rmontanana/BayesNet
1
0
Fork 0
Code Issues 2 Pull Requests 1 Actions Packages Projects Releases 6 Wiki Activity

Refactor mpi grid search process using the producer consumer pattern #15

Merged
rmontanana merged 13 commits from producer_consumer into main 2024-01-04 15:24:48 +00:00
Conversation 0 Commits 13 Files Changed 4 +255 -404
4 changed files with 255 additions and 404 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 722da7f781 - Show all commits

527
src/Platform/GridSearch.cc
View File

@@ -30,7 +30,7 @@ namespace platform {
}
std::string get_color_rank(int rank)
{
auto colors = { Colors::RED(), Colors::GREEN(), Colors::BLUE(), Colors::MAGENTA(), Colors::CYAN() };
auto colors = { Colors::WHITE(), Colors::RED(), Colors::GREEN(), Colors::BLUE(), Colors::MAGENTA(), Colors::CYAN() };
return *(colors.begin() + rank % colors.size());
}
GridSearch::GridSearch(struct ConfigGrid& config) : config(config)
@@ -77,32 +77,7 @@ namespace platform {
}
return datasets_names;
}
void showProgressComb(const int num, const int n_folds, const int total, const std::string& color)
{
int spaces = int(log(total) / log(10)) + 1;
int magic = n_folds * 3 + 22 + 2 * spaces;
std::string prefix = num == 1 ? "" : string(magic, '\b') + string(magic + 1, ' ') + string(magic + 1, '\b');
std::cout << prefix << color << "(" << setw(spaces) << num << "/" << setw(spaces) << total << ") " << Colors::RESET() << flush;
}
void showProgressFold(int fold, const std::string& color, const std::string& phase)
{
std::string prefix = phase == "a" ? "" : "\b\b\b\b";
std::cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
}
std::string getColor(bayesnet::status_t status)
{
switch (status) {
case bayesnet::NORMAL:
return Colors::GREEN();
case bayesnet::WARNING:
return Colors::YELLOW();
case bayesnet::ERROR:
return Colors::RED();
default:
return Colors::RESET();
}
}
json GridSearch::build_tasks_mpi()
json GridSearch::build_tasks_mpi(int rank)
{
auto tasks = json::array();
auto grid = GridData(Paths::grid_input(config.model));
@@ -124,10 +99,10 @@ namespace platform {
}
}
}
// It's important to shuffle the array so heavy datasets are spread across the Workers
// Shuffle the array so heavy datasets are spread across the workers
std::mt19937 g{ 271 }; // Use fixed seed to obtain the same shuffle
std::shuffle(tasks.begin(), tasks.end(), g);
std::cout << "Tasks size: " << tasks.size() << std::endl;
std::cout << get_color_rank(rank) << "* Number of tasks: " << tasks.size() << std::endl;
std::cout << "|";
for (int i = 0; i < tasks.size(); ++i) {
std::cout << (i + 1) % 10;
@@ -226,24 +201,6 @@ namespace platform {
// Update progress bar
std::cout << get_color_rank(config_mpi.rank) << "*" << std::flush;
}
// std::pair<int, int> 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<std::string>& names, Task_Result& result, json& results)
{
json json_result = {
@@ -266,6 +223,9 @@ namespace platform {
json results;
int num_tasks = tasks.size();
//
// 2a.1 Producer will loop to send all the tasks to the consumers and receive the results
//
for (int i = 0; i < num_tasks; ++i) {
MPI_Status status;
MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
@@ -275,7 +235,9 @@ namespace platform {
}
MPI_Send(&i, 1, MPI_INT, status.MPI_SOURCE, TAG_TASK, MPI_COMM_WORLD);
}
// Send end message to all workers but the manager
//
// 2a.2 Producer will send the end message to all the consumers
//
for (int i = 0; i < config_mpi.n_procs - 1; ++i) {
MPI_Status status;
MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
@@ -287,9 +249,8 @@ namespace platform {
}
return results;
}
json select_best_results_folds(json& all_results, std::string& model)
void select_best_results_folds(json& results, json& all_results, std::string& model)
{
json results;
Timer timer;
auto grid = GridData(Paths::grid_input(model));
//
@@ -317,33 +278,39 @@ namespace platform {
};
results[dataset] = json_best;
}
return results;
}
