Upgrade models version and Add class diagram

Reviewed-on: https://gitea.rmontanana.es:11000/rmontanana/BayesNet/pulls/6

.clang-uml

@@ -0,0 +1,31 @@
+compilation_database_dir: build
+output_directory: puml
+diagrams:
+  BayesNet:
+    type: class
+    glob:
+      - src/BayesNet/*.cc
+      - src/Platform/*.cc
+    using_namespace: bayesnet
+    include:
+      namespaces:
+        - bayesnet
+        - platform
+    plantuml:
+      after:
+        - "note left of {{ alias(\"MyProjectMain\") }}: Main class of myproject library."
+  sequence:
+    type: sequence
+    glob:
+      - src/Platform/main.cc
+    combine_free_functions_into_file_participants: true
+    using_namespace:
+      - std
+      - bayesnet
+      - platform
+    include:
+      paths:
+        - src/BayesNet
+        - src/Platform
+    start_from:
+      - function: main(int,const char **)

.gitignore

@@ -35,3 +35,4 @@ build/
 *.dSYM/**
 cmake-build*/**
 .idea
+puml/**

.gitmodules

@@ -10,3 +10,6 @@
 [submodule "lib/json"]
 	path = lib/json
 	url = https://github.com/nlohmann/json.git
+[submodule "lib/openXLSX"]
+	path = lib/openXLSX
+	url = https://github.com/troldal/OpenXLSX.git

.vscode/launch.json

@@ -10,7 +10,7 @@
                 "-d",
                 "iris",
                 "-m",
-                "KDB",
+                "TANLd",
                 "-s",
                 "271",
                 "-p",
@@ -25,17 +25,17 @@
             "program": "${workspaceFolder}/build/src/Platform/main",
             "args": [
                 "-m",
-                "BoostAODE",
+                "AODE",
                 "-p",
-                "/Users/rmontanana/Code/discretizbench/datasets",
-                "--discretize",
+                "/home/rmontanana/Code/discretizbench/datasets",
                 "--stratified",
                 "-d",
-                "glass",
-                "--hyperparameters",
-                "{\"repeatSparent\": true, \"maxModels\": 12}"
+                "mfeat-morphological",
+                "--discretize"
+                // "--hyperparameters",
+                // "{\"repeatSparent\": true, \"maxModels\": 12}"
             ],
-            "cwd": "/Users/rmontanana/Code/discretizbench",
+            "cwd": "/home/rmontanana/Code/discretizbench",
         },
         {
             "type": "lldb",

CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(BayesNet
-  VERSION 0.1.0
+  VERSION 0.2.0
   DESCRIPTION "Bayesian Network and basic classifiers Library."
   HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
   LANGUAGES CXX
@@ -30,7 +30,7 @@ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
 option(ENABLE_CLANG_TIDY "Enable to add clang tidy."              OFF)
 option(ENABLE_TESTING "Unit testing build"                        OFF)
 option(CODE_COVERAGE "Collect coverage from test library"         OFF)
-
+SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
 # CMakes modules
 # --------------
 set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
@@ -40,8 +40,7 @@ if (CODE_COVERAGE)
     enable_testing()
     include(CodeCoverage)
     MESSAGE("Code coverage enabled")
-    set(CMAKE_C_FLAGS " ${CMAKE_C_FLAGS} -fprofile-arcs -ftest-coverage")
-    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage")
+    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage -O0")
     SET(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
 endif (CODE_COVERAGE)
 

Makefile

@@ -32,6 +32,9 @@ clean: ## Clean the debug info
 	find . -name "*.gcda" -print0 | xargs -0 rm
 	@echo ">>> Done";
 
+clang-uml: ## Create uml class and sequence diagrams
+	clang-uml -p --add-compile-flag -I /usr/lib/gcc/x86_64-redhat-linux/8/include/
+
 debug: ## Build a debug version of the project
 	@echo ">>> Building Debug BayesNet ...";
 	@if [ -d ./build ]; then rm -rf ./build; fi

