Add hyperparameters management in experiments

sample/CMakeLists.txt

@@ -3,5 +3,6 @@ include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
 include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
+include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
 add_executable(BayesNetSample sample.cc ${BayesNet_SOURCE_DIR}/src/Platform/Folding.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc) 
 target_link_libraries(BayesNetSample BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

sample/sample.cc

@@ -3,6 +3,7 @@
 #include <string>
 #include <map>
 #include <argparse/argparse.hpp>
+#include <nlohmann/json.hpp>
 #include "ArffFiles.h"
 #include "BayesMetrics.h"
 #include "CPPFImdlp.h"
@@ -141,111 +142,97 @@ int main(int argc, char** argv)
     /*
     * Begin Processing
     */
-    auto ypred = torch::tensor({ 1,2,3,2,2,3,4,5,2,1 });
+    weights.index_put_({ mask }, weights + 10);
-    auto y = torch::tensor({ 0,0,0,0,2,3,4,0,0,0 });
+    auto handler = ArffFiles();
-    auto weights = torch::ones({ 10 }, kDouble);
+    handler.load(complete_file_name, class_last);
-    auto mask = ypred == y;
+    // Get Dataset X, y
-    cout << "ypred:" << ypred << endl;
+    vector<mdlp::samples_t>& X = handler.getX();
-    cout << "y:" << y << endl;
+    mdlp::labels_t& y = handler.getY();
-    cout << "weights:" << weights << endl;
+    // Get className & Features
-    cout << "mask:" << mask << endl;
+    auto className = handler.getClassName();
-    double value_to_add = 0.5;
+    vector<string> features;
-    weights += mask.to(torch::kDouble) * value_to_add;
+    auto attributes = handler.getAttributes();
-    cout << "New weights:" << weights << endl;
+    transform(attributes.begin(), attributes.end(), back_inserter(features),
-    auto masked_weights = weights * mask.to(weights.dtype());
+        [](const pair<string, string>& item) { return item.first; });
-    double sum_of_weights = masked_weights.sum().item<double>();
+    // Discretize Dataset
-    cout << "Sum of weights: " << sum_of_weights << endl;
+    auto [Xd, maxes] = discretize(X, y, features);
-    //weights.index_put_({ mask }, weights + 10);
+    maxes[className] = *max_element(y.begin(), y.end()) + 1;
-    // auto handler = ArffFiles();
+    map<string, vector<int>> states;
-    // handler.load(complete_file_name, class_last);
+    for (auto feature : features) {
-    // // Get Dataset X, y
+        states[feature] = vector<int>(maxes[feature]);
-    // vector<mdlp::samples_t>& X = handler.getX();
+    }
-    // mdlp::labels_t& y = handler.getY();
+    states[className] = vector<int>(maxes[className]);
-    // // Get className & Features
+    auto clf = platform::Models::instance()->create(model_name);
-    // auto className = handler.getClassName();
+    clf->fit(Xd, y, features, className, states);
-    // vector<string> features;
+    if (dump_cpt) {
-    // auto attributes = handler.getAttributes();
+        cout << "--- CPT Tables ---" << endl;
-    // transform(attributes.begin(), attributes.end(), back_inserter(features),
+        clf->dump_cpt();
-    //     [](const pair<string, string>& item) { return item.first; });
+    }
-    // // Discretize Dataset
+    auto lines = clf->show();
-    // auto [Xd, maxes] = discretize(X, y, features);
+    for (auto line : lines) {
-    // maxes[className] = *max_element(y.begin(), y.end()) + 1;
+        cout << line << endl;
-    // map<string, vector<int>> states;
+    }
-    // for (auto feature : features) {
+    cout << "--- Topological Order ---" << endl;
-    //     states[feature] = vector<int>(maxes[feature]);
+    auto order = clf->topological_order();
-    // }
+    for (auto name : order) {
-    // states[className] = vector<int>(maxes[className]);
+        cout << name << ", ";
-    // auto clf = platform::Models::instance()->create(model_name);
+    }
-    // clf->fit(Xd, y, features, className, states);
+    cout << "end." << endl;
-    // if (dump_cpt) {
+    auto score = clf->score(Xd, y);
-    //     cout << "--- CPT Tables ---" << endl;
+    cout << "Score: " << score << endl;
-    //     clf->dump_cpt();
+    auto graph = clf->graph();
-    // }
+    auto dot_file = model_name + "_" + file_name;
-    // auto lines = clf->show();
+    ofstream file(dot_file + ".dot");
-    // for (auto line : lines) {
+    file << graph;
-    //     cout << line << endl;
+    file.close();
-    // }
+    cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
-    // cout << "--- Topological Order ---" << endl;
+    cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
-    // auto order = clf->topological_order();
+    string stratified_string = stratified ? " Stratified" : "";
-    // for (auto name : order) {
+    cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
-    //     cout << name << ", ";
+    cout << "==========================================" << endl;
-    // }
+    torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
-    // cout << "end." << endl;
+    torch::Tensor yt = torch::tensor(y, torch::kInt32);
