Fix report format

Reviewed-on: https://gitea.rmontanana.es:11000/rmontanana/BayesNet/pulls/4

.clang-tidy

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

.vscode/launch.json

@@ -25,15 +25,35 @@
             "program": "${workspaceFolder}/build/src/Platform/main",
             "args": [
                 "-m",
-                "AODELd",
+                "BoostAODE",
                 "-p",
                 "/Users/rmontanana/Code/discretizbench/datasets",
+                "--discretize",
                 "--stratified",
                 "-d",
                 "iris"
             ],
             "cwd": "/Users/rmontanana/Code/discretizbench",
         },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "manage",
+            "program": "${workspaceFolder}/build/src/Platform/manage",
+            "args": [
+                "-n",
+                "20"
+            ],
+            "cwd": "/Users/rmontanana/Code/discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "list",
+            "program": "${workspaceFolder}/build/src/Platform/list",
+            "args": [],
+            "cwd": "/Users/rmontanana/Code/discretizbench",
+        },
         {
             "name": "Build & debug active file",
             "type": "cppdbg",

.vscode/tasks.json

@@ -32,6 +32,29 @@
             ],
             "group": "build",
             "detail": "Task generated by Debugger."
+        },
+        {
+            "type": "cppbuild",
+            "label": "C/C++: g++ build active file",
+            "command": "/usr/bin/g++",
+            "args": [
+                "-fdiagnostics-color=always",
+                "-g",
+                "${file}",
+                "-o",
+                "${fileDirname}/${fileBasenameNoExtension}"
+            ],
+            "options": {
+                "cwd": "${fileDirname}"
+            },
+            "problemMatcher": [
+                "$gcc"
+            ],
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            },
+            "detail": "Task generated by Debugger."
         }
     ]
 }

Makefile

@@ -15,7 +15,7 @@ dependency: ## Create a dependency graph diagram of the project (build/dependenc
 	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
+	cmake --build build -t main -t BayesNetSample -t manage -t list -j 32
 
 clean: ## Clean the debug info
 	@echo ">>> Cleaning Debug BayesNet ...";
@@ -35,7 +35,7 @@ release: ## Build a Release version of the project
 	@if [ -d ./build ]; then rm -rf ./build; fi
 	@mkdir build; 
 	cmake -S . -B build -D CMAKE_BUILD_TYPE=Release; \
-	cmake --build build -t main -t BayesNetSample -j 32;
+	cmake --build build -t main -t BayesNetSample -t manage -t list -j 32;
 	@echo ">>> Done";	
 
 test: ## Run tests

lib/Files/CMakeLists.txt

@@ -1,2 +1 @@
 add_library(ArffFiles ArffFiles.cc)
-#target_link_libraries(BayesNet "${TORCH_LIBRARIES}")

sample/sample.cc

@@ -141,43 +141,58 @@ int main(int argc, char** argv)
     /*
     * Begin Processing
     */
-    auto handler = ArffFiles();
-    handler.load(complete_file_name, class_last);
-    // Get Dataset X, y
-    vector<mdlp::samples_t>& X = handler.getX();
-    mdlp::labels_t& y = handler.getY();
-    // Get className & Features
-    auto className = handler.getClassName();
-    vector<string> features;
-    auto attributes = handler.getAttributes();
-    transform(attributes.begin(), attributes.end(), back_inserter(features),
-        [](const pair<string, string>& item) { return item.first; });
-    // Discretize Dataset
-    auto [Xd, maxes] = discretize(X, y, features);
-    maxes[className] = *max_element(y.begin(), y.end()) + 1;
-    map<string, vector<int>> states;
-    for (auto feature : features) {
-        states[feature] = vector<int>(maxes[feature]);
-    }
-    states[className] = vector<int>(maxes[className]);
-    auto clf = platform::Models::instance()->create(model_name);
-    clf->fit(Xd, y, features, className, states);
-    if (dump_cpt) {
-        cout << "--- CPT Tables ---" << endl;
-        clf->dump_cpt();
-    }
-    auto lines = clf->show();
-    for (auto line : lines) {
-        cout << line << endl;
-    }
-    cout << "--- Topological Order ---" << endl;
-    auto order = clf->topological_order();
-    for (auto name : order) {
-        cout << name << ", ";
-    }
-    cout << "end." << endl;
-    auto score = clf->score(Xd, y);
-    cout << "Score: " << score << endl;
+    auto ypred = torch::tensor({ 1,2,3,2,2,3,4,5,2,1 });
+    auto y = torch::tensor({ 0,0,0,0,2,3,4,0,0,0 });
+    auto weights = torch::ones({ 10 }, kDouble);
+    auto mask = ypred == y;
+    cout << "ypred:" << ypred << endl;
+    cout << "y:" << y << endl;
+    cout << "weights:" << weights << endl;
+    cout << "mask:" << mask << endl;
+    double value_to_add = 0.5;
+    weights += mask.to(torch::kDouble) * value_to_add;
+    cout << "New weights:" << weights << endl;
+    auto masked_weights = weights * mask.to(weights.dtype());
+    double sum_of_weights = masked_weights.sum().item<double>();
+    cout << "Sum of weights: " << sum_of_weights << endl;
+    //weights.index_put_({ mask }, weights + 10);
+    // auto handler = ArffFiles();
+    // handler.load(complete_file_name, class_last);
+    // // Get Dataset X, y
+    // vector<mdlp::samples_t>& X = handler.getX();
+    // mdlp::labels_t& y = handler.getY();
+    // // Get className & Features
+    // auto className = handler.getClassName();
+    // vector<string> features;
+    // auto attributes = handler.getAttributes();
+    // transform(attributes.begin(), attributes.end(), back_inserter(features),
+    //     [](const pair<string, string>& item) { return item.first; });
+    // // Discretize Dataset
+    // auto [Xd, maxes] = discretize(X, y, features);
+    // maxes[className] = *max_element(y.begin(), y.end()) + 1;
+    // map<string, vector<int>> states;
+    // for (auto feature : features) {
+    //     states[feature] = vector<int>(maxes[feature]);
+    // }
+    // states[className] = vector<int>(maxes[className]);
+    // auto clf = platform::Models::instance()->create(model_name);
+    // clf->fit(Xd, y, features, className, states);
+    // if (dump_cpt) {
+    //     cout << "--- CPT Tables ---" << endl;
+    //     clf->dump_cpt();
+    // }
+    // auto lines = clf->show();
+    // for (auto line : lines) {
+    //     cout << line << endl;
+    // }
+    // cout << "--- Topological Order ---" << endl;
+    // auto order = clf->topological_order();
+    // for (auto name : order) {
+    //     cout << name << ", ";
+    // }
+    // cout << "end." << endl;
+    // auto score = clf->score(Xd, y);
+    // cout << "Score: " << score << endl;
     // auto graph = clf->graph();
     // auto dot_file = model_name + "_" + file_name;
     // ofstream file(dot_file + ".dot");

src/BayesNet/AODE.cc

@@ -2,14 +2,16 @@
 
 namespace bayesnet {
     AODE::AODE() : Ensemble() {}
-    void AODE::train()
+    void AODE::buildModel(const torch::Tensor& weights)
     {
         models.clear();
         for (int i = 0; i < features.size(); ++i) {
             models.push_back(std::make_unique<SPODE>(i));
         }
+        n_models = models.size();
+        significanceModels = vector<double>(n_models, 1.0);
     }
-    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(const torch::Tensor& weights) 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

