Fix linter warnings

.vscode/launch.json

@@ -31,6 +31,8 @@
                 "--stratified",
                 "--title",
                 "Debug test",
+                "--seeds",
+                "1",
                 "-d",
                 "ionosphere"
             ],

sample/sample.cc

@@ -9,7 +9,6 @@
 #include "CPPFImdlp.h"
 #include "Folding.h"
 #include "Models.h"
-#include "modelRegister.h"
 
 
 using namespace std;
@@ -69,8 +68,9 @@ int main(int argc, char** argv)
             {"mfeat-factors",      true},
     };
     auto valid_datasets = vector<string>();
-    transform(datasets.begin(), datasets.end(), back_inserter(valid_datasets),
+    for (auto dataset : datasets) {
-        [](const pair<string, bool>& pair) { return pair.first; });
+        valid_datasets.push_back(dataset.first);
+    }
     argparse::ArgumentParser program("BayesNetSample");
     program.add_argument("-d", "--dataset")
         .help("Dataset file name")
@@ -86,13 +86,13 @@ int main(int argc, char** argv)
         .default_value(string{ PATH }
     );
     program.add_argument("-m", "--model")
-        .help("Model to use " + platform::Models::instance()->toString())
+        .help("Model to use " + platform::Models::toString())
         .action([](const std::string& value) {
-        static const vector<string> choices = platform::Models::instance()->getNames();
+        static const vector<string> choices = platform::Models::getNames();
         if (find(choices.begin(), choices.end(), value) != choices.end()) {
             return value;
         }
-        throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
+        throw runtime_error("Model must be one of " + platform::Models::toString());
             }
     );
     program.add_argument("--discretize").help("Discretize input dataset").default_value(false).implicit_value(true);
@@ -148,9 +148,9 @@ int main(int argc, char** argv)
     // Get className & Features
     auto className = handler.getClassName();
     vector<string> features;
-    auto attributes = handler.getAttributes();
+    for (auto feature : handler.getAttributes()) {
-    transform(attributes.begin(), attributes.end(), back_inserter(features),
+        features.push_back(feature.first);
-        [](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;
@@ -159,7 +159,8 @@ int main(int argc, char** argv)
         states[feature] = vector<int>(maxes[feature]);
     }
     states[className] = vector<int>(maxes[className]);
-    auto clf = platform::Models::instance()->create(model_name);
+
+    bayesnet::BaseClassifier* clf = platform::Models::get(model_name);
     clf->fit(Xd, y, features, className, states);
     auto score = clf->score(Xd, y);
     auto lines = clf->show();

src/BayesNet/AODE.h

@@ -8,7 +8,6 @@ namespace bayesnet {
         void train() override;
     public:
         AODE();
-        virtual ~AODE() {};
         vector<string> graph(string title = "AODE") override;
     };
 }

src/BayesNet/BayesMetrics.cc

@@ -67,6 +67,7 @@ namespace bayesnet {
         }
         return matrix;
     }
+    // To Interface with Python
     vector<float> Metrics::conditionalEdgeWeights()
     {
         auto matrix = conditionalEdge();

src/BayesNet/BayesMetrics.h

@@ -11,7 +11,7 @@ namespace bayesnet {
         Tensor samples;
         vector<string> features;
         string className;
-        int classNumStates = 0;
+        int classNumStates;
     public:
         Metrics() = default;
         Metrics(Tensor&, vector<string>&, string&, int);

src/BayesNet/Classifier.cc

@@ -4,7 +4,7 @@
 namespace bayesnet {
     using namespace torch;
 
-    Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
+    Classifier::Classifier(const Network& model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
     Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
     {
         dataset = torch::cat({ X, y.view({y.size(0), 1}) }, 1);

src/BayesNet/Classifier.h

@@ -27,7 +27,7 @@ namespace bayesnet {
         void checkFitParameters();
         virtual void train() = 0;
     public:
-        Classifier(Network model);
+        Classifier(const Network& model);
         virtual ~Classifier() = default;
         Classifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
         Classifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;

src/BayesNet/KDB.h

@@ -14,7 +14,6 @@ namespace bayesnet {
         void train() override;
     public:
         explicit KDB(int k, float theta = 0.03);
-        virtual ~KDB() {};
         vector<string> graph(string name = "KDB") override;
     };
 }

src/BayesNet/Mst.cc

@@ -7,7 +7,7 @@
 
 namespace bayesnet {
     using namespace std;
-    Graph::Graph(int V) : V(V), parent(vector<int>(V))
+    Graph::Graph(int V) : V(V), parent{ vector<int>(V) }
     {
         for (int i = 0; i < V; i++)
             parent[i] = i;
@@ -33,9 +33,10 @@ namespace bayesnet {
     }
     void Graph::kruskal_algorithm()
     {
+        int i;
         // sort the edges ordered on decreasing weight
         sort(G.begin(), G.end(), [](const auto& left, const auto& right) {return left.first > right.first;});
-        for (int i = 0; i < G.size(); i++) {
+        for (i = 0; i < G.size(); i++) {
             int uSt, vEd;
             uSt = find_set(G[i].second.first);
             vEd = find_set(G[i].second.second);

