); + // // Test model + // if (!config.quiet) + // showProgressFold(nfold + 1, getColor(clf->getStatus()), "b"); + // totalScore += clf->score(X_test, y_test); + // numItems++; + // if (!config.quiet) + // std::cout << "\b\b\b, \b" << flush; + // } + // delete fold; + // } + // double score = numItems == 0 ? 0.0 : totalScore / numItems; + // if (score > bestScore) { + // bestScore = score; + // bestHyperparameters = hyperparam_line; + // } + // } + // return { bestScore, bestHyperparameters }; + // } + // pair GridSearch::processFileNested(std::string fileName, Datasets& datasets, vector& combinations) + // { + // // Get dataset + // auto [X, y] = datasets.getTensors(fileName); + // auto states = datasets.getStates(fileName); + // auto features = datasets.getFeatures(fileName); + // auto className = datasets.getClassName(fileName); + // int spcs_combinations = int(log(combinations.size()) / log(10)) + 1; + // double goatScore = 0.0; + // json goatHyperparameters; + // // for dataset // for seed // for fold // for hyperparameters // for nested fold + // for (const auto& seed : config.seeds) { + // Fold* fold; + // if (config.stratified) + // fold = new StratifiedKFold(config.n_folds, y, seed); + // else + // fold = new KFold(config.n_folds, y.size(0), seed); + // double bestScore = 0.0; + // json bestHyperparameters; + // std::cout << "(" << seed << ") doing Fold: " << flush; + // for (int nfold = 0; nfold < config.n_folds; nfold++) { + // if (!config.quiet) + // std::cout << Colors::GREEN() << nfold + 1 << " " << flush; + // // First level fold + // auto [train, test] = fold->getFold(nfold); + // auto train_t = torch::tensor(train); + // auto test_t = torch::tensor(test); + // auto X_train = X.index({ "...", train_t }); + // auto y_train = y.index({ train_t }); + // auto X_test = X.index({ "...", test_t }); + // auto y_test = y.index({ test_t }); + // auto num = 0; + // json result_fold; + // double hypScore = 0.0; + // double bestHypScore = 0.0; + // json bestHypHyperparameters; + // for (const auto& hyperparam_line : combinations) { + // std::cout << "[" << setw(spcs_combinations) << ++num << "/" << setw(spcs_combinations) + // << combinations.size() << "] " << std::flush; + // Fold* nested_fold; + // if (config.stratified) + // nested_fold = new StratifiedKFold(config.nested, y_train, seed); + // else + // nested_fold = new KFold(config.nested, y_train.size(0), seed); + // for (int n_nested_fold = 0; n_nested_fold < config.nested; n_nested_fold++) { + // // Nested level fold + // auto [train_nested, test_nested] = nested_fold->getFold(n_nested_fold); + // auto train_nested_t = torch::tensor(train_nested); + // auto test_nested_t = torch::tensor(test_nested); + // auto X_nexted_train = X_train.index({ "...", train_nested_t }); + // auto y_nested_train = y_train.index({ train_nested_t }); + // auto X_nested_test = X_train.index({ "...", test_nested_t }); + // auto y_nested_test = y_train.index({ test_nested_t }); + // // Build Classifier with selected hyperparameters + // auto hyperparameters = platform::HyperParameters(datasets.getNames(), hyperparam_line); + // auto clf = Models::instance()->create(config.model); + // auto valid = clf->getValidHyperparameters(); + // hyperparameters.check(valid, fileName); + // clf->setHyperparameters(hyperparameters.get(fileName)); + // // Train model + // if (!config.quiet) + // showProgressFold(n_nested_fold + 1, getColor(clf->getStatus()), "a"); + // clf->fit(X_nexted_train, y_nested_train, features, className, states); + // // Test model + // if (!config.quiet) + // showProgressFold(n_nested_fold + 1, getColor(clf->getStatus()), "b"); + // hypScore += clf->score(X_nested_test, y_nested_test); + // if (!config.quiet) + // std::cout << "\b\b\b, \b" << flush; + // } + // int magic = 3 * config.nested + 2 * spcs_combinations + 