Merge branch 'main' into TANNew

Complete AODELd
Rename suffix of proposal classifier to Ld
2023-08-06 11:40:10 +02:00 · 2023-08-06 11:31:44 +02:00 · 2023-08-05 23:23:31 +02:00 · 2023-08-05 23:11:36 +02:00 · 2023-08-05 20:29:05 +02:00 · 2023-08-05 18:39:48 +02:00
48 changed files with 921 additions and 253 deletions
--- a/.vscode/launch.json
+++ b/.vscode/launch.json
@@ -10,12 +10,13 @@
                "-d",
                "iris",
                "-m",
-                "TAN",
+                "KDB",
+                "-s",
+                "271",
                "-p",
-                "../../data/",
-                "--tensors"
+                "/Users/rmontanana/Code/discretizbench/datasets/",
            ],
-            "cwd": "${workspaceFolder}/build/sample/",
+            //"cwd": "${workspaceFolder}/build/sample/",
        },
        {
            "type": "lldb",
@@ -24,17 +25,14 @@
            "program": "${workspaceFolder}/build/src/Platform/main",
            "args": [
                "-m",
-                "TAN",
+                "AODELd",
                "-p",
                "/Users/rmontanana/Code/discretizbench/datasets",
-                "--discretize",
                "--stratified",
-                "--title",
-                "Debug test",
                "-d",
-                "ionosphere"
+                "iris"
            ],
-            "cwd": "${workspaceFolder}/build/src/Platform",
+            "cwd": "/Users/rmontanana/Code/discretizbench",
        },
        {
            "name": "Build & debug active file",
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -7,10 +7,14 @@ project(BayesNet
  LANGUAGES CXX
 )

+if (CODE_COVERAGE AND NOT ENABLE_TESTING)
+  MESSAGE(FATAL_ERROR "Code coverage requires testing enabled")
+endif (CODE_COVERAGE AND NOT ENABLE_TESTING)
+
 find_package(Torch REQUIRED)

 if (POLICY CMP0135)
-    cmake_policy(SET CMP0135 NEW)
+  cmake_policy(SET CMP0135 NEW)
 endif ()

 # Global CMake variables
@@ -24,24 +28,31 @@ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
 # Options
 # -------
 option(ENABLE_CLANG_TIDY "Enable to add clang tidy."              OFF)
-option(ENABLE_TESTING "Unit testing build"                        ON)
-option(CODE_COVERAGE "Collect coverage from test library"         ON)
-
-set(CMAKE_BUILD_TYPE "Debug")
+option(ENABLE_TESTING "Unit testing build"                        OFF)
+option(CODE_COVERAGE "Collect coverage from test library"         OFF)

 # CMakes modules
 # --------------
 set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})

 include(AddGitSubmodule)
-include(StaticAnalyzers) # clang-tidy
-include(CodeCoverage)
+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(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
+endif (CODE_COVERAGE)
+
+if (ENABLE_CLANG_TIDY)
+  include(StaticAnalyzers) # clang-tidy
+endif (ENABLE_CLANG_TIDY)

 # External libraries - dependencies of BayesNet
 # ---------------------------------------------
 # include(FetchContent)
 add_git_submodule("lib/mdlp")
-add_git_submodule("lib/catch2")
 add_git_submodule("lib/argparse")
 add_git_submodule("lib/json")

@@ -59,18 +70,11 @@ file(GLOB Platform_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/Platform

 # Testing
 # -------
+
 if (ENABLE_TESTING)
  MESSAGE("Testing enabled")
-  enable_testing()
-  if (CODE_COVERAGE)
-    #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(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
-  endif (CODE_COVERAGE)
-  #find_package(Catch2 3 REQUIRED)
+  add_git_submodule("lib/catch2")
+  
  include(CTest)
-  #include(Catch)
  add_subdirectory(tests)
 endif (ENABLE_TESTING)
--- a/26
+++ b/26
@@ -14,16 +14,30 @@ setup: ## Install dependencies for tests and coverage
 dependency: ## Create a dependency graph diagram of the project (build/dependency.png)
 	cd build && cmake .. --graphviz=dependency.dot && dot -Tpng dependency.dot -o dependency.png

-build: ## Build the project
-	@echo ">>> Building BayesNet ...";
+build: ## Build the main and BayesNetSample
+	cmake --build build -t main -t BayesNetSample -j 32
+
+clean: ## Clean the debug info
+	@echo ">>> Cleaning Debug BayesNet ...";
+	find . -name "*.gcda" -print0 | xargs -0 rm
+	@echo ">>> Done";
+
+debug: ## Build a debug version of the project
+	@echo ">>> Building Debug BayesNet ...";
 	@if [ -d ./build ]; then rm -rf ./build; fi
 	@mkdir build; 
-	cmake -S . -B build; \
-	cd build; \
-	make; \
-	
+	cmake -S . -B build -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CODE_COVERAGE=ON; \
+	cmake --build build -j 32;
 	@echo ">>> Done";