@@ -1,33 +1,39 @@
 #include "AODELd.h"
+#include "Models.h"
 
 namespace bayesnet {
     using namespace std;
-    AODELd::AODELd() : Ensemble(), Proposal(Ensemble::Xv, Ensemble::yv, features, className) {}
+    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_;
-        states = states_;
-        train();
-        for (const auto& model : models) {
-            model->fit(X_, y_, features_, className_, states_);
-        }
-        n_models = models.size();
-        fitted = true;
+        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::train()
+    void AODELd::buildModel(const torch::Tensor& weights)
     {
         models.clear();
         for (int i = 0; i < features.size(); ++i) {
             models.push_back(std::make_unique<SPODELd>(i));
         }
+        n_models = models.size();
     }
-    Tensor AODELd::predict(Tensor& X)
+    void AODELd::trainModel(const torch::Tensor& weights)
     {
-        return Ensemble::predict(X);
+        for (const auto& model : models) {
+            model->fit(Xf, y, features, className, states);
+        }
     }
-    vector<string> AODELd::graph(const string& name)
+    vector<string> AODELd::graph(const string& name) const
     {
         return Ensemble::graph(name);
     }

src/BayesNet/AODELd.h

@@ -7,13 +7,14 @@
 namespace bayesnet {
     using namespace std;
     class AODELd : public Ensemble, public Proposal {
+    protected:
+        void trainModel(const torch::Tensor& weights) override;
+        void buildModel(const torch::Tensor& weights) 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;
-        AODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        vector<string> graph(const string& name = "AODE") override;
-        Tensor predict(Tensor& X) override;
-        void train() override;
+        vector<string> graph(const string& name = "AODE") const override;
         static inline string version() { return "0.0.1"; };
     };
 }

src/BayesNet/BaseClassifier.h

@@ -5,24 +5,28 @@
 namespace bayesnet {
     using namespace std;
     class BaseClassifier {
+    protected:
+        virtual void trainModel(const torch::Tensor& weights) = 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& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states, const torch::Tensor& weights) = 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;
+        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)
@@ -21,6 +21,31 @@ namespace bayesnet {
         }
         samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
     }
+    vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, unsigned k)
+    {
+        auto n = samples.size(0) - 1;
+        if (k == 0) {
+            k = n;
+        }
+        // compute scores
+        scoresKBest.reserve(n);
+        auto label = samples.index({ -1, "..." });
+        for (int i = 0; i < n; ++i) {
+            scoresKBest.push_back(mutualInformation(label, samples.index({ i, "..." }), weights));
+            featuresKBest.push_back(i);
+        }
+        // sort & reduce scores and features
+        sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+            { return scoresKBest[i] > scoresKBest[j]; });
+        sort(scoresKBest.begin(), scoresKBest.end(), std::greater<double>());
+        featuresKBest.resize(k);
+        scoresKBest.resize(k);
+        return featuresKBest;
+    }
+    vector<double> Metrics::getScoresKBest() const
+    {
+        return scoresKBest;
+    }
     vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
     {
         vector<pair<string, string>> result;
@@ -32,17 +57,18 @@ namespace bayesnet {
         }
         return result;
     }
-    torch::Tensor Metrics::conditionalEdge()
+    torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
     {
         auto result = vector<double>();
         auto source = vector<string>(features);
         source.push_back(className);
         auto combinations = doCombinations(source);
+        double totalWeight = weights.sum().item<double>();
         // Compute class prior
-        auto margin = torch::zeros({ classNumStates });
+        auto margin = torch::zeros({ classNumStates }, torch::kFloat);
         for (int value = 0; value < classNumStates; ++value) {
             auto mask = samples.index({ -1,  "..." }) == value;
-            margin[value] = mask.sum().item<float>() / samples.size(1);
+            margin[value] = mask.sum().item<double>() / samples.size(1);
         }
         for (auto [first, second] : combinations) {
             int index_first = find(features.begin(), features.end(), first) - features.begin();
@@ -52,8 +78,9 @@ namespace bayesnet {
                 auto mask = samples.index({ -1, "..." }) == value;
                 auto first_dataset = samples.index({ index_first, mask });
                 auto second_dataset = samples.index({ index_second, mask });
-                auto mi = mutualInformation(first_dataset, second_dataset);
-                auto pb = margin[value].item<float>();
+                auto weights_dataset = weights.index({ mask });
+                auto mi = mutualInformation(first_dataset, second_dataset, weights_dataset);
+                auto pb = margin[value].item<double>();
                 accumulated += pb * mi;
             }
             result.push_back(accumulated);
@@ -70,31 +97,32 @@ namespace bayesnet {
         return matrix;
     }
     // To use in Python
-    vector<float> Metrics::conditionalEdgeWeights()
+    vector<float> Metrics::conditionalEdgeWeights(vector<float>& weights_)
     {
-        auto matrix = conditionalEdge();
+        const torch::Tensor weights = torch::tensor(weights_);
+        auto matrix = conditionalEdge(weights);
         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, const torch::Tensor& weights)
     {
-        torch::Tensor counts = feature.bincount();
-        int totalWeight = counts.sum().item<int>();
+        torch::Tensor counts = feature.bincount(weights);
+        double totalWeight = counts.sum().item<double>();
         torch::Tensor probs = counts.to(torch::kFloat) / totalWeight;
         torch::Tensor logProbs = torch::log(probs);
         torch::Tensor entropy = -probs * logProbs;
         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, const torch::Tensor& weights)
     {
         int numSamples = firstFeature.sizes()[0];
-        torch::Tensor featureCounts = secondFeature.bincount();
+        torch::Tensor featureCounts = secondFeature.bincount(weights);
         unordered_map<int, unordered_map<int, double>> jointCounts;
         double totalWeight = 0;
         for (auto i = 0; i < numSamples; i++) {
-            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += 1;
-            totalWeight += 1;
+            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
+            totalWeight += weights[i].item<float>();
         }
         if (totalWeight == 0)
             return 0;
@@ -115,16 +143,16 @@ 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, const torch::Tensor& weights)
     {
-        return entropy(firstFeature) - conditionalEntropy(firstFeature, secondFeature);
+        return entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights);
     }
     /*
     Compute the maximum spanning tree considering the weights as distances
     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

@@ -12,17 +12,21 @@ namespace bayesnet {
         vector<string> features;
         string className;
         int classNumStates = 0;
+        vector<double> scoresKBest;
+        vector<int> featuresKBest; // sorted indices of the features
+        double entropy(const Tensor& feature, const Tensor& weights);
+        double conditionalEntropy(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
+        vector<pair<string, string>> doCombinations(const vector<string>&);
     public:
         Metrics() = default;
-        Metrics(Tensor&, vector<string>&, string&, 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&);
-        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);
+        Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates);
+        Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates);
+        vector<int> SelectKBestWeighted(const torch::Tensor& weights, unsigned k = 0);
+        vector<double> getScoresKBest() const;
+        double mutualInformation(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
+        vector<float> conditionalEdgeWeights(vector<float>& weights); // To use in Python
+        Tensor conditionalEdge(const torch::Tensor& weights);
+        vector<pair<int, int>> maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root);
     };
 }
 #endif