TAN_iris.dot

@@ -1,12 +0,0 @@
-digraph BayesNet {
-label=<BayesNet >
-fontsize=30
-fontcolor=blue
-labelloc=t
-layout=circo
- class [shape=circle, fontcolor=red, fillcolor=lightblue, style=filled ] 
- class -> sepallength class -> sepalwidth class -> petallength class -> petalwidth petallength [shape=circle] 
- petallength -> sepallength petalwidth [shape=circle] 
- sepallength [shape=circle] 
- sepallength -> sepalwidth sepalwidth [shape=circle] 
- sepalwidth -> petalwidth }

data/_TAN_cpp_accuracy__.json

@@ -1 +0,0 @@
-null

sample/sample.cc

@@ -10,7 +10,7 @@
 #include "Folding.h"
 #include "Models.h"
 #include "modelRegister.h"
-
+#include <fstream>
 
 using namespace std;
 
@@ -195,11 +195,11 @@ int main(int argc, char** argv)
         Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
     }
     float total_score = 0, total_score_train = 0, score_train, score_test;
-    Fold* fold;
+    platform::Fold* fold;
     if (stratified)
-        fold = new StratifiedKFold(nFolds, y, seed);
+        fold = new platform::StratifiedKFold(nFolds, y, seed);
     else
-        fold = new KFold(nFolds, y.size(), seed);
+        fold = new platform::KFold(nFolds, y.size(), seed);
     for (auto i = 0; i < nFolds; ++i) {
         auto [train, test] = fold->getFold(i);
         cout << "Fold: " << i + 1 << endl;

src/BayesNet/AODE.h

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

src/BayesNet/AODELd.cc

@@ -4,9 +4,9 @@
 namespace bayesnet {
     using namespace std;
     AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
-    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
@@ -26,6 +26,7 @@ namespace bayesnet {
             models.push_back(std::make_unique<SPODELd>(i));
         }
         n_models = models.size();
+        significanceModels = vector<double>(n_models, 1.0);
     }
     void AODELd::trainModel(const torch::Tensor& weights)
     {

src/BayesNet/AODELd.h

@@ -12,11 +12,10 @@ namespace bayesnet {
         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;
+        AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_) override;
         virtual ~AODELd() = default;
-        vector<string> graph(const string& name = "AODE") const override;
+        vector<string> graph(const string& name = "AODELd") const override;
         static inline string version() { return "0.0.1"; };
-        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif // !AODELD_H

src/BayesNet/BaseClassifier.h

@@ -10,11 +10,11 @@ namespace bayesnet {
         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;
+        virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const 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& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const 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;
@@ -25,7 +25,7 @@ namespace bayesnet {
         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"; };
+        const string inline getVersion() const { return "0.2.0"; };
         vector<string> virtual topological_order() = 0;
         void virtual dump_cpt()const = 0;
         virtual void setHyperparameters(nlohmann::json& hyperparameters) = 0;

src/BayesNet/BayesMetrics.cc

@@ -77,7 +77,6 @@ namespace bayesnet {
         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 }, torch::kFloat);
         for (int value = 0; value < classNumStates; ++value) {

src/BayesNet/BoostAODE.cc

@@ -37,7 +37,6 @@ namespace bayesnet {
         // Step 0: Set the finish condition
         // if not repeatSparent a finish condition is run out of features
         // n_models == maxModels
-        int numClasses = states[className].size();
         while (!exitCondition) {
             // Step 1: Build ranking with mutual information
             auto featureSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted

src/BayesNet/Classifier.cc

@@ -5,7 +5,7 @@ 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, const torch::Tensor& weights)
+    Classifier& Classifier::build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
     {
         this->features = features;
         this->className = className;
@@ -13,7 +13,7 @@ namespace bayesnet {
         m = dataset.size(1);
         n = dataset.size(0) - 1;
         checkFitParameters();
-        auto n_classes = states[className].size();
+        auto n_classes = states.at(className).size();
         metrics = Metrics(dataset, features, className, n_classes);
         model.initialize();
         buildModel(weights);
@@ -39,7 +39,7 @@ namespace bayesnet {
         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)
+    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
     {
         dataset = X;
         buildDataset(y);
@@ -47,7 +47,7 @@ namespace bayesnet {
         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)
+    Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
     {
         dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
         for (int i = 0; i < X.size(); ++i) {
@@ -58,19 +58,22 @@ namespace bayesnet {
         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)
+    Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const 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)
+    Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
     {
         this->dataset = dataset;
         return build(features, className, states, weights);
     }
     void Classifier::checkFitParameters()
     {
+        if (torch::is_floating_point(dataset)) {
+            throw invalid_argument("dataset (X, y) must be of type Integer");
+        }
         if (n != features.size()) {
             throw invalid_argument("X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
         }
@@ -160,4 +163,10 @@ namespace bayesnet {
             }
         }
     }
+    void Classifier::setHyperparameters(nlohmann::json& hyperparameters)
+    {
+        // Check if hyperparameters are valid, default is no hyperparameters
+        const vector<string> validKeys = { };
+        checkHyperparameters(validKeys, hyperparameters);
+    }
 }

src/BayesNet/Classifier.h

@@ -11,7 +11,7 @@ namespace bayesnet {
     class Classifier : public BaseClassifier {
     private:
         void buildDataset(torch::Tensor& y);
-        Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states, const torch::Tensor& weights);
+        Classifier& build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights);
     protected:
         bool fitted;
         int m, n; // m: number of samples, n: number of features
@@ -28,10 +28,10 @@ namespace bayesnet {
     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;
+        Classifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights) override;
         void addNodes();
         int getNumberOfNodes() const override;
         int getNumberOfEdges() const override;
@@ -43,6 +43,7 @@ namespace bayesnet {
         vector<string> show() const override;
         vector<string> topological_order()  override;
         void dump_cpt() const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
     };
 }
 #endif

src/BayesNet/Ensemble.cc

@@ -3,7 +3,7 @@
 namespace bayesnet {
     using namespace torch;
 
-    Ensemble::Ensemble() : Classifier(Network()) {}
+    Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
 
     void Ensemble::trainModel(const torch::Tensor& weights)
     {
@@ -17,9 +17,13 @@ namespace bayesnet {
     {
         auto y_pred_ = y_pred.accessor<int, 2>();
         vector<int> y_pred_final;
+        int numClasses = states.at(className).size();
+        // y_pred is m x n_models with the prediction of every model for each sample
         for (int i = 0; i < y_pred.size(0); ++i) {
-            vector<double> votes(y_pred.size(1), 0);
-            for (int j = 0; j < y_pred.size(1); ++j) {
+            // votes store in each index (value of class) the significance added by each model
+            // i.e. votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
+            vector<double> votes(numClasses, 0.0);
+            for (int j = 0; j < n_models; ++j) {
                 votes[y_pred_[i][j]] += significanceModels[j];
             }
             // argsort in descending order
@@ -34,7 +38,6 @@ namespace bayesnet {
             throw logic_error("Ensemble has not been fitted");
         }
         Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
-        //Create a threadpool
         auto threads{ vector<thread>() };
         mutex mtx;
         for (auto i = 0; i < n_models; ++i) {

src/BayesNet/KDB.cc

@@ -4,6 +4,18 @@ namespace bayesnet {
     using namespace torch;
 
     KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
+    void KDB::setHyperparameters(nlohmann::json& hyperparameters)
+    {
+        // Check if hyperparameters are valid
+        const vector<string> validKeys = { "k", "theta" };
+        checkHyperparameters(validKeys, hyperparameters);
+        if (hyperparameters.contains("k")) {
+            k = hyperparameters["k"];
+        }
+        if (hyperparameters.contains("theta")) {
+            theta = hyperparameters["theta"];
+        }
+    }
     void KDB::buildModel(const torch::Tensor& weights)
     {
         /*

src/BayesNet/KDB.h

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

src/BayesNet/KDBLd.cc

@@ -3,9 +3,9 @@
 namespace bayesnet {
     using namespace std;
     KDBLd::KDBLd(int k) : KDB(k), Proposal(dataset, features, className) {}
-    KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;