+release: ## Build a Release version of the project
+	@echo ">>> Building Release BayesNet ...";
+	@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;
+	@echo ">>> Done";	
+
 test: ## Run tests
 	@echo "* Running tests...";
 	find . -name "*.gcda" -print0 | xargs -0 rm
--- a/TAN_iris.dot
+++ b/TAN_iris.dot
@@ -0,0 +1,12 @@
+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 }
--- a/gcovr.cfg
+++ b/gcovr.cfg
@@ -1,5 +1,4 @@
 filter = src/
-exclude = external/
-exclude = tests/
+exclude-directories = build/lib/
 print-summary = yes
 sort-percentage = yes
--- a/lib/mdlp
+++ b/lib/mdlp
--- a/sample/sample.cc
+++ b/sample/sample.cc
@@ -1,7 +1,6 @@
 #include <iostream>
 #include <torch/torch.h>
 #include <string>
-#include <thread>
 #include <map>
 #include <argparse/argparse.hpp>
 #include "ArffFiles.h"
@@ -42,7 +41,7 @@ bool file_exists(const std::string& name)
 }
 pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vector<vector<int>> X, vector<int> y)
 {
-    vector<vector<int>> Xr;
+    vector<vector<int>> Xr; // nxm
    vector<int> yr;
    for (int col = 0; col < X.size(); ++col) {
        Xr.push_back(vector<int>());
@@ -96,6 +95,7 @@ int main(int argc, char** argv)
            }
    );
    program.add_argument("--discretize").help("Discretize input dataset").default_value(false).implicit_value(true);
+    program.add_argument("--dumpcpt").help("Dump CPT Tables").default_value(false).implicit_value(true);
    program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value(false).implicit_value(true);
    program.add_argument("--tensors").help("Use tensors to store samples").default_value(false).implicit_value(true);
    program.add_argument("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const string& value) {
@@ -113,7 +113,7 @@ int main(int argc, char** argv)
            throw runtime_error("Number of folds must be an integer");
        }});
    program.add_argument("-s", "--seed").help("Random seed").default_value(-1).scan<'i', int>();
-    bool class_last, stratified, tensors;
+    bool class_last, stratified, tensors, dump_cpt;
    string model_name, file_name, path, complete_file_name;
    int nFolds, seed;
    try {
@@ -126,6 +126,7 @@ int main(int argc, char** argv)
        tensors = program.get<bool>("tensors");
        nFolds = program.get<int>("folds");
        seed = program.get<int>("seed");
+        dump_cpt = program.get<bool>("dumpcpt");
        class_last = datasets[file_name];
        if (!file_exists(complete_file_name)) {
            throw runtime_error("Data File " + path + file_name + ".arff" + " does not exist");
@@ -161,61 +162,75 @@ int main(int argc, char** argv)
    states[className] = vector<int>(maxes[className]);
    auto clf = platform::Models::instance()->create(model_name);
    clf->fit(Xd, y, features, className, states);
-    auto score = clf->score(Xd, y);
+    if (dump_cpt) {
+        cout << "--- CPT Tables ---" << endl;
+        clf->dump_cpt();
+    }
    auto lines = clf->show();
-    auto graph = clf->graph();
    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 dot_file = model_name + "_" + file_name;
-    ofstream file(dot_file + ".dot");
-    file << graph;
-    file.close();
-    cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
-    cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
-    string stratified_string = stratified ? " Stratified" : "";
-    cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
-    cout << "==========================================" << endl;
-    torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
-    torch::Tensor yt = torch::tensor(y, torch::kInt32);
-    for (int i = 0; i < features.size(); ++i) {
-        Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
-    }
-    float total_score = 0, total_score_train = 0, score_train, score_test;
-    Fold* fold;
-    if (stratified)
-        fold = new StratifiedKFold(nFolds, y, seed);
-    else
-        fold = new KFold(nFolds, y.size(), seed);
-    for (auto i = 0; i < nFolds; ++i) {
-        auto [train, test] = fold->getFold(i);
-        cout << "Fold: " << i + 1 << endl;
-        if (tensors) {
-            auto ttrain = torch::tensor(train, torch::kInt64);
-            auto ttest = torch::tensor(test, torch::kInt64);
-            torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
-            torch::Tensor ytraint = yt.index({ ttrain });
-            torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
-            torch::Tensor ytestt = yt.index({ ttest });
-            clf->fit(Xtraint, ytraint, features, className, states);
-            score_train = clf->score(Xtraint, ytraint);
-            score_test = clf->score(Xtestt, ytestt);
-        } else {
-            auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
-            auto [Xtest, ytest] = extract_indices(test, Xd, y);
-            clf->fit(Xtrain, ytrain, features, className, states);
-            score_train = clf->score(Xtrain, ytrain);
-            score_test = clf->score(Xtest, ytest);
-        }
-        total_score_train += score_train;
-        total_score += score_test;
-        cout << "Score Train: " << score_train << endl;
-        cout << "Score Test : " << score_test << endl;
-        cout << "-------------------------------------------------------------------------------" << endl;
-    }
-    cout << "**********************************************************************************" << endl;
-    cout << "Average Score Train: " << total_score_train / nFolds << endl;
-    cout << "Average Score Test : " << total_score / nFolds << endl;
-    return 0;
+    // auto graph = clf->graph();
+    // auto dot_file = model_name + "_" + file_name;
+    // ofstream file(dot_file + ".dot");
+    // file << graph;
+    // file.close();
+    // cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
+    // cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
+    // string stratified_string = stratified ? " Stratified" : "";
+    // cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
+    // cout << "==========================================" << endl;
+    // torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
+    // torch::Tensor yt = torch::tensor(y, torch::kInt32);
+    // for (int i = 0; i < features.size(); ++i) {
+    //     Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
+    // }
+    // float total_score = 0, total_score_train = 0, score_train, score_test;
+    // Fold* fold;
+    // if (stratified)
+    //     fold = new StratifiedKFold(nFolds, y, seed);
+    // else
+    //     fold = new KFold(nFolds, y.size(), seed);
+    // for (auto i = 0; i < nFolds; ++i) {
+    //     auto [train, test] = fold->getFold(i);
+    //     cout << "Fold: " << i + 1 << endl;
+    //     if (tensors) {
+    //         auto ttrain = torch::tensor(train, torch::kInt64);
+    //         auto ttest = torch::tensor(test, torch::kInt64);
+    //         torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
+    //         torch::Tensor ytraint = yt.index({ ttrain });
+    //         torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
+    //         torch::Tensor ytestt = yt.index({ ttest });
+    //         clf->fit(Xtraint, ytraint, features, className, states);
+    //         auto temp = clf->predict(Xtraint);
+    //         score_train = clf->score(Xtraint, ytraint);
+    //         score_test = clf->score(Xtestt, ytestt);
+    //     } else {
+    //         auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
+    //         auto [Xtest, ytest] = extract_indices(test, Xd, y);
+    //         clf->fit(Xtrain, ytrain, features, className, states);
+    //         score_train = clf->score(Xtrain, ytrain);
+    //         score_test = clf->score(Xtest, ytest);
+    //     }
+    //     if (dump_cpt) {
+    //         cout << "--- CPT Tables ---" << endl;
+    //         clf->dump_cpt();
+    //     }
+    //     total_score_train += score_train;
+    //     total_score += score_test;
+    //     cout << "Score Train: " << score_train << endl;
+    //     cout << "Score Test : " << score_test << endl;
+    //     cout << "-------------------------------------------------------------------------------" << endl;
+    // }
+    // cout << "**********************************************************************************" << endl;
+    // cout << "Average Score Train: " << total_score_train / nFolds << endl;
+    // cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
 }
--- a/src/BayesNet/AODE.cc
+++ b/src/BayesNet/AODE.cc
@@ -9,7 +9,7 @@ namespace bayesnet {
            models.push_back(std::make_unique<SPODE>(i));
        }
    }
-    vector<string> AODE::graph(string title)
+    vector<string> AODE::graph(const string& title)
    {
        return Ensemble::graph(title);
    }
--- a/src/BayesNet/AODE.h
+++ b/src/BayesNet/AODE.h
@@ -9,7 +9,7 @@ namespace bayesnet {
    public:
        AODE();
        virtual ~AODE() {};
-        vector<string> graph(string title = "AODE") override;
+        vector<string> graph(const string& title = "AODE") override;
    };
 }
 #endif
--- a/src/BayesNet/AODELd.cc
+++ b/src/BayesNet/AODELd.cc
@@ -0,0 +1,34 @@
+#include "AODELd.h"
+
+namespace bayesnet {
+    using namespace std;
+    AODELd::AODELd() : Ensemble(), Proposal(Ensemble::Xv, Ensemble::yv, features, className) {}
+    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        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;
+        return *this;
+    }
+    void AODELd::train()
+    {
+        models.clear();
+        for (int i = 0; i < features.size(); ++i) {
+            models.push_back(std::make_unique<SPODELd>(i));
+        }
+    }
+    Tensor AODELd::predict(Tensor& X)
+    {
+        return Ensemble::predict(X);
+    }
+    vector<string> AODELd::graph(const string& name)
+    {
+        return Ensemble::graph(name);
+    }
+}
--- a/src/BayesNet/AODELd.h
+++ b/src/BayesNet/AODELd.h
@@ -0,0 +1,20 @@
+#ifndef AODELD_H
+#define AODELD_H
+#include "Ensemble.h"
+#include "Proposal.h"
+#include "SPODELd.h"
+
+namespace bayesnet {
+    using namespace std;