src/BayesNet/BoostAODE.cc

@@ -0,0 +1,82 @@
+#include "BoostAODE.h"
+#include "BayesMetrics.h"
+
+namespace bayesnet {
+    BoostAODE::BoostAODE() : Ensemble() {}
+    void BoostAODE::buildModel(const torch::Tensor& weights)
+    {
+        // Models shall be built in trainModel
+    }
+    void BoostAODE::trainModel(const torch::Tensor& weights)
+    {
+        models.clear();
+        n_models = 0;
+        int max_models = .1 * n > 10 ? .1 * n : n;
+        Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
+        auto X_ = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
+        auto y_ = dataset.index({ -1, "..." });
+        bool exitCondition = false;
+        bool repeatSparent = false;
+        vector<int> featuresUsed;
+        // Step 0: Set the finish condition
+        // if not repeatSparent a finish condition is run out of features
+        // n_models == max_models
+        int numClasses = states[className].size();
+        while (!exitCondition) {
+            // Step 1: Build ranking with mutual information
+            auto featureSelection = metrics.SelectKBestWeighted(weights_, n); // Get all the features sorted
+            auto feature = featureSelection[0];
+            unique_ptr<Classifier> model;
+            if (!repeatSparent) {
+                if (n_models == 0) {
+                    models.resize(n); // Resize for n==nfeatures SPODEs
+                    significanceModels.resize(n);
+                }
+                bool found = false;
+                for (int i = 0; i < featureSelection.size(); ++i) {
+                    if (find(featuresUsed.begin(), featuresUsed.end(), i) != featuresUsed.end()) {
+                        continue;
+                    }
+                    found = true;
+                    feature = i;
+                    featuresUsed.push_back(feature);
+                    n_models++;
+                    break;
+                }
+                if (!found) {
+                    exitCondition = true;
+                    continue;
+                }
+            }
+            model = std::make_unique<SPODE>(feature);
+            model->fit(dataset, features, className, states, weights_);
+            auto ypred = model->predict(X_);
+            // Step 3.1: Compute the classifier amout of say
+            auto mask_wrong = ypred != y_;
+            auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
+            double wrongWeights = masked_weights.sum().item<double>();
+            double significance = wrongWeights == 0 ? 1 : 0.5 * log((1 - wrongWeights) / wrongWeights);
+            // Step 3.2: Update weights for next classifier
+            // Step 3.2.1: Update weights of wrong samples
+            weights_ += mask_wrong.to(weights_.dtype()) * exp(significance) * weights_;
+            // Step 3.3: Normalise the weights
+            double totalWeights = torch::sum(weights_).item<double>();
+            weights_ = weights_ / totalWeights;
+            // Step 3.4: Store classifier and its accuracy to weigh its future vote
+            if (!repeatSparent) {
+                models[feature] = std::move(model);
+                significanceModels[feature] = significance;
+            } else {
+                models.push_back(std::move(model));
+                significanceModels.push_back(significance);
+                n_models++;
+            }
+            exitCondition = n_models == max_models;
+        }
+        weights.copy_(weights_);
+    }
+    vector<string> BoostAODE::graph(const string& title) const
+    {
+        return Ensemble::graph(title);
+    }
+}

src/BayesNet/BoostAODE.h

@@ -0,0 +1,16 @@
+#ifndef BOOSTAODE_H
+#define BOOSTAODE_H
+#include "Ensemble.h"
+#include "SPODE.h"
+namespace bayesnet {
+    class BoostAODE : public Ensemble {
+    protected:
+        void buildModel(const torch::Tensor& weights) override;
+        void trainModel(const torch::Tensor& weights) override;
+    public:
+        BoostAODE();
+        virtual ~BoostAODE() {};
+        vector<string> graph(const string& title = "BoostAODE") const override;
+    };
+}
+#endif

src/BayesNet/CMakeLists.txt

@@ -1,5 +1,8 @@
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
+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)
-target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")
+    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc BoostAODE.cc 
+    Mst.cc Proposal.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
+target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")

src/BayesNet/Classifier.cc

@@ -5,63 +5,74 @@ namespace bayesnet {
     using namespace torch;
 
     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)
+    Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states, const torch::Tensor& weights)
     {
-        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(weights);
+        trainModel(weights);
         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(const torch::Tensor& weights)
+    {
+        model.fit(dataset, weights, 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));
-        return build(features, className, states);
-    }
-    void Classifier::generateTensorXFromVector()
-    {
-        X = torch::zeros({ static_cast<int>(Xv.size()), static_cast<int>(Xv[0].size()) }, kInt32);
-        for (int i = 0; i < Xv.size(); ++i) {
-            X.index_put_({ i, "..." }, torch::tensor(Xv[i], kInt32));
-        }
+        dataset = X;
+        buildDataset(y);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
     }
     // 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)
     {
-        Xv = X;
-        generateTensorXFromVector();
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, states);
+        dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
+        for (int i = 0; i < X.size(); ++i) {
+            dataset.index_put_({ i, "..." }, torch::tensor(X[i], kInt32));
+        }
+        auto ytmp = torch::tensor(y, kInt32);
+        buildDataset(ytmp);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    Classifier& Classifier::fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states)
+    {
+        this->dataset = dataset;
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    Classifier& Classifier::fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states, const torch::Tensor& weights)
+    {
+        this->dataset = dataset;
+        return build(features, className, states, weights);
     }
     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");
@@ -108,7 +119,7 @@ namespace bayesnet {
         }
         return model.score(X, y);
     }
-    vector<string> Classifier::show()
+    vector<string> Classifier::show() const
     {
         return model.show();
     }
@@ -120,16 +131,16 @@ namespace bayesnet {
         }
         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;
     }
@@ -137,9 +148,8 @@ namespace bayesnet {
     {
         return model.topological_sort();
     }
-    void Classifier::dump_cpt()
+    void Classifier::dump_cpt() const
     {
         model.dump_cpt();
     }
-
 }

src/BayesNet/Classifier.h

@@ -10,39 +10,38 @@ using namespace torch;
 namespace bayesnet {
     class Classifier : public BaseClassifier {
     private:
-        bool fitted;
-        Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states);
+        void buildDataset(torch::Tensor& y);
+        Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states, const torch::Tensor& weights);
     protected:
-        Network model;
+        bool fitted;
         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
+        Network model;
         Metrics metrics;
         vector<string> features;
         string className;
         map<string, vector<int>> states;
+        Tensor dataset; // (n+1)xm tensor
         void checkFitParameters();
-        void generateTensorXFromVector();
-        virtual void train() = 0;
+        virtual void buildModel(const torch::Tensor& weights) = 0;
+        void trainModel(const torch::Tensor& weights) 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;
+        Classifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states, const torch::Tensor& weights) 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

@@ -3,63 +3,24 @@
 namespace bayesnet {
     using namespace torch;
 
-    Ensemble::Ensemble() : 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(const torch::Tensor& weights)
     {
-        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;
-        auto n_classes = states[className].size();
-        metrics = Metrics(samples, features, className, n_classes);
-        // Build models
-        train();
-        // Train models
         n_models = models.size();
         for (auto i = 0; i < n_models; ++i) {
-            if (Xv.empty()) {
-                // fit with tensors
-                models[i]->fit(X, 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;
-    }
-    void Ensemble::generateTensorXFromVector()
-    {
-        X = torch::zeros({ static_cast<int>(Xv.size()), static_cast<int>(Xv[0].size()) }, kInt32);
-        for (int i = 0; i < Xv.size(); ++i) {
-            X.index_put_({ i, "..." }, torch::tensor(Xv[i], kInt32));
-        }
-    }
-    Ensemble& Ensemble::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));
-        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)
-    {
-        Xv = X;
-        generateTensorXFromVector();
-        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(y_pred.size(1), 0);
+            vector<double> votes(y_pred.size(1), 0);
             for (int j = 0; j < y_pred.size(1); ++j) {
-                votes[y_pred_[i][j]] += 1;
+                votes[y_pred_[i][j]] += significanceModels[j];
             }
             // argsort in descending order
             auto indices = argsort(votes);
@@ -132,9 +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) {
@@ -143,7 +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) {
@@ -152,7 +112,7 @@ namespace bayesnet {
         }
         return result;
     }
-    int Ensemble::getNumberOfNodes()
+    int Ensemble::getNumberOfNodes() const
     {
         int nodes = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -160,7 +120,7 @@ namespace bayesnet {
         }
         return nodes;
     }
-    int Ensemble::getNumberOfEdges()
+    int Ensemble::getNumberOfEdges() const
     {
         int edges = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -168,7 +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 +8,32 @@ using namespace std;
 using namespace torch;
 