src/BayesNet/KDBLd.h

@@ -10,10 +10,9 @@ namespace bayesnet {
     public:
         explicit KDBLd(int k);
         virtual ~KDBLd() = default;
-        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "KDB") const override;
         Tensor predict(Tensor& X) override;
-        void setHyperparameters(nlohmann::json& hyperparameters) override {};
         static inline string version() { return "0.0.1"; };
     };
 }

src/BayesNet/Network.cc

@@ -3,8 +3,8 @@
 #include "Network.h"
 #include "bayesnetUtils.h"
 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() : features(vector<string>()), className(""), classNumStates(0), fitted(false), laplaceSmoothing(0) {}
+    Network::Network(float maxT) : features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false), laplaceSmoothing(0) {}
     Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.
         getmaxThreads()), fitted(other.fitted)
     {
@@ -174,43 +174,11 @@ namespace bayesnet {
     {
         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;
-        }
-        vector<thread> threads;
-        mutex mtx;
-        condition_variable cv;
-        int activeThreads = 0;
-        int nextNodeIndex = 0;
-        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, &weights]() {
-                while (true) {
-                    unique_lock<mutex> lock(mtx);
-                    if (nextNodeIndex >= nodes.size()) {
-                        break;  // No more work remaining
-                    }
-                    auto& pair = *std::next(nodes.begin(), nextNodeIndex);
-                    ++nextNodeIndex;
-                    lock.unlock();
-                    pair.second->computeCPT(samples, features, laplaceSmoothing, weights);
-                    lock.lock();
-                    nodes[pair.first] = std::move(pair.second);
-                    lock.unlock();
-                }
-                lock_guard<mutex> lock(mtx);
-                --activeThreads;
-                cv.notify_one();
-                });
-            ++activeThreads;
-        }
-        for (auto& thread : threads) {
-            thread.join();
-        }
+        for (auto& node : nodes) {
+            node.second->computeCPT(samples, features, laplaceSmoothing, weights);
             fitted = true;
         }
+    }
     torch::Tensor Network::predict_tensor(const torch::Tensor& samples, const bool proba)
     {
         if (!fitted) {
@@ -399,7 +367,6 @@ namespace bayesnet {
         auto result = features;
         result.erase(remove(result.begin(), result.end(), className), result.end());
         bool ending{ false };
-        int idx = 0;
         while (!ending) {
             ending = true;
             for (auto feature : features) {

src/BayesNet/Network.h

@@ -27,6 +27,7 @@ namespace bayesnet {
         Network();
         explicit Network(float);
         explicit Network(Network&);
+        ~Network() = default;
         torch::Tensor& getSamples();
         float getmaxThreads();
         void addNode(const string&);
@@ -52,7 +53,7 @@ namespace bayesnet {
         vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
         void initialize();
         void dump_cpt() const;
-        inline string version() { return "0.1.0"; }
+        inline string version() { return "0.2.0"; }
     };
 }
 #endif

src/BayesNet/Node.cc

@@ -100,7 +100,7 @@ namespace bayesnet {
         }
         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;
+            c10::List<c10::optional<at::Tensor>> coordinates;
             coordinates.push_back(dataset.index({ name_index, n_sample }));
             for (auto parent : parents) {
                 pos = find(features.begin(), features.end(), parent->getName());
@@ -118,10 +118,10 @@ namespace bayesnet {
     }
     float Node::getFactorValue(map<string, int>& evidence)
     {
-        torch::List<c10::optional<torch::Tensor>> coordinates;
+        c10::List<c10::optional<at::Tensor>> coordinates;
         // following predetermined order of indices in the cpTable (see Node.h)
-        coordinates.push_back(torch::tensor(evidence[name]));
-        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return torch::tensor(evidence[parent->getName()]); });
+        coordinates.push_back(at::tensor(evidence[name]));
+        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return at::tensor(evidence[parent->getName()]); });
         return cpTable.index({ coordinates }).item<float>();
     }
     vector<string> Node::graph(const string& className)