+    class AODELd : public Ensemble, public Proposal {
+    public:
+        AODELd();
+        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;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !AODELD_H
--- a/src/BayesNet/BaseClassifier.h
+++ b/src/BayesNet/BaseClassifier.h
@@ -6,8 +6,12 @@ namespace bayesnet {
    using namespace std;
    class BaseClassifier {
    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() = 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;
@@ -15,9 +19,10 @@ namespace bayesnet {
        int virtual getNumberOfEdges() = 0;
        int virtual getNumberOfStates() = 0;
        vector<string> virtual show() = 0;
-        vector<string> virtual graph(string title = "") = 0;
-        virtual ~BaseClassifier() = default;
+        vector<string> virtual graph(const string& title = "") = 0;
        const string inline getVersion() const { return "0.1.0"; };
+        vector<string> virtual topological_order() = 0;
+        void virtual dump_cpt() = 0;
    };
 }
 #endif
--- a/src/BayesNet/BayesMetrics.cc
+++ b/src/BayesNet/BayesMetrics.cc
@@ -1,6 +1,7 @@
 #include "BayesMetrics.h"
 #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)
        : samples(samples)
        , features(features)
@@ -8,6 +9,7 @@ namespace bayesnet {
        , classNumStates(classNumStates)
    {
    }
+    //samples is nxm vector used to fit the model
    Metrics::Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates)
        : features(features)
        , className(className)
@@ -15,9 +17,9 @@ namespace bayesnet {
        , samples(torch::zeros({ static_cast<int>(vsamples[0].size()), static_cast<int>(vsamples.size() + 1) }, torch::kInt32))
    {
        for (int i = 0; i < vsamples.size(); ++i) {
-            samples.index_put_({ "...", i }, torch::tensor(vsamples[i], torch::kInt32));
+            samples.index_put_({ i,  "..." }, torch::tensor(vsamples[i], torch::kInt32));
        }
-        samples.index_put_({ "...", -1 }, torch::tensor(labels, torch::kInt32));
+        samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
    }
    vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
    {
@@ -39,17 +41,17 @@ namespace bayesnet {
        // Compute class prior
        auto margin = torch::zeros({ classNumStates });
        for (int value = 0; value < classNumStates; ++value) {
-            auto mask = samples.index({ "...", -1 }) == value;
-            margin[value] = mask.sum().item<float>() / samples.sizes()[0];
+            auto mask = samples.index({ -1,  "..." }) == value;
+            margin[value] = mask.sum().item<float>() / samples.size(1);
        }
        for (auto [first, second] : combinations) {
            int index_first = find(features.begin(), features.end(), first) - features.begin();
            int index_second = find(features.begin(), features.end(), second) - features.begin();
            double accumulated = 0;
            for (int value = 0; value < classNumStates; ++value) {
-                auto mask = samples.index({ "...", -1 }) == value;
-                auto first_dataset = samples.index({ mask, index_first });
-                auto second_dataset = samples.index({ mask, index_second });
+                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>();
                accumulated += pb * mi;
@@ -67,6 +69,7 @@ namespace bayesnet {
        }
        return matrix;
    }
+    // To use in Python
    vector<float> Metrics::conditionalEdgeWeights()
    {
        auto matrix = conditionalEdge();
--- a/src/BayesNet/BayesMetrics.h
+++ b/src/BayesNet/BayesMetrics.h
@@ -8,7 +8,7 @@ namespace bayesnet {
    using namespace torch;
    class Metrics {
    private:
-        Tensor samples;
+        Tensor samples; // nxm tensor used to fit the model
        vector<string> features;
        string className;
        int classNumStates = 0;
@@ -19,7 +19,7 @@ namespace bayesnet {
        double entropy(Tensor&);
        double conditionalEntropy(Tensor&, Tensor&);
        double mutualInformation(Tensor&, Tensor&);
-        vector<float> conditionalEdgeWeights();
+        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);
--- a/src/BayesNet/CMakeLists.txt
+++ b/src/BayesNet/CMakeLists.txt
@@ -1,2 +1,5 @@
-add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc Mst.cc)
-target_link_libraries(BayesNet "${TORCH_LIBRARIES}")
+include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
+include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
+add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 
+    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc)
+target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")
--- a/src/BayesNet/Classifier.cc
+++ b/src/BayesNet/Classifier.cc
@@ -7,15 +7,17 @@ namespace bayesnet {
    Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
    Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
    {
-        dataset = torch::cat({ X, y.view({y.size(0), 1}) }, 1);
+        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;
        checkFitParameters();
        auto n_classes = states[className].size();
-        metrics = Metrics(dataset, features, className, n_classes);
+        metrics = Metrics(samples, features, className, n_classes);
+        model.initialize();
        train();
-        if (Xv == vector<vector<int>>()) {
+        if (Xv.empty()) {
            // fit with tensors
            model.fit(X, y, features, className);
        } else {
@@ -25,22 +27,27 @@ namespace bayesnet {
        fitted = true;
        return *this;
    }
+    // 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 = torch::transpose(X, 0, 1);
+        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));
+        }
+    }
+    // X is nxm where n is the number of features and m the number of samples
    Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
    {
-        this->X = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, kInt32);
        Xv = X;
-        for (int i = 0; i < X.size(); ++i) {
-            this->X.index_put_({ "...", i }, torch::tensor(X[i], kInt32));
-        }
+        generateTensorXFromVector();
        this->y = torch::tensor(y, kInt32);
        yv = y;
        return build(features, className, states);
@@ -48,8 +55,8 @@ namespace bayesnet {
    void Classifier::checkFitParameters()
    {
        auto sizes = X.sizes();
-        m = sizes[0];
-        n = sizes[1];
+        m = sizes[1];
+        n = sizes[0];
        if (m != y.size(0)) {
            throw invalid_argument("X and y must have the same number of samples");
        }
@@ -65,23 +72,12 @@ namespace bayesnet {
            }
        }
    }
-
    Tensor Classifier::predict(Tensor& X)
    {
        if (!fitted) {
            throw logic_error("Classifier has not been fitted");
        }
-        auto m_ = X.size(0);
-        auto n_ = X.size(1);
-        //auto Xt = torch::transpose(X, 0, 1);
-        vector<vector<int>> Xd(n_, vector<int>(m_, 0));
-        for (auto i = 0; i < n_; i++) {
-            auto temp = X.index({ "...", i });
-            Xd[i] = vector<int>(temp.data_ptr<int>(), temp.data_ptr<int>() + temp.numel());
-        }
-        auto yp = model.predict(Xd);
-        auto ypred = torch::tensor(yp, torch::kInt32);
-        return ypred;
+        return model.predict(X);
    }
    vector<int> Classifier::predict(vector<vector<int>>& X)
    {
@@ -102,8 +98,7 @@ namespace bayesnet {
        if (!fitted) {
            throw logic_error("Classifier has not been fitted");
        }
-        auto Xt = torch::transpose(X, 0, 1);
-        Tensor y_pred = predict(Xt);
+        Tensor y_pred = predict(X);
        return (y_pred == y).sum().item<float>() / y.size(0);
    }
    float Classifier::score(vector<vector<int>>& X, vector<int>& y)
@@ -111,13 +106,7 @@ namespace bayesnet {
        if (!fitted) {
            throw logic_error("Classifier has not been fitted");
        }
-        auto m_ = X[0].size();
-        auto n_ = X.size();
-        vector<vector<int>> Xd(n_, vector<int>(m_, 0));
-        for (auto i = 0; i < n_; i++) {
-            Xd[i] = vector<int>(X[i].begin(), X[i].end());
-        }
-        return model.score(Xd, y);
+        return model.score(X, y);
    }
    vector<string> Classifier::show()
    {
@@ -126,10 +115,10 @@ namespace bayesnet {
    void Classifier::addNodes()
    {
        // Add all nodes to the network
-        for (auto feature : features) {
-            model.addNode(feature, states[feature].size());
+        for (const auto& feature : features) {
+            model.addNode(feature);
        }
-        model.addNode(className, states[className].size());
+        model.addNode(className);
    }
    int Classifier::getNumberOfNodes()
    {
@@ -144,4 +133,13 @@ namespace bayesnet {
    {
        return fitted ? model.getStates() : 0;
    }
+    vector<string> Classifier::topological_order()
+    {
+        return model.topological_sort();
+    }
+    void Classifier::dump_cpt()
+    {
+        model.dump_cpt();
+    }
+
 }
--- a/src/BayesNet/Classifier.h
+++ b/src/BayesNet/Classifier.h
@@ -15,16 +15,17 @@ namespace bayesnet {
    protected:
        Network model;
        int m, n; // m: number of samples, n: number of features
-        Tensor X;
-        vector<vector<int>> Xv;
+        Tensor X; // nxm tensor
+        vector<vector<int>> Xv; // nxm vector
        Tensor y;
        vector<int> yv;
-        Tensor dataset;
+        Tensor samples; // (n+1)xm tensor
        Metrics metrics;
        vector<string> features;
        string className;
        map<string, vector<int>> states;
        void checkFitParameters();
+        void generateTensorXFromVector();
        virtual void train() = 0;
    public:
        Classifier(Network model);
@@ -35,11 +36,13 @@ namespace bayesnet {
        int getNumberOfNodes() override;
        int getNumberOfEdges() override;
        int getNumberOfStates() override;
-        Tensor predict(Tensor& X);
+        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;
    };
 }
 #endif
--- a/src/BayesNet/Ensemble.cc
+++ b/src/BayesNet/Ensemble.cc
@@ -3,25 +3,39 @@
 namespace bayesnet {
    using namespace torch;