 namespace bayesnet {
-    class Ensemble : public BaseClassifier {
+    class Ensemble : public Classifier {
     private:
         Ensemble& build(vector<string>& features, string className, map<string, vector<int>>& states);
     protected:
         unsigned n_models;
-        bool fitted;
         vector<unique_ptr<Classifier>> models;
-        Tensor X;
-        vector<vector<int>> Xv;
-        Tensor y;
-        vector<int> yv;
-        Tensor samples;
-        Metrics metrics;
-        vector<string> features;
-        string className;
-        map<string, vector<int>> states;
-        void virtual train() = 0;
+        vector<double> significanceModels;
+        void trainModel(const torch::Tensor& weights) override;
         vector<int> voting(Tensor& y_pred);
-        void generateTensorXFromVector();
     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(const torch::Tensor& weights)
     {
         /*
         1. For each feature Xi, compute mutual information, I(X;C),
@@ -28,13 +28,14 @@ namespace bayesnet {
         // 1. For each feature Xi, compute mutual information, I(X;C),
         // where C is the class.
         addNodes();
-        vector <float> mi;
+        const Tensor& y = dataset.index({ -1, "..." });
+        vector<double> mi;
         for (auto i = 0; i < features.size(); i++) {
-            Tensor firstFeature = X.index({ i, "..." });
-            mi.push_back(metrics.mutualInformation(firstFeature, y));
+            Tensor firstFeature = dataset.index({ i, "..." });
+            mi.push_back(metrics.mutualInformation(firstFeature, y, weights));
         }
         // 2. Compute class conditional mutual information I(Xi;XjIC), f or each
-        auto conditionalEdgeWeights = metrics.conditionalEdge();
+        auto conditionalEdgeWeights = metrics.conditionalEdge(weights);
         // 3. Let the used variable list, S, be empty.
         vector<int> S;
         // 4. Let the DAG network being constructed, BN, begin with a single
@@ -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

@@ -1,5 +1,6 @@
 #ifndef KDB_H
 #define KDB_H
+#include <torch/torch.h>
 #include "Classifier.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
@@ -11,11 +12,11 @@ namespace bayesnet {
         float theta;
         void add_m_edges(int idx, vector<int>& S, Tensor& weights);
     protected:
-        void train() override;
+        void buildModel(const torch::Tensor& weights) 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

@@ -2,7 +2,7 @@
 
 namespace bayesnet {
     using namespace std;
-    KDBLd::KDBLd(int k) : KDB(k), Proposal(KDB::Xv, KDB::yv, features, className) {}
+    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...
@@ -11,16 +11,11 @@ namespace bayesnet {
         Xf = X_;
         y = y_;
         // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
-        fit_local_discretization(states, y);
-        generateTensorXFromVector();
+        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(KDB::Xv, KDB::yv, features, className, states);
-        localDiscretizationProposal(states, model);
-        generateTensorXFromVector();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        model.fit(KDB::Xv, KDB::yv, features, className);
+        KDB::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
         return *this;
     }
     Tensor KDBLd::predict(Tensor& X)
@@ -28,7 +23,7 @@ namespace bayesnet {
         auto Xt = prepareX(X);
         return KDB::predict(Xt);
     }
-    vector<string> KDBLd::graph(const string& name)
+    vector<string> KDBLd::graph(const string& name) const
     {
         return KDB::graph(name);
     }

src/BayesNet/KDBLd.h

@@ -11,7 +11,7 @@ namespace bayesnet {
         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") override;
+        vector<string> graph(const string& name = "KDB") const override;
         Tensor predict(Tensor& X) override;
         static inline string version() { return "0.0.1"; };
     };

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

@@ -5,7 +5,6 @@
 namespace bayesnet {
     Network::Network() : features(vector<string>()), className(""), classNumStates(0), fitted(false) {}
     Network::Network(float maxT) : 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(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.
         getmaxThreads()), fitted(other.fitted)
     {
@@ -20,7 +19,6 @@ namespace bayesnet {
         classNumStates = 0;
         fitted = false;
         nodes.clear();
-        dataset.clear();
         samples = torch::Tensor();
     }
     float Network::getmaxThreads()
@@ -44,15 +42,15 @@ namespace bayesnet {
         }
         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) {
@@ -60,7 +58,7 @@ namespace bayesnet {
         }
         return result;
     }
-    string Network::getClassName()
+    string Network::getClassName() const
     {
         return className;
     }
@@ -105,8 +103,11 @@ 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, const torch::Tensor& weights)
     {
+        if (weights.size(0) != n_samples) {
+            throw invalid_argument("Weights (" + to_string(weights.size(0)) + ") must have the same number of elements as samples (" + to_string(n_samples) + ") in Network::fit");
+        }
         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) + ")");
         }
@@ -123,50 +124,56 @@ 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");
+            }
         }
     }
-    void Network::setStates()
+    void Network::setStates(const map<string, vector<int>>& states)
     {
         // Set states to every Node in the network
         for (int i = 0; i < features.size(); ++i) {
-            nodes[features[i]]->setNumStates(static_cast<int>(torch::max(samples.index({ i, "..." })).item<int>()) + 1);
+            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(torch::Tensor& X, torch::Tensor& y, const vector<string>& featureNames, const string& className)
+    void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
     {
-        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className);
+        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states, weights);
         this->className = className;
-        dataset.clear();
         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, weights);
+    }
+    void Network::fit(const torch::Tensor& samples, const torch::Tensor& weights, 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, weights);
+        this->className = className;
+        this->samples = samples;
+        completeFit(states, weights);
     }
     // 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<float>& weights_, 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);
+        const torch::Tensor weights = torch::tensor(weights_, torch::kFloat64);
+        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states, weights);
         this->className = className;
-        dataset.clear();
-        // 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, weights);
     }
-    void Network::completeFit()
+    void Network::completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights)
     {
-        setStates();
+        setStates(states);
+        laplaceSmoothing = 1.0 / samples.size(1); // To use in CPT computation
         int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
         if (maxThreadsRunning < 1) {
             maxThreadsRunning = 1;
@@ -179,7 +186,7 @@ namespace bayesnet {
         while (nextNodeIndex < nodes.size()) {
             unique_lock<mutex> lock(mtx);
             cv.wait(lock, [&activeThreads, &maxThreadsRunning]() { return activeThreads < maxThreadsRunning; });
-            threads.emplace_back([this, &nextNodeIndex, &mtx, &cv, &activeThreads]() {
+            threads.emplace_back([this, &nextNodeIndex, &mtx, &cv, &activeThreads, &weights]() {
                 while (true) {
                     unique_lock<mutex> lock(mtx);
                     if (nextNodeIndex >= nodes.size()) {
@@ -188,7 +195,7 @@ namespace bayesnet {
                     auto& pair = *std::next(nodes.begin(), nextNodeIndex);
                     ++nextNodeIndex;
                     lock.unlock();
-                    pair.second->computeCPT(dataset, laplaceSmoothing);
+                    pair.second->computeCPT(samples, features, laplaceSmoothing, weights);
                     lock.lock();
                     nodes[pair.first] = std::move(pair.second);
                     lock.unlock();
@@ -212,7 +219,7 @@ 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 });
+            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));
@@ -328,22 +335,22 @@ namespace bayesnet {
         mutex mtx;
         for (int i = 0; i < classNumStates; ++i) {
             threads.emplace_back([this, &result, &evidence, i, &mtx]() {
-            auto completeEvidence = map<string, int>(evidence);
-            completeEvidence[getClassName()] = i;
+                auto completeEvidence = map<string, int>(evidence);
+                completeEvidence[getClassName()] = i;
                 double factor = computeFactor(completeEvidence);
                 lock_guard<mutex> lock(mtx);
                 result[i] = factor;
-            });
+                });
         }
         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; });
+        transform(result.begin(), result.end(), result.begin(), [sum](const double& value) { return value / sum; });
         return result;
     }
-    vector<string> Network::show()
+    vector<string> Network::show() const
     {
         vector<string> result;
         // Draw the network
@@ -356,7 +363,7 @@ 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 ";
@@ -370,7 +377,7 @@ 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) {
@@ -382,6 +389,10 @@ 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 */
@@ -420,10 +431,11 @@ namespace bayesnet {
         }
         return result;
     }
-    void Network::dump_cpt()
+    void Network::dump_cpt() const
     {
         for (auto& node : nodes) {
             cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
+            cout << node.second->getCPT() << endl;
         }
     }
 }

src/BayesNet/Network.h

@@ -8,29 +8,23 @@ 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;
+        double laplaceSmoothing;
         torch::Tensor samples; // nxm tensor used to fit the model
         bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
         vector<double> predict_sample(const vector<int>&);
         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 setStates();
+        void completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights);
+        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights);
+        void setStates(const map<string, vector<int>>&);
     public:
         Network();
-        explicit Network(float, int);
         explicit Network(float);
         explicit Network(Network&);
         torch::Tensor& getSamples();
@@ -38,26 +32,26 @@ namespace bayesnet {
         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>>& input_data, const vector<int>& labels, const vector<float>& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
+        void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
+        void fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
         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

