Add states as result in Proposal methods

fix mistake in headerline (report)

.clang-tidy

@@ -13,5 +13,4 @@ HeaderFilterRegex: 'src/*'
 AnalyzeTemporaryDtors: false
 WarningsAsErrors: ''
 FormatStyle: file
-FormatStyleOptions: ''
 ...

.vscode/launch.json

@@ -25,14 +25,14 @@
             "program": "${workspaceFolder}/build/src/Platform/main",
             "args": [
                 "-m",
-                "TANNew",
+                "SPODELd",
                 "-p",
                 "/Users/rmontanana/Code/discretizbench/datasets",
                 "--stratified",
                 "-d",
                 "iris"
             ],
-            "cwd": "${workspaceFolder}/build/src/Platform",
+            "cwd": "/Users/rmontanana/Code/discretizbench",
         },
         {
             "name": "Build & debug active file",

Makefile

@@ -14,6 +14,14 @@ setup: ## Install dependencies for tests and coverage
 dependency: ## Create a dependency graph diagram of the project (build/dependency.png)
 	cd build && cmake .. --graphviz=dependency.dot && dot -Tpng dependency.dot -o dependency.png
 
+build: ## Build the main and BayesNetSample
+	cmake --build build -t main -t BayesNetSample -j 32
+
+clean: ## Clean the debug info
+	@echo ">>> Cleaning Debug BayesNet ...";
+	find . -name "*.gcda" -print0 | xargs -0 rm
+	@echo ">>> Done";
+
 debug: ## Build a debug version of the project
 	@echo ">>> Building Debug BayesNet ...";
 	@if [ -d ./build ]; then rm -rf ./build; fi

sample/sample.cc

@@ -178,61 +178,59 @@ int main(int argc, char** argv)
     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;
-    Fold* fold;
-    if (stratified)
-        fold = new StratifiedKFold(nFolds, y, seed);
-    else
-        fold = new 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 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;
+    // Fold* fold;
+    // if (stratified)
+    //     fold = new StratifiedKFold(nFolds, y, seed);
+    // else
+    //     fold = new 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/AODE.cc

@@ -2,14 +2,14 @@
 
 namespace bayesnet {
     AODE::AODE() : Ensemble() {}
-    void AODE::train()
+    void AODE::buildModel()
     {
         models.clear();
         for (int i = 0; i < features.size(); ++i) {
             models.push_back(std::make_unique<SPODE>(i));
         }
     }
-    vector<string> AODE::graph(const string& title)
+    vector<string> AODE::graph(const string& title) const
     {
         return Ensemble::graph(title);
     }

src/BayesNet/AODE.h

@@ -5,11 +5,11 @@
 namespace bayesnet {
     class AODE : public Ensemble {
     protected:
-        void train() override;
+        void buildModel() override;
     public:
         AODE();
         virtual ~AODE() {};
-        vector<string> graph(const string& title = "AODE") override;
+        vector<string> graph(const string& title = "AODE") const override;
     };
 }
 #endif

src/BayesNet/AODELd.cc

@@ -0,0 +1,40 @@
+#include "AODELd.h"
+#include "Models.h"
+
+namespace bayesnet {
+    using namespace std;
+    AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
+    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
+        Ensemble::fit(dataset, features, className, states);
+        return *this;
+
+    }
+    void AODELd::buildModel()
+    {
+        models.clear();
+        for (int i = 0; i < features.size(); ++i) {
+            models.push_back(std::make_unique<SPODELd>(i));
+        }
+        n_models = models.size();
+    }
+    void AODELd::trainModel()
+    {
+        for (const auto& model : models) {
+            model->fit(Xf, y, features, className, states);
+        }
+    }
+    vector<string> AODELd::graph(const string& name) const
+    {
+        return Ensemble::graph(name);
+    }
+}

src/BayesNet/AODELd.h

@@ -0,0 +1,21 @@
+#ifndef AODELD_H
+#define AODELD_H
+#include "Ensemble.h"
+#include "Proposal.h"
+#include "SPODELd.h"
+
+namespace bayesnet {
+    using namespace std;
+    class AODELd : public Ensemble, public Proposal {
+    protected:
+        void trainModel() override;
+        void buildModel() override;
+    public:
+        AODELd();
+        AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_) override;
+        virtual ~AODELd() = default;
+        vector<string> graph(const string& name = "AODE") const override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !AODELD_H

src/BayesNet/BaseClassifier.h

@@ -5,24 +5,27 @@
 namespace bayesnet {
     using namespace std;
     class BaseClassifier {
+    protected:
+        virtual void trainModel() = 0;
     public:
         // X is nxm vector, y is nx1 vector
         virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
         // X is nxm tensor, y is nx1 tensor
         virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        virtual ~BaseClassifier() = default;
         torch::Tensor virtual predict(torch::Tensor& X) = 0;
         vector<int> virtual predict(vector<vector<int>>& X) = 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() = 0;
-        int virtual getNumberOfEdges() = 0;
-        int virtual getNumberOfStates() = 0;
-        vector<string> virtual show() = 0;
-        vector<string> virtual graph(const string& title = "") = 0;
-        virtual ~BaseClassifier() = default;
+        int virtual getNumberOfNodes()const = 0;
+        int virtual getNumberOfEdges()const = 0;
+        int virtual getNumberOfStates() const = 0;
+        vector<string> virtual show() const = 0;
+        vector<string> virtual graph(const string& title = "") const = 0;
         const string inline getVersion() const { return "0.1.0"; };
         vector<string> virtual topological_order() = 0;
-        void virtual dump_cpt() = 0;
+        void virtual dump_cpt()const = 0;
     };
 }
 #endif

src/BayesNet/BayesMetrics.cc

@@ -2,7 +2,7 @@
 #include "Mst.h"
 namespace bayesnet {
     //samples is nxm tensor used to fit the model
-    Metrics::Metrics(torch::Tensor& samples, vector<string>& features, string& className, int classNumStates)
+    Metrics::Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates)
         : samples(samples)
         , features(features)
         , className(className)
@@ -76,7 +76,7 @@ namespace bayesnet {
         std::vector<float> v(matrix.data_ptr<float>(), matrix.data_ptr<float>() + matrix.numel());
         return v;
     }
-    double Metrics::entropy(torch::Tensor& feature)
+    double Metrics::entropy(const torch::Tensor& feature)
     {
         torch::Tensor counts = feature.bincount();
         int totalWeight = counts.sum().item<int>();
@@ -86,7 +86,7 @@ namespace bayesnet {
         return entropy.nansum().item<double>();
     }
     // H(Y|X) = sum_{x in X} p(x) H(Y|X=x)
-    double Metrics::conditionalEntropy(torch::Tensor& firstFeature, torch::Tensor& secondFeature)
+    double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature)
     {
         int numSamples = firstFeature.sizes()[0];
         torch::Tensor featureCounts = secondFeature.bincount();
@@ -115,7 +115,7 @@ namespace bayesnet {
         return entropyValue;
     }
     // I(X;Y) = H(Y) - H(Y|X)
-    double Metrics::mutualInformation(torch::Tensor& firstFeature, torch::Tensor& secondFeature)
+    double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature)
     {
         return entropy(firstFeature) - conditionalEntropy(firstFeature, secondFeature);
     }
@@ -124,7 +124,7 @@ namespace bayesnet {
     and the indices of the weights as nodes of this square matrix using
     Kruskal algorithm
     */
-    vector<pair<int, int>> Metrics::maximumSpanningTree(vector<string> features, Tensor& weights, int root)
+    vector<pair<int, int>> Metrics::maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root)
     {
         auto mst = MST(features, weights, root);
         return mst.maximumSpanningTree();