-    Ensemble::Ensemble() : m(0), n(0), n_models(0), metrics(Metrics()), fitted(false) {}
+    Ensemble::Ensemble() : n_models(0), metrics(Metrics()), fitted(false) {}
    Ensemble& Ensemble::build(vector<string>& features, string className, map<string, vector<int>>& states)
    {
-        dataset = cat({ X, y.view({y.size(0), 1}) }, 1);
+        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(dataset, features, className, n_classes);
+        metrics = Metrics(samples, features, className, n_classes);
        // Build models
        train();
        // Train models
        n_models = models.size();
        for (auto i = 0; i < n_models; ++i) {
-            models[i]->fit(Xv, yv, features, className, states);
+            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);
+            }
        }
        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;
@@ -32,40 +46,48 @@ namespace bayesnet {
    }
    Ensemble& Ensemble::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
    {
-        this->X = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, kInt32);
        Xv = X;
-        for (int i = 0; i < X.size(); ++i) {
-            this->X.index_put_({ "...", i }, torch::tensor(X[i], kInt32));
-        }
+        generateTensorXFromVector();
        this->y = torch::tensor(y, kInt32);
        yv = y;
        return build(features, className, states);
    }
-    Tensor Ensemble::predict(Tensor& X)
-    {
-        if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
-        }
-        Tensor y_pred = torch::zeros({ X.size(0), n_models }, kInt32);
-        for (auto i = 0; i < n_models; ++i) {
-            y_pred.index_put_({ "...", i }, models[i]->predict(X));
-        }
-        return torch::tensor(voting(y_pred));
-    }
    vector<int> Ensemble::voting(Tensor& y_pred)
    {
        auto y_pred_ = y_pred.accessor<int, 2>();
        vector<int> y_pred_final;
        for (int i = 0; i < y_pred.size(0); ++i) {
-            vector<float> votes(states[className].size(), 0);
+            vector<float> votes(y_pred.size(1), 0);
            for (int j = 0; j < y_pred.size(1); ++j) {
                votes[y_pred_[i][j]] += 1;
            }
+            // argsort in descending order
            auto indices = argsort(votes);
            y_pred_final.push_back(indices[0]);
        }
        return y_pred_final;
    }
+    Tensor Ensemble::predict(Tensor& X)
+    {
+        if (!fitted) {
+            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) {
+            threads.push_back(thread([&, i]() {
+                auto ypredict = models[i]->predict(X);
+                lock_guard<mutex> lock(mtx);
+                y_pred.index_put_({ "...", i }, ypredict);
+                }));
+        }
+        for (auto& thread : threads) {
+            thread.join();
+        }
+        return torch::tensor(voting(y_pred));
+    }
    vector<int> Ensemble::predict(vector<vector<int>>& X)
    {
        if (!fitted) {
@@ -121,7 +143,7 @@ namespace bayesnet {
        }
        return result;
    }
-    vector<string> Ensemble::graph(string title)
+    vector<string> Ensemble::graph(const string& title)
    {
        auto result = vector<string>();
        for (auto i = 0; i < n_models; ++i) {
--- a/src/BayesNet/Ensemble.h
+++ b/src/BayesNet/Ensemble.h
@@ -10,29 +10,29 @@ using namespace torch;
 namespace bayesnet {
    class Ensemble : public BaseClassifier {
    private:
-        bool fitted;
-        long n_models;
        Ensemble& build(vector<string>& features, string className, map<string, vector<int>>& states);
    protected:
+        unsigned n_models;
+        bool fitted;
        vector<unique_ptr<Classifier>> models;
-        int m, n; // m: number of samples, n: number of features
        Tensor X;
        vector<vector<int>> Xv;
        Tensor y;
        vector<int> yv;
-        Tensor dataset;
+        Tensor samples;
        Metrics metrics;
        vector<string> features;
        string className;
        map<string, vector<int>> states;
        void virtual train() = 0;
        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);
+        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;
@@ -40,7 +40,14 @@ namespace bayesnet {
        int getNumberOfEdges() override;
        int getNumberOfStates() override;
        vector<string> show() override;
-        vector<string> graph(string title) override;
+        vector<string> graph(const string& title) override;
+        vector<string> topological_order() override
+        {
+            return vector<string>();
+        }
+        void dump_cpt() override
+        {
+        }
    };
 }
 #endif
--- a/src/BayesNet/KDB.cc
+++ b/src/BayesNet/KDB.cc
@@ -27,9 +27,10 @@ namespace bayesnet {
        */
        // 1. For each feature Xi, compute mutual information, I(X;C),
        // where C is the class.
+        addNodes();
        vector <float> mi;
        for (auto i = 0; i < features.size(); i++) {
-            Tensor firstFeature = X.index({ "...", i });
+            Tensor firstFeature = X.index({ i, "..." });
            mi.push_back(metrics.mutualInformation(firstFeature, y));
        }
        // 2. Compute class conditional mutual information I(Xi;XjIC), f or each
@@ -38,14 +39,12 @@ namespace bayesnet {
        vector<int> S;
        // 4. Let the DAG network being constructed, BN, begin with a single
        // class node, C.
-        model.addNode(className, states[className].size());
        // 5. Repeat until S includes all domain features
        // 5.1. Select feature Xmax which is not in S and has the largest value
        // I(Xmax;C).
        auto order = argsort(mi);
        for (auto idx : order) {
            // 5.2. Add a node to BN representing Xmax.
-            model.addNode(features[idx], states[features[idx]].size());
            // 5.3. Add an arc from C to Xmax in BN.
            model.addEdge(className, features[idx]);
            // 5.4. Add m = min(lSl,/c) arcs from m distinct features Xj in S with
@@ -79,11 +78,12 @@ namespace bayesnet {
            exit_cond = num == n_edges || candidates.size(0) == 0;
        }
    }
-    vector<string> KDB::graph(string title)
+    vector<string> KDB::graph(const string& title)
    {
+        string header{ title };
        if (title == "KDB") {
-            title += " (k=" + to_string(k) + ", theta=" + to_string(theta) + ")";
+            header += " (k=" + to_string(k) + ", theta=" + to_string(theta) + ")";
        }
-        return model.graph(title);
+        return model.graph(header);
    }
 }
--- a/src/BayesNet/KDB.h
+++ b/src/BayesNet/KDB.h
@@ -15,7 +15,7 @@ namespace bayesnet {
    public:
        explicit KDB(int k, float theta = 0.03);
        virtual ~KDB() {};
-        vector<string> graph(string name = "KDB") override;
+        vector<string> graph(const string& name = "KDB") override;
    };
 }
 #endif
--- a/src/BayesNet/KDBLd.cc
+++ b/src/BayesNet/KDBLd.cc
@@ -0,0 +1,35 @@
+#include "KDBLd.h"
+
+namespace bayesnet {
+    using namespace std;
+    KDBLd::KDBLd(int k) : KDB(k), Proposal(KDB::Xv, KDB::yv, features, className) {}