src/BayesNet/Proposal.cc

@@ -9,6 +9,15 @@ namespace bayesnet {
             delete value;
         }
     }
+    void Proposal::checkInput(const torch::Tensor& X, const torch::Tensor& y)
+    {
+        if (!torch::is_floating_point(X)) {
+            throw std::invalid_argument("X must be a floating point tensor");
+        }
+        if (torch::is_floating_point(y)) {
+            throw std::invalid_argument("y must be an integer tensor");
+        }
+    }
     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...
@@ -44,15 +53,6 @@ namespace bayesnet {
             auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
             auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
             discretizers[feature]->fit(xvf, yxv);
-            //
-            //
-            //
-            // auto tmp = discretizers[feature]->transform(xvf);
-            // Xv[index] = tmp;
-            // auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
-            // iota(xStates.begin(), xStates.end(), 0);
-            // //Update new states of the feature/node
-            // states[feature] = xStates;
         }
         if (upgrade) {
             // Discretize again X (only the affected indices) with the new fitted discretizers

src/BayesNet/Proposal.h

@@ -13,6 +13,7 @@ namespace bayesnet {
         Proposal(torch::Tensor& pDataset, vector<string>& features_, string& className_);
         virtual ~Proposal();
     protected:
+        void checkInput(const torch::Tensor& X, const torch::Tensor& y);
         torch::Tensor prepareX(torch::Tensor& X);
         map<string, vector<int>> localDiscretizationProposal(const map<string, vector<int>>& states, Network& model);
         map<string, vector<int>> fit_local_discretization(const torch::Tensor& y);

src/BayesNet/SPODE.h

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

src/BayesNet/SPODELd.cc

@@ -3,9 +3,9 @@
 namespace bayesnet {
     using namespace std;
     SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
-    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
@@ -18,11 +18,13 @@ namespace bayesnet {
         states = localDiscretizationProposal(states, model);
         return *this;
     }
-    SPODELd& SPODELd::fit(torch::Tensor& dataset, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    SPODELd& SPODELd::fit(torch::Tensor& dataset, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
+        if (!torch::is_floating_point(dataset)) {
+            throw std::runtime_error("Dataset must be a floating point tensor");
+        }
         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

src/BayesNet/SPODELd.h

@@ -9,11 +9,10 @@ namespace bayesnet {
     public:
         explicit SPODELd(int root);
         virtual ~SPODELd() = default;
-        SPODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        SPODELd& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        SPODELd& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "SPODE") const override;
         Tensor predict(Tensor& X) override;
-        void setHyperparameters(nlohmann::json& hyperparameters) override {};
         static inline string version() { return "0.0.1"; };
     };
 }

src/BayesNet/TAN.h

@@ -11,7 +11,6 @@ namespace bayesnet {
         TAN();
         virtual ~TAN() {};
         vector<string> graph(const string& name = "TAN") const override;
-        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif

src/BayesNet/TANLd.cc

@@ -3,9 +3,9 @@
 namespace bayesnet {
     using namespace std;
     TANLd::TANLd() : TAN(), Proposal(dataset, features, className) {}
-    TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;

src/BayesNet/TANLd.h

@@ -10,11 +10,10 @@ namespace bayesnet {
     public:
         TANLd();
         virtual ~TANLd() = default;
-        TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        TANLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "TAN") const override;
         Tensor predict(Tensor& X) override;
         static inline string version() { return "0.0.1"; };
-        void setHyperparameters(nlohmann::json& hyperparameters) override {};
     };
 }
 #endif // !TANLD_H

src/Platform/Datasets.cc

@@ -1,6 +1,7 @@
 #include "Datasets.h"
 #include "platformUtils.h"
 #include "ArffFiles.h"
+#include <fstream>
 namespace platform {
     void Datasets::load()
     {
@@ -212,10 +213,11 @@ namespace platform {
     {
         for (int i = 0; i < features.size(); ++i) {
             states[features[i]] = vector<int>(*max_element(Xd[i].begin(), Xd[i].end()) + 1);
-            iota(begin(states[features[i]]), end(states[features[i]]), 0);
+            auto item = states.at(features[i]);
+            iota(begin(item), end(item), 0);
         }
         states[className] = vector<int>(*max_element(yv.begin(), yv.end()) + 1);
-        iota(begin(states[className]), end(states[className]), 0);
+        iota(begin(states.at(className)), end(states.at(className)), 0);
     }
     void Dataset::load_arff()
     {