src/BayesNet/BayesMetrics.h

@@ -14,15 +14,15 @@ namespace bayesnet {
         int classNumStates = 0;
     public:
         Metrics() = default;
-        Metrics(Tensor&, vector<string>&, string&, int);
+        Metrics(const Tensor&, const vector<string>&, const string&, const int);
         Metrics(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const int);
-        double entropy(Tensor&);
-        double conditionalEntropy(Tensor&, Tensor&);
-        double mutualInformation(Tensor&, Tensor&);
+        double entropy(const Tensor&);
+        double conditionalEntropy(const Tensor&, const Tensor&);
+        double mutualInformation(const Tensor&, const Tensor&);
         vector<float> conditionalEdgeWeights(); // To use in Python
         Tensor conditionalEdge();
         vector<pair<string, string>> doCombinations(const vector<string>&);
-        vector<pair<int, int>> maximumSpanningTree(vector<string> features, Tensor& weights, int root);
+        vector<pair<int, int>> maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root);
     };
 }
 #endif

src/BayesNet/CMakeLists.txt

@@ -1,4 +1,7 @@
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
-add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANNew.cc Mst.cc)
+include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
+include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
+add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 
+    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
 target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")

src/BayesNet/Classifier.cc

@@ -1,6 +1,5 @@
 #include "Classifier.h"
 #include "bayesnetUtils.h"
-#include "ArffFiles.h"
 
 namespace bayesnet {
     using namespace torch;
@@ -8,58 +7,65 @@ namespace bayesnet {
     Classifier::Classifier(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)
     {
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
         this->features = features;
         this->className = className;
         this->states = states;
+        m = dataset.size(1);
+        n = dataset.size(0) - 1;
         checkFitParameters();
         auto n_classes = states[className].size();
-        metrics = Metrics(samples, features, className, n_classes);
+        metrics = Metrics(dataset, features, className, n_classes);
         model.initialize();
-        train();
-        if (Xv.empty()) {
-            // fit with tensors
-            model.fit(X, y, features, className);
-        } else {
-            // fit with vectors
-            model.fit(Xv, yv, features, className);
-        }
+        buildModel();
+        trainModel();
         fitted = true;
         return *this;
     }
+
+    void Classifier::buildDataset(Tensor& ytmp)
+    {
+        try {
+            auto yresized = torch::transpose(ytmp.view({ ytmp.size(0), 1 }), 0, 1);
+            dataset = torch::cat({ dataset, yresized }, 0);
+        }
+        catch (const std::exception& e) {
+            std::cerr << e.what() << '\n';
+            cout << "X dimensions: " << dataset.sizes() << "\n";
+            cout << "y dimensions: " << ytmp.sizes() << "\n";
+            exit(1);
+        }
+    }
+    void Classifier::trainModel()
+    {
+        model.fit(dataset, features, className, states);
+    }
     // X is nxm where n is the number of features and m the number of samples
     Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
     {
-        this->X = X;
-        this->y = y;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        dataset = X;
+        buildDataset(y);
         return build(features, className, states);
     }
     // X is nxm where n is the number of features and m the number of samples
     Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
     {
-
-        this->X = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
-        Xv = X;
+        dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
         for (int i = 0; i < X.size(); ++i) {
-            this->X.index_put_({ i, "..." }, torch::tensor(X[i], kInt32));
+            dataset.index_put_({ i, "..." }, torch::tensor(X[i], kInt32));
         }
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
+        auto ytmp = torch::tensor(y, kInt32);
+        buildDataset(ytmp);
+        return build(features, className, states);
+    }
+    Classifier& Classifier::fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states)
+    {
+        this->dataset = dataset;
         return build(features, className, states);
     }
     void Classifier::checkFitParameters()
     {
-        auto sizes = X.sizes();
-        m = sizes[1];
-        n = sizes[0];
-        if (m != y.size(0)) {
-            throw invalid_argument("X and y must have the same number of samples");
-        }
         if (n != features.size()) {
-            throw invalid_argument("X and features must have the same number of features");
+            throw invalid_argument("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");
@@ -106,7 +112,7 @@ namespace bayesnet {
         }
         return model.score(X, y);
     }
-    vector<string> Classifier::show()
+    vector<string> Classifier::show() const
     {
         return model.show();
     }
@@ -114,22 +120,20 @@ namespace bayesnet {
     {
         // Add all nodes to the network
         for (const auto& feature : features) {
-            model.addNode(feature, states[feature].size());
-            cout << "-Adding node " << feature << " with " << states[feature].size() << " states" << endl;
+            model.addNode(feature);
         }
-        model.addNode(className, states[className].size());
-        cout << "*Adding class " << className << " with " << states[className].size() << " states" << endl;
+        model.addNode(className);
     }
-    int Classifier::getNumberOfNodes()
+    int Classifier::getNumberOfNodes() const
     {
         // Features does not include class
         return fitted ? model.getFeatures().size() + 1 : 0;
     }
-    int Classifier::getNumberOfEdges()
+    int Classifier::getNumberOfEdges() const
     {
-        return fitted ? model.getEdges().size() : 0;
+        return fitted ? model.getNumEdges() : 0;
     }
-    int Classifier::getNumberOfStates()
+    int Classifier::getNumberOfStates() const
     {
         return fitted ? model.getStates() : 0;
     }
@@ -137,61 +141,8 @@ namespace bayesnet {
     {
         return model.topological_sort();
     }
-    void Classifier::dump_cpt()
+    void Classifier::dump_cpt() const
     {
         model.dump_cpt();
     }
-    void Classifier::localDiscretizationProposal(map<string, mdlp::CPPFImdlp*>& discretizers, Tensor& Xf)
-    {
-        // order of local discretization is important. no good 0, 1, 2...
-        auto order = model.topological_sort();
-        auto& nodes = model.getNodes();
-        vector<int> indicesToReDiscretize;
-        auto n_samples = Xf.size(1);
-        bool upgrade = false; // Flag to check if we need to upgrade the model
-        for (auto feature : order) {
-            auto nodeParents = nodes[feature]->getParents();
-            int index = find(features.begin(), features.end(), feature) - features.begin();
-            vector<string> parents;
-            transform(nodeParents.begin(), nodeParents.end(), back_inserter(parents), [](const auto& p) {return p->getName(); });
-            if (parents.size() == 1) continue; // Only has class as parent
-            upgrade = true;
-            // Remove class as parent as it will be added later
-            parents.erase(remove(parents.begin(), parents.end(), className), parents.end());
-            // Get the indices of the parents
-            vector<int> indices;
-            transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(features.begin(), features.end(), p) - features.begin(); });
-            // Now we fit the discretizer of the feature conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
-            vector<string> yJoinParents;
-            transform(yv.begin(), yv.end(), back_inserter(yJoinParents), [&](const auto& p) {return to_string(p); });
-            for (auto idx : indices) {
-                for (int i = 0; i < n_samples; ++i) {
-                    yJoinParents[i] += to_string(Xv[idx][i]);
-                }
-            }
-            auto arff = ArffFiles();
-            auto yxv = arff.factorize(yJoinParents);
-            auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
-            auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
-            discretizers[feature]->fit(xvf, yxv);
-            indicesToReDiscretize.push_back(index);
-        }
-        if (upgrade) {
-            // Discretize again X (only the affected indices) with the new fitted discretizers
-            for (auto index : indicesToReDiscretize) {
-                auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
-                auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
-                Xv[index] = discretizers[features[index]]->transform(Xt);
-                auto xStates = vector<int>(discretizers[features[index]]->getCutPoints().size() + 1);
-                iota(xStates.begin(), xStates.end(), 0);
-                states[features[index]] = xStates;
-            }
-            // Now we fit the model again with the new values
-            cout << "Classifier: Upgrading model" << endl;
-            // To update the nodes states
-            addNodes();
-            model.fit(Xv, yv, features, className);
-            cout << "Classifier: Model upgraded" << endl;
-        }
-    }
 }

