Fix CMakeList manage build with Linux

Reviewed-on: #7

.vscode/launch.json

@@ -25,9 +25,9 @@
             "program": "${workspaceFolder}/build/src/Platform/main",
             "args": [
                 "-m",
-                "AODE",
+                "BoostAODE",
                 "-p",
-                "/home/rmontanana/Code/discretizbench/datasets",
+                "/Users/rmontanana/Code/discretizbench/datasets",
                 "--stratified",
                 "-d",
                 "mfeat-morphological",
@@ -35,7 +35,7 @@
                 // "--hyperparameters",
                 // "{\"repeatSparent\": true, \"maxModels\": 12}"
             ],
-            "cwd": "/home/rmontanana/Code/discretizbench",
+            "cwd": "/Users/rmontanana/Code/discretizbench",
         },
         {
             "type": "lldb",

CMakeLists.txt

@@ -40,7 +40,7 @@ if (CODE_COVERAGE)
     enable_testing()
     include(CodeCoverage)
     MESSAGE("Code coverage enabled")
-    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage -O0")
+    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage -O0 -g")
     SET(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
 endif (CODE_COVERAGE)
 
@@ -74,7 +74,6 @@ file(GLOB Platform_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/Platform
 if (ENABLE_TESTING)
   MESSAGE("Testing enabled")
   add_git_submodule("lib/catch2")  
-  
   include(CTest)
   add_subdirectory(tests)
 endif (ENABLE_TESTING)

Makefile

@@ -40,7 +40,7 @@ debug: ## Build a debug version of the project
 	@if [ -d ./build ]; then rm -rf ./build; fi
 	@mkdir build; 
 	cmake -S . -B build -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CODE_COVERAGE=ON; \
-	cmake --build build -j 32;
+	cmake --build build -t main -t BayesNetSample -t manage -t list  unit_tests -j 32;
 	@echo ">>> Done";
 