src/BayesNet/Mst.h

@@ -10,9 +10,8 @@ namespace bayesnet {
     private:
         Tensor weights;
         vector<string> features;
-        int root = 0;
+        int root;
     public:
-        MST() = default;
         MST(vector<string>& features, Tensor& weights, int root);
         vector<pair<int, int>> maximumSpanningTree();
     };

src/BayesNet/Network.cc

@@ -4,9 +4,9 @@
 #include "bayesnetUtils.h"
 namespace bayesnet {
     Network::Network() : laplaceSmoothing(1), features(vector<string>()), className(""), classNumStates(0), maxThreads(0.8), fitted(false) {}
-    Network::Network(float maxT) : laplaceSmoothing(1), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
+    Network::Network(const float maxT) : laplaceSmoothing(1), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
-    Network::Network(float maxT, int smoothing) : laplaceSmoothing(smoothing), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
+    Network::Network(const float maxT, const int smoothing) : laplaceSmoothing(smoothing), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
-    Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.getmaxThreads()), fitted(other.fitted)
+    Network::Network(const Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.classNumStates), maxThreads(other.maxThreads), fitted(other.fitted)
     {
         for (const auto& pair : other.nodes) {
             nodes[pair.first] = std::make_unique<Node>(*pair.second);
@@ -20,7 +20,7 @@ namespace bayesnet {
     {
         return samples;
     }
-    void Network::addNode(const string& name, int numStates)
+    void Network::addNode(const string& name, const int numStates)
     {
         if (find(features.begin(), features.end(), name) == features.end()) {
             features.push_back(name);
@@ -37,11 +37,11 @@ namespace bayesnet {
     {
         return features;
     }
-    int Network::getClassNumStates()
+    const int Network::getClassNumStates()
     {
         return classNumStates;
     }
-    int Network::getStates()
+    const int Network::getStates()
     {
         int result = 0;
         for (auto& node : nodes) {
@@ -49,7 +49,7 @@ namespace bayesnet {
         }
         return result;
     }
-    string Network::getClassName()
+    const string Network::getClassName()
     {
         return className;
     }
@@ -145,6 +145,9 @@ namespace bayesnet {
         while (nextNodeIndex < nodes.size()) {
             unique_lock<mutex> lock(mtx);
             cv.wait(lock, [&activeThreads, &maxThreadsRunning]() { return activeThreads < maxThreadsRunning; });
+            if (nextNodeIndex >= nodes.size()) {
+                break;  // No more work remaining
+            }
             threads.emplace_back([this, &nextNodeIndex, &mtx, &cv, &activeThreads]() {
                 while (true) {
                     unique_lock<mutex> lock(mtx);
@@ -259,7 +262,7 @@ namespace bayesnet {
 
         // Normalize result
         double sum = accumulate(result.begin(), result.end(), 0.0);
-        transform(result.begin(), result.end(), result.begin(), [sum](double& value) { return value / sum; });
+        transform(result.begin(), result.end(), result.begin(), [sum](double x) { return x / sum; });
         return result;
     }
     vector<string> Network::show()

src/BayesNet/Network.h

@@ -27,19 +27,19 @@ namespace bayesnet {
         void completeFit();
     public:
         Network();
-        explicit Network(float, int);
+        explicit Network(const float, const int);
-        explicit Network(float);
+        explicit Network(const float);
-        explicit Network(Network&);
+        explicit Network(const Network&);
         torch::Tensor& getSamples();
         float getmaxThreads();
-        void addNode(const string&, int);
+        void addNode(const string&, const int);
         void addEdge(const string&, const string&);
         map<string, std::unique_ptr<Node>>& getNodes();
         vector<string> getFeatures();
-        int getStates();
+        const int getStates();
         vector<pair<string, string>> getEdges();
-        int getClassNumStates();
+        const int getClassNumStates();
-        string getClassName();
+        const string getClassName();
         void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
         void fit(torch::Tensor&, torch::Tensor&, const vector<string>&, const string&);
         vector<int> predict(const vector<vector<int>>&);

src/BayesNet/Node.cc

@@ -88,15 +88,14 @@ namespace bayesnet {
     {
         // Get dimensions of the CPT
         dimensions.push_back(numStates);
-        transform(parents.begin(), parents.end(), back_inserter(dimensions), [](const auto& parent) { return parent->getNumStates(); });
+        transform(parents.begin(), parents.end(), back_inserter(dimensions), [](Node* parent) { return parent->getNumStates(); });
-
         // Create a tensor of zeros with the dimensions of the CPT
         cpTable = torch::zeros(dimensions, torch::kFloat) + laplaceSmoothing;
         // Fill table with counts
         for (int n_sample = 0; n_sample < dataset[name].size(); ++n_sample) {
             torch::List<c10::optional<torch::Tensor>> coordinates;
             coordinates.push_back(torch::tensor(dataset[name][n_sample]));
-            transform(parents.begin(), parents.end(), back_inserter(coordinates), [&dataset, &n_sample](const auto& parent) { return torch::tensor(dataset[parent->getName()][n_sample]); });
+            transform(parents.begin(), parents.end(), back_inserter(coordinates), [&dataset, &n_sample](Node* parent) { return torch::tensor(dataset[parent->getName()][n_sample]); });
             // Increment the count of the corresponding coordinate
             cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + 1);
         }
@@ -108,7 +107,7 @@ namespace bayesnet {
         torch::List<c10::optional<torch::Tensor>> coordinates;
         // following predetermined order of indices in the cpTable (see Node.h)
         coordinates.push_back(torch::tensor(evidence[name]));
-        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return torch::tensor(evidence[parent->getName()]); });
+        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](Node* parent) { return torch::tensor(evidence[parent->getName()]); });
         return cpTable.index({ coordinates }).item<float>();
     }
     vector<string> Node::graph(const string& className)
@@ -116,7 +115,7 @@ namespace bayesnet {
         auto output = vector<string>();
         auto suffix = name == className ? ", fontcolor=red, fillcolor=lightblue, style=filled " : "";
         output.push_back(name + " [shape=circle" + suffix + "] \n");
-        transform(children.begin(), children.end(), back_inserter(output), [this](const auto& child) { return name + " -> " + child->getName(); });
+        transform(children.begin(), children.end(), back_inserter(output), [this](Node* child) { return name + " -> " + child->getName() + "\n"; });
         return output;
     }
 }