src/BayesNet/Classifier.h

@@ -4,46 +4,43 @@
 #include "BaseClassifier.h"
 #include "Network.h"
 #include "BayesMetrics.h"
-#include "CPPFImdlp.h"
 using namespace std;
 using namespace torch;
 
 namespace bayesnet {
     class Classifier : public BaseClassifier {
     private:
-        bool fitted;
+        void buildDataset(torch::Tensor& y);
         Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states);
     protected:
+        bool fitted;
         Network model;
         int m, n; // m: number of samples, n: number of features
-        Tensor X; // nxm tensor
-        vector<vector<int>> Xv; // nxm vector
-        Tensor y;
-        vector<int> yv;
-        Tensor samples; // (n+1)xm tensor
+        Tensor dataset; // (n+1)xm tensor
         Metrics metrics;
         vector<string> features;
         string className;
         map<string, vector<int>> states;
         void checkFitParameters();
-        virtual void train() = 0;
-        void localDiscretizationProposal(map<string, mdlp::CPPFImdlp*>& discretizers, Tensor& Xf);
+        virtual void buildModel() = 0;
+        void trainModel() override;
     public:
         Classifier(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;
+        Classifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
         void addNodes();
-        int getNumberOfNodes() override;
-        int getNumberOfEdges() override;
-        int getNumberOfStates() override;
+        int getNumberOfNodes() const override;
+        int getNumberOfEdges() const override;
+        int getNumberOfStates() const override;
         Tensor predict(Tensor& X) override;
         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;
-        vector<string> show() override;
-        vector<string> topological_order() override;
-        void dump_cpt() override;
+        vector<string> show() const override;
+        vector<string> topological_order()  override;
+        void dump_cpt() const override;
     };
 }
 #endif

src/BayesNet/Ensemble.cc

@@ -3,60 +3,26 @@
 namespace bayesnet {
     using namespace torch;
 
-    Ensemble::Ensemble() : m(0), n(0), n_models(0), metrics(Metrics()), fitted(false) {}
-    Ensemble& Ensemble::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Ensemble::Ensemble() : Classifier(Network()) {}
+
+    void Ensemble::trainModel()
     {
-        dataset = cat({ X, y.view({y.size(0), 1}) }, 1);
-        this->features = features;
-        this->className = className;
-        this->states = states;
-        auto n_classes = states[className].size();
-        metrics = Metrics(dataset, features, className, n_classes);
-        // Build models
-        train();
-        // Train models
         n_models = models.size();
-        auto Xt = torch::transpose(X, 0, 1);
         for (auto i = 0; i < n_models; ++i) {
-            if (Xv == vector<vector<int>>()) {
-                // fit with tensors
-                models[i]->fit(Xt, y, features, className, states);
-            } else {
-                // fit with vectors
-                models[i]->fit(Xv, yv, features, className, states);
-            }
+            // fit with vectors
+            models[i]->fit(dataset, features, className, states);
         }
-        fitted = true;
-        return *this;
-    }
-    Ensemble& Ensemble::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
-    {
-        this->X = torch::transpose(X, 0, 1);
-        this->y = y;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        return build(features, className, states);
-    }
-    Ensemble& Ensemble::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
-    {
-        this->X = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, kInt32);
-        Xv = X;
-        for (int i = 0; i < X.size(); ++i) {
-            this->X.index_put_({ "...", i }, torch::tensor(X[i], kInt32));
-        }
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, states);
     }
     vector<int> Ensemble::voting(Tensor& y_pred)
     {
         auto y_pred_ = y_pred.accessor<int, 2>();
         vector<int> y_pred_final;
         for (int i = 0; i < y_pred.size(0); ++i) {
-            vector<float> votes(states[className].size(), 0);
+            vector<float> votes(y_pred.size(1), 0);
             for (int j = 0; j < y_pred.size(1); ++j) {
                 votes[y_pred_[i][j]] += 1;
             }
+            // argsort in descending order
             auto indices = argsort(votes);
             y_pred_final.push_back(indices[0]);
         }
@@ -70,13 +36,12 @@ namespace bayesnet {
         Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
         //Create a threadpool
         auto threads{ vector<thread>() };
-        auto lock = mutex();
+        mutex mtx;
         for (auto i = 0; i < n_models; ++i) {
             threads.push_back(thread([&, i]() {
                 auto ypredict = models[i]->predict(X);
-                lock.lock();
+                lock_guard<mutex> lock(mtx);
                 y_pred.index_put_({ "...", i }, ypredict);
-                lock.unlock();
                 }));
         }
         for (auto& thread : threads) {
@@ -128,9 +93,8 @@ namespace bayesnet {
             }
         }
         return (double)correct / y_pred.size();
-
     }
-    vector<string> Ensemble::show()
+    vector<string> Ensemble::show() const
     {
         auto result = vector<string>();
         for (auto i = 0; i < n_models; ++i) {
@@ -139,7 +103,7 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<string> Ensemble::graph(const string& title)
+    vector<string> Ensemble::graph(const string& title) const
     {
         auto result = vector<string>();
         for (auto i = 0; i < n_models; ++i) {
@@ -148,7 +112,7 @@ namespace bayesnet {
         }
         return result;
     }
-    int Ensemble::getNumberOfNodes()
+    int Ensemble::getNumberOfNodes() const
     {
         int nodes = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -156,7 +120,7 @@ namespace bayesnet {
         }
         return nodes;
     }
-    int Ensemble::getNumberOfEdges()
+    int Ensemble::getNumberOfEdges() const
     {
         int edges = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -164,7 +128,7 @@ namespace bayesnet {
         }
         return edges;
     }
-    int Ensemble::getNumberOfStates()
+    int Ensemble::getNumberOfStates() const
     {
         int nstates = 0;
         for (auto i = 0; i < n_models; ++i) {

src/BayesNet/Ensemble.h

@@ -8,44 +8,31 @@ using namespace std;
 using namespace torch;
 