@@ -84,7 +84,7 @@ 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 double laplaceSmoothing, const torch::Tensor& weights)
     {
         dimensions.clear();
         // Get dimensions of the CPT
@@ -94,12 +94,24 @@ 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);
+            cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + weights.index({ n_sample }).item<double>());
         }
         // Normalize the counts
         cpTable = cpTable / cpTable.sum(0);

src/BayesNet/Node.h

@@ -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& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights);
         int getNumStates() const;
         void setNumStates(int);
         unsigned minFill();

src/BayesNet/Proposal.cc

@@ -2,21 +2,21 @@
 #include "ArffFiles.h"
 
 namespace bayesnet {
-    Proposal::Proposal(vector<vector<int>>& Xv_, vector<int>& yv_, vector<string>& features_, string& className_) : Xv(Xv_), yv(yv_), pFeatures(features_), pClassName(className_) {}
+    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;
         }
     }
-    void Proposal::localDiscretizationProposal(map<string, vector<int>>& states, Network& model)
+    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;
-        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();
@@ -30,13 +30,13 @@ namespace bayesnet {
             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;
-            transform(yv.begin(), yv.end(), back_inserter(yJoinParents), [&](const auto& p) {return to_string(p); });
+            vector<string> yJoinParents(Xf.size(1));
             for (auto idx : indices) {
-                for (int i = 0; i < n_samples; ++i) {
-                    yJoinParents[i] += to_string(Xv[idx][i]);
+                for (int i = 0; i < Xf.size(1); ++i) {
+                    yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
                 }
             }
             auto arff = ArffFiles();
@@ -59,26 +59,32 @@ namespace bayesnet {
             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[pFeatures[index]]->transform(Xt);
+                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;
             }
+            const torch::Tensor weights = torch::full({ pDataset.size(1) }, 1.0 / pDataset.size(1), torch::kDouble);
+            model.fit(pDataset, weights, pFeatures, pClassName, states);
         }
+        return states;
     }
-    void Proposal::fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y)
+    map<string, vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
     {
-        // Sharing Xv and yv with Classifier
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        // 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 (int i = 0; i < pFeatures.size(); ++i) {
+        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);
-            Xv.push_back(discretizer->transform(Xt));
+            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;
@@ -88,6 +94,8 @@ namespace bayesnet {
         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)
     {

src/BayesNet/Proposal.h

@@ -10,19 +10,19 @@
 namespace bayesnet {
     class Proposal {
     public:
-        Proposal(vector<vector<int>>& Xv_, vector<int>& yv_, vector<string>& features_, string& className_);
+        Proposal(torch::Tensor& pDataset, vector<string>& features_, string& className_);
         virtual ~Proposal();
     protected:
         torch::Tensor prepareX(torch::Tensor& X);
-        void localDiscretizationProposal(map<string, vector<int>>& states, Network& model);
-        void fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y);
+        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;
-        vector<vector<int>>& Xv; // X discrete nxm vector
-        vector<int>& yv;
     };
 }
 

src/BayesNet/SPODE.cc

@@ -4,7 +4,7 @@ namespace bayesnet {
 
     SPODE::SPODE(int root) : Classifier(Network()), root(root) {}
 
-    void SPODE::train()
+    void SPODE::buildModel(const torch::Tensor& weights)
     {
         // 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(const torch::Tensor& weights) 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

@@ -2,7 +2,7 @@
 
 namespace bayesnet {
     using namespace std;
-    SPODELd::SPODELd(int root) : SPODE(root), Proposal(SPODE::Xv, SPODE::yv, features, className) {}
+    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...
@@ -11,24 +11,35 @@ namespace bayesnet {
         Xf = X_;
         y = y_;
         // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
-        fit_local_discretization(states, y);
-        generateTensorXFromVector();
+        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(SPODE::Xv, SPODE::yv, features, className, states);
-        localDiscretizationProposal(states, model);
-        generateTensorXFromVector();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        model.fit(SPODE::Xv, SPODE::yv, features, className);
+        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();
+        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)
+    vector<string> SPODELd::graph(const string& name) const
     {
         return SPODE::graph(name);
     }

src/BayesNet/SPODELd.h

@@ -6,12 +6,12 @@
 namespace bayesnet {
     using namespace std;
     class SPODELd : public SPODE, public Proposal {
-    private:
     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;
-        vector<string> graph(const string& name = "SPODE") 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"; };
     };

src/BayesNet/TAN.cc

@@ -5,25 +5,25 @@ namespace bayesnet {
 
     TAN::TAN() : Classifier(Network()) {}
 
-    void TAN::train()
+    void TAN::buildModel(const torch::Tensor& weights)
     {
         // 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, "..." });
-            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
+            Tensor feature_dataset = dataset.index({ i, "..." });
+            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset, weights);
             mi.push_back({ i, mi_value });
         }
         sort(mi.begin(), mi.end(), [](const auto& left, const auto& right) {return left.second < right.second;});
         auto root = mi[mi.size() - 1].first;
         // 2. Compute mutual information between each feature and the class
-        auto weights = metrics.conditionalEdge();
+        auto weights_matrix = metrics.conditionalEdge(weights);
         // 3. Compute the maximum spanning tree
-        auto mst = metrics.maximumSpanningTree(features, weights, root);
+        auto mst = metrics.maximumSpanningTree(features, weights_matrix, root);
         // 4. Add edges from the maximum spanning tree to the model
         for (auto i = 0; i < mst.size(); ++i) {
             auto [from, to] = mst[i];
@@ -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(const torch::Tensor& weights) 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

@@ -2,7 +2,7 @@
 
 namespace bayesnet {
     using namespace std;
-    TANLd::TANLd() : TAN(), Proposal(TAN::Xv, TAN::yv, features, className) {}
+    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...
@@ -11,24 +11,20 @@ namespace bayesnet {
         Xf = X_;
         y = y_;
         // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
-        fit_local_discretization(states, y);
-        generateTensorXFromVector();
+        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(TAN::Xv, TAN::yv, features, className, states);
-        localDiscretizationProposal(states, model);
-        generateTensorXFromVector();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        model.fit(TAN::Xv, TAN::yv, features, className);
+        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)
+    vector<string> TANLd::graph(const string& name) const
     {
         return TAN::graph(name);
     }

src/BayesNet/TANLd.h

@@ -11,7 +11,7 @@ namespace bayesnet {
         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") override;
+        vector<string> graph(const string& name = "TAN") const override;
         Tensor predict(Tensor& X) override;
         static inline string version() { return "0.0.1"; };
     };

src/BayesNet/bayesnetUtils.cc

@@ -4,7 +4,7 @@ namespace bayesnet {
     using namespace std;
     using namespace torch;
     // Return the indices in descending order
-    vector<int> argsort(vector<float>& nums)
+    vector<int> argsort(vector<double>& nums)
     {
         int n = nums.size();
         vector<int> indices(n);

src/BayesNet/bayesnetUtils.h

@@ -5,7 +5,7 @@
 namespace bayesnet {
     using namespace std;
     using namespace torch;
-    vector<int> argsort(vector<float>& nums);
+    vector<int> argsort(vector<double>& nums);
     vector<vector<int>> tensorToVector(Tensor& tensor);
 }
 #endif //BAYESNET_UTILS_H

src/Platform/BestResult.h

@@ -0,0 +1,10 @@
+#ifndef BESTRESULT_H
+#define BESTRESULT_H
+#include <string>
+class BestResult {
+public:
+    static std::string title() { return "STree_default (linear-ovo)"; }
+    static double score() { return 22.109799; }
+    static std::string scoreName() { return "accuracy"; }
+};
+#endif

src/Platform/CMakeLists.txt

@@ -5,4 +5,8 @@ include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
 include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
 add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc Report.cc)
+add_executable(manage manage.cc Results.cc Report.cc)
+add_executable(list list.cc platformUtils Datasets.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
+target_link_libraries(manage "${TORCH_LIBRARIES}")
+target_link_libraries(list ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/Colors.h