 release: ## Build a Release version of the project

sample/sample.cc

@@ -58,180 +58,226 @@ pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vect
 
 int main(int argc, char** argv)
 {
-    map<string, bool> datasets = {
-            {"diabetes",           true},
-            {"ecoli",              true},
-            {"glass",              true},
-            {"iris",               true},
-            {"kdd_JapaneseVowels", false},
-            {"letter",             true},
-            {"liver-disorders",    true},
-            {"mfeat-factors",      true},
-    };
-    auto valid_datasets = vector<string>();
-    transform(datasets.begin(), datasets.end(), back_inserter(valid_datasets),
-        [](const pair<string, bool>& pair) { return pair.first; });
-    argparse::ArgumentParser program("BayesNetSample");
-    program.add_argument("-d", "--dataset")
-        .help("Dataset file name")
-        .action([valid_datasets](const std::string& value) {
-        if (find(valid_datasets.begin(), valid_datasets.end(), value) != valid_datasets.end()) {
-            return value;
+    torch::Tensor weights_ = torch::full({ 10 }, 1.0 / 10, torch::kFloat64);
+    torch::Tensor y_ = torch::tensor({ 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 }, torch::kInt32);
+    torch::Tensor ypred = torch::tensor({ 1, 1, 1, 0, 0, 1, 1, 1, 1, 0 }, torch::kInt32);
+    cout << "Initial weights_: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << weights_.index({ i }).item<double>() << ", ";
     }
-        throw runtime_error("file must be one of {diabetes, ecoli, glass, iris, kdd_JapaneseVowels, letter, liver-disorders, mfeat-factors}");
+    cout << "end." << endl;
+    cout << "y_: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << y_.index({ i }).item<int>() << ", ";
     }
-    );
-    program.add_argument("-p", "--path")
-        .help(" folder where the data files are located, default")
-        .default_value(string{ PATH }
-    );
-    program.add_argument("-m", "--model")
-        .help("Model to use " + platform::Models::instance()->toString())
-        .action([](const std::string& value) {
-        static const vector<string> choices = platform::Models::instance()->getNames();
-        if (find(choices.begin(), choices.end(), value) != choices.end()) {
-            return value;
+    cout << "end." << endl;
+    cout << "ypred: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << ypred.index({ i }).item<int>() << ", ";
     }
-        throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
+    cout << "end." << endl;
+    auto mask_wrong = ypred != y_;
+    auto mask_right = ypred == y_;
+    auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
+    double epsilon_t = masked_weights.sum().item<double>();
+    cout << "epsilon_t: " << epsilon_t << endl;
+    double wt = (1 - epsilon_t) / epsilon_t;
+    cout << "wt: " << wt << endl;
+    double alpha_t = epsilon_t == 0 ? 1 : 0.5 * log(wt);
+    cout << "alpha_t: " << alpha_t << endl;
+    // Step 3.2: Update weights for next classifier
+    // Step 3.2.1: Update weights of wrong samples
+    cout << "exp(alpha_t): " << exp(alpha_t) << endl;
+    cout << "exp(-alpha_t): " << exp(-alpha_t) << endl;
+    weights_ += mask_wrong.to(weights_.dtype()) * exp(alpha_t) * weights_;
+    // Step 3.2.2: Update weights of right samples
+    weights_ += mask_right.to(weights_.dtype()) * exp(-alpha_t) * weights_;
+    // Step 3.3: Normalise the weights
+    double totalWeights = torch::sum(weights_).item<double>();
+    cout << "totalWeights: " << totalWeights << endl;
+    cout << "Before normalization: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << weights_.index({ i }).item<double>() << endl;
     }
-    );
-    program.add_argument("--discretize").help("Discretize input dataset").default_value(false).implicit_value(true);
-    program.add_argument("--dumpcpt").help("Dump CPT Tables").default_value(false).implicit_value(true);
-    program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value(false).implicit_value(true);
-    program.add_argument("--tensors").help("Use tensors to store samples").default_value(false).implicit_value(true);
-    program.add_argument("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const string& value) {
-        try {
-            auto k = stoi(value);
-            if (k < 2) {
-                throw runtime_error("Number of folds must be greater than 1");
-            }
-            return k;
-        }
-        catch (const runtime_error& err) {
-            throw runtime_error(err.what());
-        }
-        catch (...) {
-            throw runtime_error("Number of folds must be an integer");
-        }});
-    program.add_argument("-s", "--seed").help("Random seed").default_value(-1).scan<'i', int>();
-    bool class_last, stratified, tensors, dump_cpt;
-    string model_name, file_name, path, complete_file_name;
-    int nFolds, seed;
-    try {