 namespace bayesnet {
-    class Ensemble : public BaseClassifier {
+    class Ensemble : public Classifier {
     private:
-        bool fitted;
-        long n_models;
         Ensemble& build(vector<string>& features, string className, map<string, vector<int>>& states);
     protected:
+        unsigned n_models;
         vector<unique_ptr<Classifier>> models;
-        int m, n; // m: number of samples, n: number of features
-        Tensor X;
-        vector<vector<int>> Xv;
-        Tensor y;
-        vector<int> yv;
-        Tensor dataset;
-        Metrics metrics;
-        vector<string> features;
-        string className;
-        map<string, vector<int>> states;
-        void virtual train() = 0;
+        void trainModel() override;
         vector<int> voting(Tensor& y_pred);
     public:
         Ensemble();
         virtual ~Ensemble() = default;
-        Ensemble& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Ensemble& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
         Tensor predict(Tensor& X) override;
         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;
-        int getNumberOfNodes() override;
-        int getNumberOfEdges() override;
-        int getNumberOfStates() override;
-        vector<string> show() override;
-        vector<string> graph(const string& title) override;
-        vector<string> topological_order() override
+        int getNumberOfNodes() const override;
+        int getNumberOfEdges() const override;
+        int getNumberOfStates() const override;
+        vector<string> show() const override;
+        vector<string> graph(const string& title) const override;
+        vector<string> topological_order()  override
         {
             return vector<string>();
         }
-        void dump_cpt() override
+        void dump_cpt() const override
         {
         }
     };

src/BayesNet/KDB.cc

@@ -4,7 +4,7 @@ namespace bayesnet {
     using namespace torch;
 
     KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
-    void KDB::train()
+    void KDB::buildModel()
     {
         /*
         1. For each feature Xi, compute mutual information, I(X;C),
@@ -28,9 +28,10 @@ namespace bayesnet {
         // 1. For each feature Xi, compute mutual information, I(X;C),
         // where C is the class.
         addNodes();
+        const Tensor& y = dataset.index({ -1, "..." });
         vector <float> mi;
         for (auto i = 0; i < features.size(); i++) {
-            Tensor firstFeature = X.index({ i, "..." });
+            Tensor firstFeature = dataset.index({ i, "..." });
             mi.push_back(metrics.mutualInformation(firstFeature, y));
         }
         // 2. Compute class conditional mutual information I(Xi;XjIC), f or each
@@ -78,7 +79,7 @@ namespace bayesnet {
             exit_cond = num == n_edges || candidates.size(0) == 0;
         }
     }
-    vector<string> KDB::graph(const string& title)
+    vector<string> KDB::graph(const string& title) const
     {
         string header{ title };
         if (title == "KDB") {

src/BayesNet/KDB.h

@@ -11,11 +11,11 @@ namespace bayesnet {
         float theta;
         void add_m_edges(int idx, vector<int>& S, Tensor& weights);
     protected:
-        void train() override;
+        void buildModel() override;
     public:
         explicit KDB(int k, float theta = 0.03);
         virtual ~KDB() {};
-        vector<string> graph(const string& name = "KDB") override;
+        vector<string> graph(const string& name = "KDB") const override;
     };
 }
 #endif

src/BayesNet/KDBLd.cc

@@ -0,0 +1,30 @@
+#include "KDBLd.h"
+
+namespace bayesnet {
+    using namespace std;
+    KDBLd::KDBLd(int k) : KDB(k), Proposal(dataset, features, className) {}
+    KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal KDB structure, KDB::fit initializes the base Bayesian network
+        KDB::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
+        return *this;
+    }
+    Tensor KDBLd::predict(Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return KDB::predict(Xt);
+    }
+    vector<string> KDBLd::graph(const string& name) const
+    {
+        return KDB::graph(name);
+    }
+}

src/BayesNet/KDBLd.h

@@ -0,0 +1,19 @@
+#ifndef KDBLD_H
+#define KDBLD_H
+#include "KDB.h"
+#include "Proposal.h"
+
+namespace bayesnet {
+    using namespace std;
+    class KDBLd : public KDB, public Proposal {
+    private:
+    public:
+        explicit KDBLd(int k);
+        virtual ~KDBLd() = default;
+        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        vector<string> graph(const string& name = "KDB") const override;
+        Tensor predict(Tensor& X) override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !KDBLD_H

src/BayesNet/Mst.cc

@@ -94,7 +94,7 @@ namespace bayesnet {
         return result;
     }
 
-    MST::MST(vector<string>& features, Tensor& weights, int root) : features(features), weights(weights), root(root) {}
+    MST::MST(const vector<string>& features, const Tensor& weights, const int root) : features(features), weights(weights), root(root) {}
     vector<pair<int, int>> MST::maximumSpanningTree()
     {
         auto num_features = features.size();

src/BayesNet/Mst.h

@@ -13,7 +13,7 @@ namespace bayesnet {
         int root = 0;
     public:
         MST() = default;
-        MST(vector<string>& features, Tensor& weights, int root);
+        MST(const vector<string>& features, const Tensor& weights, const int root);
         vector<pair<int, int>> maximumSpanningTree();
     };
     class Graph {