+    KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        fit_local_discretization(states, y);
+        generateTensorXFromVector();
+        // 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);
+        return *this;
+    }
+    Tensor KDBLd::predict(Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return KDB::predict(Xt);
+    }
+    vector<string> KDBLd::graph(const string& name)
+    {
+        return KDB::graph(name);
+    }
+}
--- a/src/BayesNet/KDBLd.h
+++ b/src/BayesNet/KDBLd.h
@@ -0,0 +1,19 @@
+#ifndef KDBLD_H
+#define KDBLD_H
+#include "KDB.h"
+#include "Proposal.h"
+
+namespace bayesnet {
+    using namespace std;
+    class KDBLd : public KDB, public Proposal {
+    private:
+    public:
+        explicit KDBLd(int k);
+        virtual ~KDBLd() = default;
+        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        vector<string> graph(const string& name = "KDB") override;
+        Tensor predict(Tensor& X) override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !KDBLD_H
--- a/src/BayesNet/Network.cc
+++ b/src/BayesNet/Network.cc
@@ -3,15 +3,26 @@
 #include "Network.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
-    Network::Network() : laplaceSmoothing(1), features(vector<string>()), className(""), classNumStates(0), maxThreads(0.8), fitted(false) {}
-    Network::Network(float maxT) : laplaceSmoothing(1), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
+    Network::Network() : 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)
+    Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.
+        getmaxThreads()), fitted(other.fitted)
    {
        for (const auto& pair : other.nodes) {
            nodes[pair.first] = std::make_unique<Node>(*pair.second);
        }
    }
+    void Network::initialize()
+    {
+        features = vector<string>();
+        className = "";
+        classNumStates = 0;
+        fitted = false;
+        nodes.clear();
+        dataset.clear();
+        samples = torch::Tensor();
+    }
    float Network::getmaxThreads()
    {
        return maxThreads;
@@ -20,18 +31,18 @@ namespace bayesnet {
    {
        return samples;
    }
-    void Network::addNode(const string& name, int numStates)
+    void Network::addNode(const string& name)
    {
+        if (name == "") {
+            throw invalid_argument("Node name cannot be empty");
+        }
+        if (nodes.find(name) != nodes.end()) {
+            return;
+        }
        if (find(features.begin(), features.end(), name) == features.end()) {
            features.push_back(name);
        }
-        if (nodes.find(name) != nodes.end()) {
-            // if node exists update its number of states and remove parents, children and CPT
-            nodes[name]->clear();
-            nodes[name]->setNumStates(numStates);
-            return;
-        }
-        nodes[name] = std::make_unique<Node>(name, numStates);
+        nodes[name] = std::make_unique<Node>(name);
    }
    vector<string> Network::getFeatures()
    {
@@ -94,45 +105,68 @@ namespace bayesnet {
    {
        return nodes;
    }
+    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className)
+    {
+        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) + ")");
+        }
+        if (n_features != featureNames.size()) {
+            throw invalid_argument("X and features must have the same number of features in Network::fit (" + to_string(n_features) + " != " + to_string(featureNames.size()) + ")");
+        }
+        if (n_features != features.size() - 1) {
+            throw invalid_argument("X and local features must have the same number of features in Network::fit (" + to_string(n_features) + " != " + to_string(features.size() - 1) + ")");
+        }
+        if (find(features.begin(), features.end(), className) == features.end()) {
+            throw invalid_argument("className not found in Network::features");
+        }
+        for (auto& feature : featureNames) {
+            if (find(features.begin(), features.end(), feature) == features.end()) {
+                throw invalid_argument("Feature " + feature + " not found in Network::features");
+            }
+        }
+    }
+    void Network::setStates()
+    {
+        // 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);
+        }
+        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)
    {
-        features = featureNames;
+        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className);
        this->className = className;
        dataset.clear();
-        // Specific part
-        classNumStates = torch::max(y).item<int>() + 1;
-        samples = torch::cat({ X, y.view({ y.size(0), 1 }) }, 1);
+        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
+        samples = torch::cat({ X , ytmp }, 0);
        for (int i = 0; i < featureNames.size(); ++i) {
-            auto column = torch::flatten(X.index({ "...", i }));
-            auto k = vector<int>();
-            for (auto z = 0; z < X.size(0); ++z) {
-                k.push_back(column[z].item<int>());
-            }
-            dataset[featureNames[i]] = k;
+            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();
    }
+    // 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)
    {
-        features = featureNames;
+        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className);
        this->className = className;
        dataset.clear();
-        // Specific part
-        classNumStates = *max_element(labels.begin(), labels.end()) + 1;
-        // Build dataset & tensor of samples
-        samples = torch::zeros({ static_cast<int>(input_data[0].size()), static_cast<int>(input_data.size() + 1) }, torch::kInt32);
+        // Build dataset & 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));
+            samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
        }
        dataset[className] = labels;
-        samples.index_put_({ "...", -1 }, torch::tensor(labels, torch::kInt32));
+        samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
        completeFit();
    }
    void Network::completeFit()
    {
-
+        setStates();
        int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
        if (maxThreadsRunning < 1) {
            maxThreadsRunning = 1;
@@ -170,7 +204,39 @@ namespace bayesnet {
        }
        fitted = true;
    }
+    torch::Tensor Network::predict_tensor(const torch::Tensor& samples, const bool proba)
+    {
+        if (!fitted) {
+            throw logic_error("You must call fit() before calling predict()");
+        }
+        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 });
+            auto psample = predict_sample(sample);
+            auto temp = torch::tensor(psample, torch::kFloat64);
+            //            result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));
+            result.index_put_({ i, "..." }, temp);
+        }
+        if (proba)
+            return result;
+        else
+            return result.argmax(1);
+    }
+    // Return mxn tensor of probabilities
+    Tensor Network::predict_proba(const Tensor& samples)
+    {
+        return predict_tensor(samples, true);
+    }