@@ -0,0 +1,14 @@
+#ifndef COLORS_H
+#define COLORS_H
+class Colors {
+public:
+    static std::string MAGENTA() { return "\033[1;35m"; }
+    static std::string BLUE() { return "\033[1;34m"; }
+    static std::string CYAN() { return "\033[1;36m"; }
+    static std::string GREEN() { return "\033[1;32m"; }
+    static std::string YELLOW() { return "\033[1;33m"; }
+    static std::string RED() { return "\033[1;31m"; }
+    static std::string WHITE() { return "\033[1;37m"; }
+    static std::string RESET() { return "\033[0m"; }
+};
+#endif // COLORS_H

src/Platform/Datasets.cc

@@ -24,75 +24,110 @@ 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) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getFeatures();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getFeatures();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Datasets::getStates(string name)
+    map<string, vector<int>> Datasets::getStates(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getStates();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getStates();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    string Datasets::getClassName(string name)
+    void Datasets::loadDataset(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getClassName();
+        if (datasets.at(name)->isLoaded()) {
+            return;
+        } else {
+            datasets.at(name)->load();
+        }
+    }
+    string Datasets::getClassName(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getClassName();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Datasets::getNSamples(string name)
+    int Datasets::getNSamples(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getNSamples();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getNSamples();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
+    int Datasets::getNClasses(const string& name)
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto className = datasets.at(name)->getClassName();
+            if (discretize) {
+                auto states = getStates(name);
+                return states.at(className).size();
+            }
+            auto [Xv, yv] = getVectors(name);
+            return *max_element(yv.begin(), yv.end()) + 1;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    vector<int> Datasets::getClassesCounts(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto [Xv, yv] = datasets.at(name)->getVectors();
+            vector<int> counts(*max_element(yv.begin(), yv.end()) + 1);
+            for (auto y : yv) {
+                counts[y]++;
+            }
+            return counts;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    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();
         }
         return datasets[name]->getTensors();
     }
-    bool Datasets::isDataset(const string& name)
+    bool Datasets::isDataset(const string& name) const
     {
         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)
     {
     }
-    string Dataset::getName()
+    string Dataset::getName() const
     {
         return name;
     }
-    string Dataset::getClassName()
+    string Dataset::getClassName() const
     {
         return className;
     }
-    vector<string> Dataset::getFeatures()
+    vector<string> Dataset::getFeatures() const
     {
         if (loaded) {
             return features;
@@ -100,7 +135,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Dataset::getNFeatures()
+    int Dataset::getNFeatures() const
     {
         if (loaded) {
             return n_features;
@@ -108,7 +143,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Dataset::getNSamples()
+    int Dataset::getNSamples() const
     {
         if (loaded) {
             return n_samples;
@@ -116,7 +151,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Dataset::getStates()
+    map<string, vector<int>> Dataset::getStates() const
     {
         if (loaded) {
             return states;

src/Platform/Datasets.h

@@ -29,15 +29,15 @@ namespace platform {
     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) {};
         explicit Dataset(const Dataset&);
-        string getName();
-        string getClassName();
-        vector<string> getFeatures();
-        map<string, vector<int>> getStates();
+        string getName() const;
+        string getClassName() const;
+        vector<string> getFeatures() const;
+        map<string, vector<int>> getStates() const;
         pair<vector<vector<float>>&, vector<int>&> getVectors();
         pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized();
         pair<torch::Tensor&, torch::Tensor&> getTensors();
-        int getNFeatures();
-        int getNSamples();
+        int getNFeatures() const;
+        int getNSamples() const;
         void load();
         const bool inline isLoaded() const { return loaded; };
     };
@@ -51,14 +51,17 @@ 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);
-        int getNSamples(string name);
-        string getClassName(string name);
-        map<string, vector<int>> getStates(string name);
-        pair<vector<vector<float>>&, vector<int>&> getVectors(string name);
-        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(string name);
-        pair<torch::Tensor&, torch::Tensor&> getTensors(string name);
-        bool isDataset(const string& name);
+        vector<string> getFeatures(const string& name) const;
+        int getNSamples(const string& name) const;
+        string getClassName(const string& name) const;
+        int getNClasses(const string& name);
+        vector<int> getClassesCounts(const string& name) const;
+        map<string, vector<int>> getStates(const string& name) const;
+        pair<vector<vector<float>>&, vector<int>&> getVectors(const string& name);
+        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(const string& name);
+        pair<torch::Tensor&, torch::Tensor&> getTensors(const string& name);
+        bool isDataset(const string& name) const;
+        void loadDataset(const string& name) const;
     };
 };
 

src/Platform/Models.h

@@ -10,6 +10,7 @@
 #include "KDBLd.h"
 #include "SPODELd.h"
 #include "AODELd.h"
+#include "BoostAODE.h"
 namespace platform {
     class Models {
     private:

src/Platform/Paths.h

@@ -0,0 +1,11 @@
+#ifndef PATHS_H
+#define PATHS_H
+#include <string>
+namespace platform {
+    class Paths {
+    public:
+        static std::string datasets() { return "datasets/"; }
+        static std::string results() { return "results/"; }
+    };
+}
+#endif

src/Platform/Report.cc

@@ -1,66 +1,115 @@
+#include <sstream>
+#include <locale>
 #include "Report.h"
+#include "BestResult.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 = "";
-
+        stringstream oss;
+        string sep = "";
+        oss << "[";
         for (auto& item : data[key]) {
-            result += to_string(item) + ", ";
+            oss << sep << item.get<double>();
+            sep = ", ";
         }
-        return "[" + result.substr(0, result.length() - 2) + "]";
+        oss << "]";
+        return oss.str();
     }
-    string fVector(const json& data)
+    string fVector(const string& title, const json& data, const int width, const int precision)
     {
-        string result = "";
+        stringstream oss;
+        string sep = "";
+        oss << title << "[";
         for (const auto& item : data) {
-            result += to_string(item) + ", ";
+            oss << sep << fixed << setw(width) << setprecision(precision) << item.get<double>();
+            sep = ", ";
         }
-        return "[" + result.substr(0, result.length() - 2) + "]";
+        oss << "]";
+        return oss.str();
     }
     void Report::show()
     {
         header();
         body();
+        footer();
     }
+    struct separated : numpunct<char> {
+        char do_decimal_point() const { return ','; }
+        char do_thousands_sep() const { return '.'; }
+        string do_grouping() const { return "\03"; }
+    };
     void Report::header()
     {
-        cout << string(MAXL, '*') << endl;
+        locale mylocale(cout.getloc(), new separated);
+        locale::global(mylocale);
+        cout.imbue(mylocale);
+        stringstream oss;
+        cout << Colors::MAGENTA() << 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>());
+        oss << "Execution took  " << setprecision(2) << fixed << data["duration"].get<float>() << " seconds,   " << data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<string>();
+        cout << headerLine(oss.str());
         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;
+        cout << Colors::GREEN() << "Dataset                        Sampl. Feat. Cls Nodes     Edges     States    Score           Time               Hyperparameters" << endl;
+        cout << "============================== ====== ===== === ========= ========= ========= =============== ================== ===============" << endl;
+        json lastResult;
+        totalScore = 0;
+        bool odd = true;
         for (const auto& r : data["results"]) {
-            cout << setw(30) << left << r["dataset"].get<string>() << " ";
+            auto color = odd ? Colors::CYAN() : Colors::BLUE();
+            cout << color << 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 << setw(9) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
+            cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>() << " ";
+            cout << setw(11) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
+            try {
+                cout << r["hyperparameters"].get<string>();
+            }
+            catch (const exception& err) {
+                cout << r["hyperparameters"];
+            }
             cout << endl;
+            lastResult = r;
+            totalScore += r["score"].get<double>();
+            odd = !odd;
+        }
+        if (data["results"].size() == 1) {
             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 << headerLine(fVector("Train scores: ", lastResult["scores_train"], 14, 12));
+            cout << headerLine(fVector("Test  scores: ", lastResult["scores_test"], 14, 12));
+            cout << headerLine(fVector("Train  times: ", lastResult["times_train"], 10, 3));
+            cout << headerLine(fVector("Test   times: ", lastResult["times_test"], 10, 3));
             cout << string(MAXL, '*') << endl;
         }
     }
+    void Report::footer()
+    {
+        cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
+        auto score = data["score_name"].get<string>();
+        if (score == BestResult::scoreName()) {
+            stringstream oss;
+            oss << score << " compared to " << BestResult::title() << " .:  " << totalScore / BestResult::score();
+            cout << headerLine(oss.str());
+        }
+        cout << string(MAXL, '*') << endl << Colors::RESET();
+
+    }
 }