-        program.parse_args(argc, argv);
-        file_name = program.get<string>("dataset");
-        path = program.get<string>("path");
-        model_name = program.get<string>("model");
-        complete_file_name = path + file_name + ".arff";
-        stratified = program.get<bool>("stratified");
-        tensors = program.get<bool>("tensors");
-        nFolds = program.get<int>("folds");
-        seed = program.get<int>("seed");
-        dump_cpt = program.get<bool>("dumpcpt");
-        class_last = datasets[file_name];
-        if (!file_exists(complete_file_name)) {
-            throw runtime_error("Data File " + path + file_name + ".arff" + " does not exist");
-        }
-    }
-    catch (const exception& err) {
-        cerr << err.what() << endl;
-        cerr << program;
-        exit(1);
+    weights_ = weights_ / totalWeights;
+    cout << "After normalization: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << weights_.index({ i }).item<double>() << endl;
     }
+    // map<string, bool> datasets = {
+    //         {"diabetes",           true},
+    //         {"ecoli",              true},
+    //         {"glass",              true},
+    //         {"iris",               true},
+    //         {"kdd_JapaneseVowels", false},
+    //         {"letter",             true},
+    //         {"liver-disorders",    true},
+    //         {"mfeat-factors",      true},
+    // };
+    // auto valid_datasets = vector<string>();
+    // transform(datasets.begin(), datasets.end(), back_inserter(valid_datasets),
+    //     [](const pair<string, bool>& pair) { return pair.first; });
+    // argparse::ArgumentParser program("BayesNetSample");
+    // program.add_argument("-d", "--dataset")
+    //     .help("Dataset file name")
+    //     .action([valid_datasets](const std::string& value) {
+    //     if (find(valid_datasets.begin(), valid_datasets.end(), value) != valid_datasets.end()) {
+    //         return value;
+    //     }
+    //     throw runtime_error("file must be one of {diabetes, ecoli, glass, iris, kdd_JapaneseVowels, letter, liver-disorders, mfeat-factors}");
+    //         }
+    // );
+    // program.add_argument("-p", "--path")
+    //     .help(" folder where the data files are located, default")
+    //     .default_value(string{ PATH }
+    // );
+    // program.add_argument("-m", "--model")
+    //     .help("Model to use " + platform::Models::instance()->toString())
+    //     .action([](const std::string& value) {
+    //     static const vector<string> choices = platform::Models::instance()->getNames();
+    //     if (find(choices.begin(), choices.end(), value) != choices.end()) {
+    //         return value;
+    //     }
+    //     throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
+    //         }
+    // );
+    // program.add_argument("--discretize").help("Discretize input dataset").default_value(false).implicit_value(true);
+    // program.add_argument("--dumpcpt").help("Dump CPT Tables").default_value(false).implicit_value(true);
+    // program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value(false).implicit_value(true);
+    // program.add_argument("--tensors").help("Use tensors to store samples").default_value(false).implicit_value(true);
+    // program.add_argument("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const string& value) {
+    //     try {
+    //         auto k = stoi(value);
+    //         if (k < 2) {
+    //             throw runtime_error("Number of folds must be greater than 1");
+    //         }
+    //         return k;
+    //     }
+    //     catch (const runtime_error& err) {
+    //         throw runtime_error(err.what());
+    //     }
+    //     catch (...) {
+    //         throw runtime_error("Number of folds must be an integer");
+    //     }});
+    // program.add_argument("-s", "--seed").help("Random seed").default_value(-1).scan<'i', int>();
+    // bool class_last, stratified, tensors, dump_cpt;
+    // string model_name, file_name, path, complete_file_name;
+    // int nFolds, seed;
+    // try {
+    //     program.parse_args(argc, argv);
+    //     file_name = program.get<string>("dataset");
+    //     path = program.get<string>("path");
+    //     model_name = program.get<string>("model");
+    //     complete_file_name = path + file_name + ".arff";
+    //     stratified = program.get<bool>("stratified");
+    //     tensors = program.get<bool>("tensors");
+    //     nFolds = program.get<int>("folds");
+    //     seed = program.get<int>("seed");
+    //     dump_cpt = program.get<bool>("dumpcpt");
+    //     class_last = datasets[file_name];
+    //     if (!file_exists(complete_file_name)) {
+    //         throw runtime_error("Data File " + path + file_name + ".arff" + " does not exist");
+    //     }
+    // }
+    // catch (const exception& err) {
+    //     cerr << err.what() << endl;
+    //     cerr << program;
+    //     exit(1);
+    // }
 