void consumer(Datasets& datasets, json& tasks, struct ConfigGrid& config, struct ConfigMPI& config_mpi, MPI_Datatype& MPI_Result)
{
Task_Result result;
// Anounce to the producer
//
// 2b.1 Consumers announce to the producer that they are ready to receive a task
//
MPI_Send(&result, 1, MPI_Result, config_mpi.manager, TAG_QUERY, MPI_COMM_WORLD);
int task;
while (true) {
MPI_Status status;
//
// 2b.2 Consumers receive the task from the producer and process it
//
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
process_task_mpi_consumer(config, config_mpi, tasks, task, datasets, &result);
// Send result to producer
//
// 2b.3 Consumers send the result to the producer
//
MPI_Send(&result, 1, MPI_Result, config_mpi.manager, TAG_RESULT, MPI_COMM_WORLD);
}
}
void GridSearch::go_producer_consumer(struct ConfigMPI& config_mpi)
void GridSearch::go(struct ConfigMPI& config_mpi)
{
/*
* Each task is a json object with the following structure:
* {
* "dataset": "dataset_name",
* "idx_dataset": idx_dataset,
* "idx_dataset": idx_dataset, // used to identify the dataset in the results
* // this index is relative to the used datasets in the actual run not to the whole datasets
* "seed": # of seed to use,
* "Fold": # of fold to process
* }
@@ -356,14 +323,16 @@ namespace platform {
* 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
* 2a. Producer delivers the tasks to the consumers
* 2a.1 Producer will loop to send all the tasks to the consumers and receive the results
* 2a.2 Producer will send the end message to all the consumers
* 2b. Consumers process the tasks and send the results to the producer
* 2b.1 Consumers announce to the producer that they are ready to receive a task
* 2b.2 Consumers receive the task from the producer and process it
* 2b.3 Consumers send the result to the producer
* 3. Manager select the bests sccores for each dataset
* 3.1 Loop thru all the results obtained from each outer fold (task) and select the best
* 3.2 Save the results
*/
//
// 0.1 Create the MPI result type
@@ -388,7 +357,7 @@ namespace platform {
json tasks;
if (config_mpi.rank == config_mpi.manager) {
timer.start();
tasks = build_tasks_mpi();
tasks = build_tasks_mpi(config_mpi.rank);
auto tasks_str = tasks.dump();
tasks_size = tasks_str.size();
msg = new char[tasks_size + 1];
@@ -404,429 +373,33 @@ namespace platform {
MPI_Bcast(msg, tasks_size + 1, MPI_CHAR, config_mpi.manager, MPI_COMM_WORLD);
tasks = json::parse(msg);
delete[] msg;
//
// 2. All Workers will receive the tasks and start the process
//
auto datasets = Datasets(config.discretize, Paths::datasets());
if (config_mpi.rank == config_mpi.manager) {
//
// 2a. Producer delivers the tasks to the consumers
//
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);
std::cout << get_color_rank(config_mpi.rank) << "|" << std::endl;
//
// 3. Manager select the bests sccores for each dataset
//
auto results = initializeResults();
select_best_results_folds(results, all_results, config.model);
//
// 3.2 Save the results
//
save(results);
std::cout << Colors::RESET() << "|" << std::endl;
} else {
//
// 2b. Consumers process the tasks and send the results to the producer
//
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",
// * "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<double>();
// 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<double, json> GridSearch::processFileSingle(std::string fileName, Datasets& datasets, vector<json>& 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<double, json> GridSearch::processFileNested(std::string fileName, Datasets& datasets, vector<json>& 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<std::string>();
// auto seed = task["seed"].get<int>();
// auto n_fold = task["fold"].get<int>();
// // 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
// Load previous results if continue is set
json results;
if (config.continue_from != NO_CONTINUE()) {
if (!config.quiet)