+    // Return mxn tensor of probabilities
+    Tensor Network::predict(const Tensor& samples)
+    {
+        return predict_tensor(samples, false);
+    }
+
+    // Return mx1 vector of predictions
+    // tsamples is nxm vector of samples
    vector<int> Network::predict(const vector<vector<int>>& tsamples)
    {
        if (!fitted) {
@@ -191,6 +257,7 @@ namespace bayesnet {
        }
        return predictions;
    }
+    // Return mxn vector of probabilities
    vector<vector<double>> Network::predict_proba(const vector<vector<int>>& tsamples)
    {
        if (!fitted) {
@@ -218,12 +285,13 @@ namespace bayesnet {
        }
        return (double)correct / y_pred.size();
    }
+    // Return 1xn vector of probabilities
    vector<double> Network::predict_sample(const vector<int>& sample)
    {
        // Ensure the sample size is equal to the number of features
-        if (sample.size() != features.size()) {
+        if (sample.size() != features.size() - 1) {
            throw invalid_argument("Sample size (" + to_string(sample.size()) +
-                ") does not match the number of features (" + to_string(features.size()) + ")");
+                ") does not match the number of features (" + to_string(features.size() - 1) + ")");
        }
        map<string, int> evidence;
        for (int i = 0; i < sample.size(); ++i) {
@@ -231,6 +299,20 @@ namespace bayesnet {
        }
        return exactInference(evidence);
    }
+    // Return 1xn vector of probabilities
+    vector<double> Network::predict_sample(const Tensor& sample)
+    {
+        // Ensure the sample size is equal to the number of features
+        if (sample.size(0) != features.size() - 1) {
+            throw invalid_argument("Sample size (" + to_string(sample.size(0)) +
+                ") does not match the number of features (" + to_string(features.size() - 1) + ")");
+        }
+        map<string, int> evidence;
+        for (int i = 0; i < sample.size(0); ++i) {
+            evidence[features[i]] = sample[i].item<int>();
+        }
+        return exactInference(evidence);
+    }
    double Network::computeFactor(map<string, int>& completeEvidence)
    {
        double result = 1.0;
@@ -246,17 +328,16 @@ 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; });
@@ -301,4 +382,48 @@ namespace bayesnet {
        }
        return edges;
    }
+    vector<string> Network::topological_sort()
+    {
+        /* Check if al the fathers of every node are before the node */
+        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) {
+                auto fathers = nodes[feature]->getParents();
+                for (const auto& father : fathers) {
+                    auto fatherName = father->getName();
+                    if (fatherName == className) {
+                        continue;
+                    }
+                    // Check if father is placed before the actual feature
+                    auto it = find(result.begin(), result.end(), fatherName);
+                    if (it != result.end()) {
+                        auto it2 = find(result.begin(), result.end(), feature);
+                        if (it2 != result.end()) {
+                            if (distance(it, it2) < 0) {
+                                // if it is not, insert it before the feature
+                                result.erase(remove(result.begin(), result.end(), fatherName), result.end());
+                                result.insert(it2, fatherName);
+                                ending = false;
+                            }
+                        } else {
+                            throw logic_error("Error in topological sort because of node " + feature + " is not in result");
+                        }
+                    } else {
+                        throw logic_error("Error in topological sort because of node father " + fatherName + " is not in result");
+                    }
+                }
+            }
+        }
+        return result;
+    }
+    void Network::dump_cpt()
+    {
+        for (auto& node : nodes) {
+            cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
+        }
+    }
 }
--- a/src/BayesNet/Network.h
+++ b/src/BayesNet/Network.h
@@ -10,14 +10,15 @@ namespace bayesnet {
        map<string, unique_ptr<Node>> nodes;
        map<string, vector<int>> dataset;
        bool fitted;
-        float maxThreads;
+        float maxThreads = 0.95;
        int classNumStates;
-        vector<string> features;
+        vector<string> features; // Including class
        string className;
-        int laplaceSmoothing;
-        torch::Tensor samples;
+        int laplaceSmoothing = 1;
+        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&);
@@ -25,6 +26,8 @@ namespace bayesnet {
        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();
    public:
        Network();
        explicit Network(float, int);
@@ -32,7 +35,7 @@ namespace bayesnet {
        explicit Network(Network&);
        torch::Tensor& getSamples();
        float getmaxThreads();
-        void addNode(const string&, int);
+        void addNode(const string&);
        void addEdge(const string&, const string&);
        map<string, std::unique_ptr<Node>>& getNodes();
        vector<string> getFeatures();
@@ -42,13 +45,19 @@ namespace bayesnet {
        string getClassName();
        void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
        void fit(torch::Tensor&, torch::Tensor&, const vector<string>&, const string&);
-        vector<int> predict(const vector<vector<int>>&);
+        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();
-        vector<vector<double>> predict_proba(const vector<vector<int>>&);
+        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
+        void initialize();
+        void dump_cpt();
        inline string version() { return "0.1.0"; }
    };
 }
--- a/src/BayesNet/Node.cc
+++ b/src/BayesNet/Node.cc
@@ -2,8 +2,8 @@