src/BayesNet/Network.cc

@@ -20,7 +20,6 @@ namespace bayesnet {
         classNumStates = 0;
         fitted = false;
         nodes.clear();
-        dataset.clear();
         samples = torch::Tensor();
     }
     float Network::getmaxThreads()
@@ -31,31 +30,28 @@ namespace bayesnet {
     {
         return samples;
     }
-    void Network::addNode(const string& name, int numStates)
+    void Network::addNode(const string& name)
     {
         if (name == "") {
             throw invalid_argument("Node name cannot be empty");
         }
+        if (nodes.find(name) != nodes.end()) {
+            return;
+        }
         if (find(features.begin(), features.end(), name) == features.end()) {
             features.push_back(name);
         }
-        if (nodes.find(name) != nodes.end()) {
-            // if node exists update its number of states and remove parents, children and CPT
-            nodes[name]->clear();
-            nodes[name]->setNumStates(numStates);
-            return;
-        }
-        nodes[name] = std::make_unique<Node>(name, numStates);
+        nodes[name] = std::make_unique<Node>(name);
     }
-    vector<string> Network::getFeatures()
+    vector<string> Network::getFeatures() const
     {
         return features;
     }
-    int Network::getClassNumStates()
+    int Network::getClassNumStates() const
     {
         return classNumStates;
     }
-    int Network::getStates()
+    int Network::getStates() const
     {
         int result = 0;
         for (auto& node : nodes) {
@@ -63,7 +59,7 @@ namespace bayesnet {
         }
         return result;
     }
-    string Network::getClassName()
+    string Network::getClassName() const
     {
         return className;
     }
@@ -108,7 +104,7 @@ namespace bayesnet {
     {
         return nodes;
     }
-    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className)
+    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
     {
         if (n_samples != n_samples_y) {
             throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
@@ -126,45 +122,54 @@ namespace bayesnet {
             if (find(features.begin(), features.end(), feature) == features.end()) {
                 throw invalid_argument("Feature " + feature + " not found in Network::features");
             }
+            if (states.find(feature) == states.end()) {
+                throw invalid_argument("Feature " + feature + " not found in states");
+            }
         }
     }
-    // X comes in nxm, where n is the number of features and m the number of samples
-    void Network::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& featureNames, const string& className)
+    void Network::setStates(const map<string, vector<int>>& states)
     {
-        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className);
+        // 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();
+    }
+    // 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 vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
+    {
+        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states);
         this->className = className;
-        dataset.clear();
-        // Specific part
-        classNumStates = torch::max(y).item<int>() + 1;
         Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
         samples = torch::cat({ X , ytmp }, 0);
         for (int i = 0; i < featureNames.size(); ++i) {
             auto row_feature = X.index({ i, "..." });
-            dataset[featureNames[i]] = vector<int>(row_feature.data_ptr<int>(), row_feature.data_ptr<int>() + row_feature.size(0));;
         }
-        dataset[className] = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        completeFit();
+        completeFit(states);
+    }
+    void Network::fit(const torch::Tensor& samples, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
+    {
+        checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states);
+        this->className = className;
+        this->samples = samples;
+        completeFit(states);
     }
     // input_data comes in nxm, where n is the number of features and m the number of samples
-    void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className)
+    void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
     {
-        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className);
+        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states);
         this->className = className;
-        dataset.clear();
-        // Specific part
-        classNumStates = *max_element(labels.begin(), labels.end()) + 1;
-        // Build dataset & tensor of samples (nxm) (n+1 because of the class)
+        // Build tensor of samples (nxm) (n+1 because of the class)
         samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
         for (int i = 0; i < featureNames.size(); ++i) {
-            dataset[featureNames[i]] = input_data[i];
             samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
         }
-        dataset[className] = labels;
         samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
-        completeFit();
+        completeFit(states);
     }
-    void Network::completeFit()
+    void Network::completeFit(const map<string, vector<int>>& states)
     {
+        setStates(states);
         int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
         if (maxThreadsRunning < 1) {
             maxThreadsRunning = 1;
@@ -186,7 +191,7 @@ namespace bayesnet {
                     auto& pair = *std::next(nodes.begin(), nextNodeIndex);
                     ++nextNodeIndex;
                     lock.unlock();
-                    pair.second->computeCPT(dataset, laplaceSmoothing);
+                    pair.second->computeCPT(samples, features, laplaceSmoothing);
                     lock.lock();
                     nodes[pair.first] = std::move(pair.second);
                     lock.unlock();
@@ -210,8 +215,11 @@ namespace bayesnet {
         torch::Tensor result;
         result = torch::zeros({ samples.size(1), classNumStates }, torch::kFloat64);
         for (int i = 0; i < samples.size(1); ++i) {
-            auto sample = samples.index({ "...", i });
-            result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));
+            const Tensor sample = samples.index({ "...", i });
+            auto psample = predict_sample(sample);
+            auto temp = torch::tensor(psample, torch::kFloat64);
+            //            result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));
+            result.index_put_({ i, "..." }, temp);
         }
         if (proba)
             return result;
@@ -333,13 +341,12 @@ namespace bayesnet {
         for (auto& thread : threads) {
             thread.join();
         }
-
         // Normalize result
         double sum = accumulate(result.begin(), result.end(), 0.0);
         transform(result.begin(), result.end(), result.begin(), [sum](double& value) { return value / sum; });
         return result;
     }
-    vector<string> Network::show()
+    vector<string> Network::show() const
     {
         vector<string> result;
         // Draw the network
@@ -352,7 +359,7 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<string> Network::graph(const string& title)
+    vector<string> Network::graph(const string& title) const
     {
         auto output = vector<string>();
         auto prefix = "digraph BayesNet {\nlabel=<BayesNet ";
@@ -366,7 +373,7 @@ namespace bayesnet {
         output.push_back("}\n");
         return output;
     }
-    vector<pair<string, string>> Network::getEdges()
+    vector<pair<string, string>> Network::getEdges() const
     {
         auto edges = vector<pair<string, string>>();
         for (const auto& node : nodes) {
@@ -378,6 +385,10 @@ namespace bayesnet {
         }
         return edges;
     }
+    int Network::getNumEdges() const
+    {
+        return getEdges().size();
+    }
     vector<string> Network::topological_sort()
     {
         /* Check if al the fathers of every node are before the node */
@@ -416,10 +427,10 @@ namespace bayesnet {
         }
         return result;
     }
-    void Network::dump_cpt()
+    void Network::dump_cpt() const
     {
         for (auto& node : nodes) {
-            cout << "* " << node.first << ": " << node.second->getCPT() << endl;
+            cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
         }
     }
 }

src/BayesNet/Network.h

@@ -8,11 +8,10 @@ namespace bayesnet {
     class Network {
     private:
         map<string, unique_ptr<Node>> nodes;
-        map<string, vector<int>> dataset;
         bool fitted;
         float maxThreads = 0.95;
         int classNumStates;
-        vector<string> features; // Including class
+        vector<string> features; // Including classname
         string className;
         int laplaceSmoothing = 1;
         torch::Tensor samples; // nxm tensor used to fit the model
@@ -21,12 +20,9 @@ namespace bayesnet {
         vector<double> predict_sample(const torch::Tensor&);
         vector<double> exactInference(map<string, int>&);
         double computeFactor(map<string, int>&);
-        double mutual_info(torch::Tensor&, torch::Tensor&);
-        double entropy(torch::Tensor&);
-        double conditionalEntropy(torch::Tensor&, torch::Tensor&);
-        double mutualInformation(torch::Tensor&, torch::Tensor&);
-        void completeFit();
-        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className);
+        void completeFit(const map<string, vector<int>>&);
+        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>&);
+        void setStates(const map<string, vector<int>>&);
     public:
         Network();
         explicit Network(float, int);
@@ -34,29 +30,29 @@ namespace bayesnet {
         explicit Network(Network&);
         torch::Tensor& getSamples();
         float getmaxThreads();
-        void addNode(const string&, int);
+        void addNode(const string&);
         void addEdge(const string&, const string&);
         map<string, std::unique_ptr<Node>>& getNodes();
-        vector<string> getFeatures();
-        int getStates();
-        vector<pair<string, string>> getEdges();
-        int getClassNumStates();
-        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<string> getFeatures() const;
+        int getStates() const;
+        vector<pair<string, string>> getEdges() const;
+        int getNumEdges() const;
+        int getClassNumStates() const;
+        string getClassName() const;
+        void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const map<string, vector<int>>&);
+        void fit(const torch::Tensor&, const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
+        void fit(const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
         vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
         torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
-        //Computes the conditional edge weight of variable index u and v conditioned on class_node
-        torch::Tensor conditionalEdgeWeight();
         torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
         vector<vector<double>> predict_proba(const vector<vector<int>>&); // Return mxn vector of probabilities
         torch::Tensor predict_proba(const torch::Tensor&); // Return mxn tensor of probabilities
         double score(const vector<vector<int>>&, const vector<int>&);
         vector<string> topological_sort();
-        vector<string> show();
-        vector<string> graph(const string& title); // Returns a vector of strings representing the graph in graphviz format
+        vector<string> show() const;
+        vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
         void initialize();
-        void dump_cpt();
+        void dump_cpt() const;
         inline string version() { return "0.1.0"; }
     };
 }

src/BayesNet/Node.cc

@@ -2,8 +2,8 @@
 
 namespace bayesnet {
 
-    Node::Node(const std::string& name, int numStates)
-        : name(name), numStates(numStates), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
+    Node::Node(const std::string& name)
+        : name(name), numStates(0), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
     {
     }
     void Node::clear()
@@ -84,8 +84,9 @@ namespace bayesnet {
         }
         return result;
     }
-    void Node::computeCPT(map<string, vector<int>>& dataset, const int laplaceSmoothing)
+    void Node::computeCPT(const torch::Tensor& dataset, const vector<string>& features, const int laplaceSmoothing)
     {
+        dimensions.clear();
         // Get dimensions of the CPT
         dimensions.push_back(numStates);
         transform(parents.begin(), parents.end(), back_inserter(dimensions), [](const auto& parent) { return parent->getNumStates(); });
@@ -93,10 +94,22 @@ namespace bayesnet {
         // 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) {
+        auto pos = find(features.begin(), features.end(), name);
+        if (pos == features.end()) {
+            throw logic_error("Feature " + name + " not found in dataset");
+        }
+        int name_index = pos - features.begin();
+        for (int n_sample = 0; n_sample < dataset.size(1); ++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]); });
+            coordinates.push_back(dataset.index({ name_index, n_sample }));
+            for (auto parent : parents) {
+                pos = find(features.begin(), features.end(), parent->getName());
+                if (pos == features.end()) {
+                    throw logic_error("Feature parent " + parent->getName() + " not found in dataset");
+                }
+                int parent_index = pos - features.begin();
+                coordinates.push_back(dataset.index({ parent_index, n_sample }));
+            }
             // Increment the count of the corresponding coordinate
             cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + 1);
         }