src/Platform/Report.h

@@ -3,9 +3,10 @@
 #include <string>
 #include <iostream>
 #include <nlohmann/json.hpp>
+#include "Colors.h"
 
 using json = nlohmann::json;
-const int MAXL = 121;
+const int MAXL = 128;
 namespace platform {
     using namespace std;
     class Report {
@@ -16,8 +17,10 @@ namespace platform {
     private:
         void header();
         void body();
+        void footer();
         string fromVector(const string& key);
         json data;
+        double totalScore; // Total score of all results in a report
     };
 };
 #endif

src/Platform/Results.cc

@@ -0,0 +1,239 @@
+#include <filesystem>
+#include "platformUtils.h"
+#include "Results.h"
+#include "Report.h"
+#include "BestResult.h"
+#include "Colors.h"
+namespace platform {
+    Result::Result(const string& path, const string& filename)
+        : path(path)
+        , filename(filename)
+    {
+        auto data = load();
+        date = data["date"];
+        score = 0;
+        for (const auto& result : data["results"]) {
+            score += result["score"].get<double>();
+        }
+        scoreName = data["score_name"];
+        if (scoreName == BestResult::scoreName()) {
+            score /= BestResult::score();
+        }
+        title = data["title"];
+        duration = data["duration"];
+        model = data["model"];
+    }
+    json Result::load() const
+    {
+        ifstream resultData(path + "/" + filename);
+        if (resultData.is_open()) {
+            json data = json::parse(resultData);
+            return data;
+        }
+        throw invalid_argument("Unable to open result file. [" + path + "/" + filename + "]");
+    }
+    void Results::load()
+    {
+        using std::filesystem::directory_iterator;
+        for (const auto& file : directory_iterator(path)) {
+            auto filename = file.path().filename().string();
+            if (filename.find(".json") != string::npos && filename.find("results_") == 0) {
+                auto result = Result(path, filename);
+                bool addResult = true;
+                if (model != "any" && result.getModel() != model || scoreName != "any" && scoreName != result.getScoreName())
+                    addResult = false;
+                if (addResult)
+                    files.push_back(result);
+            }
+        }
+    }
+    string Result::to_string() const
+    {
+        stringstream oss;
+        oss << date << " ";
+        oss << setw(12) << left << model << " ";
+        oss << setw(11) << left << scoreName << " ";
+        oss << right << setw(11) << setprecision(7) << fixed << score << " ";
+        oss << setw(9) << setprecision(3) << fixed << duration << " ";
+        oss << setw(50) << left << title << " ";
+        return  oss.str();
+    }
+    void Results::show() const
+    {
+        cout << Colors::GREEN() << "Results found: " << files.size() << endl;
+        cout << "-------------------" << endl;
+        auto i = 0;
+        cout << " #  Date       Model        Score Name  Score       Duration  Title" << endl;
+        cout << "=== ========== ============ =========== =========== ========= =============================================================" << endl;
+        bool odd = true;
+        for (const auto& result : files) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            cout << color << setw(3) << fixed << right << i++ << " ";
+            cout << result.to_string() << endl;
+            if (i == max && max != 0) {
+                break;
+            }
+            odd = !odd;
+        }
+    }
+    int Results::getIndex(const string& intent) const
+    {
+        string color;
+        if (intent == "delete") {
+            color = Colors::RED();
+        } else {
+            color = Colors::YELLOW();
+        }
+        cout << color << "Choose result to " << intent << " (cancel=-1): ";
+        string line;
+        getline(cin, line);
+        int index = stoi(line);
+        if (index >= -1 && index < static_cast<int>(files.size())) {
+            return index;
+        }
+        cout << "Invalid index" << endl;
+        return -1;
+    }
+    void Results::report(const int index) const
+    {
+        cout << Colors::YELLOW() << "Reporting " << files.at(index).getFilename() << endl;
+        auto data = files.at(index).load();
+        Report report(data);
+        report.show();
+    }
+    void Results::menu()
+    {
+        char option;
+        int index;
+        bool finished = false;
+        string filename, line, options = "qldhsr";
+        while (!finished) {
+            cout << Colors::RESET() << "Choose option (quit='q', list='l', delete='d', hide='h', sort='s', report='r'): ";
+            getline(cin, line);
+            if (line.size() == 0)
+                continue;
+            if (options.find(line[0]) != string::npos) {
+                if (line.size() > 1) {
+                    cout << "Invalid option" << endl;
+                    continue;
+                }
+                option = line[0];
+            } else {
+                index = stoi(line);
+                if (index >= 0 && index < files.size()) {
+                    report(index);
+                } else {
+                    cout << "Invalid option" << endl;
+                }
+                continue;
+            }
+            switch (option) {
+                case 'q':
+                    finished = true;
+                    break;
+                case 'l':
+                    show();
+                    break;
+                case 'd':
+                    index = getIndex("delete");
+                    if (index == -1)
+                        break;
+                    filename = files[index].getFilename();
+                    cout << "Deleting " << filename << endl;
+                    remove((path + "/" + filename).c_str());
+                    files.erase(files.begin() + index);
+                    cout << "File: " + filename + " deleted!" << endl;
+                    show();
+                    break;
+                case 'h':
+                    index = getIndex("hide");
+                    if (index == -1)
+                        break;
+                    filename = files[index].getFilename();
+                    cout << "Hiding " << filename << endl;
+                    rename((path + "/" + filename).c_str(), (path + "/." + filename).c_str());
+                    files.erase(files.begin() + index);
+                    show();
+                    menu();
+                    break;
+                case 's':
+                    sortList();
+                    show();
+                    break;
+                case 'r':
+                    index = getIndex("report");
+                    if (index == -1)
+                        break;
+                    report(index);
+                    break;
+                default:
+                    cout << "Invalid option" << endl;
+            }
+        }
+    }
+    void Results::sortList()
+    {
+        cout << Colors::YELLOW() << "Choose sorting field (date='d', score='s', duration='u', model='m'): ";
+        string line;
+        char option;
+        getline(cin, line);
+        if (line.size() == 0)
+            return;
+        if (line.size() > 1) {
+            cout << "Invalid option" << endl;
+            return;
+        }
+        option = line[0];
+        switch (option) {
+            case 'd':
+                sortDate();
+                break;
+            case 's':
+                sortScore();
+                break;
+            case 'u':
+                sortDuration();
+                break;
+            case 'm':
+                sortModel();
+                break;
+            default:
+                cout << "Invalid option" << endl;
+        }
+    }
+    void Results::sortDate()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getDate() > b.getDate();
+            });
+    }
+    void Results::sortModel()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getModel() > b.getModel();
+            });
+    }
+    void Results::sortDuration()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getDuration() > b.getDuration();
+            });
+    }
+    void Results::sortScore()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getScore() > b.getScore();
+            });
+    }
+    void Results::manage()
+    {
+        if (files.size() == 0) {
+            cout << "No results found!" << endl;
+            exit(0);
+        }
+        show();
+        menu();
+        cout << "Done!" << endl;
+    }
+
+}