     /*
     * Begin Processing
     */
-    auto handler = ArffFiles();
-    handler.load(complete_file_name, class_last);
-    // Get Dataset X, y
-    vector<mdlp::samples_t>& X = handler.getX();
-    mdlp::labels_t& y = handler.getY();
-    // Get className & Features
-    auto className = handler.getClassName();
-    vector<string> features;
-    auto attributes = handler.getAttributes();
-    transform(attributes.begin(), attributes.end(), back_inserter(features),
-        [](const pair<string, string>& item) { return item.first; });
-    // Discretize Dataset
-    auto [Xd, maxes] = discretize(X, y, features);
-    maxes[className] = *max_element(y.begin(), y.end()) + 1;
-    map<string, vector<int>> states;
-    for (auto feature : features) {
-        states[feature] = vector<int>(maxes[feature]);
-    }
-    states[className] = vector<int>(maxes[className]);
-    auto clf = platform::Models::instance()->create(model_name);
-    clf->fit(Xd, y, features, className, states);
-    if (dump_cpt) {
-        cout << "--- CPT Tables ---" << endl;
-        clf->dump_cpt();
-    }
-    auto lines = clf->show();
-    for (auto line : lines) {
-        cout << line << endl;
-    }
-    cout << "--- Topological Order ---" << endl;
-    auto order = clf->topological_order();
-    for (auto name : order) {
-        cout << name << ", ";
-    }
-    cout << "end." << endl;
-    auto score = clf->score(Xd, y);
-    cout << "Score: " << score << endl;
-    auto graph = clf->graph();
-    auto dot_file = model_name + "_" + file_name;
-    ofstream file(dot_file + ".dot");
-    file << graph;
-    file.close();
-    cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
-    cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
-    string stratified_string = stratified ? " Stratified" : "";
-    cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
-    cout << "==========================================" << endl;
-    torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
-    torch::Tensor yt = torch::tensor(y, torch::kInt32);
-    for (int i = 0; i < features.size(); ++i) {
-        Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
-    }
-    float total_score = 0, total_score_train = 0, score_train, score_test;
-    platform::Fold* fold;
-    if (stratified)
-        fold = new platform::StratifiedKFold(nFolds, y, seed);
-    else
-        fold = new platform::KFold(nFolds, y.size(), seed);
-    for (auto i = 0; i < nFolds; ++i) {
-        auto [train, test] = fold->getFold(i);
-        cout << "Fold: " << i + 1 << endl;
-        if (tensors) {
-            auto ttrain = torch::tensor(train, torch::kInt64);
-            auto ttest = torch::tensor(test, torch::kInt64);
-            torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
-            torch::Tensor ytraint = yt.index({ ttrain });
-            torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
-            torch::Tensor ytestt = yt.index({ ttest });
-            clf->fit(Xtraint, ytraint, features, className, states);
-            auto temp = clf->predict(Xtraint);
-            score_train = clf->score(Xtraint, ytraint);
-            score_test = clf->score(Xtestt, ytestt);
-        } else {
-            auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
-            auto [Xtest, ytest] = extract_indices(test, Xd, y);
-            clf->fit(Xtrain, ytrain, features, className, states);
-            score_train = clf->score(Xtrain, ytrain);
-            score_test = clf->score(Xtest, ytest);
-        }
-        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;
+    // auto handler = ArffFiles();
+    // handler.load(complete_file_name, class_last);
+    // // Get Dataset X, y
+    // vector<mdlp::samples_t>& X = handler.getX();
+    // mdlp::labels_t& y = handler.getY();
+    // // Get className & Features
+    // auto className = handler.getClassName();
+    // vector<string> features;
+    // auto attributes = handler.getAttributes();
+    // transform(attributes.begin(), attributes.end(), back_inserter(features),
+    //     [](const pair<string, string>& item) { return item.first; });
+    // // Discretize Dataset
+    // auto [Xd, maxes] = discretize(X, y, features);
+    // maxes[className] = *max_element(y.begin(), y.end()) + 1;
+    // map<string, vector<int>> states;
+    // for (auto feature : features) {
+    //     states[feature] = vector<int>(maxes[feature]);
+    // }
+    // states[className] = vector<int>(maxes[className]);
+    // auto clf = platform::Models::instance()->create(model_name);
+    // clf->fit(Xd, y, features, className, states);
+    // if (dump_cpt) {
+    //     cout << "--- CPT Tables ---" << endl;
+    //     clf->dump_cpt();
+    // }
+    // auto lines = clf->show();
+    // for (auto line : lines) {
+    //     cout << line << endl;
+    // }
+    // cout << "--- Topological Order ---" << endl;
+    // auto order = clf->topological_order();
+    // for (auto name : order) {
+    //     cout << name << ", ";
+    // }
+    // cout << "end." << endl;
+    // auto score = clf->score(Xd, y);
+    // cout << "Score: " << score << endl;
+    // auto graph = clf->graph();
+    // auto dot_file = model_name + "_" + file_name;
+    // ofstream file(dot_file + ".dot");
+    // file << graph;
+    // file.close();
+    // cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
+    // cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
+    // string stratified_string = stratified ? " Stratified" : "";
+    // cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
+    // cout << "==========================================" << endl;
+    // torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
+    // torch::Tensor yt = torch::tensor(y, torch::kInt32);
+    // for (int i = 0; i < features.size(); ++i) {
+    //     Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
+    // }
+    // float total_score = 0, total_score_train = 0, score_train, score_test;
+    // platform::Fold* fold;
+    // if (stratified)
+    //     fold = new platform::StratifiedKFold(nFolds, y, seed);
+    // else
+    //     fold = new platform::KFold(nFolds, y.size(), seed);
+    // for (auto i = 0; i < nFolds; ++i) {
+    //     auto [train, test] = fold->getFold(i);
+    //     cout << "Fold: " << i + 1 << endl;
+    //     if (tensors) {
+    //         auto ttrain = torch::tensor(train, torch::kInt64);
+    //         auto ttest = torch::tensor(test, torch::kInt64);
+    //         torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
+    //         torch::Tensor ytraint = yt.index({ ttrain });
+    //         torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
+    //         torch::Tensor ytestt = yt.index({ ttest });
+    //         clf->fit(Xtraint, ytraint, features, className, states);
+    //         auto temp = clf->predict(Xtraint);
+    //         score_train = clf->score(Xtraint, ytraint);
+    //         score_test = clf->score(Xtestt, ytestt);
+    //     } else {
+    //         auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
+    //         auto [Xtest, ytest] = extract_indices(test, Xd, y);
+    //         clf->fit(Xtrain, ytrain, features, className, states);
+    //         score_train = clf->score(Xtrain, ytrain);
+    //         score_test = clf->score(Xtest, ytest);
+    //     }
+    //     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/BaseClassifier.h