src/BayesNet/Node.h

@@ -16,7 +16,7 @@ namespace bayesnet {
         vector<int64_t> dimensions; // dimensions of the cpTable
     public:
         vector<pair<string, string>> combinations(const vector<string>&);
-        Node(const string&, int);
+        Node(const std::string&, int);
         void clear();
         void addParent(Node*);
         void addChild(Node*);

src/BayesNet/SPODE.h

@@ -1,7 +1,6 @@
 #ifndef SPODE_H
 #define SPODE_H
 #include "Classifier.h"
-
 namespace bayesnet {
     class SPODE : public Classifier {
     private:
@@ -10,7 +9,6 @@ namespace bayesnet {
         void train() override;
     public:
         explicit SPODE(int root);
-        virtual ~SPODE() {};
         vector<string> graph(string name = "SPODE") override;
     };
 }

src/BayesNet/TAN.h

@@ -10,7 +10,6 @@ namespace bayesnet {
         void train() override;
     public:
         TAN();
-        virtual ~TAN() {};
         vector<string> graph(string name = "TAN") override;
     };
 }

src/Platform/CMakeLists.txt

@@ -4,5 +4,5 @@ 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(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc)
+add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc CrossValidation.cc Models.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/CrossValidation.cc

@@ -0,0 +1,79 @@
+#include "CrossValidation.h"
+#include "Models.h"
+
+namespace platform {
+    using json = nlohmann::json;
+    using namespace std::chrono;
+
+    CrossValidation::CrossValidation(const string& modelName, bool stratified, int nfolds, const vector<int>& randomSeeds, platform::Datasets& datasets) : modelName(modelName), stratified(stratified), nfolds(nfolds), randomSeeds(randomSeeds), datasets(datasets)
+    {
+    }
+
+    Result CrossValidation::crossValidate(const string& fileName)
+    {
+        auto [Xt, y] = datasets.getTensors(fileName);
+        auto states = datasets.getStates(fileName);
+        auto className = datasets.getClassName(fileName);
+        auto features = datasets.getFeatures(fileName);
+        auto samples = datasets.getNSamples(fileName);
+        auto result = Result();
+        auto [values, counts] = at::_unique(y);
+        result.setSamples(Xt.size(1)).setFeatures(Xt.size(0)).setClasses(values.size(0));
+        int nSeeds = static_cast<int>(randomSeeds.size());
+        auto accuracy_test = torch::zeros({ nfolds * nSeeds }, torch::kFloat64);
+        auto accuracy_train = torch::zeros({ nfolds * nSeeds }, torch::kFloat64);
+        auto train_time = torch::zeros({ nfolds * nSeeds }, torch::kFloat64);
+        auto test_time = torch::zeros({ nfolds * nSeeds }, torch::kFloat64);
+        auto nodes = torch::zeros({ nfolds * nSeeds }, torch::kFloat64);
+        auto edges = torch::zeros({ nfolds * nSeeds }, torch::kFloat64);
+        auto num_states = torch::zeros({ nfolds * nSeeds }, torch::kFloat64);
+        Timer train_timer, test_timer;
+        int item = 0;
+        for (auto seed : randomSeeds) {
+            cout << "(" << seed << ") " << flush;
+            Fold* fold;
+            if (stratified)
+                fold = new StratifiedKFold(nfolds, y, seed);
+            else
+                fold = new KFold(nfolds, samples, seed);
+            cout << "Fold: " << flush;
+            for (int nfold = 0; nfold < nfolds; nfold++) {
+                bayesnet::BaseClassifier* model = Models::get(modelName);
+                result.setModelVersion(model->getVersion());
+                train_timer.start();
+                auto [train, test] = fold->getFold(nfold);
+                auto train_t = torch::tensor(train);
+                auto test_t = torch::tensor(test);
+                auto X_train = Xt.index({ "...", train_t });
+                auto y_train = y.index({ train_t });
+                auto X_test = Xt.index({ "...", test_t });
+                auto y_test = y.index({ test_t });
+                cout << nfold + 1 << ", " << flush;
+                model->fit(X_train, y_train, features, className, states);
+                nodes[item] = model->getNumberOfNodes();
+                edges[item] = model->getNumberOfEdges();
+                num_states[item] = model->getNumberOfStates();
+                train_time[item] = train_timer.getDuration();
+                auto accuracy_train_value = model->score(X_train, y_train);
+                test_timer.start();
+                auto accuracy_test_value = model->score(X_test, y_test);
+                test_time[item] = test_timer.getDuration();
+                accuracy_train[item] = accuracy_train_value;
+                accuracy_test[item] = accuracy_test_value;
+                // Store results and times in vector
+                result.addScoreTrain(accuracy_train_value);
+                result.addScoreTest(accuracy_test_value);
+                result.addTimeTrain(train_time[item].item<double>());
+                result.addTimeTest(test_time[item].item<double>());
+                item++;
+            }
+            delete fold;
+        }
+        cout << "end." << endl;
+        result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
+        result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
+        result.setTrainTime(torch::mean(train_time).item<double>()).setTestTime(torch::mean(test_time).item<double>());
+        result.setNodes(torch::mean(nodes).item<double>()).setLeaves(torch::mean(edges).item<double>()).setDepth(torch::mean(num_states).item<double>());
+        return result;
+    }
+} // namespace platform