 namespace bayesnet {

-    Node::Node(const std::string& name, int numStates)
-        : name(name), numStates(numStates), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
+    Node::Node(const std::string& name)
+        : name(name), numStates(0), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
    {
    }
    void Node::clear()
@@ -86,6 +86,7 @@ namespace bayesnet {
    }
    void Node::computeCPT(map<string, vector<int>>& dataset, const int laplaceSmoothing)
    {
+        dimensions.clear();
        // Get dimensions of the CPT
        dimensions.push_back(numStates);
        transform(parents.begin(), parents.end(), back_inserter(dimensions), [](const auto& parent) { return parent->getNumStates(); });
--- a/src/BayesNet/Node.h
+++ b/src/BayesNet/Node.h
@@ -16,7 +16,7 @@ namespace bayesnet {
        vector<int64_t> dimensions; // dimensions of the cpTable
    public:
        vector<pair<string, string>> combinations(const vector<string>&);
-        Node(const string&, int);
+        explicit Node(const string&);
        void clear();
        void addParent(Node*);
        void addChild(Node*);
--- a/src/BayesNet/Proposal.cc
+++ b/src/BayesNet/Proposal.cc
@@ -0,0 +1,102 @@
+#include "Proposal.h"
+#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()
+    {
+        for (auto& [key, value] : discretizers) {
+            delete value;
+        }
+    }
+    void Proposal::localDiscretizationProposal(map<string, vector<int>>& states, 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();
+        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();
+            if (nodeParents.size() < 2) continue; // Only has class as parent
+            upgrade = true;
+            int index = find(pFeatures.begin(), pFeatures.end(), feature) - pFeatures.begin();
+            indicesToReDiscretize.push_back(index); // We need to re-discretize this feature
+            vector<string> parents;
+            transform(nodeParents.begin(), nodeParents.end(), back_inserter(parents), [](const auto& p) { return p->getName(); });
+            // Remove class as parent as it will be added later
+            parents.erase(remove(parents.begin(), parents.end(), pClassName), parents.end());
+            // Get the indices of the parents
+            vector<int> indices;
+            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); });
+            for (auto idx : indices) {
+                for (int i = 0; i < n_samples; ++i) {
+                    yJoinParents[i] += to_string(Xv[idx][i]);
+                }
+            }
+            auto arff = ArffFiles();
+            auto yxv = arff.factorize(yJoinParents);
+            auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
+            auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
+            discretizers[feature]->fit(xvf, yxv);
+            //
+            //
+            //
+            // auto tmp = discretizers[feature]->transform(xvf);
+            // Xv[index] = tmp;
+            // auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
+            // iota(xStates.begin(), xStates.end(), 0);
+            // //Update new states of the feature/node
+            // states[feature] = xStates;
+        }
+        if (upgrade) {
+            // Discretize again X (only the affected indices) with the new fitted discretizers
+            for (auto index : indicesToReDiscretize) {
+                auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
+                auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+                Xv[index] = 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;
+            }
+        }
+    }
+    void Proposal::fit_local_discretization(map<string, vector<int>>& states, 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 input data by feature(row)
+        for (int 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));
+            auto xStates = vector<int>(discretizer->getCutPoints().size() + 1);
+            iota(xStates.begin(), xStates.end(), 0);
+            states[pFeatures[i]] = xStates;
+            discretizers[pFeatures[i]] = discretizer;
+        }
+        int n_classes = torch::max(y).item<int>() + 1;
+        auto yStates = vector<int>(n_classes);
+        iota(yStates.begin(), yStates.end(), 0);
+        states[pClassName] = yStates;
+    }
+    torch::Tensor Proposal::prepareX(torch::Tensor& X)
+    {
+        auto Xtd = torch::zeros_like(X, torch::kInt32);
+        for (int i = 0; i < X.size(0); ++i) {
+            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
+            auto Xd = discretizers[pFeatures[i]]->transform(Xt);
+            Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
+        }
+        return Xtd;
+    }
+}
--- a/src/BayesNet/Proposal.h
+++ b/src/BayesNet/Proposal.h
@@ -0,0 +1,29 @@
+#ifndef PROPOSAL_H
+#define PROPOSAL_H
+#include <string>
+#include <map>
+#include <torch/torch.h>
+#include "Network.h"
+#include "CPPFImdlp.h"
+#include "Classifier.h"
+
+namespace bayesnet {
+    class Proposal {
+    public:
+        Proposal(vector<vector<int>>& Xv_, vector<int>& yv_, 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);
+        torch::Tensor Xf; // X continuous nxm tensor
+        map<string, mdlp::CPPFImdlp*> discretizers;
+    private:
+        vector<string>& pFeatures;
+        string& pClassName;
+        vector<vector<int>>& Xv; // X discrete nxm vector
+        vector<int>& yv;
+    };
+}
+
+#endif
--- a/src/BayesNet/SPODE.cc
+++ b/src/BayesNet/SPODE.cc
@@ -17,7 +17,7 @@ namespace bayesnet {
            }
        }
    }
-    vector<string> SPODE::graph(string name )
+    vector<string> SPODE::graph(const string& name)
    {
        return model.graph(name);
    }
--- a/src/BayesNet/SPODE.h
+++ b/src/BayesNet/SPODE.h
@@ -11,7 +11,7 @@ namespace bayesnet {
    public:
        explicit SPODE(int root);
        virtual ~SPODE() {};
-        vector<string> graph(string name = "SPODE") override;
+        vector<string> graph(const string& name = "SPODE") override;
    };
 }
 #endif
--- a/src/BayesNet/SPODELd.cc
+++ b/src/BayesNet/SPODELd.cc
@@ -0,0 +1,35 @@
+#include "SPODELd.h"
+
+namespace bayesnet {
+    using namespace std;
+    SPODELd::SPODELd(int root) : SPODE(root), Proposal(SPODE::Xv, SPODE::yv, features, className) {}
+    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        fit_local_discretization(states, y);
+        generateTensorXFromVector();
+        // 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);
+        return *this;
+    }
+    Tensor SPODELd::predict(Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return SPODE::predict(Xt);
+    }
+    vector<string> SPODELd::graph(const string& name)
+    {
+        return SPODE::graph(name);
+    }
+}
--- a/src/BayesNet/SPODELd.h
+++ b/src/BayesNet/SPODELd.h
@@ -0,0 +1,19 @@
+#ifndef SPODELD_H
+#define SPODELD_H
+#include "SPODE.h"
+#include "Proposal.h"
+
+namespace bayesnet {
+    using namespace std;
+    class SPODELd : public SPODE, public Proposal {
+    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;
+        Tensor predict(Tensor& X) override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !SPODELD_H
--- a/src/BayesNet/TAN.cc
+++ b/src/BayesNet/TAN.cc
@@ -12,9 +12,9 @@ namespace bayesnet {
        // 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 = dataset.index({ "...", -1 });
+        Tensor class_dataset = samples.index({ -1, "..." });
        for (int i = 0; i < static_cast<int>(features.size()); ++i) {
-            Tensor feature_dataset = dataset.index({ "...", i });
+            Tensor feature_dataset = samples.index({ i, "..." });
            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
            mi.push_back({ i, mi_value });
        }
@@ -34,7 +34,7 @@ namespace bayesnet {
            model.addEdge(className, feature);
        }
    }
-    vector<string> TAN::graph(string title)
+    vector<string> TAN::graph(const string& title)
    {
        return model.graph(title);
    }
--- a/src/BayesNet/TAN.h
+++ b/src/BayesNet/TAN.h
@@ -11,7 +11,7 @@ namespace bayesnet {
    public:
        TAN();
        virtual ~TAN() {};
-        vector<string> graph(string name = "TAN") override;
+        vector<string> graph(const string& name = "TAN") override;
    };
 }
 #endif
--- a/src/BayesNet/TANLd.cc
+++ b/src/BayesNet/TANLd.cc
@@ -0,0 +1,35 @@
+#include "TANLd.h"
+
+namespace bayesnet {
+    using namespace std;
+    TANLd::TANLd() : TAN(), Proposal(TAN::Xv, TAN::yv, features, className) {}
+    TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    {
+        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        fit_local_discretization(states, y);
+        generateTensorXFromVector();
+        // 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);
+        return *this;
+    }
+    Tensor TANLd::predict(Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return TAN::predict(Xt);
+    }
+    vector<string> TANLd::graph(const string& name)
+    {
+        return TAN::graph(name);
+    }
+}
--- a/src/BayesNet/TANLd.h
+++ b/src/BayesNet/TANLd.h
@@ -0,0 +1,19 @@
+#ifndef TANLD_H
+#define TANLD_H
+#include "TAN.h"
+#include "Proposal.h"
+
+namespace bayesnet {
+    using namespace std;
+    class TANLd : public TAN, public Proposal {
+    private:
+    public:
+        TANLd();
+        virtual ~TANLd() = default;
+        TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        vector<string> graph(const string& name = "TAN") override;
+        Tensor predict(Tensor& X) override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !TANLD_H
--- a/src/BayesNet/bayesnetUtils.cc
+++ b/src/BayesNet/bayesnetUtils.cc
@@ -3,6 +3,7 @@
 namespace bayesnet {
    using namespace std;
    using namespace torch;
+    // Return the indices in descending order
    vector<int> argsort(vector<float>& nums)
    {
        int n = nums.size();
--- a/src/Platform/CMakeLists.txt
+++ b/src/Platform/CMakeLists.txt
@@ -4,5 +4,5 @@ include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
 include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
-add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc)
+add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc Report.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
--- a/src/Platform/Datasets.cc
+++ b/src/Platform/Datasets.cc
@@ -207,9 +207,9 @@ namespace platform {
        if (discretize) {
            Xd = discretizeDataset(Xv, yv);
            computeStates();
-            n_samples = Xd[0].size();
-            n_features = Xd.size();
        }
+        n_samples = Xv[0].size();
+        n_features = Xv.size();
        loaded = true;
    }
    void Dataset::buildTensors()
--- a/src/Platform/Experiment.cc
+++ b/src/Platform/Experiment.cc
@@ -1,6 +1,7 @@
 #include "Experiment.h"
 #include "Datasets.h"
 #include "Models.h"
+#include "Report.h"