4; + // std::cout << string(magic, '\b') << string(magic, ' ') << string(magic, '\b') << flush; + // delete nested_fold; + // hypScore /= config.nested; + // if (hypScore > bestHypScore) { + // bestHypScore = hypScore; + // bestHypHyperparameters = hyperparam_line; + // } + // } + // // Build Classifier with selected hyperparameters + // auto clf = Models::instance()->create(config.model); + // clf->setHyperparameters(bestHypHyperparameters); + // // Train model + // if (!config.quiet) + // showProgressFold(nfold + 1, getColor(clf->getStatus()), "a"); + // clf->fit(X_train, y_train, features, className, states); + // // Test model + // if (!config.quiet) + // showProgressFold(nfold + 1, getColor(clf->getStatus()), "b"); + // double score = clf->score(X_test, y_test); + // if (!config.quiet) + // std::cout << string(2 * config.nested - 1, '\b') << "," << string(2 * config.nested, ' ') << string(2 * config.nested - 1, '\b') << flush; + // if (score > bestScore) { + // bestScore = score; + // bestHyperparameters = bestHypHyperparameters; + // } + // } + // if (bestScore > goatScore) { + // goatScore = bestScore; + // goatHyperparameters = bestHyperparameters; + // } + // delete fold; + // } + // return { goatScore, goatHyperparameters }; + // } + // void GridSearch::process_task_mpi(struct ConfigMPI& config_mpi, json& task, Datasets& datasets, json& results) + // { + // // Process the task and store the result in the results json + // Timer timer; + // timer.start(); + // auto grid = GridData(Paths::grid_input(config.model)); + // auto dataset = task["dataset"].get(); + // auto seed = task["seed"].get(); + // auto n_fold = task["fold"].get(); + // // Generate the hyperparamters combinations + // auto combinations = grid.getGrid(dataset); + // auto [X, y] = datasets.getTensors(dataset); + // auto states = datasets.getStates(dataset); + // auto features = datasets.getFeatures(dataset); + // auto className = datasets.getClassName(dataset); + // // + // // Start working on task + // // + // Fold* fold; + // if (config.stratified) + // fold = new StratifiedKFold(config.n_folds, y, seed); + // else + // fold = new KFold(config.n_folds, y.size(0), seed); + // auto [train, test] = fold->getFold(n_fold); + // auto train_t = torch::tensor(train); + // auto test_t = torch::tensor(test); + // auto X_train = X.index({ "...", train_t }); + // auto y_train = y.index({ train_t }); + // auto X_test = X.index({ "...", test_t }); + // auto y_test = y.index({ test_t }); + // auto num = 0; + // double best_fold_score = 0.0; + // json best_fold_hyper; + // for (const auto& hyperparam_line : combinations) { + // auto hyperparameters = platform::HyperParameters(datasets.getNames(), hyperparam_line); + // Fold* nested_fold; + // if (config.stratified) + // nested_fold = new StratifiedKFold(config.nested, y_train, seed); + // else + // nested_fold = new KFold(config.nested, y_train.size(0), seed); + // double score = 0.0; + // for (int n_nested_fold = 0; n_nested_fold < config.nested; n_nested_fold++) { + // // Nested level fold + // auto [train_nested, test_nested] = nested_fold->getFold(n_nested_fold); + // auto train_nested_t = torch::tensor(train_nested); + // auto test_nested_t = torch::tensor(test_nested); + // auto X_nested_train = X_train.index({ "...", train_nested_t }); + // auto y_nested_train = y_train.index({ train_nested_t }); + // auto X_nested_test = X_train.index({ "...", test_nested_t }); + // auto y_nested_test = y_train.index({ test_nested_t }); + // // Build Classifier with selected hyperparameters + // auto clf = Models::instance()->create(config.model); + // auto valid = clf->getValidHyperparameters(); + // hyperparameters.check(valid, dataset); + // clf->setHyperparameters(hyperparameters.get(dataset)); + // // Train model + // clf->fit(X_nested_train, y_nested_train, features, className, states); + // // Test