@@ -5,6 +5,7 @@
 #include <vector>
 namespace bayesnet {
     using namespace std;
+    enum status_t { NORMAL, WARNING, ERROR };
     class BaseClassifier {
     protected:
         virtual void trainModel(const torch::Tensor& weights) = 0;
@@ -18,6 +19,7 @@ namespace bayesnet {
         virtual ~BaseClassifier() = default;
         torch::Tensor virtual predict(torch::Tensor& X) = 0;
         vector<int> virtual predict(vector<vector<int>>& X) = 0;
+        status_t virtual getStatus() const = 0;
         float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
         float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
         int virtual getNumberOfNodes()const = 0;

src/BayesNet/BoostAODE.cc

@@ -1,6 +1,9 @@
 #include "BoostAODE.h"
 #include <set>
 #include "BayesMetrics.h"
+#include "Colors.h"
+#include "Folding.h"
+#include <limits.h>
 
 namespace bayesnet {
     BoostAODE::BoostAODE() : Ensemble() {}
@@ -11,7 +14,7 @@ namespace bayesnet {
     void BoostAODE::setHyperparameters(nlohmann::json& hyperparameters)
     {
         // Check if hyperparameters are valid
-        const vector<string> validKeys = { "repeatSparent", "maxModels", "ascending" };
+        const vector<string> validKeys = { "repeatSparent", "maxModels", "ascending", "convergence" };
         checkHyperparameters(validKeys, hyperparameters);
         if (hyperparameters.contains("repeatSparent")) {
             repeatSparent = hyperparameters["repeatSparent"];
@@ -22,6 +25,38 @@ namespace bayesnet {
         if (hyperparameters.contains("ascending")) {
             ascending = hyperparameters["ascending"];
         }
+        if (hyperparameters.contains("convergence")) {
+            convergence = hyperparameters["convergence"];
+        }
+    }
+    void BoostAODE::validationInit()
+    {
+        auto y_ = dataset.index({ -1, "..." });
+        if (convergence) {
+            // Prepare train & validation sets from train data
+            auto fold = platform::StratifiedKFold(5, y_, 271);
+            dataset_ = torch::clone(dataset);
+            // save input dataset
+            auto [train, test] = fold.getFold(0);
+            auto train_t = torch::tensor(train);
+            auto test_t = torch::tensor(test);
+            // Get train and validation sets
+            X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), train_t });
+            y_train = dataset.index({ -1, train_t });
+            X_test = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), test_t });
+            y_test = dataset.index({ -1, test_t });
+            dataset = X_train;
+            m = X_train.size(1);
+            auto n_classes = states.at(className).size();
+            metrics = Metrics(dataset, features, className, n_classes);
+            // Build dataset with train data
+            buildDataset(y_train);
+        } else {
+            // Use all data to train
+            X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
+            y_train = y_;
+        }
+
     }
     void BoostAODE::trainModel(const torch::Tensor& weights)
     {
@@ -29,14 +64,22 @@ namespace bayesnet {
         n_models = 0;
         if (maxModels == 0)
             maxModels = .1 * n > 10 ? .1 * n : n;
+        validationInit();
         Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
-        auto X_ = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
-        auto y_ = dataset.index({ -1, "..." });
         bool exitCondition = false;
         unordered_set<int> featuresUsed;
+        // Variables to control the accuracy finish condition
+        double priorAccuracy = 0.0;
+        double delta = 1.0;
+        double threshold = 1e-4;
+        int tolerance = 5; // number of times the accuracy can be lower than the threshold
+        int count = 0; // number of times the accuracy is lower than the threshold
+        fitted = true; // to enable predict
         // Step 0: Set the finish condition
         // if not repeatSparent a finish condition is run out of features
         // n_models == maxModels
+        // epsiolon sub t > 0.5 => inverse the weights policy
+        // validation error is not decreasing
         while (!exitCondition) {
             // Step 1: Build ranking with mutual information
             auto featureSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted
@@ -59,29 +102,44 @@ namespace bayesnet {
             }
             featuresUsed.insert(feature);
             model = std::make_unique<SPODE>(feature);
-            n_models++;
             model->fit(dataset, features, className, states, weights_);
-            auto ypred = model->predict(X_);
+            auto ypred = model->predict(X_train);
             // Step 3.1: Compute the classifier amout of say
-            auto mask_wrong = ypred != y_;
+            auto mask_wrong = ypred != y_train;
+            auto mask_right = ypred == y_train;
             auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
-            double wrongWeights = masked_weights.sum().item<double>();
-            double significance = wrongWeights == 0 ? 1 : 0.5 * log((1 - wrongWeights) / wrongWeights);
+            double epsilon_t = masked_weights.sum().item<double>();
+            double wt = (1 - epsilon_t) / epsilon_t;
+            double alpha_t = epsilon_t == 0 ? 1 : 0.5 * log(wt);
             // Step 3.2: Update weights for next classifier
             // Step 3.2.1: Update weights of wrong samples
-            weights_ += mask_wrong.to(weights_.dtype()) * exp(significance) * weights_;
+            weights_ += mask_wrong.to(weights_.dtype()) * exp(alpha_t) * weights_;
+            // Step 3.2.2: Update weights of right samples
+            weights_ += mask_right.to(weights_.dtype()) * exp(-alpha_t) * weights_;
             // Step 3.3: Normalise the weights
             double totalWeights = torch::sum(weights_).item<double>();
             weights_ = weights_ / totalWeights;
             // Step 3.4: Store classifier and its accuracy to weigh its future vote
             models.push_back(std::move(model));
-            significanceModels.push_back(significance);
-            exitCondition = n_models == maxModels && repeatSparent;
+            significanceModels.push_back(alpha_t);
+            n_models++;
+            if (convergence) {
+                auto y_val_predict = predict(X_test);
+                double accuracy = (y_val_predict == y_test).sum().item<double>() / (double)y_test.size(0);
+                if (priorAccuracy == 0) {
+                    priorAccuracy = accuracy;
+                } else {
+                    delta = accuracy - priorAccuracy;
+                }
+                if (delta < threshold) {
+                    count++;
+                }
+            }
+            exitCondition = n_models == maxModels && repeatSparent || epsilon_t > 0.5 || count > tolerance;
         }
         if (featuresUsed.size() != features.size()) {
-            cout << "Warning: BoostAODE did not use all the features" << endl;
+            status = WARNING;
         }
-        weights.copy_(weights_);
     }
     vector<string> BoostAODE::graph(const string& title) const
     {

src/BayesNet/BoostAODE.h

@@ -13,9 +13,13 @@ namespace bayesnet {
         void buildModel(const torch::Tensor& weights) override;
         void trainModel(const torch::Tensor& weights) override;
     private:
-        bool repeatSparent=false;
-        int maxModels=0;
-        bool ascending=false; //Process KBest features ascending or descending order
+        torch::Tensor dataset_;
+        torch::Tensor X_train, y_train, X_test, y_test;
+        void validationInit();
+        bool repeatSparent = false;
+        int maxModels = 0;
+        bool ascending = false; //Process KBest features ascending or descending order
+        bool convergence = false; //if true, stop when the model does not improve
     };
 }
 #endif

src/BayesNet/Classifier.cc

@@ -75,7 +75,7 @@ namespace bayesnet {
             throw invalid_argument("dataset (X, y) must be of type Integer");
         }
         if (n != features.size()) {
-            throw invalid_argument("X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
+            throw invalid_argument("Classifier: X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
         }
         if (states.find(className) == states.end()) {
             throw invalid_argument("className not found in states");