10
src/Platform/GridSearch.h
View File

@@ -44,9 +44,7 @@ namespace platform {
class GridSearch {
public:
explicit GridSearch(struct ConfigGrid& config);
// void go();
// void go_mpi(struct ConfigMPI& config_mpi);
void go_producer_consumer(struct ConfigMPI& config_mpi);
void go(struct ConfigMPI& config_mpi);
~GridSearch() = default;
json loadResults();
static inline std::string NO_CONTINUE() { return "NO_CONTINUE"; }
@@ -54,12 +52,8 @@ namespace platform {
void save(json& results);
json initializeResults();
std::vector<std::string> filterDatasets(Datasets& datasets) const;
// 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);
struct ConfigGrid config;
// pair<int, int> 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);
json build_tasks_mpi(int rank);
Timer timer; // used to measure the time of the whole process
};
} /* namespace platform */

43
src/Platform/b_grid.cc
View File

@@ -32,7 +32,6 @@ void manageArguments(argparse::ArgumentParser& program)
group.add_argument("--report").help("Report the computed hyperparameters").default_value(false).implicit_value(true);
group.add_argument("--compute").help("Perform computation of the grid output hyperparameters").default_value(false).implicit_value(true);
program.add_argument("--discretize").help("Discretize input datasets").default_value((bool)stoi(env.get("discretize"))).implicit_value(true);
program.add_argument("--mpi").help("Use MPI computing grid").default_value(false).implicit_value(true);
program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value((bool)stoi(env.get("stratified"))).implicit_value(true);
program.add_argument("--quiet").help("Don't display detailed progress").default_value(false).implicit_value(true);
program.add_argument("--continue").help("Continue computing from that dataset").default_value(platform::GridSearch::NO_CONTINUE());
@@ -108,8 +107,8 @@ void list_results(json& results, std::string& model)
+ " Nested: " + (results["nested"].get<int>() == 0 ? "False" : to_string(results["nested"].get<int>()))
);
std::cout << std::string(MAXL, '*') << std::endl;
int spaces = 0;
int hyperparameters_spaces = 0;
int spaces = 7;
int hyperparameters_spaces = 15;
for (const auto& item : results["results"].items()) {
auto key = item.key();
auto value = item.value();
@@ -128,11 +127,10 @@ void list_results(json& results, std::string& model)
int index = 0;
for (const auto& item : results["results"].items()) {
auto color = odd ? Colors::CYAN() : Colors::BLUE();
auto key = item.key();
auto value = item.value();
std::cout << color;
std::cout << std::setw(3) << std::right << index++ << " ";
std::cout << left << setw(spaces) << key << " " << value["date"].get<string>()
std::cout << left << setw(spaces) << item.key() << " " << value["date"].get<string>()
<< " " << setw(8) << right << value["duration"].get<string>() << " " << setw(8) << setprecision(6)
<< fixed << right << value["score"].get<double>() << " " << value["hyperparameters"].dump() << std::endl;
odd = !odd;
@@ -171,11 +169,6 @@ int main(int argc, char** argv)
}
auto excluded = program.get<std::string>("exclude");
config.excluded = json::parse(excluded);
if (program.get<bool>("mpi")) {
if (!compute || config.nested == 0) {
throw std::runtime_error("Cannot use --mpi without --compute or without --nested");
}
}
}
catch (const exception& err) {
cerr << err.what() << std::endl;
@@ -195,23 +188,21 @@ int main(int argc, char** argv)
list_dump(config.model);
} else {
if (compute) {
if (program.get<bool>("mpi")) {
struct platform::ConfigMPI mpi_config;
mpi_config.manager = 0; // which process is the manager
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &mpi_config.rank);
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.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;
struct platform::ConfigMPI mpi_config;
mpi_config.manager = 0; // which process is the manager
MPI_Init(&argc, &argv);
MPI_Comm_rank(MPI_COMM_WORLD, &mpi_config.rank);
MPI_Comm_size(MPI_COMM_WORLD, &mpi_config.n_procs);
if (mpi_config.n_procs < 2) {
throw std::runtime_error("Cannot use --compute with less than 2 mpi processes, try mpirun -np 2 ...");
}
grid_search.go(mpi_config);
if (mpi_config.rank == mpi_config.manager) {
auto results = grid_search.loadResults();
list_results(results, config.model);
std::cout << "Process took " << timer.getDurationString() << std::endl;
}
MPI_Finalize();
} else {
// List results
auto results = grid_search.loadResults();