 namespace platform {
    using json = nlohmann::json;
@@ -86,6 +87,13 @@ namespace platform {
        file.close();
    }

+    void Experiment::report()
+    {
+        json data = build_json();
+        Report report(data);
+        report.show();
+    }
+
    void Experiment::show()
    {
        json data = build_json();
@@ -104,7 +112,7 @@ namespace platform {

    void Experiment::cross_validation(const string& path, const string& fileName)
    {
-        auto datasets = platform::Datasets(path, true, platform::ARFF);
+        auto datasets = platform::Datasets(path, discretized, platform::ARFF);
        // Get dataset
        auto [X, y] = datasets.getTensors(fileName);
        auto states = datasets.getStates(fileName);
@@ -114,7 +122,7 @@ namespace platform {
        cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
        // Prepare Result
        auto result = Result();
-        auto [values, counts] = at::_unique(y);;
+        auto [values, counts] = at::_unique(y);
        result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
        int nResults = nfolds * static_cast<int>(randomSeeds.size());
        auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
--- a/src/Platform/Experiment.h
+++ b/src/Platform/Experiment.h
@@ -108,6 +108,7 @@ namespace platform {
        void cross_validation(const string& path, const string& fileName);
        void go(vector<string> filesToProcess, const string& path);
        void show();
+        void report();
    };
 }
 #endif
--- a/src/Platform/Models.h
+++ b/src/Platform/Models.h
@@ -6,6 +6,10 @@
 #include "TAN.h"
 #include "KDB.h"
 #include "SPODE.h"
+#include "TANLd.h"
+#include "KDBLd.h"
+#include "SPODELd.h"
+#include "AODELd.h"
 namespace platform {
    class Models {
    private:
--- a/src/Platform/Report.cc
+++ b/src/Platform/Report.cc
@@ -0,0 +1,66 @@
+#include "Report.h"
+
+namespace platform {
+    string headerLine(const string& text)
+    {
+        int n = MAXL - text.length() - 3;
+        return "* " + text + string(n, ' ') + "*\n";
+    }
+    string Report::fromVector(const string& key)
+    {
+        string result = "";
+
+        for (auto& item : data[key]) {
+            result += to_string(item) + ", ";
+        }
+        return "[" + result.substr(0, result.length() - 2) + "]";
+    }
+    string fVector(const json& data)
+    {
+        string result = "";
+        for (const auto& item : data) {
+            result += to_string(item) + ", ";
+        }
+        return "[" + result.substr(0, result.length() - 2) + "]";
+    }
+    void Report::show()
+    {
+        header();
+        body();
+    }
+    void Report::header()
+    {
+        cout << string(MAXL, '*') << endl;
+        cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
+        cout << headerLine(data["title"].get<string>());
+        cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
+        cout << headerLine("Execution took  " + to_string(data["duration"].get<float>()) + " seconds,   " + to_string(data["duration"].get<float>() / 3600) + " hours, on " + data["platform"].get<string>());
+        cout << headerLine("Score is " + data["score_name"].get<string>());
+        cout << string(MAXL, '*') << endl;
+        cout << endl;
+    }
+    void Report::body()
+    {
+        cout << "Dataset                        Sampl. Feat. Cls Nodes   Edges   States  Score           Time              Hyperparameters" << endl;
+        cout << "============================== ====== ===== === ======= ======= ======= =============== ================= ===============" << endl;
+        for (const auto& r : data["results"]) {
+            cout << setw(30) << left << r["dataset"].get<string>() << " ";
+            cout << setw(6) << right << r["samples"].get<int>() << " ";
+            cout << setw(5) << right << r["features"].get<int>() << " ";
+            cout << setw(3) << right << r["classes"].get<int>() << " ";
+            cout << setw(7) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
+            cout << setw(7) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
+            cout << setw(7) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
+            cout << setw(8) << right << setprecision(6) << fixed << r["score_test"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_test_std"].get<double>() << " ";
+            cout << setw(10) << right << setprecision(6) << fixed << r["test_time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["test_time_std"].get<double>() << " ";
+            cout << " " << r["hyperparameters"].get<string>();
+            cout << endl;
+            cout << string(MAXL, '*') << endl;
+            cout << headerLine("Train scores: " + fVector(r["scores_train"]));
+            cout << headerLine("Test  scores: " + fVector(r["scores_test"]));
+            cout << headerLine("Train  times: " + fVector(r["times_train"]));
+            cout << headerLine("Test   times: " + fVector(r["times_test"]));
+            cout << string(MAXL, '*') << endl;
+        }
+    }
+}
--- a/src/Platform/Report.h
+++ b/src/Platform/Report.h
@@ -0,0 +1,23 @@
+#ifndef REPORT_H
+#define REPORT_H
+#include <string>
+#include <iostream>
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+const int MAXL = 121;
+namespace platform {
+    using namespace std;
+    class Report {
+    public:
+        explicit Report(json data_) { data = data_; };
+        virtual ~Report() = default;
+        void show();
+    private:
+        void header();
+        void body();
+        string fromVector(const string& key);
+        json data;
+    };
+};
+#endif
--- a/src/Platform/main.cc
+++ b/src/Platform/main.cc
@@ -99,13 +99,13 @@ int main(int argc, char** argv)
        filesToTest = platform::Datasets(path, true, platform::ARFF).getNames();
        saveResults = true;
    }
-
    /*
    * Begin Processing
    */
+    auto env = platform::DotEnv();
    auto experiment = platform::Experiment();
    experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("1.0.0");
-    experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform("BayesNet");
+    experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
    experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
    for (auto seed : seeds) {
        experiment.addRandomSeed(seed);
@@ -117,7 +117,7 @@ int main(int argc, char** argv)
    if (saveResults)
        experiment.save(PATH_RESULTS);
    else
-        experiment.show();
+        experiment.report();
    cout << "Done!" << endl;
    return 0;
 }
--- a/src/Platform/modelRegister.h
+++ b/src/Platform/modelRegister.h
@@ -2,10 +2,18 @@
 #define MODEL_REGISTER_H
 static platform::Registrar registrarT("TAN",
    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TAN();});
+static platform::Registrar registrarTLD("TANLd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TANLd();});
 static platform::Registrar registrarS("SPODE",
    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODE(2);});
+static platform::Registrar registrarSLD("SPODELd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODELd(2);});
 static platform::Registrar registrarK("KDB",
    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDB(2);});
+static platform::Registrar registrarKLD("KDBLd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDBLd(2);});
 static platform::Registrar registrarA("AODE",
    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
+static platform::Registrar registrarALD("AODELd",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODELd();});
 #endif
--- a/tests/BayesNetwork.cc
+++ b/tests/BayesNetwork.cc
@@ -9,29 +9,21 @@ TEST_CASE("Test Bayesian Network")
 {
    auto [Xd, y, features, className, states] = loadFile("iris");

-    SECTION("Test Update Nodes")
-    {
-        auto net = bayesnet::Network();
-        net.addNode("A", 3);
-        REQUIRE(net.getStates() == 3);
-        net.addNode("A", 5);
-        REQUIRE(net.getStates() == 5);
-    }
    SECTION("Test get features")
    {
        auto net = bayesnet::Network();
-        net.addNode("A", 3);
-        net.addNode("B", 5);
+        net.addNode("A");
+        net.addNode("B");
        REQUIRE(net.getFeatures() == vector<string>{"A", "B"});
-        net.addNode("C", 2);
+        net.addNode("C");
        REQUIRE(net.getFeatures() == vector<string>{"A", "B", "C"});
    }
    SECTION("Test get edges")
    {
        auto net = bayesnet::Network();
-        net.addNode("A", 3);
-        net.addNode("B", 5);
-        net.addNode("C", 2);
+        net.addNode("A");
+        net.addNode("B");
+        net.addNode("C");
        net.addEdge("A", "B");
        net.addEdge("B", "C");
        REQUIRE(net.getEdges() == vector<pair<string, string>>{ {"A", "B"}, { "B", "C" } });
Author	SHA1	Message	Date
Ricardo Montañana	2da0fb5d8f	Merge branch 'main' into TANNew	2023-08-06 11:40:10 +02:00
Ricardo Montañana	14ea51648a	Complete AODELd	2023-08-06 11:31:44 +02:00
Ricardo Montañana	9e94f4e140	Rename suffix of proposal classifier to Ld	2023-08-05 23:23:31 +02:00
Ricardo Montañana	1d0fd629c9	Add SPODENew to models	2023-08-05 23:11:36 +02:00
Ricardo Montañana	506ef34c6f	Add report output to main	2023-08-05 20:29:05 +02:00
Ricardo Montañana	7f45495837	Refactor New classifiers to extract predict	2023-08-05 18:39:48 +02:00
Ricardo Montañana	1a09ccca4c	Add KDBNew fix computeCPT error	2023-08-05 14:40:42 +02:00
Ricardo Montañana	a1c6ab18f3	TANNew restructured with poor results	2023-08-04 20:11:22 +02:00
Ricardo Montañana	64ac8fb4f2	TANNew as a TAN variant working	2023-08-04 19:42:18 +02:00
Ricardo Montañana	c568ba111d	Add Proposal class	2023-08-04 13:05:12 +02:00
Ricardo Montañana	45c1d052ac	Compile TANNew with poor accuracy	2023-08-04 01:35:45 +02:00
Ricardo Montañana	eb1cec58a3	Complete nxm	2023-08-03 20:22:33 +02:00
Ricardo Montañana	f520b40016	Almost complete proposal in TANNew	2023-08-02 02:21:55 +02:00
Ricardo Montañana	cdfb45d2cb	Add topological order to Network	2023-08-02 00:56:52 +02:00
Ricardo Montañana	f63a9a64f9	Update Makefile to add Release & Debug build	2023-08-01 19:02:37 +02:00
Ricardo Montañana	285f0938a6	Update mdlp library	2023-08-01 17:33:01 +02:00
Ricardo Montañana	8f8f9773ce	Make TANNew same as TAN with local discretization	2023-08-01 13:17:12 +02:00
Ricardo Montañana	a9ba21560d	Add environment platform to experiment result	2023-08-01 10:55:53 +02:00
Ricardo Montañana	a18fbe5594	Begin implementation	2023-07-31 19:53:55 +02:00
Ricardo Montañana	adf650d257	Max threading	2023-07-31 18:49:18 +02:00
Ricardo Montañana	43bb017d5d	Fix problem with tensors way	2023-07-30 19:00:02 +02:00
Ricardo Montañana	53697648e7	Merge branch 'aftermath' into main	2023-07-30 01:05:31 +02:00