src/BayesNet/Classifier.h

@@ -10,7 +10,6 @@ using namespace torch;
 namespace bayesnet {
     class Classifier : public BaseClassifier {
     private:
-        void buildDataset(torch::Tensor& y);
         Classifier& build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights);
     protected:
         bool fitted;
@@ -21,10 +20,12 @@ namespace bayesnet {
         string className;
         map<string, vector<int>> states;
         Tensor dataset; // (n+1)xm tensor
+        status_t status = NORMAL;
         void checkFitParameters();
         virtual void buildModel(const torch::Tensor& weights) = 0;
         void trainModel(const torch::Tensor& weights) override;
         void checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters);
+        void buildDataset(torch::Tensor& y);
     public:
         Classifier(Network model);
         virtual ~Classifier() = default;
@@ -37,6 +38,7 @@ namespace bayesnet {
         int getNumberOfEdges() const override;
         int getNumberOfStates() const override;
         Tensor predict(Tensor& X) override;
+        status_t getStatus() const override { return status; }
         vector<int> predict(vector<vector<int>>& X) override;
         float score(Tensor& X, Tensor& y) override;
         float score(vector<vector<int>>& X, vector<int>& y) override;

src/BayesNet/Ensemble.cc

@@ -24,7 +24,7 @@ namespace bayesnet {
             // i.e. votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
             vector<double> votes(numClasses, 0.0);
             for (int j = 0; j < n_models; ++j) {
-                votes[y_pred_[i][j]] += significanceModels[j];
+                votes[y_pred_[i][j]] += significanceModels.at(j);
             }
             // argsort in descending order
             auto indices = argsort(votes);

src/BayesNet/Network.cc

@@ -132,10 +132,10 @@ namespace bayesnet {
     void Network::setStates(const map<string, vector<int>>& states)
     {
         // Set states to every Node in the network
-        for (int i = 0; i < features.size(); ++i) {
-            nodes[features[i]]->setNumStates(states.at(features[i]).size());
-        }
-        classNumStates = nodes[className]->getNumStates();
+        for_each(features.begin(), features.end(), [this, &states](const string& feature) {
+            nodes.at(feature)->setNumStates(states.at(feature).size());
+            });
+        classNumStates = nodes.at(className)->getNumStates();
     }
     // X comes in nxm, where n is the number of features and m the number of samples
     void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
@@ -174,10 +174,16 @@ namespace bayesnet {
     {
         setStates(states);
         laplaceSmoothing = 1.0 / samples.size(1); // To use in CPT computation
+        vector<thread> threads;
         for (auto& node : nodes) {
+            threads.emplace_back([this, &node, &weights]() {
                 node.second->computeCPT(samples, features, laplaceSmoothing, weights);
-            fitted = true;
+                });
         }
+        for (auto& thread : threads) {
+            thread.join();
+        }
+        fitted = true;
     }
     torch::Tensor Network::predict_tensor(const torch::Tensor& samples, const bool proba)
     {

src/Platform/CMakeLists.txt

@@ -8,5 +8,9 @@ add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.c
 add_executable(manage manage.cc Results.cc ReportConsole.cc ReportExcel.cc ReportBase.cc)
 add_executable(list list.cc platformUtils Datasets.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
-target_link_libraries(manage "${TORCH_LIBRARIES}" OpenXLSX::OpenXLSX)
+if (${CMAKE_HOST_SYSTEM_NAME} MATCHES "Linux")
+    target_link_libraries(manage "${TORCH_LIBRARIES}" OpenXLSX::OpenXLSX stdc++fs)
+else()
+    target_link_libraries(manage "${TORCH_LIBRARIES}" OpenXLSX::OpenXLSX)
+endif()
 target_link_libraries(list ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/Experiment.cc

@@ -111,6 +111,26 @@ namespace platform {
         }
     }
 
+    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();
+        }
+    }
+
+    void showProgress(int fold, const string& color, const string& phase)
+    {
+        string prefix = phase == "a" ? "" : "\b\b\b\b";
+        cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
+
+    }
     void Experiment::cross_validation(const string& path, const string& fileName)
     {
         auto datasets = platform::Datasets(path, discretized, platform::ARFF);
@@ -159,20 +179,24 @@ namespace platform {
                 auto y_train = y.index({ train_t });
                 auto X_test = X.index({ "...", test_t });
                 auto y_test = y.index({ test_t });
-                cout << nfold + 1 << ", " << flush;
+                showProgress(nfold + 1, getColor(clf->getStatus()), "a");
                 // Train model
                 clf->fit(X_train, y_train, features, className, states);
+                showProgress(nfold + 1, getColor(clf->getStatus()), "b");
                 nodes[item] = clf->getNumberOfNodes();
                 edges[item] = clf->getNumberOfEdges();
                 num_states[item] = clf->getNumberOfStates();
                 train_time[item] = train_timer.getDuration();
+                // Score train
                 auto accuracy_train_value = clf->score(X_train, y_train);
                 // Test model
+                showProgress(nfold + 1, getColor(clf->getStatus()), "c");
                 test_timer.start();
                 auto accuracy_test_value = clf->score(X_test, y_test);
                 test_time[item] = test_timer.getDuration();
                 accuracy_train[item] = accuracy_train_value;
                 accuracy_test[item] = accuracy_test_value;
+                cout << "\b\b\b, " << flush;
                 // Store results and times in vector
                 result.addScoreTrain(accuracy_train_value);
                 result.addScoreTest(accuracy_test_value);