src/Platform/CrossValidation.h

@@ -0,0 +1,25 @@
+#ifndef CROSSVALIDATION_H
+#define CROSSVALIDATION_H
+#include <torch/torch.h>
+#include <nlohmann/json.hpp>
+#include <string>
+#include <chrono>
+#include "Folding.h"
+#include "Datasets.h"
+#include "Experiment.h"
+
+namespace platform {
+    class CrossValidation {
+    private:
+        bool stratified;
+        int nfolds;
+        string modelName;
+        vector<int> randomSeeds;
+        platform::Datasets& datasets;
+    public:
+        CrossValidation(const string& modelName, bool stratified, int nfolds, const vector<int>& randomSeeds, platform::Datasets& datasets);
+        ~CrossValidation() = default;
+        Result crossValidate(const string& fileName);
+    };
+}
+#endif // !CROSSVALIDATION_H

src/Platform/Datasets.cc

@@ -2,6 +2,16 @@
 #include "platformUtils.h"
 #include "ArffFiles.h"
 namespace platform {
+    vector<string> split(const string& text, char delimiter)
+    {
+        vector<string> result;
+        stringstream ss(text);
+        string token;
+        while (getline(ss, token, delimiter)) {
+            result.push_back(token);
+        }
+        return result;
+    }
     void Datasets::load()
     {
         ifstream catalog(path + "/all.txt");
@@ -24,7 +34,7 @@ namespace platform {
         transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
         return result;
     }
-    vector<string> Datasets::getFeatures(string name)
+    vector<string> Datasets::getFeatures(const string& name)
     {
         if (datasets[name]->isLoaded()) {
             return datasets[name]->getFeatures();
@@ -32,7 +42,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Datasets::getStates(string name)
+    map<string, vector<int>> Datasets::getStates(const string& name)
     {
         if (datasets[name]->isLoaded()) {
             return datasets[name]->getStates();
@@ -40,7 +50,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    string Datasets::getClassName(string name)
+    string Datasets::getClassName(const string& name)
     {
         if (datasets[name]->isLoaded()) {
             return datasets[name]->getClassName();
@@ -48,7 +58,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Datasets::getNSamples(string name)
+    int Datasets::getNSamples(const string& name)
     {
         if (datasets[name]->isLoaded()) {
             return datasets[name]->getNSamples();
@@ -56,21 +66,21 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
+    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectors();
     }
-    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(string name)
+    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectorsDiscretized();
     }
-    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(string name)
+    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
@@ -81,9 +91,7 @@ namespace platform {
     {
         return datasets.find(name) != datasets.end();
     }
-    Dataset::Dataset(const Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType)
+    Dataset::Dataset(Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType) {}
-    {
-    }
     string Dataset::getName()
     {
         return name;
@@ -192,7 +200,7 @@ namespace platform {
         // Get className & Features
         className = arff.getClassName();
         auto attributes = arff.getAttributes();
-        transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& attribute) { return attribute.first; });
+        transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& f) { return f.first; });
     }
     void Dataset::load()
     {

src/Platform/Datasets.h

@@ -13,7 +13,7 @@ namespace platform {
         string name;
         fileType_t fileType;
         string className;
-        int n_samples{ 0 }, n_features{ 0 };
+        int n_samples, n_features;
         vector<string> features;
         map<string, vector<int>> states;
         bool loaded;
@@ -27,8 +27,8 @@ namespace platform {
         void load_arff();
         void computeStates();
     public:
-        Dataset(const string& path, const string& name, const string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
+        Dataset(const string& path, const string& name, const string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType), n_samples(0), n_features(0) {};
-        explicit Dataset(const Dataset&);
+        explicit Dataset(Dataset&);
         string getName();
         string getClassName();
         vector<string> getFeatures();
@@ -51,15 +51,16 @@ namespace platform {
     public:
         explicit Datasets(const string& path, bool discretize = false, fileType_t fileType = ARFF) : path(path), discretize(discretize), fileType(fileType) { load(); };
         vector<string> getNames();
-        vector<string> getFeatures(string name);
+        vector<string> getFeatures(const string& name);
-        int getNSamples(string name);
+        int getNSamples(const string& name);
-        string getClassName(string name);
+        string getClassName(const string& name);
-        map<string, vector<int>> getStates(string name);
+        map<string, vector<int>> getStates(const string& name);
-        pair<vector<vector<float>>&, vector<int>&> getVectors(string name);
+        pair<vector<vector<float>>&, vector<int>&> getVectors(const string& name);
-        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(string name);
+        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(const string& name);
-        pair<torch::Tensor&, torch::Tensor&> getTensors(string name);
+        pair<torch::Tensor&, torch::Tensor&> getTensors(const string& name);
         bool isDataset(const string& name);
     };
+    vector<string> split(const string&, char);
 };
 