src/Platform/Results.h

@@ -0,0 +1,56 @@
+#ifndef RESULTS_H
+#define RESULTS_H
+#include <map>
+#include <vector>
+#include <string>
+#include <nlohmann/json.hpp>
+namespace platform {
+    using namespace std;
+    using json = nlohmann::json;
+
+    class Result {
+    public:
+        Result(const string& path, const string& filename);
+        json load() const;
+        string to_string() const;
+        string getFilename() const { return filename; };
+        string getDate() const { return date; };
+        double getScore() const { return score; };
+        string getTitle() const { return title; };
+        double getDuration() const { return duration; };
+        string getModel() const { return model; };
+        string getScoreName() const { return scoreName; };
+    private:
+        string path;
+        string filename;
+        string date;
+        double score;
+        string title;
+        double duration;
+        string model;
+        string scoreName;
+    };
+    class Results {
+    public:
+        Results(const string& path, const int max, const string& model, const string& score) : path(path), max(max), model(model), scoreName(score) { load(); };
+        void manage();
+    private:
+        string path;
+        int max;
+        string model;
+        string scoreName;
+        vector<Result> files;
+        void load(); // Loads the list of results
+        void show() const;
+        void report(const int index) const;
+        int getIndex(const string& intent) const;
+        void menu();
+        void sortList();
+        void sortDate();
+        void sortScore();
+        void sortModel();
+        void sortDuration();
+    };
+};
+
+#endif

src/Platform/list.cc

@@ -0,0 +1,57 @@
+#include <iostream>
+#include <locale>
+#include "Paths.h"
+#include "Colors.h"
+#include "Datasets.h"
+
+using namespace std;
+const int BALANCE_LENGTH = 75;
+
+struct separated : numpunct<char> {
+    char do_decimal_point() const { return ','; }
+    char do_thousands_sep() const { return '.'; }
+    string do_grouping() const { return "\03"; }
+};
+
+void outputBalance(const string& balance)
+{
+    auto temp = string(balance);
+    while (temp.size() > BALANCE_LENGTH - 1) {
+        auto part = temp.substr(0, BALANCE_LENGTH);
+        cout << part << endl;
+        cout << setw(48) << " ";
+        temp = temp.substr(BALANCE_LENGTH);
+    }
+    cout << temp << endl;
+}
+
+int main(int argc, char** argv)
+{
+    auto data = platform::Datasets(platform::Paths().datasets(), false);
+    locale mylocale(cout.getloc(), new separated);
+    locale::global(mylocale);
+    cout.imbue(mylocale);
+    cout << Colors::GREEN() << "Dataset                        Sampl. Feat. Cls. Balance" << endl;
+    string balanceBars = string(BALANCE_LENGTH, '=');
+    cout << "============================== ====== ===== === " << balanceBars << endl;
+    bool odd = true;
+    for (const auto& dataset : data.getNames()) {
+        auto color = odd ? Colors::CYAN() : Colors::BLUE();
+        cout << color << setw(30) << left << dataset << " ";
+        data.loadDataset(dataset);
+        auto nSamples = data.getNSamples(dataset);
+        cout << setw(6) << right << nSamples << " ";
+        cout << setw(5) << right << data.getFeatures(dataset).size() << " ";
+        cout << setw(3) << right << data.getNClasses(dataset) << " ";
+        stringstream oss;
+        string sep = "";
+        for (auto number : data.getClassesCounts(dataset)) {
+            oss << sep << setprecision(2) << fixed << (float)number / nSamples * 100.0 << "% (" << number << ")";
+            sep = " / ";
+        }
+        outputBalance(oss.str());
+        odd = !odd;
+    }
+    cout << Colors::RESET() << endl;
+    return 0;
+}

src/Platform/main.cc

@@ -6,20 +6,19 @@
 #include "DotEnv.h"
 #include "Models.h"
 #include "modelRegister.h"
+#include "Paths.h"
+
 
 using namespace std;
-const string PATH_RESULTS = "results";
-const string PATH_DATASETS = "datasets";
 
 argparse::ArgumentParser manageArguments(int argc, char** argv)
 {
     auto env = platform::DotEnv();
-    argparse::ArgumentParser program("BayesNetSample");
+    argparse::ArgumentParser program("main");
     program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
     program.add_argument("-p", "--path")
         .help("folder where the data files are located, default")
-        .default_value(string{ PATH_DATASETS }
-    );
+        .default_value(string{ platform::Paths::datasets() });
     program.add_argument("-m", "--model")
         .help("Model to use " + platform::Models::instance()->toString())
         .action([](const std::string& value) {
@@ -104,7 +103,7 @@ int main(int argc, char** argv)
     */
     auto env = platform::DotEnv();
     auto experiment = platform::Experiment();
-    experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("1.0.0");
+    experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("14.0.3");
     experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
     experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
     for (auto seed : seeds) {
@@ -115,7 +114,7 @@ int main(int argc, char** argv)
     experiment.go(filesToTest, path);
     experiment.setDuration(timer.getDuration());
     if (saveResults)
-        experiment.save(PATH_RESULTS);
+        experiment.save(platform::Paths::results());
     else
         experiment.report();
     cout << "Done!" << endl;

src/Platform/manage.cc

@@ -0,0 +1,41 @@
+#include <iostream>
+#include <argparse/argparse.hpp>
+#include "platformUtils.h"
+#include "Paths.h"
+#include "Results.h"
+
+using namespace std;
+
+argparse::ArgumentParser manageArguments(int argc, char** argv)
+{
+    argparse::ArgumentParser program("manage");
+    program.add_argument("-n", "--number").default_value(0).help("Number of results to show (0 = all)").scan<'i', int>();
+    program.add_argument("-m", "--model").default_value("any").help("Filter results of the selected model)");
+    program.add_argument("-s", "--score").default_value("any").help("Filter results of the score name supplied");
+    try {
+        program.parse_args(argc, argv);
+        auto number = program.get<int>("number");
+        if (number < 0) {
+            throw runtime_error("Number of results must be greater than or equal to 0");
+        }
+        auto model = program.get<string>("model");
+        auto score = program.get<string>("score");
+    }
+    catch (const exception& err) {
+        cerr << err.what() << endl;
+        cerr << program;
+        exit(1);
+    }
+    return program;
+}
+
+int main(int argc, char** argv)
+{
+    auto program = manageArguments(argc, argv);
+    auto number = program.get<int>("number");
+    auto model = program.get<string>("model");
+    auto score = program.get<string>("score");
+    auto results = platform::Results(platform::Paths::results(), number, model, score);
+    results.manage();
+    return 0;
+}

src/Platform/modelRegister.h

@@ -16,4 +16,6 @@ static platform::Registrar registrarA("AODE",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
 static platform::Registrar registrarALD("AODELd",
     [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODELd();});
+static platform::Registrar registrarBA("BoostAODE",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::BoostAODE();});
 #endif

src/Platform/platformUtils.cc

@@ -1,4 +1,5 @@
 #include "platformUtils.h"
+#include "Paths.h"
 
 using namespace torch;
 
@@ -85,7 +86,7 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
 tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(const string& name)
 {
     auto handler = ArffFiles();
-    handler.load(PATH + static_cast<string>(name) + ".arff");
+    handler.load(platform::Paths::datasets() + static_cast<string>(name) + ".arff");
     // Get Dataset X, y
     vector<mdlp::samples_t>& X = handler.getX();
     mdlp::labels_t& y = handler.getY();