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);
+        explicit Node(const string&);
         void clear();
         void addParent(Node*);
         void addChild(Node*);
@@ -26,7 +26,7 @@ namespace bayesnet {
         vector<Node*>& getParents();
         vector<Node*>& getChildren();
         torch::Tensor& getCPT();
-        void computeCPT(map<string, vector<int>>&, const int);
+        void computeCPT(const torch::Tensor&, const vector<string>&, const int);
         int getNumStates() const;
         void setNumStates(int);
         unsigned minFill();

src/BayesNet/Proposal.cc

@@ -0,0 +1,109 @@
+#include "Proposal.h"
+#include "ArffFiles.h"
+
+namespace bayesnet {
+    Proposal::Proposal(torch::Tensor& dataset_, vector<string>& features_, string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_) {}
+    Proposal::~Proposal()
+    {
+        for (auto& [key, value] : discretizers) {
+            delete value;
+        }
+    }
+    map<string, vector<int>> Proposal::localDiscretizationProposal(const map<string, vector<int>>& oldStates, Network& model)
+    {
+        // order of local discretization is important. no good 0, 1, 2...
+        // although we rediscretize features after the local discretization of every feature
+        auto order = model.topological_sort();
+        auto& nodes = model.getNodes();
+        map<string, vector<int>> states = oldStates;
+        vector<int> indicesToReDiscretize;
+        bool upgrade = false; // Flag to check if we need to upgrade the model
+        for (auto feature : order) {
+            auto nodeParents = nodes[feature]->getParents();
+            if (nodeParents.size() < 2) continue; // Only has class as parent
+            upgrade = true;
+            int index = find(pFeatures.begin(), pFeatures.end(), feature) - pFeatures.begin();
+            indicesToReDiscretize.push_back(index); // We need to re-discretize this feature
+            vector<string> parents;
+            transform(nodeParents.begin(), nodeParents.end(), back_inserter(parents), [](const auto& p) { return p->getName(); });
+            // Remove class as parent as it will be added later
+            parents.erase(remove(parents.begin(), parents.end(), pClassName), parents.end());
+            // Get the indices of the parents
+            vector<int> indices;
+            indices.push_back(-1); // Add class index
+            transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(pFeatures.begin(), pFeatures.end(), p) - pFeatures.begin(); });
+            // Now we fit the discretizer of the feature, conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
+            vector<string> yJoinParents(Xf.size(1));
+            for (auto idx : indices) {
+                for (int i = 0; i < Xf.size(1); ++i) {
+                    yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
+                }
+            }
+            auto arff = ArffFiles();
+            auto yxv = arff.factorize(yJoinParents);
+            auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
+            auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
+            discretizers[feature]->fit(xvf, yxv);
+            //
+            //
+            //
+            // auto tmp = discretizers[feature]->transform(xvf);
+            // Xv[index] = tmp;
+            // auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
+            // iota(xStates.begin(), xStates.end(), 0);
+            // //Update new states of the feature/node
+            // states[feature] = xStates;
+        }
+        if (upgrade) {
+            // Discretize again X (only the affected indices) with the new fitted discretizers
+            for (auto index : indicesToReDiscretize) {
+                auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
+                auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+                pDataset.index_put_({ index, "..." }, torch::tensor(discretizers[pFeatures[index]]->transform(Xt)));
+                auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
+                iota(xStates.begin(), xStates.end(), 0);
+                //Update new states of the feature/node
+                states[pFeatures[index]] = xStates;
+            }
+            model.fit(pDataset, pFeatures, pClassName, states);
+        }
+        return states;
+    }
+    map<string, vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
+    {
+        // Discretize the continuous input data and build pDataset (Classifier::dataset)
+        int m = Xf.size(1);
+        int n = Xf.size(0);
+        map<string, vector<int>> states;
+        pDataset = torch::zeros({ n + 1, m }, kInt32);
+        auto yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        // discretize input data by feature(row)
+        for (auto i = 0; i < pFeatures.size(); ++i) {
+            auto* discretizer = new mdlp::CPPFImdlp();
+            auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
+            auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+            discretizer->fit(Xt, yv);
+            pDataset.index_put_({ i, "..." }, torch::tensor(discretizer->transform(Xt)));
+            auto xStates = vector<int>(discretizer->getCutPoints().size() + 1);
+            iota(xStates.begin(), xStates.end(), 0);
+            states[pFeatures[i]] = xStates;
+            discretizers[pFeatures[i]] = discretizer;
+        }
+        int n_classes = torch::max(y).item<int>() + 1;
+        auto yStates = vector<int>(n_classes);
+        iota(yStates.begin(), yStates.end(), 0);
+        states[pClassName] = yStates;
+        pDataset.index_put_({ n, "..." }, y);
+        return states;
+    }
+    torch::Tensor Proposal::prepareX(torch::Tensor& X)
+    {
+        auto Xtd = torch::zeros_like(X, torch::kInt32);
+        for (int i = 0; i < X.size(0); ++i) {
+            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
+            auto Xd = discretizers[pFeatures[i]]->transform(Xt);
+            Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
+        }
+        return Xtd;
+    }
+}

src/BayesNet/Proposal.h

@@ -0,0 +1,29 @@
+#ifndef PROPOSAL_H
+#define PROPOSAL_H
+#include <string>
+#include <map>
+#include <torch/torch.h>
+#include "Network.h"
+#include "CPPFImdlp.h"
+#include "Classifier.h"
+
+namespace bayesnet {
+    class Proposal {
+    public:
+        Proposal(torch::Tensor& pDataset, vector<string>& features_, string& className_);
+        virtual ~Proposal();
+    protected:
+        torch::Tensor prepareX(torch::Tensor& X);
+        map<string, vector<int>> localDiscretizationProposal(const map<string, vector<int>>& states, Network& model);
+        map<string, vector<int>> fit_local_discretization(const torch::Tensor& y);
+        torch::Tensor Xf; // X continuous nxm tensor
+        torch::Tensor y; // y discrete nx1 tensor
+        map<string, mdlp::CPPFImdlp*> discretizers;
+    private:
+        torch::Tensor& pDataset; // (n+1)xm tensor
+        vector<string>& pFeatures;
+        string& pClassName;
+    };
+}
+
+#endif  