-    // auto score = clf->score(Xd, y);
+    for (int i = 0; i < features.size(); ++i) {
-    // cout << "Score: " << score << endl;
+        Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
-    // auto graph = clf->graph();
+    }
-    // auto dot_file = model_name + "_" + file_name;
+    float total_score = 0, total_score_train = 0, score_train, score_test;
-    // ofstream file(dot_file + ".dot");
+    Fold* fold;
-    // file << graph;
+    if (stratified)
-    // file.close();
+        fold = new StratifiedKFold(nFolds, y, seed);
-    // cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
+    else
-    // cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
+        fold = new KFold(nFolds, y.size(), seed);
-    // string stratified_string = stratified ? " Stratified" : "";
+    for (auto i = 0; i < nFolds; ++i) {
-    // cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
+        auto [train, test] = fold->getFold(i);
-    // cout << "==========================================" << endl;
+        cout << "Fold: " << i + 1 << endl;
-    // torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
+        if (tensors) {
-    // torch::Tensor yt = torch::tensor(y, torch::kInt32);
+            auto ttrain = torch::tensor(train, torch::kInt64);
-    // for (int i = 0; i < features.size(); ++i) {
+            auto ttest = torch::tensor(test, torch::kInt64);
-    //     Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
+            torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
-    // }
+            torch::Tensor ytraint = yt.index({ ttrain });
-    // float total_score = 0, total_score_train = 0, score_train, score_test;
+            torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
-    // Fold* fold;
+            torch::Tensor ytestt = yt.index({ ttest });
-    // if (stratified)
+            clf->fit(Xtraint, ytraint, features, className, states);
-    //     fold = new StratifiedKFold(nFolds, y, seed);
+            auto temp = clf->predict(Xtraint);
-    // else
+            score_train = clf->score(Xtraint, ytraint);
-    //     fold = new KFold(nFolds, y.size(), seed);
+            score_test = clf->score(Xtestt, ytestt);
-    // for (auto i = 0; i < nFolds; ++i) {
+        } else {
-    //     auto [train, test] = fold->getFold(i);
+            auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
-    //     cout << "Fold: " << i + 1 << endl;
+            auto [Xtest, ytest] = extract_indices(test, Xd, y);
-    //     if (tensors) {
+            clf->fit(Xtrain, ytrain, features, className, states);
-    //         auto ttrain = torch::tensor(train, torch::kInt64);
+            score_train = clf->score(Xtrain, ytrain);
-    //         auto ttest = torch::tensor(test, torch::kInt64);
+            score_test = clf->score(Xtest, ytest);
-    //         torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
+        }
-    //         torch::Tensor ytraint = yt.index({ ttrain });
+        if (dump_cpt) {
-    //         torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
+            cout << "--- CPT Tables ---" << endl;
-    //         torch::Tensor ytestt = yt.index({ ttest });
+            clf->dump_cpt();
-    //         clf->fit(Xtraint, ytraint, features, className, states);
+        }
-    //         auto temp = clf->predict(Xtraint);
+        total_score_train += score_train;
-    //         score_train = clf->score(Xtraint, ytraint);
+        total_score += score_test;
-    //         score_test = clf->score(Xtestt, ytestt);
+        cout << "Score Train: " << score_train << endl;
-    //     } else {
+        cout << "Score Test : " << score_test << endl;
-    //         auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
+        cout << "-------------------------------------------------------------------------------" << endl;
-    //         auto [Xtest, ytest] = extract_indices(test, Xd, y);
+    }
-    //         clf->fit(Xtrain, ytrain, features, className, states);
+    cout << "**********************************************************************************" << endl;
-    //         score_train = clf->score(Xtrain, ytrain);
+    cout << "Average Score Train: " << total_score_train / nFolds << endl;
-    //         score_test = clf->score(Xtest, ytest);
+    cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
-    //     }
-    //     if (dump_cpt) {
-    //         cout << "--- CPT Tables ---" << endl;
-    //         clf->dump_cpt();
-    //     }
-    //     total_score_train += score_train;
-    //     total_score += score_test;
-    //     cout << "Score Train: " << score_train << endl;
-    //     cout << "Score Test : " << score_test << endl;
-    //     cout << "-------------------------------------------------------------------------------" << endl;
-    // }
-    // cout << "**********************************************************************************" << endl;
-    // cout << "Average Score Train: " << total_score_train / nFolds << endl;
-    // cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
 }

src/BayesNet/AODE.h

@@ -10,6 +10,7 @@ namespace bayesnet {
         AODE();
         virtual ~AODE() {};
         vector<string> graph(const string& title = "AODE") const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif

src/BayesNet/AODELd.h

@@ -16,6 +16,7 @@ namespace bayesnet {
         virtual ~AODELd() = default;
         vector<string> graph(const string& name = "AODE") const override;
         static inline string version() { return "0.0.1"; };
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif // !AODELD_H

src/BayesNet/BaseClassifier.h

@@ -1,6 +1,7 @@
 #ifndef BASE_H
 #define BASE_H
 #include <torch/torch.h>
+#include <nlohmann/json.hpp>
 #include <vector>
 namespace bayesnet {
     using namespace std;
@@ -27,6 +28,7 @@ namespace bayesnet {
         const string inline getVersion() const { return "0.1.0"; };
         vector<string> virtual topological_order() = 0;
         void virtual dump_cpt()const = 0;
+        virtual void setHyperparameters(nlohmann::json& hyperparameters) = 0;
     };
 }
 #endif

src/BayesNet/BoostAODE.cc

@@ -2,11 +2,17 @@
 #include "BayesMetrics.h"
 
 namespace bayesnet {
-    BoostAODE::BoostAODE() : Ensemble() {}
+    BoostAODE::BoostAODE() : Ensemble(), repeatSparent(false) {}
     void BoostAODE::buildModel(const torch::Tensor& weights)
     {
         // Models shall be built in trainModel
     }
+    void BoostAODE::setHyperparameters(nlohmann::json& hyperparameters)
+    {
+        if (hyperparameters.contains("repeatSparent")) {
+            repeatSparent = hyperparameters["repeatSparent"];
+        }
+    }
     void BoostAODE::trainModel(const torch::Tensor& weights)
     {
         models.clear();
@@ -16,7 +22,6 @@ namespace bayesnet {
         auto X_ = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
         auto y_ = dataset.index({ -1, "..." });
         bool exitCondition = false;
-        bool repeatSparent = false;
         vector<int> featuresUsed;
         // Step 0: Set the finish condition
         // if not repeatSparent a finish condition is run out of features

src/BayesNet/BoostAODE.h

@@ -4,13 +4,16 @@
 #include "SPODE.h"
 namespace bayesnet {
     class BoostAODE : public Ensemble {
-    protected:
-        void buildModel(const torch::Tensor& weights) override;
-        void trainModel(const torch::Tensor& weights) override;
     public:
         BoostAODE();
         virtual ~BoostAODE() {};
         vector<string> graph(const string& title = "BoostAODE") const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
+    protected:
+        void buildModel(const torch::Tensor& weights) override;
+        void trainModel(const torch::Tensor& weights) override;
+    private:
+        bool repeatSparent;
     };
 }
 #endif

src/BayesNet/CMakeLists.txt

@@ -1,5 +1,6 @@
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
+include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
 include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
 include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
 add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 

src/BayesNet/KDB.h

@@ -16,6 +16,7 @@ namespace bayesnet {
     public:
         explicit KDB(int k, float theta = 0.03);
         virtual ~KDB() {};
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
         vector<string> graph(const string& name = "KDB") const override;
     };
 }

src/BayesNet/KDBLd.h

@@ -13,6 +13,7 @@ namespace bayesnet {
         KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "KDB") const override;
         Tensor predict(Tensor& X) override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
         static inline string version() { return "0.0.1"; };
     };
 }

src/BayesNet/SPODE.h

@@ -12,6 +12,7 @@ namespace bayesnet {
         explicit SPODE(int root);
         virtual ~SPODE() {};
         vector<string> graph(const string& name = "SPODE") const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif

src/BayesNet/SPODELd.h

@@ -13,6 +13,7 @@ namespace bayesnet {
         SPODELd& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "SPODE") const override;
         Tensor predict(Tensor& X) override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
         static inline string version() { return "0.0.1"; };
     };
 }

src/BayesNet/TAN.h

@@ -3,7 +3,6 @@
 #include "Classifier.h"
 namespace bayesnet {
     using namespace std;
-    using namespace torch;
     class TAN : public Classifier {
     private:
     protected:
@@ -12,6 +11,7 @@ namespace bayesnet {
         TAN();
         virtual ~TAN() {};
         vector<string> graph(const string& name = "TAN") const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif

src/BayesNet/TANLd.h

@@ -14,6 +14,7 @@ namespace bayesnet {
         vector<string> graph(const string& name = "TAN") const override;
         Tensor predict(Tensor& X) override;
         static inline string version() { return "0.0.1"; };
+        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif // !TANLD_H

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);
     }