model + // score += clf->score(X_nested_test, y_nested_test); + // } + // delete nested_fold; + // score /= config.nested; + // if (score > best_fold_score) { + // best_fold_score = score; + // best_fold_hyper = hyperparam_line; + // } + // } + // delete fold; + // // Build Classifier with the best hyperparameters to obtain the best score + // auto hyperparameters = platform::HyperParameters(datasets.getNames(), best_fold_hyper); + // auto clf = Models::instance()->create(config.model); + // auto valid = clf->getValidHyperparameters(); + // hyperparameters.check(valid, dataset); + // clf->setHyperparameters(best_fold_hyper); + // clf->fit(X_train, y_train, features, className, states); + // best_fold_score = clf->score(X_test, y_test); + // // Save results + // results[dataset][std::to_string(n_fold)]["score"] = best_fold_score; + // results[dataset][std::to_string(n_fold)]["hyperparameters"] = best_fold_hyper; + // results[dataset][std::to_string(n_fold)]["seed"] = seed; + // results[dataset][std::to_string(n_fold)]["duration"] = timer.getDuration(); + // std::cout << get_color_rank(config_mpi.rank) << "*" << std::flush; + // } json GridSearch::initializeResults() { // Load previous results diff --git a/src/Platform/GridSearch.h b/src/Platform/GridSearch.h index 08b874d..05ece4f 100644 --- a/src/Platform/GridSearch.h +++ b/src/Platform/GridSearch.h @@ -44,22 +44,22 @@ namespace platform { class GridSearch { public: explicit GridSearch(struct ConfigGrid& config); - void go(); - void go_mpi(struct ConfigMPI& config_mpi); + // void go(); + // void go_mpi(struct ConfigMPI& config_mpi); void go_producer_consumer(struct ConfigMPI& config_mpi); ~GridSearch() = default; - json getResults(); + json loadResults(); static inline std::string NO_CONTINUE() { return "NO_CONTINUE"; } private: void save(json& results); json initializeResults(); - vector processDatasets(Datasets& datasets) const; - pair processFileSingle(std::string fileName, Datasets& datasets, std::vector& combinations); - pair processFileNested(std::string fileName, Datasets& datasets, std::vector& combinations); + vector filterDatasets(Datasets& datasets) const; + // pair processFileSingle(std::string fileName, Datasets& datasets, std::vector& combinations); + // pair processFileNested(std::string fileName, Datasets& datasets, std::vector& combinations); struct ConfigGrid config; - pair part_range_mpi(int n_tasks, int nprocs, int rank); + // pair part_range_mpi(int n_tasks, int nprocs, int rank); json build_tasks_mpi(); - void process_task_mpi(struct ConfigMPI& config_mpi, json& task, Datasets& datasets, json& results); + // void process_task_mpi(struct ConfigMPI& config_mpi, json& task, Datasets& datasets, json& results); Timer timer; // used to measure the time of the whole process }; } /* namespace platform */ diff --git a/src/Platform/b_grid.cc b/src/Platform/b_grid.cc index 055da26..1d42543 100644 --- a/src/Platform/b_grid.cc +++ b/src/Platform/b_grid.cc @@ -203,18 +203,18 @@ int main(int argc, char** argv) MPI_Comm_size(MPI_COMM_WORLD, &mpi_config.n_procs); grid_search.go_producer_consumer(mpi_config); if (mpi_config.rank == mpi_config.manager) { - auto results = grid_search.getResults(); + auto results = grid_search.loadResults(); list_results(results, config.model); std::cout << "Process took " << timer.getDurationString() << std::endl; } MPI_Finalize(); - } else { - grid_search.go(); - std::cout << "Process took " << timer.getDurationString() << std::endl; + // } else { + // grid_search.go(); + // std::cout << "Process took " << timer.getDurationString() << std::endl; } } else { // List results - auto results = grid_search.getResults(); + auto results = grid_search.loadResults(); if (results.empty()) { std::cout << "** No results found" << std::endl; } else {