src/Platform/Experiment.cc

@@ -2,7 +2,7 @@
 #include "Datasets.h"
 #include "Models.h"
 #include "ReportConsole.h"
-
+#include <fstream>
 namespace platform {
     using json = nlohmann::json;
     string get_date()
@@ -179,8 +179,10 @@ namespace platform {
                 result.addTimeTrain(train_time[item].item<double>());
                 result.addTimeTest(test_time[item].item<double>());
                 item++;
+                clf.reset();
             }
             cout << "end. " << flush;
+            delete fold;
         }
         result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
         result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());

src/Platform/Folding.cc

@@ -1,6 +1,7 @@
 #include "Folding.h"
 #include <algorithm>
 #include <map>
+namespace platform {
     Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
     {
         random_device rd;
@@ -93,3 +94,4 @@ pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
         }
         return { train_indices, test_indices };
     }
+}

src/Platform/Folding.h

@@ -4,7 +4,7 @@
 #include <vector>
 #include <random> 
 using namespace std;
-
+namespace platform {
     class Fold {
     protected:
         int k;
@@ -34,4 +34,5 @@ public:
         StratifiedKFold(int k, torch::Tensor& y, int seed = -1);
         pair<vector<int>, vector<int>> getFold(int nFold) override;
     };
+}
 #endif

src/Platform/Models.cc

@@ -26,7 +26,7 @@ namespace platform {
             instance = it->second();
         // wrap instance in a shared ptr and return
         if (instance != nullptr)
-            return shared_ptr<bayesnet::BaseClassifier>(instance);
+            return unique_ptr<bayesnet::BaseClassifier>(instance);
         else
             return nullptr;
     }

src/Platform/ReportExcel.cc

@@ -47,11 +47,11 @@ namespace platform {
 
     void ReportExcel::body()
     {
-        auto header = vector<string>(
+        auto head = vector<string>(
             { "Dataset", "Samples", "Features", "Classes", "Nodes", "Edges", "States", "Score", "Score Std.", "Time",
              "Time Std.", "Hyperparameters" });
         int col = 1;
-        for (const auto& item : header) {
+        for (const auto& item : head) {
             wks.cell(8, col++).value() = item;
         }
         int row = 9;

src/Platform/Results.cc

@@ -100,11 +100,11 @@ namespace platform {
         cout << Colors::YELLOW() << "Reporting " << files.at(index).getFilename() << endl;
         auto data = files.at(index).load();
         if (excelReport) {
-            ReportExcel report(data);
-            report.show();
+            ReportExcel reporter(data);
+            reporter.show();
         } else {
-            ReportConsole report(data);
-            report.show();
+            ReportConsole reporter(data);
+            reporter.show();
         }
     }
     void Results::menu()

src/Platform/platformUtils.cc

@@ -69,11 +69,12 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
         Xd = torch::zeros({ static_cast<int>(Xr[0].size()), static_cast<int>(Xr.size()) }, torch::kInt32);
         for (int i = 0; i < features.size(); ++i) {
             states[features[i]] = vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
-            iota(begin(states[features[i]]), end(states[features[i]]), 0);
+            auto item = states.at(features[i]);
+            iota(begin(item), end(item), 0);
             Xd.index_put_({ "...", i }, torch::tensor(Xr[i], torch::kInt32));
         }
         states[className] = vector<int>(*max_element(y.begin(), y.end()) + 1);
-        iota(begin(states[className]), end(states[className]), 0);
+        iota(begin(states.at(className)), end(states.at(className)), 0);
     } else {
         Xd = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, torch::kFloat32);
         for (int i = 0; i < features.size(); ++i) {