src/BayesNet/SPODE.cc

@@ -4,7 +4,7 @@ namespace bayesnet {
 
     SPODE::SPODE(int root) : Classifier(Network()), root(root) {}
 
-    void SPODE::train()
+    void SPODE::buildModel()
     {
         // 0. Add all nodes to the model
         addNodes();
@@ -17,7 +17,7 @@ namespace bayesnet {
             }
         }
     }
-    vector<string> SPODE::graph(const string& name)
+    vector<string> SPODE::graph(const string& name) const
     {
         return model.graph(name);
     }

src/BayesNet/SPODE.h

@@ -7,11 +7,11 @@ namespace bayesnet {
     private:
         int root;
     protected:
-        void train() override;
+        void buildModel() override;
     public:
         explicit SPODE(int root);
         virtual ~SPODE() {};
-        vector<string> graph(const string& name = "SPODE") override;
+        vector<string> graph(const string& name = "SPODE") const override;
     };
 }
 #endif

src/BayesNet/SPODELd.cc

@@ -0,0 +1,47 @@
+#include "SPODELd.h"
+
+namespace bayesnet {
+    using namespace std;
+    SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
+    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
+        SPODE::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
+        return *this;
+    }
+    SPODELd& SPODELd::fit(torch::Tensor& dataset, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
+        cout << "Xf " << Xf.sizes() << " dtype: " << Xf.dtype() << endl;
+        y = dataset.index({ -1, "..." }).clone();
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
+        SPODE::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
+        return *this;
+    }
+
+    Tensor SPODELd::predict(Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return SPODE::predict(Xt);
+    }
+    vector<string> SPODELd::graph(const string& name) const
+    {
+        return SPODE::graph(name);
+    }
+}

src/BayesNet/SPODELd.h

@@ -0,0 +1,19 @@
+#ifndef SPODELD_H
+#define SPODELD_H
+#include "SPODE.h"
+#include "Proposal.h"
+
+namespace bayesnet {
+    using namespace std;
+    class SPODELd : public SPODE, public Proposal {
+    public:
+        explicit SPODELd(int root);
+        virtual ~SPODELd() = default;
+        SPODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        SPODELd& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        vector<string> graph(const string& name = "SPODE") const override;
+        Tensor predict(Tensor& X) override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !SPODELD_H

src/BayesNet/TAN.cc

@@ -5,16 +5,16 @@ namespace bayesnet {
 
     TAN::TAN() : Classifier(Network()) {}
 
-    void TAN::train()
+    void TAN::buildModel()
     {
         // 0. Add all nodes to the model
         addNodes();
         // 1. Compute mutual information between each feature and the class and set the root node
         // as the highest mutual information with the class
         auto mi = vector <pair<int, float >>();
-        Tensor class_dataset = samples.index({ -1, "..." });
+        Tensor class_dataset = dataset.index({ -1, "..." });
         for (int i = 0; i < static_cast<int>(features.size()); ++i) {
-            Tensor feature_dataset = samples.index({ i, "..." });
+            Tensor feature_dataset = dataset.index({ i, "..." });
             auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
             mi.push_back({ i, mi_value });
         }
@@ -34,7 +34,7 @@ namespace bayesnet {
             model.addEdge(className, feature);
         }
     }
-    vector<string> TAN::graph(const string& title)
+    vector<string> TAN::graph(const string& title) const
     {
         return model.graph(title);
     }

src/BayesNet/TAN.h

@@ -7,11 +7,11 @@ namespace bayesnet {
     class TAN : public Classifier {
     private:
     protected:
-        void train() override;
+        void buildModel() override;
     public:
         TAN();
         virtual ~TAN() {};
-        vector<string> graph(const string& name = "TAN") override;
+        vector<string> graph(const string& name = "TAN") const override;
     };
 }
 #endif

src/BayesNet/TANLd.cc

@@ -0,0 +1,31 @@
+#include "TANLd.h"
+
+namespace bayesnet {
+    using namespace std;
+    TANLd::TANLd() : TAN(), Proposal(dataset, features, className) {}
+    TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
+        TAN::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
+        return *this;
+
+    }
+    Tensor TANLd::predict(Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return TAN::predict(Xt);
+    }
+    vector<string> TANLd::graph(const string& name) const
+    {
+        return TAN::graph(name);
+    }
+}

src/BayesNet/TANLd.h

@@ -0,0 +1,19 @@
+#ifndef TANLD_H
+#define TANLD_H
+#include "TAN.h"
+#include "Proposal.h"
+
+namespace bayesnet {
+    using namespace std;
+    class TANLd : public TAN, public Proposal {
+    private:
+    public:
+        TANLd();
+        virtual ~TANLd() = default;
+        TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        vector<string> graph(const string& name = "TAN") const override;
+        Tensor predict(Tensor& X) override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !TANLD_H

src/BayesNet/TANNew.cc

@@ -1,55 +0,0 @@
-#include "TANNew.h"
-
-namespace bayesnet {
-    using namespace std;
-    TANNew::TANNew() : TAN() {}
-    TANNew::~TANNew() {}
-    TANNew& TANNew::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
-    {
-        Xf = X_;
-        y = y_;
-        features = features_;
-        className = className_;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        // discretize input data by feature(row)
-        for (int i = 0; i < features.size(); ++i) {
-            auto* discretizer = new mdlp::CPPFImdlp();
-            auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
-            auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
-            discretizer->fit(Xt, yv);
-            Xv.push_back(discretizer->transform(Xt));
-            auto xStates = vector<int>(discretizer->getCutPoints().size() + 1);
-            iota(xStates.begin(), xStates.end(), 0);
-            states[features[i]] = xStates;
-            discretizers[features[i]] = discretizer;
-        }
-        int n_classes = torch::max(y).item<int>() + 1;
-        auto yStates = vector<int>(n_classes);
-        iota(yStates.begin(), yStates.end(), 0);
-        states[className] = yStates;
-        // Now we have standard TAN and now we implement the proposal
-        // 1st we need to fit the model to build the TAN structure
-        cout << "TANNew: Fitting model" << endl;
-        TAN::fit(Xv, yv, features, className, states);
-        cout << "TANNew: Model fitted" << endl;
-        localDiscretizationProposal(discretizers, Xf);
-        return *this;
-    }
-
-    Tensor TANNew::predict(Tensor& X)
-    {
-        auto Xtd = torch::zeros_like(X, torch::kInt32);
-        for (int i = 0; i < X.size(0); ++i) {
-            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
-            auto Xd = discretizers[features[i]]->transform(Xt);
-            Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
-        }
-        cout << "TANNew Xtd: " << Xtd.sizes() << endl;
-        return TAN::predict(Xtd);
-    }
-    vector<string> TANNew::graph(const string& name)
-    {
-        return TAN::graph(name);
-    }
-}

src/BayesNet/TANNew.h

@@ -1,21 +0,0 @@
-#ifndef TANNEW_H
-#define TANNEW_H
-#include "TAN.h"
-#include "CPPFImdlp.h"
-
-namespace bayesnet {
-    using namespace std;
-    class TANNew : public TAN {
-    private:
-        map<string, mdlp::CPPFImdlp*> discretizers;
-        torch::Tensor Xf; // X continuous nxm tensor
-    public:
-        TANNew();
-        virtual ~TANNew();
-        TANNew& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        vector<string> graph(const string& name = "TAN") override;
-        Tensor predict(Tensor& X) override;
-        static inline string version() { return "0.0.1"; };
-    };
-}
-#endif // !TANNEW_H

src/BayesNet/bayesnetUtils.cc

@@ -3,6 +3,7 @@
 namespace bayesnet {
     using namespace std;
     using namespace torch;
+    // Return the indices in descending order
     vector<int> argsort(vector<float>& nums)
     {
         int n = nums.size();

