Add hyperparameters management in experiments

src/Platform/Experiment.cc

@@ -25,6 +25,7 @@ namespace platform {
         oss << std::put_time(timeinfo, "%H:%M:%S");
         return oss.str();
     }
+    Experiment::Experiment() : hyperparameters(json::parse("{}")) {}
     string Experiment::get_file_name()
     {
         string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
@@ -124,6 +125,8 @@ namespace platform {
         auto result = Result();
         auto [values, counts] = at::_unique(y);
         result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
+        result.setHyperparameters(hyperparameters);
+        // Initialize results vectors
         int nResults = nfolds * static_cast<int>(randomSeeds.size());
         auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
         auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
@@ -144,6 +147,10 @@ namespace platform {
             for (int nfold = 0; nfold < nfolds; nfold++) {
                 auto clf = Models::instance()->create(model);
                 setModelVersion(clf->getVersion());
+                if (hyperparameters.size() != 0) {
+                    clf->setHyperparameters(hyperparameters);
+                }
+                // Split train - test dataset
                 train_timer.start();
                 auto [train, test] = fold->getFold(nfold);
                 auto train_t = torch::tensor(train);
@@ -153,12 +160,14 @@ namespace platform {
                 auto X_test = X.index({ "...", test_t });
                 auto y_test = y.index({ test_t });
                 cout << nfold + 1 << ", " << flush;
+                // Train model
                 clf->fit(X_train, y_train, features, className, states);
                 nodes[item] = clf->getNumberOfNodes();
                 edges[item] = clf->getNumberOfEdges();
                 num_states[item] = clf->getNumberOfStates();
                 train_time[item] = train_timer.getDuration();
                 auto accuracy_train_value = clf->score(X_train, y_train);
+                // Test model
                 test_timer.start();
                 auto accuracy_test_value = clf->score(X_test, y_test);
                 test_time[item] = test_timer.getDuration();

src/Platform/Experiment.h

@@ -29,7 +29,8 @@ namespace platform {
     };
     class Result {
     private:
-        string dataset, hyperparameters, model_version;
+        string dataset, model_version;
+        json hyperparameters;
         int samples{ 0 }, features{ 0 }, classes{ 0 };
         double score_train{ 0 }, score_test{ 0 }, score_train_std{ 0 }, score_test_std{ 0 }, train_time{ 0 }, train_time_std{ 0 }, test_time{ 0 }, test_time_std{ 0 };
         float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
@@ -37,7 +38,7 @@ namespace platform {
     public:
         Result() = default;
         Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
-        Result& setHyperparameters(const string& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
+        Result& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
         Result& setSamples(int samples) { this->samples = samples; return *this; }
         Result& setFeatures(int features) { this->features = features; return *this; }
         Result& setClasses(int classes) { this->classes = classes; return *this; }
@@ -59,7 +60,7 @@ namespace platform {
         const float get_score_train() const { return score_train; }
         float get_score_test() { return score_test; }
         const string& getDataset() const { return dataset; }
-        const string& getHyperparameters() const { return hyperparameters; }
+        const json& getHyperparameters() const { return hyperparameters; }
         const int getSamples() const { return samples; }
         const int getFeatures() const { return features; }
         const int getClasses() const { return classes; }
@@ -85,11 +86,12 @@ namespace platform {
         bool discretized{ false }, stratified{ false };
         vector<Result> results;
         vector<int> randomSeeds;
+        json hyperparameters = "{}";
         int nfolds{ 0 };
         float duration{ 0 };
         json build_json();
     public:
-        Experiment() = default;
+        Experiment();
         Experiment& setTitle(const string& title) { this->title = title; return *this; }
         Experiment& setModel(const string& model) { this->model = model; return *this; }
         Experiment& setPlatform(const string& platform) { this->platform = platform; return *this; }
@@ -103,6 +105,7 @@ namespace platform {
         Experiment& addResult(Result result) { results.push_back(result); return *this; }
         Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
         Experiment& setDuration(float duration) { this->duration = duration; return *this; }
+        Experiment& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
         string get_file_name();
         void save(const string& path);
         void cross_validation(const string& path, const string& fileName);

src/Platform/main.cc

@@ -1,5 +1,6 @@
 #include <iostream>
 #include <argparse/argparse.hpp>
+#include <nlohmann/json.hpp>
 #include "platformUtils.h"
 #include "Experiment.h"
 #include "Datasets.h"
@@ -10,12 +11,14 @@
 
 
 using namespace std;
+using json = nlohmann::json;
 
 argparse::ArgumentParser manageArguments(int argc, char** argv)
 {
     auto env = platform::DotEnv();
     argparse::ArgumentParser program("main");
     program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
+    program.add_argument("--hyperparameters").default_value("{}").help("Hyperparamters passed to the model in Experiment");
     program.add_argument("-p", "--path")
         .help("folder where the data files are located, default")
         .default_value(string{ platform::Paths::datasets() });
@@ -59,6 +62,7 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
         auto seeds = program.get<vector<int>>("seeds");
         auto complete_file_name = path + file_name + ".arff";
         auto title = program.get<string>("title");
+        auto hyperparameters = program.get<string>("hyperparameters");
         if (title == "" && file_name == "") {
             throw runtime_error("title is mandatory if dataset is not provided");
         }
@@ -82,6 +86,7 @@ int main(int argc, char** argv)
     auto stratified = program.get<bool>("stratified");
     auto n_folds = program.get<int>("folds");
     auto seeds = program.get<vector<int>>("seeds");
+    auto hyperparameters =program.get<string>("hyperparameters");
     vector<string> filesToTest;
     auto datasets = platform::Datasets(path, true, platform::ARFF);
     auto title = program.get<string>("title");
@@ -106,6 +111,7 @@ int main(int argc, char** argv)
     experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("14.0.3");
     experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
     experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
+    experiment.setHyperparameters(json::parse(hyperparameters));
     for (auto seed : seeds) {
         experiment.addRandomSeed(seed);
     }