 #endif

src/Platform/DotEnv.h

@@ -4,10 +4,18 @@
 #include <map>
 #include <fstream>
 #include <sstream>
-#include "platformUtils.h"
+std::vector<std::string> split(std::string text, char delimiter)
-namespace platform {
+{
-    class DotEnv {
+    std::vector<std::string> result;
-    private:
+    std::stringstream ss(text);
+    std::string token;
+    while (getline(ss, token, delimiter)) {
+        result.push_back(token);
+    }
+    return result;
+}
+class DotEnv {
+private:
     std::map<std::string, std::string> env;
     std::string trim(const std::string& str)
     {
@@ -20,7 +28,7 @@ namespace platform {
             }).base(), result.end());
         return result;
     }
-    public:
+public:
     DotEnv()
     {
         std::ifstream file(".env");
@@ -52,11 +60,8 @@ namespace platform {
         seeds_str = trim(seeds_str);
         seeds_str = seeds_str.substr(1, seeds_str.size() - 2);
         auto seeds_str_split = split(seeds_str, ',');
-            transform(seeds_str_split.begin(), seeds_str_split.end(), back_inserter(seeds), [](const std::string& str) {
+        transform(seeds_str_split.begin(), seeds_str_split.end(), back_inserter(seeds), [](const auto& s) { return stoi(s); });
-                return stoi(str);
-                });
         return seeds;
     }
-    };
+};
-}
 #endif

src/Platform/Experiment.cc

@@ -1,6 +1,4 @@
 #include "Experiment.h"
-#include "Datasets.h"
-#include "Models.h"
 
 namespace platform {
     using json = nlohmann::json;
@@ -45,7 +43,7 @@ namespace platform {
         result["discretized"] = discretized;
         result["stratified"] = stratified;
         result["folds"] = nfolds;
-        result["seeds"] = randomSeeds;
+        result["seeds"] = random_seeds;
         result["duration"] = duration;
         result["results"] = json::array();
         for (const auto& r : results) {
@@ -85,92 +83,10 @@ namespace platform {
         file << data;
         file.close();
     }
-
     void Experiment::show()
     {
         json data = build_json();
         cout << data.dump(4) << endl;
     }
 
-    void Experiment::go(vector<string> filesToProcess, const string& path)
-    {
-        cout << "*** Starting experiment: " << title << " ***" << endl;
-        for (auto fileName : filesToProcess) {
-            cout << "- " << setw(20) << left << fileName << " " << right << flush;
-            cross_validation(path, fileName);
-            cout << endl;
-        }
-    }
-
-    void Experiment::cross_validation(const string& path, const string& fileName)
-    {
-        auto datasets = platform::Datasets(path, true, platform::ARFF);
-        // Get dataset
-        auto [X, y] = datasets.getTensors(fileName);
-        auto states = datasets.getStates(fileName);
-        auto features = datasets.getFeatures(fileName);
-        auto samples = datasets.getNSamples(fileName);
-        auto className = datasets.getClassName(fileName);
-        cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
-        // Prepare Result
-        auto result = Result();
-        auto [values, counts] = at::_unique(y);;
-        result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
-        int nResults = nfolds * static_cast<int>(randomSeeds.size());
-        auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
-        auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
-        auto train_time = torch::zeros({ nResults }, torch::kFloat64);
-        auto test_time = torch::zeros({ nResults }, torch::kFloat64);
-        auto nodes = torch::zeros({ nResults }, torch::kFloat64);
-        auto edges = torch::zeros({ nResults }, torch::kFloat64);
-        auto num_states = torch::zeros({ nResults }, torch::kFloat64);
-        Timer train_timer, test_timer;
-        int item = 0;
-        for (auto seed : randomSeeds) {
-            cout << "(" << seed << ") doing Fold: " << flush;
-            Fold* fold;
-            if (stratified)
-                fold = new StratifiedKFold(nfolds, y, seed);
-            else
-                fold = new KFold(nfolds, y.size(0), seed);
-            for (int nfold = 0; nfold < nfolds; nfold++) {
-                auto clf = Models::instance()->create(model);
-                setModelVersion(clf->getVersion());
-                train_timer.start();
-                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 });
-                cout << nfold + 1 << ", " << flush;
-                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_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;
-                // Store results and times in vector
-                result.addScoreTrain(accuracy_train_value);
-                result.addScoreTest(accuracy_test_value);
-                result.addTimeTrain(train_time[item].item<double>());
-                result.addTimeTest(test_time[item].item<double>());
-                item++;
-            }
-            cout << "end. " << flush;
-            delete fold;
-        }
-        result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
-        result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
-        result.setTrainTime(torch::mean(train_time).item<double>()).setTestTime(torch::mean(test_time).item<double>());
-        result.setNodes(torch::mean(nodes).item<double>()).setLeaves(torch::mean(edges).item<double>()).setDepth(torch::mean(num_states).item<double>());
-        result.setDataset(fileName);
-        addResult(result);
-    }
 }

src/Platform/Experiment.h

@@ -4,11 +4,6 @@
 #include <nlohmann/json.hpp>
 #include <string>
 #include <chrono>
-#include "Folding.h"
-#include "BaseClassifier.h"
-#include "TAN.h"
-#include "KDB.h"
-#include "AODE.h"
 
 using namespace std;
 namespace platform {
@@ -29,33 +24,34 @@ namespace platform {
     };
     class Result {
     private:
-        string dataset, hyperparameters, model_version;
+        string dataset = "", hyperparameters = "", model_version = "";
         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 };
+        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;
+        vector<double> scores_train{}, scores_test{}, times_train{}, times_test{};
         float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
-        vector<double> scores_train, scores_test, times_train, times_test;
     public:
         Result() = default;
         Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
         Result& setHyperparameters(const string& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
-        Result& setSamples(int samples) { this->samples = samples; return *this; }
+        Result& setSamples(const int samples) { this->samples = samples; return *this; }
-        Result& setFeatures(int features) { this->features = features; return *this; }
+        Result& setFeatures(const int features) { this->features = features; return *this; }
-        Result& setClasses(int classes) { this->classes = classes; return *this; }
+        Result& setClasses(const int classes) { this->classes = classes; return *this; }
-        Result& setScoreTrain(double score) { this->score_train = score; return *this; }
+        Result& setScoreTrain(const double score) { this->score_train = score; return *this; }
-        Result& setScoreTest(double score) { this->score_test = score; return *this; }
+        Result& setScoreTest(const double score) { this->score_test = score; return *this; }
-        Result& setScoreTrainStd(double score_std) { this->score_train_std = score_std; return *this; }
+        Result& setScoreTrainStd(const double score_std) { this->score_train_std = score_std; return *this; }
-        Result& setScoreTestStd(double score_std) { this->score_test_std = score_std; return *this; }
+        Result& setScoreTestStd(const double score_std) { this->score_test_std = score_std; return *this; }
-        Result& setTrainTime(double train_time) { this->train_time = train_time; return *this; }
+        Result& setTrainTime(const double train_time) { this->train_time = train_time; return *this; }
-        Result& setTrainTimeStd(double train_time_std) { this->train_time_std = train_time_std; return *this; }
+        Result& setTrainTimeStd(const double train_time_std) { this->train_time_std = train_time_std; return *this; }
-        Result& setTestTime(double test_time) { this->test_time = test_time; return *this; }
+        Result& setTestTime(const double test_time) { this->test_time = test_time; return *this; }
-        Result& setTestTimeStd(double test_time_std) { this->test_time_std = test_time_std; return *this; }
+        Result& setTestTimeStd(const double test_time_std) { this->test_time_std = test_time_std; return *this; }
-        Result& setNodes(float nodes) { this->nodes = nodes; return *this; }
+        Result& setNodes(const float nodes) { this->nodes = nodes; return *this; }
-        Result& setLeaves(float leaves) { this->leaves = leaves; return *this; }
+        Result& setLeaves(const float leaves) { this->leaves = leaves; return *this; }
-        Result& setDepth(float depth) { this->depth = depth; return *this; }
+        Result& setDepth(const float depth) { this->depth = depth; return *this; }
-        Result& addScoreTrain(double score) { scores_train.push_back(score); return *this; }
+        Result& setModelVersion(const string& model_version) { this->model_version = model_version; return *this; }
-        Result& addScoreTest(double score) { scores_test.push_back(score); return *this; }
+        Result& addScoreTrain(const double score) { scores_train.push_back(score); return *this; }
-        Result& addTimeTrain(double time) { times_train.push_back(time); return *this; }
+        Result& addScoreTest(const double score) { scores_test.push_back(score); return *this; }
-        Result& addTimeTest(double time) { times_test.push_back(time); return *this; }
+        Result& addTimeTrain(const double time) { times_train.push_back(time); return *this; }
+        Result& addTimeTest(const double time) { times_test.push_back(time); return *this; }
         const float get_score_train() const { return score_train; }
         float get_score_test() { return score_test; }
         const string& getDataset() const { return dataset; }
@@ -78,15 +74,16 @@ namespace platform {
         const vector<double>& getScoresTest() const { return scores_test; }
         const vector<double>& getTimesTrain() const { return times_train; }
         const vector<double>& getTimesTest() const { return times_test; }
+        const string& getModelVersion() const { return model_version; }
     };
     class Experiment {
     private:
-        string title, model, platform, score_name, model_version, language_version, language;
+        string title{""}, model{""}, platform{""}, score_name{""}, model_version{""}, language_version{""}, language{""};
-        bool discretized{ false }, stratified{ false };
+        bool discretized{false}, stratified{false};
         vector<Result> results;
-        vector<int> randomSeeds;
+        vector<int> random_seeds;
-        int nfolds{ 0 };
+        int nfolds{0};
-        float duration{ 0 };
+        float duration{0};
         json build_json();
     public:
         Experiment() = default;
@@ -97,16 +94,14 @@ namespace platform {
         Experiment& setModelVersion(const string& model_version) { this->model_version = model_version; return *this; }
         Experiment& setLanguage(const string& language) { this->language = language; return *this; }
         Experiment& setLanguageVersion(const string& language_version) { this->language_version = language_version; return *this; }
-        Experiment& setDiscretized(bool discretized) { this->discretized = discretized; return *this; }
+        Experiment& setDiscretized(const bool discretized) { this->discretized = discretized; return *this; }
-        Experiment& setStratified(bool stratified) { this->stratified = stratified; return *this; }
+        Experiment& setStratified(const bool stratified) { this->stratified = stratified; return *this; }
-        Experiment& setNFolds(int nfolds) { this->nfolds = nfolds; return *this; }
+        Experiment& setNFolds(const int nfolds) { this->nfolds = nfolds; return *this; }
         Experiment& addResult(Result result) { results.push_back(result); return *this; }
-        Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
+        Experiment& addRandomSeed(const int random_seed) { random_seeds.push_back(random_seed); return *this; }
-        Experiment& setDuration(float duration) { this->duration = duration; return *this; }
+        Experiment& setDuration(const float duration) { this->duration = duration; return *this; }
         string get_file_name();
         void save(const string& path);
-        void cross_validation(const string& path, const string& fileName);
-        void go(vector<string> filesToProcess, const string& path);
         void show();
     };
 }

src/Platform/Folding.cc

@@ -7,7 +7,7 @@ Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
     random_seed = default_random_engine(seed == -1 ? rd() : seed);
     srand(seed == -1 ? time(0) : seed);
 }
-KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
+KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>())
 {
     iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
     shuffle(indices.begin(), indices.end(), random_seed);

src/Platform/Models.cc

@@ -1,54 +1,8 @@
 #include "Models.h"
 namespace platform {
     using namespace std;
-    // Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
+    map<string, bayesnet::BaseClassifier*> Models::classifiers = map<string, bayesnet::BaseClassifier*>({
-    Models* Models::factory = nullptr;;
+        { "AODE", new bayesnet::AODE() }, { "KDB", new bayesnet::KDB(2) },
-    Models* Models::instance()
+        { "SPODE",  new bayesnet::SPODE(2) }, { "TAN",  new bayesnet::TAN() }
-    {
+        });
-        //manages singleton
-        if (factory == nullptr)
-            factory = new Models();
-        return factory;
-    }
-    void Models::registerFactoryFunction(const string& name,
-        function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
-    {
-        // register the class factory function
-        functionRegistry[name] = classFactoryFunction;
-    }
-    shared_ptr<bayesnet::BaseClassifier> Models::create(const string& name)
-    {
-        bayesnet::BaseClassifier* instance = nullptr;
-
-        // find name in the registry and call factory method.
-        auto it = functionRegistry.find(name);
-        if (it != functionRegistry.end())
-            instance = it->second();
-        // wrap instance in a shared ptr and return
-        if (instance != nullptr)
-            return shared_ptr<bayesnet::BaseClassifier>(instance);
-        else
-            return nullptr;
-    }
-    vector<string> Models::getNames()
-    {
-        vector<string> names;
-        transform(functionRegistry.begin(), functionRegistry.end(), back_inserter(names),
-            [](const pair<string, function<bayesnet::BaseClassifier* (void)>>& pair) { return pair.first; });
-        return names;
-    }
-    string Models::toString()
-    {
-        string result = "";
-        for (const auto& pair : functionRegistry) {
-            result += pair.first + ", ";
-        }
-        return "{" + result.substr(0, result.size() - 2) + "}";
-    }
-
-    Registrar::Registrar(const string& name, function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
-    {
-        // register the class factory function 
-        Models::instance()->registerFactoryFunction(name, classFactoryFunction);
-    }
 }

src/Platform/Models.h

@@ -9,24 +9,25 @@
 namespace platform {
     class Models {
     private:
-        map<string, function<bayesnet::BaseClassifier* (void)>> functionRegistry;
+        static map<string, bayesnet::BaseClassifier*> classifiers;
-        static Models* factory; //singleton
-        Models() {};
     public:
-        Models(Models&) = delete;
+        static bayesnet::BaseClassifier* get(string name) { return classifiers[name]; }
-        void operator=(const Models&) = delete;
+        static vector<string> getNames()
-        // Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
+        {
-        static Models* instance();
+            vector<string> names;
-        shared_ptr<bayesnet::BaseClassifier> create(const string& name);
+            for (auto& [name, classifier] : classifiers) {
-        void registerFactoryFunction(const string& name,
+                names.push_back(name);
-            function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
+            }
-        vector<string> getNames();
+            return names;
-        string toString();
+        }
-
+        static string toString()
-    };
+        {
-    class Registrar {
+            string names = "";
-    public:
+            for (auto& [name, classifier] : classifiers) {
-        Registrar(const string& className, function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
+                names += name + ", ";
+            }
+            return "{" + names.substr(0, names.size() - 2) + "}";
+        }
     };
 }
 #endif

src/Platform/main.cc

@@ -4,8 +4,9 @@
 #include "Experiment.h"
 #include "Datasets.h"
 #include "DotEnv.h"
+#include "CrossValidation.h"
 #include "Models.h"
-#include "modelRegister.h"
+
 
 using namespace std;
 const string PATH_RESULTS = "results";
@@ -13,7 +14,7 @@ const string PATH_DATASETS = "datasets";
 
 argparse::ArgumentParser manageArguments(int argc, char** argv)
 {
-    auto env = platform::DotEnv();
+    auto env = DotEnv();
     argparse::ArgumentParser program("BayesNetSample");
     program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
     program.add_argument("-p", "--path")
@@ -21,13 +22,13 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
         .default_value(string{ PATH_DATASETS }
     );
     program.add_argument("-m", "--model")
-        .help("Model to use " + platform::Models::instance()->toString())
+        .help("Model to use " + platform::Models::toString())
         .action([](const std::string& value) {
-        static const vector<string> choices = platform::Models::instance()->getNames();
+        static const vector<string> choices = platform::Models::getNames();
         if (find(choices.begin(), choices.end(), value) != choices.end()) {
             return value;
         }
-        throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
+        throw runtime_error("Model must be one of " + platform::Models::toString());
             }
     );
     program.add_argument("--title").default_value("").help("Experiment title");
@@ -83,7 +84,7 @@ 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");
-    vector<string> filesToTest;
+    vector<string> filesToProcess;
     auto datasets = platform::Datasets(path, true, platform::ARFF);
     auto title = program.get<string>("title");
     if (file_name != "") {
@@ -94,10 +95,10 @@ int main(int argc, char** argv)
         if (title == "") {
             title = "Test " + file_name + " " + model_name + " " + to_string(n_folds) + " folds";
         }
-        filesToTest.push_back(file_name);
+        filesToProcess.push_back(file_name);
     } else {
-        filesToTest = platform::Datasets(path, true, platform::ARFF).getNames();
+        filesToProcess = platform::Datasets(path, true, platform::ARFF).getNames();
-        saveResults = true;
+        saveResults = true; // Only save results if all datasets are processed
     }
 
     /*
@@ -111,8 +112,20 @@ int main(int argc, char** argv)
         experiment.addRandomSeed(seed);
     }
     platform::Timer timer;
+    cout << "*** Starting experiment: " << title << " ***" << endl;
     timer.start();
-    experiment.go(filesToTest, path);
+    auto validation = platform::CrossValidation(model_name, stratified, n_folds, seeds, datasets);
+    for (auto fileName : filesToProcess) {
+        cout << "- " << setw(20) << left << fileName << " " << right << flush;
+        auto [X, y] = datasets.getTensors(fileName);
+        auto features = datasets.getFeatures(fileName);
+        auto samples = datasets.getNSamples(fileName);
+        cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
+        auto result = validation.crossValidate(fileName);
+        result.setDataset(fileName);
+        experiment.setModelVersion(result.getModelVersion());
+        experiment.addResult(result);
+    }
     experiment.setDuration(timer.getDuration());
     if (saveResults)
         experiment.save(PATH_RESULTS);

src/Platform/modelRegister.h

@@ -1,11 +0,0 @@
-#ifndef MODEL_REGISTER_H
-#define MODEL_REGISTER_H
-static platform::Registrar registrarT("TAN",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TAN();});
-static platform::Registrar registrarS("SPODE",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODE(2);});
-static platform::Registrar registrarK("KDB",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDB(2);});
-static platform::Registrar registrarA("AODE",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
-#endif

src/Platform/platformUtils.cc

@@ -2,17 +2,6 @@
 
 using namespace torch;
 
-vector<string> split(const string& text, char delimiter)
-{
-    vector<string> result;
-    stringstream ss(text);
-    string token;
-    while (getline(ss, token, delimiter)) {
-        result.push_back(token);
-    }
-    return result;
-}
-
 pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features)
 {
     vector<mdlp::labels_t> Xd;
@@ -39,7 +28,7 @@ vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::label
     return Xd;
 }
 
-bool file_exists(const string& name)
+bool file_exists(const std::string& name)
 {
     if (FILE* file = fopen(name.c_str(), "r")) {
         fclose(file);
@@ -60,7 +49,7 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
     auto className = handler.getClassName();
     vector<string> features;
     auto attributes = handler.getAttributes();
-    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
+    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& f) { return f.first; });
     Tensor Xd;
     auto states = map<string, vector<int>>();
     if (discretize_dataset) {
@@ -93,7 +82,7 @@ tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vect
     auto className = handler.getClassName();
     vector<string> features;
     auto attributes = handler.getAttributes();
-    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
+    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& f) { return f.first; });
     // Discretize Dataset
     vector<mdlp::labels_t> Xd;
     map<string, int> maxes;

src/Platform/platformUtils.h

@@ -11,10 +11,9 @@ using namespace std;
 const string PATH = "../../data/";
 
 bool file_exists(const std::string& name);
-vector<string> split(const string& text, char delimiter);
 pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features);
 vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y);
-pair<torch::Tensor, map<string, vector<int>>> discretizeTorch(torch::Tensor& X, torch::Tensor& y, vector<string>& features, const string& className);
+// pair<torch::Tensor, map<string, vector<int>>> discretizeTorch(torch::Tensor& X, torch::Tensor& y, vector<string>& features, const string& className);
 tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(const string& name);
 tuple<torch::Tensor, torch::Tensor, vector<string>, string, map<string, vector<int>>> loadDataset(const string& path, const string& name, bool class_last, bool discretize_dataset);
 map<string, vector<int>> get_states(vector<string>& features, string className, map<string, int>& maxes);