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 Models.cc Report.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/Experiment.cc

@@ -1,6 +1,7 @@
 #include "Experiment.h"
 #include "Datasets.h"
 #include "Models.h"
+#include "Report.h"
 
 namespace platform {
     using json = nlohmann::json;
@@ -86,6 +87,13 @@ namespace platform {
         file.close();
     }
 
+    void Experiment::report()
+    {
+        json data = build_json();
+        Report report(data);
+        report.show();
+    }
+
     void Experiment::show()
     {
         json data = build_json();

src/Platform/Experiment.h

@@ -108,6 +108,7 @@ namespace platform {
         void cross_validation(const string& path, const string& fileName);
         void go(vector<string> filesToProcess, const string& path);
         void show();
+        void report();
     };
 }
 #endif

src/Platform/Models.h

@@ -6,7 +6,10 @@
 #include "TAN.h"
 #include "KDB.h"
 #include "SPODE.h"
-#include "TANNew.h"
+#include "TANLd.h"
+#include "KDBLd.h"
+#include "SPODELd.h"
+#include "AODELd.h"
 namespace platform {
     class Models {
     private:

src/Platform/Report.cc

@@ -0,0 +1,67 @@
+#include "Report.h"
+
+namespace platform {
+    string headerLine(const string& text)
+    {
+        int n = MAXL - text.length() - 3;
+        n = n < 0 ? 0 : n;
+        return "* " + text + string(n, ' ') + "*\n";
+    }
+    string Report::fromVector(const string& key)
+    {
+        string result = "";
+
+        for (auto& item : data[key]) {
+            result += to_string(item) + ", ";
+        }
+        return "[" + result.substr(0, result.size() - 2) + "]";
+    }
+    string fVector(const json& data)
+    {
+        string result = "";
+        for (const auto& item : data) {
+            result += to_string(item) + ", ";
+        }
+        return "[" + result.substr(0, result.size() - 2) + "]";
+    }
+    void Report::show()
+    {
+        header();
+        body();
+    }
+    void Report::header()
+    {
+        cout << string(MAXL, '*') << endl;
+        cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
+        cout << headerLine(data["title"].get<string>());
+        cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
+        cout << headerLine("Execution took  " + to_string(data["duration"].get<float>()) + " seconds,   " + to_string(data["duration"].get<float>() / 3600) + " hours, on " + data["platform"].get<string>());
+        cout << headerLine("Score is " + data["score_name"].get<string>());
+        cout << string(MAXL, '*') << endl;
+        cout << endl;
+    }
+    void Report::body()
+    {
+        cout << "Dataset                        Sampl. Feat. Cls Nodes   Edges   States  Score           Time              Hyperparameters" << endl;
+        cout << "============================== ====== ===== === ======= ======= ======= =============== ================= ===============" << endl;
+        for (const auto& r : data["results"]) {
+            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>() << " ";
+            cout << setw(7) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
+            cout << setw(7) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
+            cout << setw(7) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
+            cout << setw(8) << right << setprecision(6) << fixed << r["score_test"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_test_std"].get<double>() << " ";
+            cout << setw(10) << right << setprecision(6) << fixed << r["test_time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["test_time_std"].get<double>() << " ";
+            cout << " " << r["hyperparameters"].get<string>();
+            cout << endl;
+            cout << string(MAXL, '*') << endl;
+            cout << headerLine("Train scores: " + fVector(r["scores_train"]));
+            cout << headerLine("Test  scores: " + fVector(r["scores_test"]));
+            cout << headerLine("Train  times: " + fVector(r["times_train"]));
+            cout << headerLine("Test   times: " + fVector(r["times_test"]));
+            cout << string(MAXL, '*') << endl;
+        }
+    }
+}

src/Platform/Report.h

@@ -0,0 +1,23 @@
+#ifndef REPORT_H
+#define REPORT_H
+#include <string>
+#include <iostream>
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+const int MAXL = 121;
+namespace platform {
+    using namespace std;
+    class Report {
+    public:
+        explicit Report(json data_) { data = data_; };
+        virtual ~Report() = default;
+        void show();
+    private:
+        void header();
+        void body();
+        string fromVector(const string& key);
+        json data;
+    };
+};
+#endif

src/Platform/main.cc

@@ -102,9 +102,10 @@ int main(int argc, char** argv)
     /*
     * Begin Processing
     */
+    auto env = platform::DotEnv();
     auto experiment = platform::Experiment();
     experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("1.0.0");
-    experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform("BayesNet");
+    experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
     experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
     for (auto seed : seeds) {
         experiment.addRandomSeed(seed);
@@ -116,7 +117,7 @@ int main(int argc, char** argv)
     if (saveResults)
         experiment.save(PATH_RESULTS);
     else
-        experiment.show();
+        experiment.report();
     cout << "Done!" << endl;
     return 0;
 }

src/Platform/modelRegister.h

@@ -2,12 +2,18 @@
 #define MODEL_REGISTER_H
 static platform::Registrar registrarT("TAN",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TAN();});
-static platform::Registrar registrarTN("TANNew",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TANNew();});
+static platform::Registrar registrarTLD("TANLd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TANLd();});
 static platform::Registrar registrarS("SPODE",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODE(2);});
+static platform::Registrar registrarSLD("SPODELd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODELd(2);});
 static platform::Registrar registrarK("KDB",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDB(2);});
+static platform::Registrar registrarKLD("KDBLd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDBLd(2);});
 static platform::Registrar registrarA("AODE",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
+static platform::Registrar registrarALD("AODELd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODELd();});
 #endif

tests/BayesNetwork.cc

@@ -9,29 +9,21 @@ TEST_CASE("Test Bayesian Network")
 {
     auto [Xd, y, features, className, states] = loadFile("iris");
 
-    SECTION("Test Update Nodes")
-    {
-        auto net = bayesnet::Network();
-        net.addNode("A", 3);
-        REQUIRE(net.getStates() == 3);
-        net.addNode("A", 5);
-        REQUIRE(net.getStates() == 5);
-    }
     SECTION("Test get features")
     {
         auto net = bayesnet::Network();
-        net.addNode("A", 3);
-        net.addNode("B", 5);
+        net.addNode("A");
+        net.addNode("B");
         REQUIRE(net.getFeatures() == vector<string>{"A", "B"});
-        net.addNode("C", 2);
+        net.addNode("C");
         REQUIRE(net.getFeatures() == vector<string>{"A", "B", "C"});
     }
     SECTION("Test get edges")
     {
         auto net = bayesnet::Network();
-        net.addNode("A", 3);
-        net.addNode("B", 5);
-        net.addNode("C", 2);
+        net.addNode("A");
+        net.addNode("B");
+        net.addNode("C");
         net.addEdge("A", "B");
         net.addEdge("B", "C");
         REQUIRE(net.getEdges() == vector<pair<string, string>>{ {"A", "B"}, { "B", "C" } });