src/Platform/ReportConsole.cc

@@ -36,14 +36,21 @@ namespace platform {
     }
     void ReportConsole::body()
     {
-        cout << Colors::GREEN() << "Dataset                        Sampl. Feat. Cls Nodes     Edges     States    Score           Time               Hyperparameters" << endl;
-        cout << "============================== ====== ===== === ========= ========= ========= =============== ================== ===============" << endl;
+        cout << Colors::GREEN() << " #  Dataset                        Sampl. Feat. Cls Nodes     Edges     States    Score           Time               Hyperparameters" << endl;
+        cout << "=== ============================== ====== ===== === ========= ========= ========= =============== ================== ===============" << endl;
         json lastResult;
         double totalScore = 0.0;
         bool odd = true;
+        int index = 0;
         for (const auto& r : data["results"]) {
+            if (selectedIndex != -1 && index != selectedIndex) {
+                index++;
+                continue;
+            }
             auto color = odd ? Colors::CYAN() : Colors::BLUE();
-            cout << color << setw(30) << left << r["dataset"].get<string>() << " ";
+            cout << color;
+            cout << setw(3) << index++ << " ";
+            cout << setw(30) << left << r["dataset"].get<string>() << " ";
             cout << setw(6) << right << r["samples"].get<int>() << " ";
             cout << setw(5) << right << r["features"].get<int>() << " ";
             cout << setw(3) << right << r["classes"].get<int>() << " ";
@@ -63,7 +70,7 @@ namespace platform {
             totalScore += r["score"].get<double>();
             odd = !odd;
         }
-        if (data["results"].size() == 1) {
+        if (data["results"].size() == 1 || selectedIndex != -1) {
             cout << string(MAXL, '*') << endl;
             cout << headerLine(fVector("Train scores: ", lastResult["scores_train"], 14, 12));
             cout << headerLine(fVector("Test  scores: ", lastResult["scores_test"], 14, 12));

src/Platform/ReportConsole.h

@@ -7,12 +7,13 @@
 
 namespace platform {
     using namespace std;
-    const int MAXL = 128;
-    class ReportConsole : public ReportBase{
+    const int MAXL = 132;
+    class ReportConsole : public ReportBase {
     public:
-        explicit ReportConsole(json data_) : ReportBase(data_) {};
+        explicit ReportConsole(json data_, int index = -1) : ReportBase(data_), selectedIndex(index) {};
         virtual ~ReportConsole() = default;
     private:
+        int selectedIndex;
         string headerLine(const string& text);
         void header() override;
         void body() override;

src/Platform/Results.cc

@@ -23,6 +23,7 @@ namespace platform {
         title = data["title"];
         duration = data["duration"];
         model = data["model"];
+        complete = data["results"].size() > 1;
     }
     json Result::load() const
     {
@@ -41,7 +42,7 @@ namespace platform {
             if (filename.find(".json") != string::npos && filename.find("results_") == 0) {
                 auto result = Result(path, filename);
                 bool addResult = true;
-                if (model != "any" && result.getModel() != model || scoreName != "any" && scoreName != result.getScoreName())
+                if (model != "any" && result.getModel() != model || scoreName != "any" && scoreName != result.getScoreName() || complete && !result.isComplete() || partial && result.isComplete())
                     addResult = false;
                 if (addResult)
                     files.push_back(result);
@@ -55,6 +56,8 @@ namespace platform {
         oss << setw(12) << left << model << " ";
         oss << setw(11) << left << scoreName << " ";
         oss << right << setw(11) << setprecision(7) << fixed << score << " ";
+        auto completeString = isComplete() ? "C" : "P";
+        oss << setw(1) << " " << completeString << "  ";
         oss << setw(9) << setprecision(3) << fixed << duration << " ";
         oss << setw(50) << left << title << " ";
         return  oss.str();
@@ -63,9 +66,15 @@ namespace platform {
     {
         cout << Colors::GREEN() << "Results found: " << files.size() << endl;
         cout << "-------------------" << endl;
+        if (complete) {
+            cout << Colors::MAGENTA() << "Only listing complete results" << endl;
+        }
+        if (partial) {
+            cout << Colors::MAGENTA() << "Only listing partial results" << endl;
+        }
         auto i = 0;
-        cout << " #  Date       Model        Score Name  Score       Duration  Title" << endl;
-        cout << "=== ========== ============ =========== =========== ========= =============================================================" << endl;
+        cout << Colors::GREEN() << " #  Date       Model        Score Name  Score       C/P Duration  Title" << endl;
+        cout << "=== ========== ============ =========== =========== === ========= =============================================================" << endl;
         bool odd = true;
         for (const auto& result : files) {
             auto color = odd ? Colors::BLUE() : Colors::CYAN();
@@ -107,6 +116,17 @@ namespace platform {
             reporter.show();
         }
     }
+    void Results::showIndex(const int index, const int idx) const
+    {
+        auto data = files.at(index).load();
+        if (idx < 0 or idx >= static_cast<int>(data["results"].size())) {
+            cout << "Invalid index" << endl;
+            return;
+        }
+        cout << Colors::YELLOW() << "Showing " << files.at(index).getFilename() << endl;
+        ReportConsole reporter(data, idx);
+        reporter.show();
+    }
     void Results::menu()
     {
         char option;
@@ -126,9 +146,16 @@ namespace platform {
                 option = line[0];
             } else {
                 if (all_of(line.begin(), line.end(), ::isdigit)) {
-                    index = stoi(line);
+                    int idx = stoi(line);
+                    if (indexList) {
+                        index = idx;
                         if (index >= 0 && index < files.size()) {
                             report(index, false);
+                            indexList = false;
+                            continue;
+                        }
+                    } else {
+                        showIndex(index, idx);
                         continue;
                     }
                 }
@@ -141,6 +168,7 @@ namespace platform {
                     break;
                 case 'l':
                     show();
+                    indexList = true;
                     break;
                 case 'd':
                     index = getIndex("delete");
@@ -152,6 +180,7 @@ namespace platform {
                     files.erase(files.begin() + index);
                     cout << "File: " + filename + " deleted!" << endl;
                     show();
+                    indexList = true;
                     break;
                 case 'h':
                     index = getIndex("hide");
@@ -163,21 +192,25 @@ namespace platform {
                     files.erase(files.begin() + index);
                     show();
                     menu();
+                    indexList = true;
                     break;
                 case 's':
                     sortList();
+                    indexList = true;
                     show();
                     break;
                 case 'r':
                     index = getIndex("report");
                     if (index == -1)
                         break;
+                    indexList = false;
                     report(index, false);
                     break;
                 case 'e':
                     index = getIndex("excel");
                     if (index == -1)
                         break;
+                    indexList = true;
                     report(index, true);
                     break;
                 default:

src/Platform/Results.h

@@ -20,6 +20,7 @@ namespace platform {
         double getDuration() const { return duration; };
         string getModel() const { return model; };
         string getScoreName() const { return scoreName; };
+        bool isComplete() const { return complete; };
     private:
         string path;
         string filename;
@@ -29,20 +30,25 @@ namespace platform {
         double duration;
         string model;
         string scoreName;
+        bool complete;
     };
     class Results {
     public:
-        Results(const string& path, const int max, const string& model, const string& score) : path(path), max(max), model(model), scoreName(score) { load(); };
+        Results(const string& path, const int max, const string& model, const string& score, bool complete, bool partial) : path(path), max(max), model(model), scoreName(score), complete(complete), partial(partial) { load(); };
         void manage();
     private:
         string path;
         int max;
         string model;
         string scoreName;
+        bool complete;
+        bool partial;
+        bool indexList = true;
         vector<Result> files;
         void load(); // Loads the list of results
         void show() const;
         void report(const int index, const bool excelReport) const;
+        void showIndex(const int index, const int idx) const;
         int getIndex(const string& intent) const;
         void menu();
         void sortList();

src/Platform/manage.cc

@@ -12,6 +12,8 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
     program.add_argument("-n", "--number").default_value(0).help("Number of results to show (0 = all)").scan<'i', int>();
     program.add_argument("-m", "--model").default_value("any").help("Filter results of the selected model)");
     program.add_argument("-s", "--score").default_value("any").help("Filter results of the score name supplied");
+    program.add_argument("--complete").help("Show only results with all datasets").default_value(false).implicit_value(true);
+    program.add_argument("--partial").help("Show only partial results").default_value(false).implicit_value(true);
     try {
         program.parse_args(argc, argv);
         auto number = program.get<int>("number");
@@ -20,6 +22,8 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
         }
         auto model = program.get<string>("model");
         auto score = program.get<string>("score");
+        auto complete = program.get<bool>("complete");
+        auto partial = program.get<bool>("partial");
     }
     catch (const exception& err) {
         cerr << err.what() << endl;
@@ -35,7 +39,11 @@ int main(int argc, char** argv)
     auto number = program.get<int>("number");
     auto model = program.get<string>("model");
     auto score = program.get<string>("score");
-    auto results = platform::Results(platform::Paths::results(), number, model, score);
+    auto complete = program.get<bool>("complete");
+    auto partial = program.get<bool>("partial");
+    if (complete)
+        partial = false;
+    auto results = platform::Results(platform::Paths::results(), number, model, score, complete, partial);
     results.manage();
     return 0;
 }

tests/CMakeLists.txt

@@ -4,6 +4,7 @@ if(ENABLE_TESTING)
     include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
     include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
     include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
+    include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
     set(TEST_SOURCES BayesModels.cc BayesNetwork.cc ${BayesNet_SOURCE_DIR}/src/Platform/platformUtils.cc ${BayesNet_SOURCES})
     add_executable(${TEST_MAIN} ${TEST_SOURCES})
     target_link_libraries(${TEST_MAIN} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain)