Add date/time to header of report best

Add multiple sheets to excel file
Add format and color to sheets
Add comparison with ZeroR
Add comparison with Best Results
Separate contextual menu from general in manage

.clang-tidy

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

.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 +35,5 @@ build/
 *.dSYM/**
 cmake-build*/**
 .idea
+puml/**
+.vscode/settings.json

.gitmodules

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

.vscode/launch.json

@@ -10,12 +10,13 @@
                 "-d",
                 "iris",
                 "-m",
-                "TAN",
+                "TANLd",
+                "-s",
+                "271",
                 "-p",
-                "../../data/",
-                "--tensors"
+                "/Users/rmontanana/Code/discretizbench/datasets/",
             ],
-            "cwd": "${workspaceFolder}/build/sample/",
+            //"cwd": "${workspaceFolder}/build/sample/",
         },
         {
             "type": "lldb",
@@ -24,17 +25,50 @@
             "program": "${workspaceFolder}/build/src/Platform/main",
             "args": [
                 "-m",
-                "TAN",
+                "BoostAODE",
                 "-p",
                 "/Users/rmontanana/Code/discretizbench/datasets",
-                "--discretize",
                 "--stratified",
-                "--title",
-                "Debug test",
                 "-d",
-                "ionosphere"
+                "mfeat-morphological",
+                "--discretize"
+                // "--hyperparameters",
+                // "{\"repeatSparent\": true, \"maxModels\": 12}"
             ],
-            "cwd": "${workspaceFolder}/build/src/Platform",
+            "cwd": "/Users/rmontanana/Code/discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "best",
+            "program": "${workspaceFolder}/build/src/Platform/best",
+            "args": [
+                "-m",
+                "BoostAODE",
+                "-s",
+                "accuracy",
+                "--build",
+            ],
+            "cwd": "/Users/rmontanana/Code/discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "manage",
+            "program": "${workspaceFolder}/build/src/Platform/manage",
+            "args": [
+                "-n",
+                "20"
+            ],
+            "cwd": "/Users/rmontanana/Code/discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "list",
+            "program": "${workspaceFolder}/build/src/Platform/list",
+            "args": [],
+            "cwd": "/Users/rmontanana/Code/discretizbench",
         },
         {
             "name": "Build & debug active file",

.vscode/settings.json

@@ -1,109 +0,0 @@
-{
-    "files.associations": {
-        "*.rmd": "markdown",
-        "*.py": "python",
-        "vector": "cpp",
-        "__bit_reference": "cpp",
-        "__bits": "cpp",
-        "__config": "cpp",
-        "__debug": "cpp",
-        "__errc": "cpp",
-        "__hash_table": "cpp",
-        "__locale": "cpp",
-        "__mutex_base": "cpp",
-        "__node_handle": "cpp",
-        "__nullptr": "cpp",
-        "__split_buffer": "cpp",
-        "__string": "cpp",
-        "__threading_support": "cpp",
-        "__tuple": "cpp",
-        "array": "cpp",
-        "atomic": "cpp",
-        "bitset": "cpp",
-        "cctype": "cpp",
-        "chrono": "cpp",
-        "clocale": "cpp",
-        "cmath": "cpp",
-        "compare": "cpp",
-        "complex": "cpp",
-        "concepts": "cpp",
-        "cstdarg": "cpp",
-        "cstddef": "cpp",
-        "cstdint": "cpp",
-        "cstdio": "cpp",
-        "cstdlib": "cpp",
-        "cstring": "cpp",
-        "ctime": "cpp",
-        "cwchar": "cpp",
-        "cwctype": "cpp",
-        "exception": "cpp",
-        "initializer_list": "cpp",
-        "ios": "cpp",
-        "iosfwd": "cpp",
-        "istream": "cpp",
-        "limits": "cpp",
-        "locale": "cpp",
-        "memory": "cpp",
-        "mutex": "cpp",
-        "new": "cpp",
-        "optional": "cpp",
-        "ostream": "cpp",
-        "ratio": "cpp",
-        "sstream": "cpp",
-        "stdexcept": "cpp",
-        "streambuf": "cpp",
-        "string": "cpp",
-        "string_view": "cpp",
-        "system_error": "cpp",
-        "tuple": "cpp",
-        "type_traits": "cpp",
-        "typeinfo": "cpp",
-        "unordered_map": "cpp",
-        "variant": "cpp",
-        "algorithm": "cpp",
-        "iostream": "cpp",
-        "iomanip": "cpp",
-        "numeric": "cpp",
-        "set": "cpp",
-        "__tree": "cpp",
-        "deque": "cpp",
-        "list": "cpp",
-        "map": "cpp",
-        "unordered_set": "cpp",
-        "any": "cpp",
-        "condition_variable": "cpp",
-        "forward_list": "cpp",
-        "fstream": "cpp",
-        "stack": "cpp",
-        "thread": "cpp",
-        "__memory": "cpp",
-        "filesystem": "cpp",
-        "*.toml": "toml",
-        "utility": "cpp",
-        "__verbose_abort": "cpp",
-        "bit": "cpp",
-        "random": "cpp",
-        "*.tcc": "cpp",
-        "functional": "cpp",
-        "iterator": "cpp",
-        "memory_resource": "cpp",
-        "format": "cpp",
-        "valarray": "cpp",
-        "regex": "cpp",
-        "span": "cpp",
-        "cfenv": "cpp",
-        "cinttypes": "cpp",
-        "csetjmp": "cpp",
-        "future": "cpp",
-        "queue": "cpp",
-        "typeindex": "cpp",
-        "shared_mutex": "cpp",
-        "*.ipp": "cpp",
-        "cassert": "cpp",
-        "charconv": "cpp",
-        "source_location": "cpp",
-        "ranges": "cpp"
-    },
-    "cmake.configureOnOpen": false,
-    "C_Cpp.default.configurationProvider": "ms-vscode.cmake-tools"
-}

.vscode/tasks.json

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

CMakeLists.txt

@@ -1,16 +1,20 @@
 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
 )
 
+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
@@ -24,26 +28,33 @@ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
 # Options
 # -------
 option(ENABLE_CLANG_TIDY "Enable to add clang tidy."              OFF)
-option(ENABLE_TESTING "Unit testing build"                        ON)
-option(CODE_COVERAGE "Collect coverage from test library"         ON)
-
-set(CMAKE_BUILD_TYPE "Debug")
-
+option(ENABLE_TESTING "Unit testing build"                        OFF)
+option(CODE_COVERAGE "Collect coverage from test library"         OFF)
+SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
 # 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_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage -O0 -g")
+    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")
+find_library(XLSXWRITER_LIB libxlsxwriter.dylib PATHS /usr/local/lib)
 
 # Subdirectories
 # --------------
@@ -59,18 +70,10 @@ 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)

Makefile

@@ -11,17 +11,45 @@ setup: ## Install dependencies for tests and coverage
 		pip install gcovr; \
 	fi
 
+dest ?= ../discretizbench
+copy: ## Copy binary files to selected folder
+	@echo "Destination folder: $(dest)"
+	make build
+	@echo ">>> Copying files to $(dest)"
+	@cp build/src/Platform/main $(dest)
+	@cp build/src/Platform/list $(dest)
+	@cp build/src/Platform/manage $(dest)
+	@cp build/src/Platform/best $(dest)
+	@echo ">>> Done"
+
 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 -t manage -t list -t best -j 32
+
+clean: ## Clean the debug info
+	@echo ">>> Cleaning Debug BayesNet ...";
+	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
 	@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 -t main -t BayesNetSample -t manage -t list -t best -t unit_tests -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 -t manage -t list -t best -j 32;
 	@echo ">>> Done";	
 
 test: ## Run tests

README.md

@@ -2,4 +2,36 @@
 
 Bayesian Network Classifier with libtorch from scratch
 
+## 0. Setup
+
+### libxlswriter
+
+Before compiling BayesNet.
+
+```bash
+cd lib/libxlsxwriter
+make
+sudo make install
+```
+
+It has to be installed in /usr/local/lib otherwise CMakeLists.txt has to be modified accordingly
+
+Environment variable has to be set:
+
+```bash
+ export LD_LIBRARY_PATH=/usr/local/lib
+ ```
+
+### Release
+
+```bash
+make release
+```
+
+### Debug & Tests
+
+```bash
+make debug
+```
+
 ## 1. Introduction

data/_TAN_cpp_accuracy__.json

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

gcovr.cfg

@@ -1,5 +1,4 @@
 filter = src/
-exclude = external/
-exclude = tests/
+exclude-directories = build/lib/
 print-summary = yes
 sort-percentage = yes

lib/Files/CMakeLists.txt

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

sample/CMakeLists.txt

@@ -3,5 +3,6 @@ include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
 include_directories(${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(BayesNetSample sample.cc ${BayesNet_SOURCE_DIR}/src/Platform/Folding.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc) 
 target_link_libraries(BayesNetSample BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

sample/sample.cc

@@ -1,16 +1,16 @@
 #include <iostream>
 #include <torch/torch.h>
 #include <string>
-#include <thread>
 #include <map>
 #include <argparse/argparse.hpp>
+#include <nlohmann/json.hpp>
 #include "ArffFiles.h"
 #include "BayesMetrics.h"
 #include "CPPFImdlp.h"
 #include "Folding.h"
 #include "Models.h"
 #include "modelRegister.h"
-
+#include <fstream>
 
 using namespace std;
 
@@ -42,7 +42,7 @@ 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>());
@@ -58,6 +58,52 @@ pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vect
 
 int main(int argc, char** argv)
 {
+    torch::Tensor weights_ = torch::full({ 10 }, 1.0 / 10, torch::kFloat64);
+    torch::Tensor y_ = torch::tensor({ 1, 1, 1, 1, 1, 0, 0, 0, 0, 0 }, torch::kInt32);
+    torch::Tensor ypred = torch::tensor({ 1, 1, 1, 0, 0, 1, 1, 1, 1, 0 }, torch::kInt32);
+    cout << "Initial weights_: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << weights_.index({ i }).item<double>() << ", ";
+    }
+    cout << "end." << endl;
+    cout << "y_: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << y_.index({ i }).item<int>() << ", ";
+    }
+    cout << "end." << endl;
+    cout << "ypred: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << ypred.index({ i }).item<int>() << ", ";
+    }
+    cout << "end." << endl;
+    auto mask_wrong = ypred != y_;
+    auto mask_right = ypred == y_;
+    auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
+    double epsilon_t = masked_weights.sum().item<double>();
+    cout << "epsilon_t: " << epsilon_t << endl;
+    double wt = (1 - epsilon_t) / epsilon_t;
+    cout << "wt: " << wt << endl;
+    double alpha_t = epsilon_t == 0 ? 1 : 0.5 * log(wt);
+    cout << "alpha_t: " << alpha_t << endl;
+    // Step 3.2: Update weights for next classifier
+    // Step 3.2.1: Update weights of wrong samples
+    cout << "exp(alpha_t): " << exp(alpha_t) << endl;
+    cout << "exp(-alpha_t): " << exp(-alpha_t) << endl;
+    weights_ += mask_wrong.to(weights_.dtype()) * exp(alpha_t) * weights_;
+    // Step 3.2.2: Update weights of right samples
+    weights_ += mask_right.to(weights_.dtype()) * exp(-alpha_t) * weights_;
+    // Step 3.3: Normalise the weights
+    double totalWeights = torch::sum(weights_).item<double>();
+    cout << "totalWeights: " << totalWeights << endl;
+    cout << "Before normalization: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << weights_.index({ i }).item<double>() << endl;
+    }
+    weights_ = weights_ / totalWeights;
+    cout << "After normalization: " << endl;
+    for (int i = 0; i < 10; i++) {
+        cout << weights_.index({ i }).item<double>() << endl;
+    }
     map<string, bool> datasets = {
             {"diabetes",           true},
             {"ecoli",              true},
@@ -96,6 +142,7 @@ 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 +160,7 @@ 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 +173,7 @@ 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");
@@ -161,13 +209,23 @@ 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 graph = clf->graph();
     auto dot_file = model_name + "_" + file_name;
     ofstream file(dot_file + ".dot");
     file << graph;
@@ -183,11 +241,11 @@ 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;
@@ -199,6 +257,7 @@ int main(int argc, char** argv)
             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 {
@@ -208,6 +267,10 @@ int main(int argc, char** argv)
             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;
@@ -216,6 +279,5 @@ int main(int argc, char** argv)
     }
     cout << "**********************************************************************************" << endl;
     cout << "Average Score Train: " << total_score_train / nFolds << endl;
-    cout << "Average Score Test : " << total_score / nFolds << endl;
-    return 0;
+    cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
 }

src/BayesNet/AODE.cc

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

src/BayesNet/AODE.h

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

src/BayesNet/AODELd.cc

@@ -0,0 +1,41 @@
+#include "AODELd.h"
+#include "Models.h"
+
+namespace bayesnet {
+    using namespace std;
+    AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
+    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
+    {
+        checkInput(X_, y_);
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
+        Ensemble::fit(dataset, features, className, states);
+        return *this;
+
+    }
+    void AODELd::buildModel(const torch::Tensor& weights)
+    {
+        models.clear();
+        for (int i = 0; i < features.size(); ++i) {
+            models.push_back(std::make_unique<SPODELd>(i));
+        }
+        n_models = models.size();
+        significanceModels = vector<double>(n_models, 1.0);
+    }
+    void AODELd::trainModel(const torch::Tensor& weights)
+    {
+        for (const auto& model : models) {
+            model->fit(Xf, y, features, className, states);
+        }
+    }
+    vector<string> AODELd::graph(const string& name) const
+    {
+        return Ensemble::graph(name);
+    }
+}

src/BayesNet/AODELd.h

@@ -0,0 +1,21 @@
+#ifndef AODELD_H
+#define AODELD_H
+#include "Ensemble.h"
+#include "Proposal.h"
+#include "SPODELd.h"
+
+namespace bayesnet {
+    using namespace std;
+    class AODELd : public Ensemble, public Proposal {
+    protected:
+        void trainModel(const torch::Tensor& weights) override;
+        void buildModel(const torch::Tensor& weights) override;
+    public:
+        AODELd();
+        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 = "AODELd") const override;
+        static inline string version() { return "0.0.1"; };
+    };
+}
+#endif // !AODELD_H

src/BayesNet/BaseClassifier.h

@@ -1,23 +1,36 @@
 #ifndef BASE_H
 #define BASE_H
 #include <torch/torch.h>
+#include <nlohmann/json.hpp>
 #include <vector>
 namespace bayesnet {
     using namespace std;
+    enum status_t { NORMAL, WARNING, ERROR };
     class BaseClassifier {
+    protected:
+        virtual void trainModel(const torch::Tensor& weights) = 0;
     public:
-        virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
-        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        // X is nxm vector, y is nx1 vector
+        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, 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;
+        status_t virtual getStatus() const = 0;
         float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
         float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
-        int virtual getNumberOfNodes() = 0;
-        int virtual getNumberOfEdges() = 0;
-        int virtual getNumberOfStates() = 0;
-        vector<string> virtual show() = 0;
-        vector<string> virtual graph(string title = "") = 0;
-        virtual ~BaseClassifier() = default;
-        const string inline getVersion() const { return "0.1.0"; };
+        int virtual getNumberOfNodes()const = 0;
+        int virtual getNumberOfEdges()const = 0;
+        int virtual getNumberOfStates() const = 0;
+        vector<string> virtual show() const = 0;
+        vector<string> virtual graph(const string& title = "") const = 0;
+        const string inline getVersion() const { return "0.2.0"; };
+        vector<string> virtual topological_order() = 0;
+        void virtual dump_cpt()const = 0;
+        virtual void setHyperparameters(nlohmann::json& hyperparameters) = 0;
     };
 }
 #endif

src/BayesNet/BayesMetrics.cc

@@ -1,13 +1,15 @@
 #include "BayesMetrics.h"
 #include "Mst.h"
 namespace bayesnet {
-    Metrics::Metrics(torch::Tensor& samples, vector<string>& features, string& className, int classNumStates)
+    //samples is nxm tensor used to fit the model
+    Metrics::Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates)
         : samples(samples)
         , features(features)
         , className(className)
         , 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 +17,48 @@ 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<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
+    {
+        // Return the K Best features 
+        auto n = samples.size(0) - 1;
+        if (k == 0) {
+            k = n;
+        }
+        // compute scores
+        scoresKBest.clear();
+        featuresKBest.clear();
+        auto label = samples.index({ -1, "..." });
+        for (int i = 0; i < n; ++i) {
+            scoresKBest.push_back(mutualInformation(label, samples.index({ i, "..." }), weights));
+            featuresKBest.push_back(i);
+        }
+        // sort & reduce scores and features
+        if (ascending) {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] < scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::less<double>());
+            if (k < n) {
+                for (int i = 0; i < n - k; ++i) {
+                    featuresKBest.erase(featuresKBest.begin());
+                    scoresKBest.erase(scoresKBest.begin());
+                }
+            }
+        } else {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] > scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::greater<double>());
+            featuresKBest.resize(k);
+            scoresKBest.resize(k);
+        }
+        return featuresKBest;
+    }
+    vector<double> Metrics::getScoresKBest() const
+    {
+        return scoresKBest;
     }
     vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
     {
@@ -30,28 +71,29 @@ namespace bayesnet {
         }
         return result;
     }
-    torch::Tensor Metrics::conditionalEdge()
+    torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
     {
         auto result = vector<double>();
         auto source = vector<string>(features);
         source.push_back(className);
         auto combinations = doCombinations(source);
         // Compute class prior
-        auto margin = torch::zeros({ classNumStates });
+        auto margin = torch::zeros({ classNumStates }, torch::kFloat);
         for (int value = 0; value < classNumStates; ++value) {
-            auto mask = samples.index({ "...", -1 }) == value;
-            margin[value] = mask.sum().item<float>() / samples.sizes()[0];
+            auto mask = samples.index({ -1,  "..." }) == value;
+            margin[value] = mask.sum().item<double>() / samples.size(1);
         }
         for (auto [first, second] : combinations) {
             int index_first = find(features.begin(), features.end(), first) - features.begin();
             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 mi = mutualInformation(first_dataset, second_dataset);
-                auto pb = margin[value].item<float>();
+                auto mask = samples.index({ -1, "..." }) == value;
+                auto first_dataset = samples.index({ index_first, mask });
+                auto second_dataset = samples.index({ index_second, mask });
+                auto weights_dataset = weights.index({ mask });
+                auto mi = mutualInformation(first_dataset, second_dataset, weights_dataset);
+                auto pb = margin[value].item<double>();
                 accumulated += pb * mi;
             }
             result.push_back(accumulated);
@@ -67,31 +109,33 @@ namespace bayesnet {
         }
         return matrix;
     }
-    vector<float> Metrics::conditionalEdgeWeights()
+    // To use in Python
+    vector<float> Metrics::conditionalEdgeWeights(vector<float>& weights_)
     {
-        auto matrix = conditionalEdge();
+        const torch::Tensor weights = torch::tensor(weights_);
+        auto matrix = conditionalEdge(weights);
         std::vector<float> v(matrix.data_ptr<float>(), matrix.data_ptr<float>() + matrix.numel());
         return v;
     }
-    double Metrics::entropy(torch::Tensor& feature)
+    double Metrics::entropy(const torch::Tensor& feature, const torch::Tensor& weights)
     {
-        torch::Tensor counts = feature.bincount();
-        int totalWeight = counts.sum().item<int>();
+        torch::Tensor counts = feature.bincount(weights);
+        double totalWeight = counts.sum().item<double>();
         torch::Tensor probs = counts.to(torch::kFloat) / totalWeight;
         torch::Tensor logProbs = torch::log(probs);
         torch::Tensor entropy = -probs * logProbs;
         return entropy.nansum().item<double>();
     }
     // H(Y|X) = sum_{x in X} p(x) H(Y|X=x)
-    double Metrics::conditionalEntropy(torch::Tensor& firstFeature, torch::Tensor& secondFeature)
+    double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
     {
         int numSamples = firstFeature.sizes()[0];
-        torch::Tensor featureCounts = secondFeature.bincount();
+        torch::Tensor featureCounts = secondFeature.bincount(weights);
         unordered_map<int, unordered_map<int, double>> jointCounts;
         double totalWeight = 0;
         for (auto i = 0; i < numSamples; i++) {
-            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += 1;
-            totalWeight += 1;
+            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
+            totalWeight += weights[i].item<float>();
         }
         if (totalWeight == 0)
             return 0;
@@ -112,16 +156,16 @@ namespace bayesnet {
         return entropyValue;
     }
     // I(X;Y) = H(Y) - H(Y|X)
-    double Metrics::mutualInformation(torch::Tensor& firstFeature, torch::Tensor& secondFeature)
+    double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
     {
-        return entropy(firstFeature) - conditionalEntropy(firstFeature, secondFeature);
+        return entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights);
     }
     /*
     Compute the maximum spanning tree considering the weights as distances
     and the indices of the weights as nodes of this square matrix using
     Kruskal algorithm
     */
-    vector<pair<int, int>> Metrics::maximumSpanningTree(vector<string> features, Tensor& weights, int root)
+    vector<pair<int, int>> Metrics::maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root)
     {
         auto mst = MST(features, weights, root);
         return mst.maximumSpanningTree();

src/BayesNet/BayesMetrics.h

@@ -8,21 +8,25 @@ 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;
+        vector<double> scoresKBest;
+        vector<int> featuresKBest; // sorted indices of the features
+        double entropy(const Tensor& feature, const Tensor& weights);
+        double conditionalEntropy(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
+        vector<pair<string, string>> doCombinations(const vector<string>&);
     public:
         Metrics() = default;
-        Metrics(Tensor&, vector<string>&, string&, int);
-        Metrics(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const int);
-        double entropy(Tensor&);
-        double conditionalEntropy(Tensor&, Tensor&);
-        double mutualInformation(Tensor&, Tensor&);
-        vector<float> conditionalEdgeWeights();
-        Tensor conditionalEdge();
-        vector<pair<string, string>> doCombinations(const vector<string>&);
-        vector<pair<int, int>> maximumSpanningTree(vector<string> features, Tensor& weights, int root);
+        Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates);
+        Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates);
+        vector<int> SelectKBestWeighted(const torch::Tensor& weights, bool ascending=false, unsigned k = 0);
+        vector<double> getScoresKBest() const;
+        double mutualInformation(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
+        vector<float> conditionalEdgeWeights(vector<float>& weights); // To use in Python
+        Tensor conditionalEdge(const torch::Tensor& weights);
+        vector<pair<int, int>> maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root);
     };
 }
 #endif

src/BayesNet/BoostAODE.cc

@@ -0,0 +1,148 @@
+#include "BoostAODE.h"
+#include <set>
+#include "BayesMetrics.h"
+#include "Colors.h"
+#include "Folding.h"
+#include <limits.h>
+
+namespace bayesnet {
+    BoostAODE::BoostAODE() : Ensemble() {}
+    void BoostAODE::buildModel(const torch::Tensor& weights)
+    {
+        // Models shall be built in trainModel
+    }
+    void BoostAODE::setHyperparameters(nlohmann::json& hyperparameters)
+    {
+        // Check if hyperparameters are valid
+        const vector<string> validKeys = { "repeatSparent", "maxModels", "ascending", "convergence" };
+        checkHyperparameters(validKeys, hyperparameters);
+        if (hyperparameters.contains("repeatSparent")) {
+            repeatSparent = hyperparameters["repeatSparent"];
+        }
+        if (hyperparameters.contains("maxModels")) {
+            maxModels = hyperparameters["maxModels"];
+        }
+        if (hyperparameters.contains("ascending")) {
+            ascending = hyperparameters["ascending"];
+        }
+        if (hyperparameters.contains("convergence")) {
+            convergence = hyperparameters["convergence"];
+        }
+    }
+    void BoostAODE::validationInit()
+    {
+        auto y_ = dataset.index({ -1, "..." });
+        if (convergence) {
+            // Prepare train & validation sets from train data
+            auto fold = platform::StratifiedKFold(5, y_, 271);
+            dataset_ = torch::clone(dataset);
+            // save input dataset
+            auto [train, test] = fold.getFold(0);
+            auto train_t = torch::tensor(train);
+            auto test_t = torch::tensor(test);
+            // Get train and validation sets
+            X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), train_t });
+            y_train = dataset.index({ -1, train_t });
+            X_test = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), test_t });
+            y_test = dataset.index({ -1, test_t });
+            dataset = X_train;
+            m = X_train.size(1);
+            auto n_classes = states.at(className).size();
+            metrics = Metrics(dataset, features, className, n_classes);
+            // Build dataset with train data
+            buildDataset(y_train);
+        } else {
+            // Use all data to train
+            X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
+            y_train = y_;
+        }
+
+    }
+    void BoostAODE::trainModel(const torch::Tensor& weights)
+    {
+        models.clear();
+        n_models = 0;
+        if (maxModels == 0)
+            maxModels = .1 * n > 10 ? .1 * n : n;
+        validationInit();
+        Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
+        bool exitCondition = false;
+        unordered_set<int> featuresUsed;
+        // Variables to control the accuracy finish condition
+        double priorAccuracy = 0.0;
+        double delta = 1.0;
+        double threshold = 1e-4;
+        int tolerance = 5; // number of times the accuracy can be lower than the threshold
+        int count = 0; // number of times the accuracy is lower than the threshold
+        fitted = true; // to enable predict
+        // Step 0: Set the finish condition
+        // if not repeatSparent a finish condition is run out of features
+        // n_models == maxModels
+        // epsiolon sub t > 0.5 => inverse the weights policy
+        // validation error is not decreasing
+        while (!exitCondition) {
+            // Step 1: Build ranking with mutual information
+            auto featureSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted
+            unique_ptr<Classifier> model;
+            auto feature = featureSelection[0];
+            if (!repeatSparent || featuresUsed.size() < featureSelection.size()) {
+                bool found = false;
+                for (auto feat : featureSelection) {
+                    if (find(featuresUsed.begin(), featuresUsed.end(), feat) != featuresUsed.end()) {
+                        continue;
+                    }
+                    found = true;
+                    feature = feat;
+                    break;
+                }
+                if (!found) {
+                    exitCondition = true;
+                    continue;
+                }
+            }
+            featuresUsed.insert(feature);
+            model = std::make_unique<SPODE>(feature);
+            model->fit(dataset, features, className, states, weights_);
+            auto ypred = model->predict(X_train);
+            // Step 3.1: Compute the classifier amout of say
+            auto mask_wrong = ypred != y_train;
+            auto mask_right = ypred == y_train;
+            auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
+            double epsilon_t = masked_weights.sum().item<double>();
+            double wt = (1 - epsilon_t) / epsilon_t;
+            double alpha_t = epsilon_t == 0 ? 1 : 0.5 * log(wt);
+            // Step 3.2: Update weights for next classifier
+            // Step 3.2.1: Update weights of wrong samples
+            weights_ += mask_wrong.to(weights_.dtype()) * exp(alpha_t) * weights_;
+            // Step 3.2.2: Update weights of right samples
+            weights_ += mask_right.to(weights_.dtype()) * exp(-alpha_t) * weights_;
+            // Step 3.3: Normalise the weights
+            double totalWeights = torch::sum(weights_).item<double>();
+            weights_ = weights_ / totalWeights;
+            // Step 3.4: Store classifier and its accuracy to weigh its future vote
+            models.push_back(std::move(model));
+            significanceModels.push_back(alpha_t);
+            n_models++;
+            if (convergence) {
+                auto y_val_predict = predict(X_test);
+                double accuracy = (y_val_predict == y_test).sum().item<double>() / (double)y_test.size(0);
+                if (priorAccuracy == 0) {
+                    priorAccuracy = accuracy;
+                } else {
+                    delta = accuracy - priorAccuracy;
+                }
+                if (delta < threshold) {
+                    count++;
+                }
+            }
+            exitCondition = n_models == maxModels && repeatSparent || epsilon_t > 0.5 || count > tolerance;
+        }
+        if (featuresUsed.size() != features.size()) {
+            status = WARNING;
+        }
+    }
+    vector<string> BoostAODE::graph(const string& title) const
+    {
+        return Ensemble::graph(title);
+    }
+}

src/BayesNet/BoostAODE.h

@@ -0,0 +1,25 @@
+#ifndef BOOSTAODE_H
+#define BOOSTAODE_H
+#include "Ensemble.h"
+#include "SPODE.h"
+namespace bayesnet {
+    class BoostAODE : public Ensemble {
+    public:
+        BoostAODE();
+        virtual ~BoostAODE() {};
+        vector<string> graph(const string& title = "BoostAODE") const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
+    protected:
+        void buildModel(const torch::Tensor& weights) override;
+        void trainModel(const torch::Tensor& weights) override;
+    private:
+        torch::Tensor dataset_;
+        torch::Tensor X_train, y_train, X_test, y_test;
+        void validationInit();
+        bool repeatSparent = false;
+        int maxModels = 0;
+        bool ascending = false; //Process KBest features ascending or descending order
+        bool convergence = false; //if true, stop when the model does not improve
+    };
+}
+#endif

src/BayesNet/CMakeLists.txt

@@ -1,2 +1,9 @@
-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(${BayesNet_SOURCE_DIR}/lib/Files)
+include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
+include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
+include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
+add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 
+    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc BoostAODE.cc 
+    Mst.cc Proposal.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
+target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")

src/BayesNet/Classifier.cc

@@ -5,56 +5,77 @@ namespace bayesnet {
     using namespace torch;
 
     Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
-    Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
     {
-        dataset = torch::cat({ X, y.view({y.size(0), 1}) }, 1);
         this->features = features;
         this->className = className;
         this->states = states;
+        m = dataset.size(1);
+        n = dataset.size(0) - 1;
         checkFitParameters();
-        auto n_classes = states[className].size();
+        auto n_classes = states.at(className).size();
         metrics = Metrics(dataset, features, className, n_classes);
-        train();
-        if (Xv == vector<vector<int>>()) {
-            // fit with tensors
-            model.fit(X, y, features, className);
-        } else {
-            // fit with vectors
-            model.fit(Xv, yv, features, className);
-        }
+        model.initialize();
+        buildModel(weights);
+        trainModel(weights);
         fitted = true;
         return *this;
     }
-    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    void Classifier::buildDataset(Tensor& ytmp)
     {
-        this->X = torch::transpose(X, 0, 1);
-        this->y = y;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        return build(features, className, states);
-    }
-
-    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));
+        try {
+            auto yresized = torch::transpose(ytmp.view({ ytmp.size(0), 1 }), 0, 1);
+            dataset = torch::cat({ dataset, yresized }, 0);
         }
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, states);
+        catch (const std::exception& e) {
+            std::cerr << e.what() << '\n';
+            cout << "X dimensions: " << dataset.sizes() << "\n";
+            cout << "y dimensions: " << ytmp.sizes() << "\n";
+            exit(1);
+        }
+    }
+    void Classifier::trainModel(const torch::Tensor& weights)
+    {
+        model.fit(dataset, weights, features, className, states);
+    }
+    // X is nxm where n is the number of features and m the number of samples
+    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
+    {
+        dataset = X;
+        buildDataset(y);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    // X is nxm where n is the number of features and m the number of samples
+    Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, 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) {
+            dataset.index_put_({ i, "..." }, torch::tensor(X[i], kInt32));
+        }
+        auto ytmp = torch::tensor(y, kInt32);
+        buildDataset(ytmp);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    Classifier& Classifier::fit(torch::Tensor& dataset, 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, 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()
     {
-        auto sizes = X.sizes();
-        m = sizes[0];
-        n = sizes[1];
-        if (m != y.size(0)) {
-            throw invalid_argument("X and y must have the same number of samples");
+        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 and features must have the same number of features");
+            throw invalid_argument("Classifier: X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
         }
         if (states.find(className) == states.end()) {
             throw invalid_argument("className not found in states");
@@ -65,23 +86,12 @@ 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 +112,7 @@ 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)
@@ -111,37 +120,53 @@ 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()
+    vector<string> Classifier::show() const
     {
         return model.show();
     }
     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()
+    int Classifier::getNumberOfNodes() const
     {
         // Features does not include class
         return fitted ? model.getFeatures().size() + 1 : 0;
     }
-    int Classifier::getNumberOfEdges()
+    int Classifier::getNumberOfEdges() const
     {
-        return fitted ? model.getEdges().size() : 0;
+        return fitted ? model.getNumEdges() : 0;
     }
-    int Classifier::getNumberOfStates()
+    int Classifier::getNumberOfStates() const
     {
         return fitted ? model.getStates() : 0;
     }
+    vector<string> Classifier::topological_order()
+    {
+        return model.topological_sort();
+    }
+    void Classifier::dump_cpt() const
+    {
+        model.dump_cpt();
+    }
+    void Classifier::checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters)
+    {
+        for (const auto& item : hyperparameters.items()) {
+            if (find(validKeys.begin(), validKeys.end(), item.key()) == validKeys.end()) {
+                throw invalid_argument("Hyperparameter " + item.key() + " is not valid");
+            }
+        }
+    }
+    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

@@ -10,36 +10,42 @@ using namespace torch;
 namespace bayesnet {
     class Classifier : public BaseClassifier {
     private:
-        bool fitted;
-        Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states);
+        Classifier& build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights);
     protected:
-        Network model;
+        bool fitted;
         int m, n; // m: number of samples, n: number of features
-        Tensor X;
-        vector<vector<int>> Xv;
-        Tensor y;
-        vector<int> yv;
-        Tensor dataset;
+        Network model;
         Metrics metrics;
         vector<string> features;
         string className;
         map<string, vector<int>> states;
+        Tensor dataset; // (n+1)xm tensor
+        status_t status = NORMAL;
         void checkFitParameters();
-        virtual void train() = 0;
+        virtual void buildModel(const torch::Tensor& weights) = 0;
+        void trainModel(const torch::Tensor& weights) override;
+        void checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters);
+        void buildDataset(torch::Tensor& y);
     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(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() override;
-        int getNumberOfEdges() override;
-        int getNumberOfStates() override;
-        Tensor predict(Tensor& X);
+        int getNumberOfNodes() const override;
+        int getNumberOfEdges() const override;
+        int getNumberOfStates() const override;
+        Tensor predict(Tensor& X) override;
+        status_t getStatus() const override { return status; }
         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> show() const override;
+        vector<string> topological_order()  override;
+        void dump_cpt() const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
     };
 }
 #endif

src/BayesNet/Ensemble.cc

@@ -3,69 +3,55 @@
 namespace bayesnet {
     using namespace torch;
 
-    Ensemble::Ensemble() : m(0), n(0), n_models(0), metrics(Metrics()), fitted(false) {}
-    Ensemble& Ensemble::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
+
+    void Ensemble::trainModel(const torch::Tensor& weights)
     {
-        dataset = cat({ X, y.view({y.size(0), 1}) }, 1);
-        this->features = features;
-        this->className = className;
-        this->states = states;
-        auto n_classes = states[className].size();
-        metrics = Metrics(dataset, features, className, n_classes);
-        // Build models
-        train();
-        // Train models
         n_models = models.size();
         for (auto i = 0; i < n_models; ++i) {
-            models[i]->fit(Xv, yv, features, className, states);
+            // fit with vectors
+            models[i]->fit(dataset, features, className, states);
         }
-        fitted = true;
-        return *this;
     }
-    Ensemble& Ensemble::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    vector<int> Ensemble::voting(Tensor& y_pred)
     {
-        this->X = X;
-        this->y = y;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        return build(features, className, states);
-    }
-    Ensemble& Ensemble::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
-    {
-        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));
+        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) {
+            // 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.at(j);
+            }
+            // argsort in descending order
+            auto indices = argsort(votes);
+            y_pred_final.push_back(indices[0]);
         }
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, states);
+        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(0), n_models }, kInt32);
+        Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
+        auto threads{ vector<thread>() };
+        mutex mtx;
         for (auto i = 0; i < n_models; ++i) {
-            y_pred.index_put_({ "...", i }, models[i]->predict(X));
+            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::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);
-            for (int j = 0; j < y_pred.size(1); ++j) {
-                votes[y_pred_[i][j]] += 1;
-            }
-            auto indices = argsort(votes);
-            y_pred_final.push_back(indices[0]);
-        }
-        return y_pred_final;
-    }
     vector<int> Ensemble::predict(vector<vector<int>>& X)
     {
         if (!fitted) {
@@ -110,9 +96,8 @@ namespace bayesnet {
             }
         }
         return (double)correct / y_pred.size();
-
     }
-    vector<string> Ensemble::show()
+    vector<string> Ensemble::show() const
     {
         auto result = vector<string>();
         for (auto i = 0; i < n_models; ++i) {
@@ -121,7 +106,7 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<string> Ensemble::graph(string title)
+    vector<string> Ensemble::graph(const string& title) const
     {
         auto result = vector<string>();
         for (auto i = 0; i < n_models; ++i) {
@@ -130,7 +115,7 @@ namespace bayesnet {
         }
         return result;
     }
-    int Ensemble::getNumberOfNodes()
+    int Ensemble::getNumberOfNodes() const
     {
         int nodes = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -138,7 +123,7 @@ namespace bayesnet {
         }
         return nodes;
     }
-    int Ensemble::getNumberOfEdges()
+    int Ensemble::getNumberOfEdges() const
     {
         int edges = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -146,7 +131,7 @@ namespace bayesnet {
         }
         return edges;
     }
-    int Ensemble::getNumberOfStates()
+    int Ensemble::getNumberOfStates() const
     {
         int nstates = 0;
         for (auto i = 0; i < n_models; ++i) {

src/BayesNet/Ensemble.h

@@ -8,39 +8,34 @@ using namespace std;
 using namespace torch;
 
 namespace bayesnet {
-    class Ensemble : public BaseClassifier {
+    class Ensemble : public Classifier {
     private:
-        bool fitted;
-        long n_models;
         Ensemble& build(vector<string>& features, string className, map<string, vector<int>>& states);
     protected:
+        unsigned n_models;
         vector<unique_ptr<Classifier>> models;
-        int m, n; // m: number of samples, n: number of features
-        Tensor X;
-        vector<vector<int>> Xv;
-        Tensor y;
-        vector<int> yv;
-        Tensor dataset;
-        Metrics metrics;
-        vector<string> features;
-        string className;
-        map<string, vector<int>> states;
-        void virtual train() = 0;
+        vector<double> significanceModels;
+        void trainModel(const torch::Tensor& weights) override;
         vector<int> voting(Tensor& y_pred);
     public:
         Ensemble();
         virtual ~Ensemble() = default;
-        Ensemble& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Ensemble& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Tensor predict(Tensor& X);
+        Tensor predict(Tensor& X) override;
         vector<int> predict(vector<vector<int>>& X) override;
         float score(Tensor& X, Tensor& y) override;
         float score(vector<vector<int>>& X, vector<int>& y) override;
-        int getNumberOfNodes() override;
-        int getNumberOfEdges() override;
-        int getNumberOfStates() override;
-        vector<string> show() override;
-        vector<string> graph(string title) override;
+        int getNumberOfNodes() const override;
+        int getNumberOfEdges() const override;
+        int getNumberOfStates() const override;
+        vector<string> show() const override;
+        vector<string> graph(const string& title) const override;
+        vector<string> topological_order()  override
+        {
+            return vector<string>();
+        }
+        void dump_cpt() const override
+        {
+        }
     };
 }
 #endif

src/BayesNet/KDB.cc

@@ -4,7 +4,19 @@ namespace bayesnet {
     using namespace torch;
 
     KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
-    void KDB::train()
+    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)
     {
         /*
         1. For each feature Xi, compute mutual information, I(X;C),
@@ -27,25 +39,25 @@ namespace bayesnet {
         */
         // 1. For each feature Xi, compute mutual information, I(X;C),
         // where C is the class.
-        vector <float> mi;
+        addNodes();
+        const Tensor& y = dataset.index({ -1, "..." });
+        vector<double> mi;
         for (auto i = 0; i < features.size(); i++) {
-            Tensor firstFeature = X.index({ "...", i });
-            mi.push_back(metrics.mutualInformation(firstFeature, y));
+            Tensor firstFeature = dataset.index({ i, "..." });
+            mi.push_back(metrics.mutualInformation(firstFeature, y, weights));
         }
         // 2. Compute class conditional mutual information I(Xi;XjIC), f or each
-        auto conditionalEdgeWeights = metrics.conditionalEdge();
+        auto conditionalEdgeWeights = metrics.conditionalEdge(weights);
         // 3. Let the used variable list, S, be empty.
         vector<int> S;
         // 4. Let the DAG network being constructed, BN, begin with a single
         // 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 +91,12 @@ namespace bayesnet {
             exit_cond = num == n_edges || candidates.size(0) == 0;
         }
     }
-    vector<string> KDB::graph(string title)
+    vector<string> KDB::graph(const string& title) const
     {
+        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);
     }
 }

src/BayesNet/KDB.h

@@ -1,5 +1,6 @@
 #ifndef KDB_H
 #define KDB_H
+#include <torch/torch.h>
 #include "Classifier.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
@@ -11,11 +12,12 @@ namespace bayesnet {
         float theta;
         void add_m_edges(int idx, vector<int>& S, Tensor& weights);
     protected:
-        void train() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         explicit KDB(int k, float theta = 0.03);
         virtual ~KDB() {};
-        vector<string> graph(string name = "KDB") override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
+        vector<string> graph(const string& name = "KDB") const override;
     };
 }
 #endif

src/BayesNet/KDBLd.cc

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

src/BayesNet/KDBLd.h

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

src/BayesNet/Mst.cc

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

src/BayesNet/Mst.h

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

src/BayesNet/Network.cc

@@ -3,15 +3,24 @@
 #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(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() : 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)
     {
         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();
+        samples = torch::Tensor();
+    }
     float Network::getmaxThreads()
     {
         return maxThreads;
@@ -20,28 +29,28 @@ namespace bayesnet {
     {
         return samples;
     }
-    void Network::addNode(const string& name, int numStates)
+    void Network::addNode(const string& name)
     {
+        if (name == "") {
+            throw invalid_argument("Node name cannot be empty");
+        }
+        if (nodes.find(name) != nodes.end()) {
+            return;
+        }
         if (find(features.begin(), features.end(), name) == features.end()) {
             features.push_back(name);
         }
-        if (nodes.find(name) != nodes.end()) {
-            // if node exists update its number of states and remove parents, children and CPT
-            nodes[name]->clear();
-            nodes[name]->setNumStates(numStates);
-            return;
-        }
-        nodes[name] = std::make_unique<Node>(name, numStates);
+        nodes[name] = std::make_unique<Node>(name);
     }
-    vector<string> Network::getFeatures()
+    vector<string> Network::getFeatures() const
     {
         return features;
     }
-    int Network::getClassNumStates()
+    int Network::getClassNumStates() const
     {
         return classNumStates;
     }
-    int Network::getStates()
+    int Network::getStates() const
     {
         int result = 0;
         for (auto& node : nodes) {
@@ -49,7 +58,7 @@ namespace bayesnet {
         }
         return result;
     }
-    string Network::getClassName()
+    string Network::getClassName() const
     {
         return className;
     }
@@ -94,83 +103,121 @@ namespace bayesnet {
     {
         return nodes;
     }
-    void Network::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& featureNames, const string& className)
+    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights)
     {
-        features = featureNames;
-        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);
-        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>());
+        if (weights.size(0) != n_samples) {
+            throw invalid_argument("Weights (" + to_string(weights.size(0)) + ") must have the same number of elements as samples (" + to_string(n_samples) + ") in Network::fit");
+        }
+        if (n_samples != n_samples_y) {
+            throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
+        }
+        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");
+            }
+            if (states.find(feature) == states.end()) {
+                throw invalid_argument("Feature " + feature + " not found in states");
             }
-            dataset[featureNames[i]] = k;
         }
-        dataset[className] = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        completeFit();
     }
-    void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className)
+    void Network::setStates(const map<string, vector<int>>& states)
     {
-        features = featureNames;
+        // Set states to every Node in the network
+        for_each(features.begin(), features.end(), [this, &states](const string& feature) {
+            nodes.at(feature)->setNumStates(states.at(feature).size());
+            });
+        classNumStates = nodes.at(className)->getNumStates();
+    }
+    // X comes in nxm, where n is the number of features and m the number of samples
+    void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
+    {
+        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states, weights);
         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);
+        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) {
-            dataset[featureNames[i]] = input_data[i];
-            samples.index_put_({ "...", i }, torch::tensor(input_data[i], torch::kInt32));
+            auto row_feature = X.index({ i, "..." });
         }
-        dataset[className] = labels;
-        samples.index_put_({ "...", -1 }, torch::tensor(labels, torch::kInt32));
-        completeFit();
+        completeFit(states, weights);
     }
-    void Network::completeFit()
+    void Network::fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
     {
-
-        int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
-        if (maxThreadsRunning < 1) {
-            maxThreadsRunning = 1;
+        checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states, weights);
+        this->className = className;
+        this->samples = samples;
+        completeFit(states, weights);
+    }
+    // input_data comes in nxm, where n is the number of features and m the number of samples
+    void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<float>& weights_, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
+    {
+        const torch::Tensor weights = torch::tensor(weights_, torch::kFloat64);
+        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states, weights);
+        this->className = className;
+        // Build tensor of samples (nxm) (n+1 because of the class)
+        samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
+        for (int i = 0; i < featureNames.size(); ++i) {
+            samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
         }
+        samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
+        completeFit(states, weights);
+    }
+    void Network::completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights)
+    {
+        setStates(states);
+        laplaceSmoothing = 1.0 / samples.size(1); // To use in CPT computation
         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]() {
-                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(dataset, laplaceSmoothing);
-                    lock.lock();
-                    nodes[pair.first] = std::move(pair.second);
-                    lock.unlock();
-                }
-                lock_guard<mutex> lock(mtx);
-                --activeThreads;
-                cv.notify_one();
+        for (auto& node : nodes) {
+            threads.emplace_back([this, &node, &weights]() {
+                node.second->computeCPT(samples, features, laplaceSmoothing, weights);
                 });
-            ++activeThreads;
         }
         for (auto& thread : threads) {
             thread.join();
         }
         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) {
+            const Tensor sample = samples.index({ "...", i });
+            auto psample = predict_sample(sample);
+            auto temp = torch::tensor(psample, torch::kFloat64);
+            //            result.index_put_({ i, "..." }, torch::tensor(predict_sample(sample), torch::kFloat64));
+            result.index_put_({ i, "..." }, temp);
+        }
+        if (proba)
+            return result;
+        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 +238,7 @@ namespace bayesnet {
         }
         return predictions;
     }
+    // Return mxn vector of probabilities
     vector<vector<double>> Network::predict_proba(const vector<vector<int>>& tsamples)
     {
         if (!fitted) {
@@ -218,12 +266,13 @@ 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 +280,20 @@ 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;
@@ -256,13 +319,12 @@ namespace bayesnet {
         for (auto& thread : threads) {
             thread.join();
         }
-
         // Normalize result
         double sum = accumulate(result.begin(), result.end(), 0.0);
-        transform(result.begin(), result.end(), result.begin(), [sum](double& value) { return value / sum; });
+        transform(result.begin(), result.end(), result.begin(), [sum](const double& value) { return value / sum; });
         return result;
     }
-    vector<string> Network::show()
+    vector<string> Network::show() const
     {
         vector<string> result;
         // Draw the network
@@ -275,7 +337,7 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<string> Network::graph(const string& title)
+    vector<string> Network::graph(const string& title) const
     {
         auto output = vector<string>();
         auto prefix = "digraph BayesNet {\nlabel=<BayesNet ";
@@ -289,7 +351,7 @@ namespace bayesnet {
         output.push_back("}\n");
         return output;
     }
-    vector<pair<string, string>> Network::getEdges()
+    vector<pair<string, string>> Network::getEdges() const
     {
         auto edges = vector<pair<string, string>>();
         for (const auto& node : nodes) {
@@ -301,4 +363,52 @@ namespace bayesnet {
         }
         return edges;
     }
+    int Network::getNumEdges() const
+    {
+        return getEdges().size();
+    }
+    vector<string> Network::topological_sort()
+    {
+        /* Check if al the fathers of every node are before the node */
+        auto result = features;
+        result.erase(remove(result.begin(), result.end(), className), result.end());
+        bool ending{ false };
+        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() const
+    {
+        for (auto& node : nodes) {
+            cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
+            cout << node.second->getCPT() << endl;
+        }
+    }
 }

src/BayesNet/Network.h

@@ -8,48 +8,52 @@ namespace bayesnet {
     class Network {
     private:
         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 classname
         string className;
-        int laplaceSmoothing;
-        torch::Tensor samples;
+        double laplaceSmoothing;
+        torch::Tensor samples; // nxm tensor used to fit the model
         bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
         vector<double> predict_sample(const vector<int>&);
+        vector<double> predict_sample(const torch::Tensor&);
         vector<double> exactInference(map<string, int>&);
         double computeFactor(map<string, int>&);
-        double mutual_info(torch::Tensor&, torch::Tensor&);
-        double entropy(torch::Tensor&);
-        double conditionalEntropy(torch::Tensor&, torch::Tensor&);
-        double mutualInformation(torch::Tensor&, torch::Tensor&);
-        void completeFit();
+        void completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights);
+        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights);
+        void setStates(const map<string, vector<int>>&);
     public:
         Network();
-        explicit Network(float, int);
         explicit Network(float);
         explicit Network(Network&);
+        ~Network() = default;
         torch::Tensor& getSamples();
         float getmaxThreads();
-        void addNode(const string&, int);
+        void addNode(const string&);
         void addEdge(const string&, const string&);
         map<string, std::unique_ptr<Node>>& getNodes();
-        vector<string> getFeatures();
-        int getStates();
-        vector<pair<string, string>> getEdges();
-        int getClassNumStates();
-        string getClassName();
-        void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
-        void fit(torch::Tensor&, torch::Tensor&, const vector<string>&, const string&);
-        vector<int> predict(const vector<vector<int>>&);
-        //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>>&);
+        vector<string> getFeatures() const;
+        int getStates() const;
+        vector<pair<string, string>> getEdges() const;
+        int getNumEdges() const;
+        int getClassNumStates() const;
+        string getClassName() const;
+        void fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<float>& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
+        void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
+        void fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
+        vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
+        torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
+        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> show();
-        vector<string> graph(const string& title); // Returns a vector of strings representing the graph in graphviz format
-        inline string version() { return "0.1.0"; }
+        vector<string> topological_sort();
+        vector<string> show() const;
+        vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
+        void initialize();
+        void dump_cpt() const;
+        inline string version() { return "0.2.0"; }
     };
 }
 #endif

src/BayesNet/Node.cc

@@ -2,8 +2,8 @@
 
 namespace bayesnet {
 
-    Node::Node(const std::string& name, int numStates)
-        : name(name), numStates(numStates), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
+    Node::Node(const std::string& name)
+        : name(name), numStates(0), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
     {
     }
     void Node::clear()
@@ -84,8 +84,9 @@ namespace bayesnet {
         }
         return result;
     }
-    void Node::computeCPT(map<string, vector<int>>& dataset, const int laplaceSmoothing)
+    void Node::computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights)
     {
+        dimensions.clear();
         // Get dimensions of the CPT
         dimensions.push_back(numStates);
         transform(parents.begin(), parents.end(), back_inserter(dimensions), [](const auto& parent) { return parent->getNumStates(); });
@@ -93,22 +94,34 @@ namespace bayesnet {
         // Create a tensor of zeros with the dimensions of the CPT
         cpTable = torch::zeros(dimensions, torch::kFloat) + laplaceSmoothing;
         // Fill table with counts
-        for (int n_sample = 0; n_sample < dataset[name].size(); ++n_sample) {
-            torch::List<c10::optional<torch::Tensor>> coordinates;
-            coordinates.push_back(torch::tensor(dataset[name][n_sample]));
-            transform(parents.begin(), parents.end(), back_inserter(coordinates), [&dataset, &n_sample](const auto& parent) { return torch::tensor(dataset[parent->getName()][n_sample]); });
+        auto pos = find(features.begin(), features.end(), name);
+        if (pos == features.end()) {
+            throw logic_error("Feature " + name + " not found in dataset");
+        }
+        int name_index = pos - features.begin();
+        for (int n_sample = 0; n_sample < dataset.size(1); ++n_sample) {
+            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());
+                if (pos == features.end()) {
+                    throw logic_error("Feature parent " + parent->getName() + " not found in dataset");
+                }
+                int parent_index = pos - features.begin();
+                coordinates.push_back(dataset.index({ parent_index, n_sample }));
+            }
             // Increment the count of the corresponding coordinate
-            cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + 1);
+            cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + weights.index({ n_sample }).item<double>());
         }
         // Normalize the counts
         cpTable = cpTable / cpTable.sum(0);
     }
     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/Node.h

@@ -16,7 +16,7 @@ namespace bayesnet {
         vector<int64_t> dimensions; // dimensions of the cpTable
     public:
         vector<pair<string, string>> combinations(const vector<string>&);
-        Node(const string&, int);
+        explicit Node(const string&);
         void clear();
         void addParent(Node*);
         void addChild(Node*);
@@ -26,7 +26,7 @@ namespace bayesnet {
         vector<Node*>& getParents();
         vector<Node*>& getChildren();
         torch::Tensor& getCPT();
-        void computeCPT(map<string, vector<int>>&, const int);
+        void computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights);
         int getNumStates() const;
         void setNumStates(int);
         unsigned minFill();

src/BayesNet/Proposal.cc

@@ -0,0 +1,110 @@
+#include "Proposal.h"
+#include "ArffFiles.h"
+
+namespace bayesnet {
+    Proposal::Proposal(torch::Tensor& dataset_, vector<string>& features_, string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_) {}
+    Proposal::~Proposal()
+    {
+        for (auto& [key, value] : discretizers) {
+            delete value;
+        }
+    }
+    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...
+        // although we rediscretize features after the local discretization of every feature
+        auto order = model.topological_sort();
+        auto& nodes = model.getNodes();
+        map<string, vector<int>> states = oldStates;
+        vector<int> indicesToReDiscretize;
+        bool upgrade = false; // Flag to check if we need to upgrade the model
+        for (auto feature : order) {
+            auto nodeParents = nodes[feature]->getParents();
+            if (nodeParents.size() < 2) continue; // Only has class as parent
+            upgrade = true;
+            int index = find(pFeatures.begin(), pFeatures.end(), feature) - pFeatures.begin();
+            indicesToReDiscretize.push_back(index); // We need to re-discretize this feature
+            vector<string> parents;
+            transform(nodeParents.begin(), nodeParents.end(), back_inserter(parents), [](const auto& p) { return p->getName(); });
+            // Remove class as parent as it will be added later
+            parents.erase(remove(parents.begin(), parents.end(), pClassName), parents.end());
+            // Get the indices of the parents
+            vector<int> indices;
+            indices.push_back(-1); // Add class index
+            transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(pFeatures.begin(), pFeatures.end(), p) - pFeatures.begin(); });
+            // Now we fit the discretizer of the feature, conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
+            vector<string> yJoinParents(Xf.size(1));
+            for (auto idx : indices) {
+                for (int i = 0; i < Xf.size(1); ++i) {
+                    yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
+                }
+            }
+            auto arff = ArffFiles();
+            auto yxv = arff.factorize(yJoinParents);
+            auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
+            auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
+            discretizers[feature]->fit(xvf, yxv);
+        }
+        if (upgrade) {
+            // Discretize again X (only the affected indices) with the new fitted discretizers
+            for (auto index : indicesToReDiscretize) {
+                auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
+                auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+                pDataset.index_put_({ index, "..." }, torch::tensor(discretizers[pFeatures[index]]->transform(Xt)));
+                auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
+                iota(xStates.begin(), xStates.end(), 0);
+                //Update new states of the feature/node
+                states[pFeatures[index]] = xStates;
+            }
+            const torch::Tensor weights = torch::full({ pDataset.size(1) }, 1.0 / pDataset.size(1), torch::kDouble);
+            model.fit(pDataset, weights, pFeatures, pClassName, states);
+        }
+        return states;
+    }
+    map<string, vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
+    {
+        // Discretize the continuous input data and build pDataset (Classifier::dataset)
+        int m = Xf.size(1);
+        int n = Xf.size(0);
+        map<string, vector<int>> states;
+        pDataset = torch::zeros({ n + 1, m }, kInt32);
+        auto yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        // discretize input data by feature(row)
+        for (auto i = 0; i < pFeatures.size(); ++i) {
+            auto* discretizer = new mdlp::CPPFImdlp();
+            auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
+            auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+            discretizer->fit(Xt, yv);
+            pDataset.index_put_({ i, "..." }, torch::tensor(discretizer->transform(Xt)));
+            auto xStates = vector<int>(discretizer->getCutPoints().size() + 1);
+            iota(xStates.begin(), xStates.end(), 0);
+            states[pFeatures[i]] = xStates;
+            discretizers[pFeatures[i]] = discretizer;
+        }
+        int n_classes = torch::max(y).item<int>() + 1;
+        auto yStates = vector<int>(n_classes);
+        iota(yStates.begin(), yStates.end(), 0);
+        states[pClassName] = yStates;
+        pDataset.index_put_({ n, "..." }, y);
+        return states;
+    }
+    torch::Tensor Proposal::prepareX(torch::Tensor& X)
+    {
+        auto Xtd = torch::zeros_like(X, torch::kInt32);
+        for (int i = 0; i < X.size(0); ++i) {
+            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
+            auto Xd = discretizers[pFeatures[i]]->transform(Xt);
+            Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
+        }
+        return Xtd;
+    }
+}

src/BayesNet/Proposal.h

@@ -0,0 +1,30 @@
+#ifndef PROPOSAL_H
+#define PROPOSAL_H
+#include <string>
+#include <map>
+#include <torch/torch.h>
+#include "Network.h"
+#include "CPPFImdlp.h"
+#include "Classifier.h"
+
+namespace bayesnet {
+    class Proposal {
+    public:
+        Proposal(torch::Tensor& pDataset, vector<string>& features_, string& className_);
+        virtual ~Proposal();
+    protected:
+        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);
+        torch::Tensor Xf; // X continuous nxm tensor
+        torch::Tensor y; // y discrete nx1 tensor
+        map<string, mdlp::CPPFImdlp*> discretizers;
+    private:
+        torch::Tensor& pDataset; // (n+1)xm tensor
+        vector<string>& pFeatures;
+        string& pClassName;
+    };
+}
+
+#endif  

src/BayesNet/SPODE.cc

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

src/BayesNet/SPODE.h

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

src/BayesNet/SPODELd.cc

@@ -0,0 +1,48 @@
+#include "SPODELd.h"
+
+namespace bayesnet {
+    using namespace std;
+    SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
+    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
+    {
+        checkInput(X_, y_);
+        features = features_;
+        className = className_;
+        Xf = X_;
+        y = y_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
+        SPODE::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
+        return *this;
+    }
+    SPODELd& SPODELd::fit(torch::Tensor& dataset, 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();
+        features = features_;
+        className = className_;
+        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
+        SPODE::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
+        return *this;
+    }
+
+    Tensor SPODELd::predict(Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return SPODE::predict(Xt);
+    }
+    vector<string> SPODELd::graph(const string& name) const
+    {
+        return SPODE::graph(name);
+    }
+}

src/BayesNet/SPODELd.h

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

src/BayesNet/TAN.cc

@@ -5,25 +5,25 @@ namespace bayesnet {
 
     TAN::TAN() : Classifier(Network()) {}
 
-    void TAN::train()
+    void TAN::buildModel(const torch::Tensor& weights)
     {
         // 0. Add all nodes to the model
         addNodes();
         // 1. Compute mutual information between each feature and the class and set the root node
         // as the highest mutual information with the class
         auto mi = vector <pair<int, float >>();
-        Tensor class_dataset = dataset.index({ "...", -1 });
+        Tensor class_dataset = dataset.index({ -1, "..." });
         for (int i = 0; i < static_cast<int>(features.size()); ++i) {
-            Tensor feature_dataset = dataset.index({ "...", i });
-            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
+            Tensor feature_dataset = dataset.index({ i, "..." });
+            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset, weights);
             mi.push_back({ i, mi_value });
         }
         sort(mi.begin(), mi.end(), [](const auto& left, const auto& right) {return left.second < right.second;});
         auto root = mi[mi.size() - 1].first;
         // 2. Compute mutual information between each feature and the class
-        auto weights = metrics.conditionalEdge();
+        auto weights_matrix = metrics.conditionalEdge(weights);
         // 3. Compute the maximum spanning tree
-        auto mst = metrics.maximumSpanningTree(features, weights, root);
+        auto mst = metrics.maximumSpanningTree(features, weights_matrix, root);
         // 4. Add edges from the maximum spanning tree to the model
         for (auto i = 0; i < mst.size(); ++i) {
             auto [from, to] = mst[i];
@@ -34,7 +34,7 @@ namespace bayesnet {
             model.addEdge(className, feature);
         }
     }
-    vector<string> TAN::graph(string title)
+    vector<string> TAN::graph(const string& title) const
     {
         return model.graph(title);
     }

src/BayesNet/TAN.h

@@ -3,15 +3,14 @@
 #include "Classifier.h"
 namespace bayesnet {
     using namespace std;
-    using namespace torch;
     class TAN : public Classifier {
     private:
     protected:
-        void train() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         TAN();
         virtual ~TAN() {};
-        vector<string> graph(string name = "TAN") override;
+        vector<string> graph(const string& name = "TAN") const override;
     };
 }
 #endif

src/BayesNet/TANLd.cc

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

src/BayesNet/TANLd.h

@@ -0,0 +1,19 @@
+#ifndef TANLD_H
+#define TANLD_H
+#include "TAN.h"
+#include "Proposal.h"
+
+namespace bayesnet {
+    using namespace std;
+    class TANLd : public TAN, public Proposal {
+    private:
+    public:
+        TANLd();
+        virtual ~TANLd() = default;
+        TANLd& fit(torch::Tensor& X, torch::Tensor& y, 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"; };
+    };
+}
+#endif // !TANLD_H

src/BayesNet/bayesnetUtils.cc

@@ -3,7 +3,8 @@
 namespace bayesnet {
     using namespace std;
     using namespace torch;
-    vector<int> argsort(vector<float>& nums)
+    // Return the indices in descending order
+    vector<int> argsort(vector<double>& nums)
     {
         int n = nums.size();
         vector<int> indices(n);

src/BayesNet/bayesnetUtils.h

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

src/Platform/BestResults.cc

@@ -0,0 +1,305 @@
+#include <filesystem>
+#include <fstream>
+#include <iostream>
+#include <sstream>
+#include <set>
+#include "BestResults.h"
+#include "Result.h"
+#include "Colors.h"
+
+
+
+namespace fs = std::filesystem;
+// function ftime_to_string, Code taken from 
+// https://stackoverflow.com/a/58237530/1389271
+template <typename TP>
+std::string ftime_to_string(TP tp)
+{
+    using namespace std::chrono;
+    auto sctp = time_point_cast<system_clock::duration>(tp - TP::clock::now()
+        + system_clock::now());
+    auto tt = system_clock::to_time_t(sctp);
+    std::tm* gmt = std::gmtime(&tt);
+    std::stringstream buffer;
+    buffer << std::put_time(gmt, "%Y-%m-%d %H:%M");
+    return buffer.str();
+}
+
+namespace platform {
+
+    string BestResults::build()
+    {
+        auto files = loadResultFiles();
+        if (files.size() == 0) {
+            cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << endl;
+            exit(1);
+        }
+        json bests;
+        for (const auto& file : files) {
+            auto result = Result(path, file);
+            auto data = result.load();
+            for (auto const& item : data.at("results")) {
+                bool update = false;
+                if (bests.contains(item.at("dataset").get<string>())) {
+                    if (item.at("score").get<double>() > bests[item.at("dataset").get<string>()].at(0).get<double>()) {
+                        update = true;
+                    }
+                } else {
+                    update = true;
+                }
+                if (update) {
+                    bests[item.at("dataset").get<string>()] = { item.at("score").get<double>(), item.at("hyperparameters"), file };
+                }
+            }
+        }
+        string bestFileName = path + bestResultFile();
+        if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+            fclose(fileTest);
+            cout << Colors::MAGENTA() << "File " << bestFileName << " already exists and it shall be overwritten." << Colors::RESET() << endl;
+        }
+        ofstream file(bestFileName);
+        file << bests;
+        file.close();
+        return bestFileName;
+    }
+
+    string BestResults::bestResultFile()
+    {
+        return "best_results_" + score + "_" + model + ".json";
+    }
+
+    pair<string, string> getModelScore(string name)
+    {
+        // results_accuracy_BoostAODE_MacBookpro16_2023-09-06_12:27:00_1.json
+        int i = 0;
+        auto pos = name.find("_");
+        auto pos2 = name.find("_", pos + 1);
+        string score = name.substr(pos + 1, pos2 - pos - 1);
+        pos = name.find("_", pos2 + 1);
+        string model = name.substr(pos2 + 1, pos - pos2 - 1);
+        return { model, score };
+    }
+
+    vector<string> BestResults::loadResultFiles()
+    {
+        vector<string> files;
+        using std::filesystem::directory_iterator;
+        string fileModel, fileScore;
+        for (const auto& file : directory_iterator(path)) {
+            auto fileName = file.path().filename().string();
+            if (fileName.find(".json") != string::npos && fileName.find("results_") == 0) {
+                tie(fileModel, fileScore) = getModelScore(fileName);
+                if (score == fileScore && (model == fileModel || model == "any")) {
+                    files.push_back(fileName);
+                }
+            }
+        }
+        return files;
+    }
+
+    json BestResults::loadFile(const string& fileName)
+    {
+        ifstream resultData(fileName);
+        if (resultData.is_open()) {
+            json data = json::parse(resultData);
+            return data;
+        }
+        throw invalid_argument("Unable to open result file. [" + fileName + "]");
+    }
+    set<string> BestResults::getModels()
+    {
+        set<string> models;
+        auto files = loadResultFiles();
+        if (files.size() == 0) {
+            cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << endl;
+            exit(1);
+        }
+        string fileModel, fileScore;
+        for (const auto& file : files) {
+            // extract the model from the file name
+            tie(fileModel, fileScore) = getModelScore(file);
+            // add the model to the vector of models
+            models.insert(fileModel);
+        }
+        return models;
+    }
+
+    void BestResults::buildAll()
+    {
+        auto models = getModels();
+        for (const auto& model : models) {
+            cout << "Building best results for model: " << model << endl;
+            this->model = model;
+            build();
+        }
+        model = "any";
+    }
+
+    void BestResults::reportSingle()
+    {
+        string bestFileName = path + bestResultFile();
+        if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+            fclose(fileTest);
+        } else {
+            cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << endl;
+            exit(1);
+        }
+        auto date = ftime_to_string(filesystem::last_write_time(bestFileName));
+        auto data = loadFile(bestFileName);
+        cout << Colors::GREEN() << "Best results for " << model << " and " << score << " as of " << date << endl;
+        cout << "--------------------------------------------------------" << endl;
+        cout << Colors::GREEN() << " #  Dataset                   Score       File                                                               Hyperparameters" << endl;
+        cout << "=== ========================= =========== ================================================================== ================================================= " << endl;
+        auto i = 0;
+        bool odd = true;
+        for (auto const& item : data.items()) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            cout << color << setw(3) << fixed << right << i++ << " ";
+            cout << setw(25) << left << item.key() << " ";
+            cout << setw(11) << setprecision(9) << fixed << item.value().at(0).get<double>() << " ";
+            cout << setw(66) << item.value().at(2).get<string>() << " ";
+            cout << item.value().at(1) << " ";
+            cout << endl;
+            odd = !odd;
+        }
+    }
+    json BestResults::buildTableResults(set<string> models)
+    {
+        int numberOfDatasets = 0;
+        bool first = true;
+        json origin;
+        json table;
+        auto maxDate = filesystem::file_time_type::max();
+        for (const auto& model : models) {
+            this->model = model;
+            string bestFileName = path + bestResultFile();
+            if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+                fclose(fileTest);
+            } else {
+                cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << endl;
+                exit(1);
+            }
+            auto dateWrite = filesystem::last_write_time(bestFileName);
+            if (dateWrite < maxDate) {
+                maxDate = dateWrite;
+            }
+            auto data = loadFile(bestFileName);
+            if (first) {
+                // Get the number of datasets of the first file and check that is the same for all the models
+                first = false;
+                numberOfDatasets = data.size();
+                origin = data;
+            } else {
+                if (numberOfDatasets != data.size()) {
+                    cerr << Colors::MAGENTA() << "The number of datasets in the best results files is not the same for all the models." << Colors::RESET() << endl;
+                    exit(1);
+                }
+            }
+            table[model] = data;
+        }
+        table["dateTable"] = ftime_to_string(maxDate);
+        return table;
+    }
+    void BestResults::printTableResults(set<string> models, json table)
+    {
+        cout << Colors::GREEN() << "Best results for " << score << " as of " << table.at("dateTable").get<string>() << endl;
+        cout << "------------------------------------------------" << endl;
+        cout << Colors::GREEN() << " #  Dataset                   ";
+        for (const auto& model : models) {
+            cout << setw(12) << left << model << " ";
+        }
+        cout << endl;
+        cout << "=== ========================= ";
+        for (const auto& model : models) {
+            cout << "============ ";
+        }
+        cout << endl;
+        auto i = 0;
+        bool odd = true;
+        map<string, double> totals;
+        map<string, int> ranks;
+        for (const auto& model : models) {
+            totals[model] = 0.0;
+        }
+        json origin = table.begin().value();
+        for (auto const& item : origin.items()) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            cout << color << setw(3) << fixed << right << i++ << " ";
+            cout << setw(25) << left << item.key() << " ";
+            double maxValue = 0;
+            vector<pair<string, double>> ranksOrder;
+            // Find out the max value for this dataset
+            for (const auto& model : models) {
+                double value = table[model].at(item.key()).at(0).get<double>();
+                if (value > maxValue) {
+                    maxValue = value;
+                }
+                ranksOrder.push_back({ model, value });
+            }
+            // sort the ranksOrder vector by value
+            sort(ranksOrder.begin(), ranksOrder.end(), [](const pair<string, double>& a, const pair<string, double>& b) {
+                return a.second > b.second;
+                });
+            // Assign the ranks
+            for (int i = 0; i < ranksOrder.size(); i++) {
+                ranks[ranksOrder[i].first] = i + 1;
+            }
+            // Print the row with red colors on max values
+            for (const auto& model : models) {
+                string efectiveColor = color;
+                double value = table[model].at(item.key()).at(0).get<double>();
+                if (value == maxValue) {
+                    efectiveColor = Colors::RED();
+                }
+                totals[model] += value;
+                cout << efectiveColor << setw(12) << setprecision(10) << fixed << value << " ";
+            }
+            cout << endl;
+            odd = !odd;
+        }
+        cout << Colors::GREEN() << "=== ========================= ";
+        for (const auto& model : models) {
+            cout << "============ ";
+        }
+        cout << endl;
+        cout << Colors::GREEN() << setw(30) << "    Totals...................";
+        double max = 0.0;
+        for (const auto& total : totals) {
+            if (total.second > max) {
+                max = total.second;
+            }
+        }
+        for (const auto& model : models) {
+            string efectiveColor = Colors::GREEN();
+            if (totals[model] == max) {
+                efectiveColor = Colors::RED();
+            }
+            cout << efectiveColor << setw(12) << setprecision(9) << fixed << totals[model] << " ";
+        }
+        // Output the averaged ranks
+        cout << endl;
+        int min = 1;
+        for (const auto& rank : ranks) {
+            if (rank.second < min) {
+                min = rank.second;
+            }
+        }
+        cout << Colors::GREEN() << setw(30) << "    Averaged ranks...........";
+        for (const auto& model : models) {
+            string efectiveColor = Colors::GREEN();
+            if (ranks[model] == min) {
+                efectiveColor = Colors::RED();
+            }
+            cout << efectiveColor << setw(12) << setprecision(10) << fixed << (double)ranks[model] / (double)origin.size() << " ";
+        }
+        cout << endl;
+    }
+    void BestResults::reportAll()
+    {
+        auto models = getModels();
+        // Build the table of results
+        json table = buildTableResults(models);
+        // Print the table of results
+        printTableResults(models, table);
+    }
+}

src/Platform/BestResults.h

@@ -0,0 +1,28 @@
+#ifndef BESTRESULTS_H
+#define BESTRESULTS_H
+#include <string>
+#include <set>
+#include <nlohmann/json.hpp>
+using namespace std;
+using json = nlohmann::json;
+namespace platform {
+    class BestResults {
+    public:
+        explicit BestResults(const string& path, const string& score, const string& model) : path(path), score(score), model(model) {}
+        string build();
+        void reportSingle();
+        void reportAll();
+        void buildAll();
+    private:
+        set<string> getModels();
+        vector<string> loadResultFiles();
+        json buildTableResults(set<string> models);
+        void printTableResults(set<string> models, json table);
+        string bestResultFile();
+        json loadFile(const string& fileName);
+        string path;
+        string score;
+        string model;
+    };
+}
+#endif //BESTRESULTS_H

src/Platform/BestScore.h

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

src/Platform/CMakeLists.txt

@@ -4,5 +4,16 @@ 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)
+include_directories(${BayesNet_SOURCE_DIR}/lib/libxlsxwriter/include)
+add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc ReportConsole.cc ReportBase.cc)
+add_executable(manage manage.cc Results.cc Result.cc ReportConsole.cc ReportExcel.cc ReportBase.cc Datasets.cc platformUtils.cc)
+add_executable(list list.cc platformUtils Datasets.cc)
+add_executable(best best.cc BestResults.cc Result.cc)
 target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
+if (${CMAKE_HOST_SYSTEM_NAME} MATCHES "Linux")
+    target_link_libraries(manage "${TORCH_LIBRARIES}" libxlsxwriter.so ArffFiles mdlp stdc++fs)
+    target_link_libraries(best stdc++fs)
+else()
+    target_link_libraries(manage "${TORCH_LIBRARIES}" "${XLSXWRITER_LIB}" ArffFiles mdlp)
+endif()
+target_link_libraries(list ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/Colors.h

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

src/Platform/Datasets.cc

@@ -1,6 +1,7 @@
 #include "Datasets.h"
 #include "platformUtils.h"
 #include "ArffFiles.h"
+#include <fstream>
 namespace platform {
     void Datasets::load()
     {
@@ -24,75 +25,110 @@ namespace platform {
         transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
         return result;
     }
-    vector<string> Datasets::getFeatures(string name)
+    vector<string> Datasets::getFeatures(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getFeatures();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getFeatures();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Datasets::getStates(string name)
+    map<string, vector<int>> Datasets::getStates(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getStates();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getStates();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    string Datasets::getClassName(string name)
+    void Datasets::loadDataset(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getClassName();
+        if (datasets.at(name)->isLoaded()) {
+            return;
+        } else {
+            datasets.at(name)->load();
+        }
+    }
+    string Datasets::getClassName(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getClassName();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Datasets::getNSamples(string name)
+    int Datasets::getNSamples(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getNSamples();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getNSamples();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
+    int Datasets::getNClasses(const string& name)
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto className = datasets.at(name)->getClassName();
+            if (discretize) {
+                auto states = getStates(name);
+                return states.at(className).size();
+            }
+            auto [Xv, yv] = getVectors(name);
+            return *max_element(yv.begin(), yv.end()) + 1;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    vector<int> Datasets::getClassesCounts(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto [Xv, yv] = datasets.at(name)->getVectors();
+            vector<int> counts(*max_element(yv.begin(), yv.end()) + 1);
+            for (auto y : yv) {
+                counts[y]++;
+            }
+            return counts;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectors();
     }
-    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(string name)
+    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectorsDiscretized();
     }
-    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(string name)
+    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getTensors();
     }
-    bool Datasets::isDataset(const string& name)
+    bool Datasets::isDataset(const string& name) const
     {
         return datasets.find(name) != datasets.end();
     }
     Dataset::Dataset(const Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType)
     {
     }
-    string Dataset::getName()
+    string Dataset::getName() const
     {
         return name;
     }
-    string Dataset::getClassName()
+    string Dataset::getClassName() const
     {
         return className;
     }
-    vector<string> Dataset::getFeatures()
+    vector<string> Dataset::getFeatures() const
     {
         if (loaded) {
             return features;
@@ -100,7 +136,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Dataset::getNFeatures()
+    int Dataset::getNFeatures() const
     {
         if (loaded) {
             return n_features;
@@ -108,7 +144,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Dataset::getNSamples()
+    int Dataset::getNSamples() const
     {
         if (loaded) {
             return n_samples;
@@ -116,7 +152,7 @@ namespace platform {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Dataset::getStates()
+    map<string, vector<int>> Dataset::getStates() const
     {
         if (loaded) {
             return states;
@@ -177,10 +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()
     {
@@ -207,9 +244,9 @@ 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()

src/Platform/Datasets.h

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

src/Platform/Experiment.cc

@@ -1,7 +1,8 @@
 #include "Experiment.h"
 #include "Datasets.h"
 #include "Models.h"
-
+#include "ReportConsole.h"
+#include <fstream>
 namespace platform {
     using json = nlohmann::json;
     string get_date()
@@ -24,6 +25,7 @@ namespace platform {
         oss << std::put_time(timeinfo, "%H:%M:%S");
         return oss.str();
     }
+    Experiment::Experiment() : hyperparameters(json::parse("{}")) {}
     string Experiment::get_file_name()
     {
         string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
@@ -86,6 +88,13 @@ namespace platform {
         file.close();
     }
 
+    void Experiment::report()
+    {
+        json data = build_json();
+        ReportConsole report(data);
+        report.show();
+    }
+
     void Experiment::show()
     {
         json data = build_json();
@@ -102,9 +111,29 @@ namespace platform {
         }
     }
 
+    string getColor(bayesnet::status_t status)
+    {
+        switch (status) {
+            case bayesnet::NORMAL:
+                return Colors::GREEN();
+            case bayesnet::WARNING:
+                return Colors::YELLOW();
+            case bayesnet::ERROR:
+                return Colors::RED();
+            default:
+                return Colors::RESET();
+        }
+    }
+
+    void showProgress(int fold, const string& color, const string& phase)
+    {
+        string prefix = phase == "a" ? "" : "\b\b\b\b";
+        cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
+
+    }
     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);
@@ -114,8 +143,10 @@ 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));
+        result.setHyperparameters(hyperparameters);
+        // Initialize results vectors
         int nResults = nfolds * static_cast<int>(randomSeeds.size());
         auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
         auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
@@ -136,6 +167,10 @@ namespace platform {
             for (int nfold = 0; nfold < nfolds; nfold++) {
                 auto clf = Models::instance()->create(model);
                 setModelVersion(clf->getVersion());
+                if (hyperparameters.size() != 0) {
+                    clf->setHyperparameters(hyperparameters);
+                }
+                // Split train - test dataset
                 train_timer.start();
                 auto [train, test] = fold->getFold(nfold);
                 auto train_t = torch::tensor(train);
@@ -144,24 +179,31 @@ namespace platform {
                 auto y_train = y.index({ train_t });
                 auto X_test = X.index({ "...", test_t });
                 auto y_test = y.index({ test_t });
-                cout << nfold + 1 << ", " << flush;
+                showProgress(nfold + 1, getColor(clf->getStatus()), "a");
+                // Train model
                 clf->fit(X_train, y_train, features, className, states);
+                showProgress(nfold + 1, getColor(clf->getStatus()), "b");
                 nodes[item] = clf->getNumberOfNodes();
                 edges[item] = clf->getNumberOfEdges();
                 num_states[item] = clf->getNumberOfStates();
                 train_time[item] = train_timer.getDuration();
+                // Score train
                 auto accuracy_train_value = clf->score(X_train, y_train);
+                // Test model
+                showProgress(nfold + 1, getColor(clf->getStatus()), "c");
                 test_timer.start();
                 auto accuracy_test_value = clf->score(X_test, y_test);
                 test_time[item] = test_timer.getDuration();
                 accuracy_train[item] = accuracy_train_value;
                 accuracy_test[item] = accuracy_test_value;
+                cout << "\b\b\b, " << flush;
                 // Store results and times in vector
                 result.addScoreTrain(accuracy_train_value);
                 result.addScoreTest(accuracy_test_value);
                 result.addTimeTrain(train_time[item].item<double>());
                 result.addTimeTest(test_time[item].item<double>());
                 item++;
+                clf.reset();
             }
             cout << "end. " << flush;
             delete fold;
@@ -169,6 +211,7 @@ namespace platform {
         result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
         result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
         result.setTrainTime(torch::mean(train_time).item<double>()).setTestTime(torch::mean(test_time).item<double>());
+        result.setTestTimeStd(torch::std(test_time).item<double>()).setTrainTimeStd(torch::std(train_time).item<double>());
         result.setNodes(torch::mean(nodes).item<double>()).setLeaves(torch::mean(edges).item<double>()).setDepth(torch::mean(num_states).item<double>());
         result.setDataset(fileName);
         addResult(result);

src/Platform/Experiment.h

@@ -29,7 +29,8 @@ namespace platform {
     };
     class Result {
     private:
-        string dataset, hyperparameters, model_version;
+        string dataset, model_version;
+        json hyperparameters;
         int samples{ 0 }, features{ 0 }, classes{ 0 };
         double score_train{ 0 }, score_test{ 0 }, score_train_std{ 0 }, score_test_std{ 0 }, train_time{ 0 }, train_time_std{ 0 }, test_time{ 0 }, test_time_std{ 0 };
         float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
@@ -37,7 +38,7 @@ namespace platform {
     public:
         Result() = default;
         Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
-        Result& setHyperparameters(const string& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
+        Result& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
         Result& setSamples(int samples) { this->samples = samples; return *this; }
         Result& setFeatures(int features) { this->features = features; return *this; }
         Result& setClasses(int classes) { this->classes = classes; return *this; }
@@ -59,7 +60,7 @@ namespace platform {
         const float get_score_train() const { return score_train; }
         float get_score_test() { return score_test; }
         const string& getDataset() const { return dataset; }
-        const string& getHyperparameters() const { return hyperparameters; }
+        const json& getHyperparameters() const { return hyperparameters; }
         const int getSamples() const { return samples; }
         const int getFeatures() const { return features; }
         const int getClasses() const { return classes; }
@@ -85,11 +86,12 @@ namespace platform {
         bool discretized{ false }, stratified{ false };
         vector<Result> results;
         vector<int> randomSeeds;
+        json hyperparameters = "{}";
         int nfolds{ 0 };
         float duration{ 0 };
         json build_json();
     public:
-        Experiment() = default;
+        Experiment();
         Experiment& setTitle(const string& title) { this->title = title; return *this; }
         Experiment& setModel(const string& model) { this->model = model; return *this; }
         Experiment& setPlatform(const string& platform) { this->platform = platform; return *this; }
@@ -103,11 +105,13 @@ namespace platform {
         Experiment& addResult(Result result) { results.push_back(result); return *this; }
         Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
         Experiment& setDuration(float duration) { this->duration = duration; return *this; }
+        Experiment& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
         string get_file_name();
         void save(const string& path);
         void cross_validation(const string& path, const string& fileName);
         void go(vector<string> filesToProcess, const string& path);
         void show();
+        void report();
     };
 }
 #endif

src/Platform/Folding.cc

@@ -1,95 +1,97 @@
 #include "Folding.h"
 #include <algorithm>
 #include <map>
-Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
-{
-    random_device rd;
-    random_seed = default_random_engine(seed == -1 ? rd() : seed);
-    srand(seed == -1 ? time(0) : seed);
-}
-KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
-{
-    iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
-    shuffle(indices.begin(), indices.end(), random_seed);
-}
-pair<vector<int>, vector<int>> KFold::getFold(int nFold)
-{
-    if (nFold >= k || nFold < 0) {
-        throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
+namespace platform {
+    Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
+    {
+        random_device rd;
+        random_seed = default_random_engine(seed == -1 ? rd() : seed);
+        srand(seed == -1 ? time(0) : seed);
     }
-    int nTest = n / k;
-    auto train = vector<int>();
-    auto test = vector<int>();
-    for (int i = 0; i < n; i++) {
-        if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
-            test.push_back(indices[i]);
-        } else {
-            train.push_back(indices[i]);
-        }
-    }
-    return { train, test };
-}
-StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
-{
-    n = y.numel();
-    this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
-    build();
-}
-StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
-    : Fold(k, y.size(), seed)
-{
-    this->y = y;
-    n = y.size();
-    build();
-}
-void StratifiedKFold::build()
-{
-    stratified_indices = vector<vector<int>>(k);
-    int fold_size = n / k;
-    // Compute class counts and indices
-    auto class_indices = map<int, vector<int>>();
-    vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
-    for (auto i = 0; i < n; ++i) {
-        class_counts[y[i]]++;
-        class_indices[y[i]].push_back(i);
-    }
-    // Shuffle class indices
-    for (auto& [cls, indices] : class_indices) {
+    KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
+    {
+        iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
         shuffle(indices.begin(), indices.end(), random_seed);
     }
-    // Assign indices to folds
-    for (auto label = 0; label < class_counts.size(); ++label) {
-        auto num_samples_to_take = class_counts[label] / k;
-        if (num_samples_to_take == 0)
-            continue;
-        auto remainder_samples_to_take = class_counts[label] % k;
-        for (auto fold = 0; fold < k; ++fold) {
-            auto it = next(class_indices[label].begin(), num_samples_to_take);
-            move(class_indices[label].begin(), it, back_inserter(stratified_indices[fold]));  // ##
-            class_indices[label].erase(class_indices[label].begin(), it);
+    pair<vector<int>, vector<int>> KFold::getFold(int nFold)
+    {
+        if (nFold >= k || nFold < 0) {
+            throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
         }
-        while (remainder_samples_to_take > 0) {
-            int fold = (rand() % static_cast<int>(k));
-            if (stratified_indices[fold].size() == fold_size + 1) {
-                continue;
+        int nTest = n / k;
+        auto train = vector<int>();
+        auto test = vector<int>();
+        for (int i = 0; i < n; i++) {
+            if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
+                test.push_back(indices[i]);
+            } else {
+                train.push_back(indices[i]);
+            }
+        }
+        return { train, test };
+    }
+    StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
+    {
+        n = y.numel();
+        this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
+        build();
+    }
+    StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
+        : Fold(k, y.size(), seed)
+    {
+        this->y = y;
+        n = y.size();
+        build();
+    }
+    void StratifiedKFold::build()
+    {
+        stratified_indices = vector<vector<int>>(k);
+        int fold_size = n / k;
+        // Compute class counts and indices
+        auto class_indices = map<int, vector<int>>();
+        vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
+        for (auto i = 0; i < n; ++i) {
+            class_counts[y[i]]++;
+            class_indices[y[i]].push_back(i);
+        }
+        // Shuffle class indices
+        for (auto& [cls, indices] : class_indices) {
+            shuffle(indices.begin(), indices.end(), random_seed);
+        }
+        // Assign indices to folds
+        for (auto label = 0; label < class_counts.size(); ++label) {
+            auto num_samples_to_take = class_counts[label] / k;
+            if (num_samples_to_take == 0)
+                continue;
+            auto remainder_samples_to_take = class_counts[label] % k;
+            for (auto fold = 0; fold < k; ++fold) {
+                auto it = next(class_indices[label].begin(), num_samples_to_take);
+                move(class_indices[label].begin(), it, back_inserter(stratified_indices[fold]));  // ##
+                class_indices[label].erase(class_indices[label].begin(), it);
+            }
+            while (remainder_samples_to_take > 0) {
+                int fold = (rand() % static_cast<int>(k));
+                if (stratified_indices[fold].size() == fold_size + 1) {
+                    continue;
+                }
+                auto it = next(class_indices[label].begin(), 1);
+                stratified_indices[fold].push_back(*class_indices[label].begin());
+                class_indices[label].erase(class_indices[label].begin(), it);
+                remainder_samples_to_take--;
             }
-            auto it = next(class_indices[label].begin(), 1);
-            stratified_indices[fold].push_back(*class_indices[label].begin());
-            class_indices[label].erase(class_indices[label].begin(), it);
-            remainder_samples_to_take--;
         }
     }
-}
-pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
-{
-    if (nFold >= k || nFold < 0) {
-        throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
+    pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
+    {
+        if (nFold >= k || nFold < 0) {
+            throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
+        }
+        vector<int> test_indices = stratified_indices[nFold];
+        vector<int> train_indices;
+        for (int i = 0; i < k; ++i) {
+            if (i == nFold) continue;
+            train_indices.insert(train_indices.end(), stratified_indices[i].begin(), stratified_indices[i].end());
+        }
+        return { train_indices, test_indices };
     }
-    vector<int> test_indices = stratified_indices[nFold];
-    vector<int> train_indices;
-    for (int i = 0; i < k; ++i) {
-        if (i == nFold) continue;
-        train_indices.insert(train_indices.end(), stratified_indices[i].begin(), stratified_indices[i].end());
-    }
-    return { train_indices, test_indices };
 }

src/Platform/Folding.h

@@ -4,34 +4,35 @@
 #include <vector>
 #include <random> 
 using namespace std;
-
-class Fold {
-protected:
-    int k;
-    int n;
-    int seed;
-    default_random_engine random_seed;
-public:
-    Fold(int k, int n, int seed = -1);
-    virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
-    virtual ~Fold() = default;
-    int getNumberOfFolds() { return k; }
-};
-class KFold : public Fold {
-private:
-    vector<int> indices;
-public:
-    KFold(int k, int n, int seed = -1);
-    pair<vector<int>, vector<int>> getFold(int nFold) override;
-};
-class StratifiedKFold : public Fold {
-private:
-    vector<int> y;
-    vector<vector<int>> stratified_indices;
-    void build();
-public:
-    StratifiedKFold(int k, const vector<int>& y, int seed = -1);
-    StratifiedKFold(int k, torch::Tensor& y, int seed = -1);
-    pair<vector<int>, vector<int>> getFold(int nFold) override;
-};
+namespace platform {
+    class Fold {
+    protected:
+        int k;
+        int n;
+        int seed;
+        default_random_engine random_seed;
+    public:
+        Fold(int k, int n, int seed = -1);
+        virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
+        virtual ~Fold() = default;
+        int getNumberOfFolds() { return k; }
+    };
+    class KFold : public Fold {
+    private:
+        vector<int> indices;
+    public:
+        KFold(int k, int n, int seed = -1);
+        pair<vector<int>, vector<int>> getFold(int nFold) override;
+    };
+    class StratifiedKFold : public Fold {
+    private:
+        vector<int> y;
+        vector<vector<int>> stratified_indices;
+        void build();
+    public:
+        StratifiedKFold(int k, const vector<int>& y, int seed = -1);
+        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/Models.h

@@ -6,6 +6,11 @@
 #include "TAN.h"
 #include "KDB.h"
 #include "SPODE.h"
+#include "TANLd.h"
+#include "KDBLd.h"
+#include "SPODELd.h"
+#include "AODELd.h"
+#include "BoostAODE.h"
 namespace platform {
     class Models {
     private:

src/Platform/Paths.h

@@ -0,0 +1,12 @@
+#ifndef PATHS_H
+#define PATHS_H
+#include <string>
+namespace platform {
+    class Paths {
+    public:
+        static std::string datasets() { return "datasets/"; }
+        static std::string results() { return "results/"; }
+        static std::string excel() { return "excel/"; }
+    };
+}
+#endif

src/Platform/ReportBase.cc

@@ -0,0 +1,114 @@
+#include <sstream>
+#include <locale>
+#include "Datasets.h"
+#include "ReportBase.h"
+#include "BestScore.h"
+
+
+namespace platform {
+    ReportBase::ReportBase(json data_, bool compare) : data(data_), compare(compare), margin(0.1)
+    {
+        stringstream oss;
+        oss << "Better than ZeroR + " << setprecision(1) << fixed << margin * 100 << "%";
+        meaning = {
+            {Symbols::equal_best, "Equal to best"},
+            {Symbols::better_best, "Better than best"},
+            {Symbols::cross, "Less than or equal to ZeroR"},
+            {Symbols::upward_arrow, oss.str()}
+        };
+    }
+    string ReportBase::fromVector(const string& key)
+    {
+        stringstream oss;
+        string sep = "";
+        oss << "[";
+        for (auto& item : data[key]) {
+            oss << sep << item.get<double>();
+            sep = ", ";
+        }
+        oss << "]";
+        return oss.str();
+    }
+    string ReportBase::fVector(const string& title, const json& data, const int width, const int precision)
+    {
+        stringstream oss;
+        string sep = "";
+        oss << title << "[";
+        for (const auto& item : data) {
+            oss << sep << fixed << setw(width) << setprecision(precision) << item.get<double>();
+            sep = ", ";
+        }
+        oss << "]";
+        return oss.str();
+    }
+    void ReportBase::show()
+    {
+        header();
+        body();
+    }
+    string ReportBase::compareResult(const string& dataset, double result)
+    {
+        string status = " ";
+        if (compare) {
+            double best = bestResult(dataset, data["model"].get<string>());
+            if (result == best) {
+                status = Symbols::equal_best;
+            } else if (result > best) {
+                status = Symbols::better_best;
+            }
+        } else {
+            if (data["score_name"].get<string>() == "accuracy") {
+                auto dt = Datasets(Paths::datasets(), false);
+                dt.loadDataset(dataset);
+                auto numClasses = dt.getNClasses(dataset);
+                if (numClasses == 2) {
+                    vector<int> distribution = dt.getClassesCounts(dataset);
+                    double nSamples = dt.getNSamples(dataset);
+                    vector<int>::iterator maxValue = max_element(distribution.begin(), distribution.end());
+                    double mark = *maxValue / nSamples * (1 + margin);
+                    if (mark > 1) {
+                        mark = 0.9995;
+                    }
+                    status = result < mark ? Symbols::cross : result > mark ? Symbols::upward_arrow : "=";
+                }
+            }
+        }
+        if (status != " ") {
+            auto item = summary.find(status);
+            if (item != summary.end()) {
+                summary[status]++;
+            } else {
+                summary[status] = 1;
+            }
+        }
+        return status;
+    }
+    double ReportBase::bestResult(const string& dataset, const string& model)
+    {
+        double value = 0.0;
+        if (bestResults.size() == 0) {
+            // try to load the best results
+            string score = data["score_name"];
+            replace(score.begin(), score.end(), '_', '-');
+            string fileName = "best_results_" + score + "_" + model + ".json";
+            ifstream resultData(Paths::results() + "/" + fileName);
+            if (resultData.is_open()) {
+                bestResults = json::parse(resultData);
+            } else {
+                existBestFile = false;
+            }
+        }
+        try {
+            value = bestResults.at(dataset).at(0);
+        }
+        catch (exception) {
+            value = 1.0;
+
+        }
+        return value;
+    }
+    bool ReportBase::getExistBestFile()
+    {
+        return existBestFile;
+    }
+}

src/Platform/ReportBase.h

@@ -0,0 +1,46 @@
+#ifndef REPORTBASE_H
+#define REPORTBASE_H
+#include <string>
+#include <iostream>
+#include "Paths.h"
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+namespace platform {
+    using namespace std;
+    class Symbols {
+    public:
+        inline static const string check_mark{ "\u2714" };
+        inline static const string exclamation{ "\u2757" };
+        inline static const string black_star{ "\u2605" };
+        inline static const string cross{ "\u2717" };
+        inline static const string upward_arrow{ "\u27B6" };
+        inline static const string down_arrow{ "\u27B4" };
+        inline static const string equal_best{ check_mark };
+        inline static const string better_best{ black_star };
+    };
+    class ReportBase {
+    public:
+        explicit ReportBase(json data_, bool compare);
+        virtual ~ReportBase() = default;
+        void show();
+    protected:
+        json data;
+        string fromVector(const string& key);
+        string fVector(const string& title, const json& data, const int width, const int precision);
+        bool getExistBestFile();
+        virtual void header() = 0;
+        virtual void body() = 0;
+        virtual void showSummary() = 0;
+        string compareResult(const string& dataset, double result);
+        map<string, int> summary;
+        double margin;
+        map<string, string> meaning;
+        bool compare;
+    private:
+        double bestResult(const string& dataset, const string& model);
+        json bestResults;
+        bool existBestFile = true;
+    };
+};
+#endif

src/Platform/ReportConsole.cc

@@ -0,0 +1,112 @@
+#include <sstream>
+#include <locale>
+#include "ReportConsole.h"
+#include "BestScore.h"
+
+
+namespace platform {
+    struct separated : numpunct<char> {
+        char do_decimal_point() const { return ','; }
+        char do_thousands_sep() const { return '.'; }
+        string do_grouping() const { return "\03"; }
+    };
+
+    string ReportConsole::headerLine(const string& text, int utf = 0)
+    {
+        int n = MAXL - text.length() - 3;
+        n = n < 0 ? 0 : n;
+        return "* " + text + string(n + utf, ' ') + "*\n";
+    }
+
+    void ReportConsole::header()
+    {
+        locale mylocale(cout.getloc(), new separated);
+        locale::global(mylocale);
+        cout.imbue(mylocale);
+        stringstream oss;
+        cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
+        cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
+        cout << headerLine(data["title"].get<string>());
+        cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
+        oss << "Execution took  " << setprecision(2) << fixed << data["duration"].get<float>() << " seconds,   " << data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<string>();
+        cout << headerLine(oss.str());
+        cout << headerLine("Score is " + data["score_name"].get<string>());
+        cout << string(MAXL, '*') << endl;
+        cout << endl;
+    }
+    void ReportConsole::body()
+    {
+        cout << Colors::GREEN() << " #  Dataset                   Sampl. Feat. Cls Nodes     Edges     States    Score           Time                Hyperparameters" << endl;
+        cout << "=== ========================= ====== ===== === ========= ========= ========= =============== =================== ====================" << endl;
+        json lastResult;
+        double totalScore = 0.0;
+        bool odd = true;
+        int index = 0;
+        for (const auto& r : data["results"]) {
+            if (selectedIndex != -1 && index != selectedIndex) {
+                index++;
+                continue;
+            }
+            auto color = odd ? Colors::CYAN() : Colors::BLUE();
+            cout << color;
+            cout << setw(3) << index++ << " ";
+            cout << setw(25) << 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(9) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
+            cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>();
+            const string status = compareResult(r["dataset"].get<string>(), r["score"].get<double>());
+            cout << status;
+            cout << setw(12) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
+            try {
+                cout << r["hyperparameters"].get<string>();
+            }
+            catch (const exception& err) {
+                cout << r["hyperparameters"];
+            }
+            cout << endl;
+            lastResult = r;
+            totalScore += r["score"].get<double>();
+            odd = !odd;
+        }
+        if (data["results"].size() == 1 || selectedIndex != -1) {
+            cout << string(MAXL, '*') << endl;
+            cout << headerLine(fVector("Train scores: ", lastResult["scores_train"], 14, 12));
+            cout << headerLine(fVector("Test  scores: ", lastResult["scores_test"], 14, 12));
+            cout << headerLine(fVector("Train  times: ", lastResult["times_train"], 10, 3));
+            cout << headerLine(fVector("Test   times: ", lastResult["times_test"], 10, 3));
+            cout << string(MAXL, '*') << endl;
+        } else {
+            footer(totalScore);
+        }
+    }
+    void ReportConsole::showSummary()
+    {
+        for (const auto& item : summary) {
+            stringstream oss;
+            oss << setw(3) << left << item.first;
+            oss << setw(3) << right << item.second << " ";
+            oss << left << meaning.at(item.first);
+            cout << headerLine(oss.str(), 2);
+        }
+    }
+
+    void ReportConsole::footer(double totalScore)
+    {
+        cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
+        showSummary();
+        auto score = data["score_name"].get<string>();
+        if (score == BestScore::scoreName()) {
+            stringstream oss;
+            oss << score << " compared to " << BestScore::title() << " .:  " << totalScore / BestScore::score();
+            cout << headerLine(oss.str());
+        }
+        if (!getExistBestFile() && compare) {
+            cout << headerLine("*** Best Results File not found. Couldn't compare any result!");
+        }
+        cout << string(MAXL, '*') << endl << Colors::RESET();
+    }
+}

src/Platform/ReportConsole.h

@@ -0,0 +1,24 @@
+#ifndef REPORTCONSOLE_H
+#define REPORTCONSOLE_H
+#include <string>
+#include <iostream>
+#include "ReportBase.h"
+#include "Colors.h"
+
+namespace platform {
+    using namespace std;
+    const int MAXL = 133;
+    class ReportConsole : public ReportBase {
+    public:
+        explicit ReportConsole(json data_, bool compare = false, int index = -1) : ReportBase(data_, compare), selectedIndex(index) {};
+        virtual ~ReportConsole() = default;
+    private:
+        int selectedIndex;
+        string headerLine(const string& text, int utf);
+        void header() override;
+        void body() override;
+        void footer(double totalScore);
+        void showSummary() override;
+    };
+};
+#endif

src/Platform/ReportExcel.cc

@@ -0,0 +1,333 @@
+#include <sstream>
+#include <locale>
+#include "ReportExcel.h"
+#include "BestScore.h"
+
+
+namespace platform {
+    struct separated : numpunct<char> {
+        char do_decimal_point() const { return ','; }
+
+        char do_thousands_sep() const { return '.'; }
+
+        string do_grouping() const { return "\03"; }
+    };
+
+    ReportExcel::ReportExcel(json data_, bool compare, lxw_workbook* workbook) : ReportBase(data_, compare), row(0), workbook(workbook)
+    {
+        normalSize = 14; //font size for report body
+        colorTitle = 0xB1A0C7;
+        colorOdd = 0xDCE6F1;
+        colorEven = 0xFDE9D9;
+        createFile();
+    }
+
+    lxw_workbook* ReportExcel::getWorkbook()
+    {
+        return workbook;
+    }
+
+    lxw_format* ReportExcel::efectiveStyle(const string& style)
+    {
+        lxw_format* efectiveStyle;
+        if (style == "") {
+            efectiveStyle = NULL;
+        } else {
+            string suffix = row % 2 ? "_odd" : "_even";
+            efectiveStyle = styles.at(style + suffix);
+        }
+        return efectiveStyle;
+    }
+
+    void ReportExcel::writeString(int row, int col, const string& text, const string& style)
+    {
+        worksheet_write_string(worksheet, row, col, text.c_str(), efectiveStyle(style));
+    }
+    void ReportExcel::writeInt(int row, int col, const int number, const string& style)
+    {
+        worksheet_write_number(worksheet, row, col, number, efectiveStyle(style));
+    }
+    void ReportExcel::writeDouble(int row, int col, const double number, const string& style)
+    {
+        worksheet_write_number(worksheet, row, col, number, efectiveStyle(style));
+    }
+
+    void ReportExcel::formatColumns()
+    {
+        worksheet_freeze_panes(worksheet, 6, 1);
+        vector<int> columns_sizes = { 22, 10, 9, 7, 12, 12, 12, 12, 12, 3, 15, 12, 23 };
+        for (int i = 0; i < columns_sizes.size(); ++i) {
+            worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
+        }
+    }
+
+    void ReportExcel::addColor(lxw_format* style, bool odd)
+    {
+        uint32_t efectiveColor = odd ? colorEven : colorOdd;
+        format_set_bg_color(style, lxw_color_t(efectiveColor));
+    }
+    void ReportExcel::createStyle(const string& name, lxw_format* style, bool odd)
+    {
+        addColor(style, odd);
+        if (name == "textCentered") {
+            format_set_align(style, LXW_ALIGN_CENTER);
+            format_set_font_size(style, normalSize);
+            format_set_border(style, LXW_BORDER_THIN);
+        } else if (name == "text") {
+            format_set_font_size(style, normalSize);
+            format_set_border(style, LXW_BORDER_THIN);
+        } else if (name == "bodyHeader") {
+            format_set_bold(style);
+            format_set_font_size(style, normalSize);
+            format_set_align(style, LXW_ALIGN_CENTER);
+            format_set_align(style, LXW_ALIGN_VERTICAL_CENTER);
+            format_set_border(style, LXW_BORDER_THIN);
+            format_set_bg_color(style, lxw_color_t(colorTitle));
+        } else if (name == "result") {
+            format_set_font_size(style, normalSize);
+            format_set_border(style, LXW_BORDER_THIN);
+            format_set_num_format(style, "0.0000000");
+        } else if (name == "time") {
+            format_set_font_size(style, normalSize);
+            format_set_border(style, LXW_BORDER_THIN);
+            format_set_num_format(style, "#,##0.000000");
+        } else if (name == "ints") {
+            format_set_font_size(style, normalSize);
+            format_set_num_format(style, "###,##0");
+            format_set_border(style, LXW_BORDER_THIN);
+        } else if (name == "floats") {
+            format_set_border(style, LXW_BORDER_THIN);
+            format_set_font_size(style, normalSize);
+            format_set_num_format(style, "#,##0.00");
+        }
+    }
+
+    void ReportExcel::createFormats()
+    {
+        auto styleNames = { "text", "textCentered", "bodyHeader", "result", "time", "ints", "floats" };
+        lxw_format* style;
+        for (string name : styleNames) {
+            lxw_format* style = workbook_add_format(workbook);
+            style = workbook_add_format(workbook);
+            createStyle(name, style, true);
+            styles[name + "_odd"] = style;
+            style = workbook_add_format(workbook);
+            createStyle(name, style, false);
+            styles[name + "_even"] = style;
+        }
+
+        // Header 1st line
+        lxw_format* headerFirst = workbook_add_format(workbook);
+        format_set_bold(headerFirst);
+        format_set_font_size(headerFirst, 18);
+        format_set_align(headerFirst, LXW_ALIGN_CENTER);
+        format_set_align(headerFirst, LXW_ALIGN_VERTICAL_CENTER);
+        format_set_border(headerFirst, LXW_BORDER_THIN);
+        format_set_bg_color(headerFirst, lxw_color_t(colorTitle));
+
+        // Header rest
+        lxw_format* headerRest = workbook_add_format(workbook);
+        format_set_bold(headerRest);
+        format_set_align(headerRest, LXW_ALIGN_CENTER);
+        format_set_font_size(headerRest, 16);
+        format_set_align(headerRest, LXW_ALIGN_VERTICAL_CENTER);
+        format_set_border(headerRest, LXW_BORDER_THIN);
+        format_set_bg_color(headerRest, lxw_color_t(colorOdd));
+
+        // Header small
+        lxw_format* headerSmall = workbook_add_format(workbook);
+        format_set_bold(headerSmall);
+        format_set_align(headerSmall, LXW_ALIGN_LEFT);
+        format_set_font_size(headerSmall, 12);
+        format_set_border(headerSmall, LXW_BORDER_THIN);
+        format_set_align(headerSmall, LXW_ALIGN_VERTICAL_CENTER);
+        format_set_bg_color(headerSmall, lxw_color_t(colorOdd));
+
+        // Summary style
+        lxw_format* summaryStyle = workbook_add_format(workbook);
+        format_set_bold(summaryStyle);
+        format_set_font_size(summaryStyle, 16);
+        format_set_border(summaryStyle, LXW_BORDER_THIN);
+        format_set_align(summaryStyle, LXW_ALIGN_VERTICAL_CENTER);
+
+        styles["headerFirst"] = headerFirst;
+        styles["headerRest"] = headerRest;
+        styles["headerSmall"] = headerSmall;
+        styles["summaryStyle"] = summaryStyle;
+    }
+
+    void ReportExcel::setProperties()
+    {
+        char line[data["title"].get<string>().size() + 1];
+        strcpy(line, data["title"].get<string>().c_str());
+        lxw_doc_properties properties = {
+            .title = line,
+            .subject = (char*)"Machine learning results",
+            .author = (char*)"Ricardo Montañana Gómez",
+            .manager = (char*)"Dr. J. A. Gámez, Dr. J. M. Puerta",
+            .company = (char*)"UCLM",
+            .comments = (char*)"Created with libxlsxwriter and c++",
+        };
+        workbook_set_properties(workbook, &properties);
+    }
+
+    void ReportExcel::createFile()
+    {
+        if (workbook == NULL) {
+            workbook = workbook_new((Paths::excel() + fileName).c_str());
+        }
+        const string name = data["model"].get<string>();
+        string suffix = "";
+        string efectiveName;
+        int num = 1;
+        // Create a sheet with the name of the model
+        while (true) {
+            efectiveName = name + suffix;
+            if (workbook_get_worksheet_by_name(workbook, efectiveName.c_str())) {
+                suffix = to_string(++num);
+            } else {
+                worksheet = workbook_add_worksheet(workbook, efectiveName.c_str());
+                break;
+            }
+            if (num > 100) {
+                throw invalid_argument("Couldn't create sheet " + efectiveName);
+            }
+        }
+        cout << "Adding sheet " << efectiveName << " to " << Paths::excel() + fileName << endl;
+        setProperties();
+        createFormats();
+        formatColumns();
+    }
+
+    void ReportExcel::closeFile()
+    {
+        workbook_close(workbook);
+    }
+
+    void ReportExcel::header()
+    {
+        locale mylocale(cout.getloc(), new separated);
+        locale::global(mylocale);
+        cout.imbue(mylocale);
+        stringstream oss;
+        string message = data["model"].get<string>() + " ver. " + data["version"].get<string>() + " " +
+            data["language"].get<string>() + " ver. " + data["language_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>();
+        worksheet_merge_range(worksheet, 0, 0, 0, 12, message.c_str(), styles["headerFirst"]);
+        worksheet_merge_range(worksheet, 1, 0, 1, 12, data["title"].get<string>().c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 0, 3, 0, ("Score is " + data["score_name"].get<string>()).c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 1, 3, 3, "Execution time", styles["headerRest"]);
+        oss << setprecision(2) << fixed << data["duration"].get<float>() << " s";
+        worksheet_merge_range(worksheet, 2, 4, 2, 5, oss.str().c_str(), styles["headerRest"]);
+        oss.str("");
+        oss.clear();
+        oss << setprecision(2) << fixed << data["duration"].get<float>() / 3600 << " h";
+        worksheet_merge_range(worksheet, 3, 4, 3, 5, oss.str().c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 6, 3, 7, "Platform", styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 8, 3, 9, data["platform"].get<string>().c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 10, 2, 12, ("Random seeds: " + fromVector("seeds")).c_str(), styles["headerSmall"]);
+        oss.str("");
+        oss.clear();
+        oss << "Stratified: " << (data["stratified"].get<bool>() ? "True" : "False");
+        worksheet_merge_range(worksheet, 3, 10, 3, 11, oss.str().c_str(), styles["headerSmall"]);
+        oss.str("");
+        oss.clear();
+        oss << "Discretized: " << (data["discretized"].get<bool>() ? "True" : "False");
+        worksheet_write_string(worksheet, 3, 12, oss.str().c_str(), styles["headerSmall"]);
+    }
+
+    void ReportExcel::body()
+    {
+        auto head = vector<string>(
+            { "Dataset", "Samples", "Features", "Classes", "Nodes", "Edges", "States", "Score", "Score Std.", "St.", "Time",
+             "Time Std.", "Hyperparameters" });
+        int col = 0;
+        for (const auto& item : head) {
+            writeString(5, col++, item, "bodyHeader");
+        }
+        row = 6;
+        col = 0;
+        int hypSize = 22;
+        json lastResult;
+        double totalScore = 0.0;
+        string hyperparameters;
+        for (const auto& r : data["results"]) {
+            writeString(row, col, r["dataset"].get<string>(), "text");
+            writeInt(row, col + 1, r["samples"].get<int>(), "ints");
+            writeInt(row, col + 2, r["features"].get<int>(), "ints");
+            writeInt(row, col + 3, r["classes"].get<int>(), "ints");
+            writeDouble(row, col + 4, r["nodes"].get<float>(), "floats");
+            writeDouble(row, col + 5, r["leaves"].get<float>(), "floats");
+            writeDouble(row, col + 6, r["depth"].get<double>(), "floats");
+            writeDouble(row, col + 7, r["score"].get<double>(), "result");
+            writeDouble(row, col + 8, r["score_std"].get<double>(), "result");
+            const string status = compareResult(r["dataset"].get<string>(), r["score"].get<double>());
+            writeString(row, col + 9, status, "textCentered");
+            writeDouble(row, col + 10, r["time"].get<double>(), "time");
+            writeDouble(row, col + 11, r["time_std"].get<double>(), "time");
+            try {
+                hyperparameters = r["hyperparameters"].get<string>();
+            }
+            catch (const exception& err) {
+                stringstream oss;
+                oss << r["hyperparameters"];
+                hyperparameters = oss.str();
+            }
+            if (hyperparameters.size() > hypSize) {
+                hypSize = hyperparameters.size();
+            }
+            writeString(row, col + 12, hyperparameters, "text");
+            lastResult = r;
+            totalScore += r["score"].get<double>();
+            row++;
+
+        }
+        // Set the right column width of hyperparameters with the maximum length
+        worksheet_set_column(worksheet, 12, 12, hypSize + 5, NULL);
+        // Show totals if only one dataset is present in the result
+        if (data["results"].size() == 1) {
+            for (const string& group : { "scores_train", "scores_test", "times_train", "times_test" }) {
+                row++;
+                col = 1;
+                writeString(row, col, group, "text");
+                for (double item : lastResult[group]) {
+                    string style = group.find("scores") != string::npos ? "result" : "time";
+                    writeDouble(row, ++col, item, style);
+                }
+            }
+            // Set with of columns to show those totals completely
+            worksheet_set_column(worksheet, 1, 1, 12, NULL);
+            for (int i = 2; i < 7; ++i) {
+                // doesn't work with from col to col, so...
+                worksheet_set_column(worksheet, i, i, 15, NULL);
+            }
+        } else {
+            footer(totalScore, row);
+        }
+    }
+
+    void ReportExcel::showSummary()
+    {
+        for (const auto& item : summary) {
+            worksheet_write_string(worksheet, row + 2, 1, item.first.c_str(), styles["summaryStyle"]);
+            worksheet_write_number(worksheet, row + 2, 2, item.second, styles["summaryStyle"]);
+            worksheet_merge_range(worksheet, row + 2, 3, row + 2, 5, meaning.at(item.first).c_str(), styles["summaryStyle"]);
+            row += 1;
+        }
+    }
+
+    void ReportExcel::footer(double totalScore, int row)
+    {
+        showSummary();
+        row += 4 + summary.size();
+        auto score = data["score_name"].get<string>();
+        if (score == BestScore::scoreName()) {
+            worksheet_merge_range(worksheet, row, 1, row, 5, (score + " compared to " + BestScore::title() + " .:").c_str(), efectiveStyle("text"));
+            writeDouble(row, 6, totalScore / BestScore::score(), "result");
+        }
+        if (!getExistBestFile() && compare) {
+            worksheet_write_string(worksheet, row + 1, 0, "*** Best Results File not found. Couldn't compare any result!", styles["summaryStyle"]);
+        }
+    }
+}

src/Platform/ReportExcel.h

@@ -0,0 +1,42 @@
+#ifndef REPORTEXCEL_H
+#define REPORTEXCEL_H
+#include<map>
+#include "xlsxwriter.h"
+#include "ReportBase.h"
+#include "Colors.h"
+namespace platform {
+    using namespace std;
+    const int MAXLL = 128;
+
+    class ReportExcel : public ReportBase {
+    public:
+        explicit ReportExcel(json data_, bool compare, lxw_workbook* workbook);
+        lxw_workbook* getWorkbook();
+    private:
+        void writeString(int row, int col, const string& text, const string& style = "");
+        void writeInt(int row, int col, const int number, const string& style = "");
+        void writeDouble(int row, int col, const double number, const string& style = "");
+        void formatColumns();
+        void createFormats();
+        void setProperties();
+        void createFile();
+        void closeFile();
+        lxw_workbook* workbook;
+        lxw_worksheet* worksheet;
+        map<string, lxw_format*> styles;
+        int row;
+        int normalSize; //font size for report body
+        uint32_t colorTitle;
+        uint32_t colorOdd;
+        uint32_t colorEven;
+        const string fileName = "some_results.xlsx";
+        void header() override;
+        void body() override;
+        void showSummary() override;
+        void footer(double totalScore, int row);
+        void createStyle(const string& name, lxw_format* style, bool odd);
+        void addColor(lxw_format* style, bool odd);
+        lxw_format* efectiveStyle(const string& name);
+    };
+};
+#endif // !REPORTEXCEL_H

src/Platform/Result.cc

@@ -0,0 +1,51 @@
+#include <filesystem>
+#include <fstream>
+#include <sstream>
+#include "Result.h"
+#include "Colors.h"
+#include "BestScore.h"
+namespace platform {
+    Result::Result(const string& path, const string& filename)
+        : path(path)
+        , filename(filename)
+    {
+        auto data = load();
+        date = data["date"];
+        score = 0;
+        for (const auto& result : data["results"]) {
+            score += result["score"].get<double>();
+        }
+        scoreName = data["score_name"];
+        if (scoreName == BestScore::scoreName()) {
+            score /= BestScore::score();
+        }
+        title = data["title"];
+        duration = data["duration"];
+        model = data["model"];
+        complete = data["results"].size() > 1;
+    }
+
+    json Result::load() const
+    {
+        ifstream resultData(path + "/" + filename);
+        if (resultData.is_open()) {
+            json data = json::parse(resultData);
+            return data;
+        }
+        throw invalid_argument("Unable to open result file. [" + path + "/" + filename + "]");
+    }
+
+    string Result::to_string() const
+    {
+        stringstream oss;
+        oss << date << " ";
+        oss << setw(12) << left << model << " ";
+        oss << setw(11) << left << scoreName << " ";
+        oss << right << setw(11) << setprecision(7) << fixed << score << " ";
+        auto completeString = isComplete() ? "C" : "P";
+        oss << setw(1) << " " << completeString << "  ";
+        oss << setw(9) << setprecision(3) << fixed << duration << " ";
+        oss << setw(50) << left << title << " ";
+        return  oss.str();
+    }
+}

src/Platform/Result.h

@@ -0,0 +1,37 @@
+#ifndef RESULT_H
+#define RESULT_H
+#include <map>
+#include <vector>
+#include <string>
+#include <nlohmann/json.hpp>
+namespace platform {
+    using namespace std;
+    using json = nlohmann::json;
+
+    class Result {
+    public:
+        Result(const string& path, const string& filename);
+        json load() const;
+        string to_string() const;
+        string getFilename() const { return filename; };
+        string getDate() const { return date; };
+        double getScore() const { return score; };
+        string getTitle() const { return title; };
+        double getDuration() const { return duration; };
+        string getModel() const { return model; };
+        string getScoreName() const { return scoreName; };
+        bool isComplete() const { return complete; };
+    private:
+        string path;
+        string filename;
+        string date;
+        double score;
+        string title;
+        double duration;
+        string model;
+        string scoreName;
+        bool complete;
+    };
+};
+
+#endif

src/Platform/Results.cc

@@ -0,0 +1,268 @@
+#include <filesystem>
+#include "platformUtils.h"
+#include "Results.h"
+#include "ReportConsole.h"
+#include "ReportExcel.h"
+#include "BestScore.h"
+#include "Colors.h"
+namespace platform {
+    void Results::load()
+    {
+        using std::filesystem::directory_iterator;
+        for (const auto& file : directory_iterator(path)) {
+            auto filename = file.path().filename().string();
+            if (filename.find(".json") != string::npos && filename.find("results_") == 0) {
+                auto result = Result(path, filename);
+                bool addResult = true;
+                if (model != "any" && result.getModel() != model || scoreName != "any" && scoreName != result.getScoreName() || complete && !result.isComplete() || partial && result.isComplete())
+                    addResult = false;
+                if (addResult)
+                    files.push_back(result);
+            }
+        }
+        if (max == 0) {
+            max = files.size();
+        }
+    }
+    void Results::show() const
+    {
+        cout << Colors::GREEN() << "Results found: " << files.size() << endl;
+        cout << "-------------------" << endl;
+        if (complete) {
+            cout << Colors::MAGENTA() << "Only listing complete results" << endl;
+        }
+        if (partial) {
+            cout << Colors::MAGENTA() << "Only listing partial results" << endl;
+        }
+        auto i = 0;
+        cout << Colors::GREEN() << " #  Date       Model        Score Name  Score       C/P Duration  Title" << endl;
+        cout << "=== ========== ============ =========== =========== === ========= =============================================================" << endl;
+        bool odd = true;
+        for (const auto& result : files) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            cout << color << setw(3) << fixed << right << i++ << " ";
+            cout << result.to_string() << endl;
+            if (i == max && max != 0) {
+                break;
+            }
+            odd = !odd;
+        }
+    }
+    int Results::getIndex(const string& intent) const
+    {
+        string color;
+        if (intent == "delete") {
+            color = Colors::RED();
+        } else {
+            color = Colors::YELLOW();
+        }
+        cout << color << "Choose result to " << intent << " (cancel=-1): ";
+        string line;
+        getline(cin, line);
+        int index = stoi(line);
+        if (index >= -1 && index < static_cast<int>(files.size())) {
+            return index;
+        }
+        cout << "Invalid index" << endl;
+        return -1;
+    }
+    void Results::report(const int index, const bool excelReport)
+    {
+        cout << Colors::YELLOW() << "Reporting " << files.at(index).getFilename() << endl;
+        auto data = files.at(index).load();
+        if (excelReport) {
+            ReportExcel reporter(data, compare, workbook);
+            reporter.show();
+            openExcel = true;
+            workbook = reporter.getWorkbook();
+        } else {
+            ReportConsole reporter(data, compare);
+            reporter.show();
+        }
+    }
+    void Results::showIndex(const int index, const int idx) const
+    {
+        auto data = files.at(index).load();
+        if (idx < 0 or idx >= static_cast<int>(data["results"].size())) {
+            cout << "Invalid index" << endl;
+            return;
+        }
+        cout << Colors::YELLOW() << "Showing " << files.at(index).getFilename() << endl;
+        ReportConsole reporter(data, compare, idx);
+        reporter.show();
+    }
+    void Results::menu()
+    {
+        char option;
+        int index;
+        bool finished = false;
+        string color, context;
+        string filename, line, options = "qldhsre";
+        while (!finished) {
+            if (indexList) {
+                color = Colors::GREEN();
+                context = " (quit='q', list='l', delete='d', hide='h', sort='s', report='r', excel='e'): ";
+                options = "qldhsre";
+            } else {
+                color = Colors::MAGENTA();
+                context = " (quit='q', list='l'): ";
+                options = "ql";
+            }
+            cout << Colors::RESET() << color;
+
+            cout << "Choose option " << context;
+            getline(cin, line);
+            if (line.size() == 0)
+                continue;
+            if (options.find(line[0]) != string::npos) {
+                if (line.size() > 1) {
+                    cout << "Invalid option" << endl;
+                    continue;
+                }
+                option = line[0];
+            } else {
+                if (all_of(line.begin(), line.end(), ::isdigit)) {
+                    int idx = stoi(line);
+                    if (indexList) {
+                        // The value is about the files list
+                        index = idx;
+                        if (index >= 0 && index < max) {
+                            report(index, false);
+                            indexList = false;
+                            continue;
+                        }
+                    } else {
+                        // The value is about the result showed on screen
+                        showIndex(index, idx);
+                        continue;
+                    }
+                }
+                cout << "Invalid option" << endl;
+                continue;
+            }
+            switch (option) {
+                case 'q':
+                    finished = true;
+                    break;
+                case 'l':
+                    show();
+                    indexList = true;
+                    break;
+                case 'd':
+                    index = getIndex("delete");
+                    if (index == -1)
+                        break;
+                    filename = files[index].getFilename();
+                    cout << "Deleting " << filename << endl;
+                    remove((path + "/" + filename).c_str());
+                    files.erase(files.begin() + index);
+                    cout << "File: " + filename + " deleted!" << endl;
+                    show();
+                    indexList = true;
+                    break;
+                case 'h':
+                    index = getIndex("hide");
+                    if (index == -1)
+                        break;
+                    filename = files[index].getFilename();
+                    cout << "Hiding " << filename << endl;
+                    rename((path + "/" + filename).c_str(), (path + "/." + filename).c_str());
+                    files.erase(files.begin() + index);
+                    show();
+                    menu();
+                    indexList = true;
+                    break;
+                case 's':
+                    sortList();
+                    indexList = true;
+                    show();
+                    break;
+                case 'r':
+                    index = getIndex("report");
+                    if (index == -1)
+                        break;
+                    indexList = false;
+                    report(index, false);
+                    break;
+                case 'e':
+                    index = getIndex("excel");
+                    if (index == -1)
+                        break;
+                    indexList = true;
+                    report(index, true);
+                    break;
+                default:
+                    cout << "Invalid option" << endl;
+            }
+        }
+    }
+    void Results::sortList()
+    {
+        cout << Colors::YELLOW() << "Choose sorting field (date='d', score='s', duration='u', model='m'): ";
+        string line;
+        char option;
+        getline(cin, line);
+        if (line.size() == 0)
+            return;
+        if (line.size() > 1) {
+            cout << "Invalid option" << endl;
+            return;
+        }
+        option = line[0];
+        switch (option) {
+            case 'd':
+                sortDate();
+                break;
+            case 's':
+                sortScore();
+                break;
+            case 'u':
+                sortDuration();
+                break;
+            case 'm':
+                sortModel();
+                break;
+            default:
+                cout << "Invalid option" << endl;
+        }
+    }
+    void Results::sortDate()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getDate() > b.getDate();
+            });
+    }
+    void Results::sortModel()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getModel() > b.getModel();
+            });
+    }
+    void Results::sortDuration()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getDuration() > b.getDuration();
+            });
+    }
+    void Results::sortScore()
+    {
+        sort(files.begin(), files.end(), [](const Result& a, const Result& b) {
+            return a.getScore() > b.getScore();
+            });
+    }
+    void Results::manage()
+    {
+        if (files.size() == 0) {
+            cout << "No results found!" << endl;
+            exit(0);
+        }
+        sortDate();
+        show();
+        menu();
+        if (openExcel) {
+            workbook_close(workbook);
+        }
+        cout << Colors::RESET() << "Done!" << endl;
+    }
+
+}

src/Platform/Results.h

@@ -0,0 +1,47 @@
+#ifndef RESULTS_H
+#define RESULTS_H
+#include "xlsxwriter.h"
+#include <map>
+#include <vector>
+#include <string>
+#include <nlohmann/json.hpp>
+#include "Result.h"
+namespace platform {
+    using namespace std;
+    using json = nlohmann::json;
+
+    class Results {
+    public:
+        Results(const string& path, const int max, const string& model, const string& score, bool complete, bool partial, bool compare) :
+            path(path), max(max), model(model), scoreName(score), complete(complete), partial(partial), compare(compare)
+        {
+            load();
+        };
+        void manage();
+    private:
+        string path;
+        int max;
+        string model;
+        string scoreName;
+        bool complete;
+        bool partial;
+        bool indexList = true;
+        bool openExcel = false;
+        bool compare;
+        lxw_workbook* workbook = NULL;
+        vector<Result> files;
+        void load(); // Loads the list of results
+        void show() const;
+        void report(const int index, const bool excelReport);
+        void showIndex(const int index, const int idx) const;
+        int getIndex(const string& intent) const;
+        void menu();
+        void sortList();
+        void sortDate();
+        void sortScore();
+        void sortModel();
+        void sortDuration();
+    };
+};
+
+#endif

src/Platform/best.cc

@@ -0,0 +1,63 @@
+#include <iostream>
+#include <argparse/argparse.hpp>
+#include "Paths.h"
+#include "BestResults.h"
+#include "Colors.h"
+
+using namespace std;
+
+argparse::ArgumentParser manageArguments(int argc, char** argv)
+{
+    argparse::ArgumentParser program("best");
+    program.add_argument("-m", "--model").default_value("").help("Filter results of the selected model) (any for all models)");
+    program.add_argument("-s", "--score").default_value("").help("Filter results of the score name supplied");
+    program.add_argument("--build").help("build best score results file").default_value(false).implicit_value(true);
+    program.add_argument("--report").help("report of best score results file").default_value(false).implicit_value(true);
+    try {
+        program.parse_args(argc, argv);
+        auto model = program.get<string>("model");
+        auto score = program.get<string>("score");
+        auto build = program.get<bool>("build");
+        auto report = program.get<bool>("report");
+        if (model == "" || score == "") {
+            throw runtime_error("Model and score name must be supplied");
+        }
+    }
+    catch (const exception& err) {
+        cerr << err.what() << endl;
+        cerr << program;
+        exit(1);
+    }
+    return program;
+}
+
+int main(int argc, char** argv)
+{
+    auto program = manageArguments(argc, argv);
+    auto model = program.get<string>("model");
+    auto score = program.get<string>("score");
+    auto build = program.get<bool>("build");
+    auto report = program.get<bool>("report");
+    if (!report && !build) {
+        cerr << "Either build, report or both, have to be selected to do anything!" << endl;
+        cerr << program;
+        exit(1);
+    }
+    auto results = platform::BestResults(platform::Paths::results(), score, model);
+    if (build) {
+        if (model == "any") {
+            results.buildAll();
+        } else {
+            string fileName = results.build();
+            cout << Colors::GREEN() << fileName << " created!" << Colors::RESET() << endl;
+        }
+    }
+    if (report) {
+        if (model == "any") {
+            results.reportAll();
+        } else {
+            results.reportSingle();
+        }
+    }
+    return 0;
+}

src/Platform/list.cc

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

src/Platform/main.cc

@@ -1,25 +1,27 @@
 #include <iostream>
 #include <argparse/argparse.hpp>
+#include <nlohmann/json.hpp>
 #include "platformUtils.h"
 #include "Experiment.h"
 #include "Datasets.h"
 #include "DotEnv.h"
 #include "Models.h"
 #include "modelRegister.h"
+#include "Paths.h"
+
 
 using namespace std;
-const string PATH_RESULTS = "results";
-const string PATH_DATASETS = "datasets";
+using json = nlohmann::json;
 
 argparse::ArgumentParser manageArguments(int argc, char** argv)
 {
     auto env = platform::DotEnv();
-    argparse::ArgumentParser program("BayesNetSample");
+    argparse::ArgumentParser program("main");
     program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
+    program.add_argument("--hyperparameters").default_value("{}").help("Hyperparamters passed to the model in Experiment");
     program.add_argument("-p", "--path")
         .help("folder where the data files are located, default")
-        .default_value(string{ PATH_DATASETS }
-    );
+        .default_value(string{ platform::Paths::datasets() });
     program.add_argument("-m", "--model")
         .help("Model to use " + platform::Models::instance()->toString())
         .action([](const std::string& value) {
@@ -32,6 +34,7 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
     );
     program.add_argument("--title").default_value("").help("Experiment title");
     program.add_argument("--discretize").help("Discretize input dataset").default_value((bool)stoi(env.get("discretize"))).implicit_value(true);
+    program.add_argument("--save").help("Save result (always save if no dataset is supplied)").default_value(false).implicit_value(true);
     program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value((bool)stoi(env.get("stratified"))).implicit_value(true);
     program.add_argument("-f", "--folds").help("Number of folds").default_value(stoi(env.get("n_folds"))).scan<'i', int>().action([](const string& value) {
         try {
@@ -60,6 +63,8 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
         auto seeds = program.get<vector<int>>("seeds");
         auto complete_file_name = path + file_name + ".arff";
         auto title = program.get<string>("title");
+        auto hyperparameters = program.get<string>("hyperparameters");
+        auto saveResults = program.get<bool>("save");
         if (title == "" && file_name == "") {
             throw runtime_error("title is mandatory if dataset is not provided");
         }
@@ -75,7 +80,6 @@ argparse::ArgumentParser manageArguments(int argc, char** argv)
 int main(int argc, char** argv)
 {
     auto program = manageArguments(argc, argv);
-    bool saveResults = false;
     auto file_name = program.get<string>("dataset");
     auto path = program.get<string>("path");
     auto model_name = program.get<string>("model");
@@ -83,9 +87,11 @@ int main(int argc, char** argv)
     auto stratified = program.get<bool>("stratified");
     auto n_folds = program.get<int>("folds");
     auto seeds = program.get<vector<int>>("seeds");
+    auto hyperparameters = program.get<string>("hyperparameters");
     vector<string> filesToTest;
     auto datasets = platform::Datasets(path, true, platform::ARFF);
     auto title = program.get<string>("title");
+    auto saveResults = program.get<bool>("save");
     if (file_name != "") {
         if (!datasets.isDataset(file_name)) {
             cerr << "Dataset " << file_name << " not found" << endl;
@@ -96,17 +102,18 @@ int main(int argc, char** argv)
         }
         filesToTest.push_back(file_name);
     } else {
-        filesToTest = platform::Datasets(path, true, platform::ARFF).getNames();
+        filesToTest = datasets.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.setTitle(title).setLanguage("cpp").setLanguageVersion("14.0.3");
+    experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
     experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
+    experiment.setHyperparameters(json::parse(hyperparameters));
     for (auto seed : seeds) {
         experiment.addRandomSeed(seed);
     }
@@ -114,10 +121,10 @@ int main(int argc, char** argv)
     timer.start();
     experiment.go(filesToTest, path);
     experiment.setDuration(timer.getDuration());
-    if (saveResults)
-        experiment.save(PATH_RESULTS);
-    else
-        experiment.show();
+    if (saveResults) {
+        experiment.save(platform::Paths::results());
+    }
+    experiment.report();
     cout << "Done!" << endl;
     return 0;
 }

src/Platform/manage.cc

@@ -0,0 +1,52 @@
+#include <iostream>
+#include <argparse/argparse.hpp>
+#include "platformUtils.h"
+#include "Paths.h"
+#include "Results.h"
+
+using namespace std;
+
+argparse::ArgumentParser manageArguments(int argc, char** argv)
+{
+    argparse::ArgumentParser program("manage");
+    program.add_argument("-n", "--number").default_value(0).help("Number of results to show (0 = all)").scan<'i', int>();
+    program.add_argument("-m", "--model").default_value("any").help("Filter results of the selected model)");
+    program.add_argument("-s", "--score").default_value("any").help("Filter results of the score name supplied");
+    program.add_argument("--complete").help("Show only results with all datasets").default_value(false).implicit_value(true);
+    program.add_argument("--partial").help("Show only partial results").default_value(false).implicit_value(true);
+    program.add_argument("--compare").help("Compare with best results").default_value(false).implicit_value(true);
+    try {
+        program.parse_args(argc, argv);
+        auto number = program.get<int>("number");
+        if (number < 0) {
+            throw runtime_error("Number of results must be greater than or equal to 0");
+        }
+        auto model = program.get<string>("model");
+        auto score = program.get<string>("score");
+        auto complete = program.get<bool>("complete");
+        auto partial = program.get<bool>("partial");
+        auto compare = program.get<bool>("compare");
+    }
+    catch (const exception& err) {
+        cerr << err.what() << endl;
+        cerr << program;
+        exit(1);
+    }
+    return program;
+}
+
+int main(int argc, char** argv)
+{
+    auto program = manageArguments(argc, argv);
+    auto number = program.get<int>("number");
+    auto model = program.get<string>("model");
+    auto score = program.get<string>("score");
+    auto complete = program.get<bool>("complete");
+    auto partial = program.get<bool>("partial");
+    auto compare = program.get<bool>("compare");
+    if (complete)
+        partial = false;
+    auto results = platform::Results(platform::Paths::results(), number, model, score, complete, partial, compare);
+    results.manage();
+    return 0;
+}

src/Platform/modelRegister.h

@@ -2,10 +2,20 @@
 #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();});
+static platform::Registrar registrarBA("BoostAODE",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::BoostAODE();});
 #endif

src/Platform/platformUtils.cc

@@ -1,4 +1,5 @@
 #include "platformUtils.h"
+#include "Paths.h"
 
 using namespace torch;
 
@@ -68,11 +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) {
@@ -85,7 +87,7 @@ tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadData
 tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(const string& name)
 {
     auto handler = ArffFiles();
-    handler.load(PATH + static_cast<string>(name) + ".arff");
+    handler.load(platform::Paths::datasets() + static_cast<string>(name) + ".arff");
     // Get Dataset X, y
     vector<mdlp::samples_t>& X = handler.getX();
     mdlp::labels_t& y = handler.getY();

src/Platform/platformUtils.h

@@ -8,7 +8,6 @@
 #include "ArffFiles.h"
 #include "CPPFImdlp.h"
 using namespace std;
-const string PATH = "../../data/";
 
 bool file_exists(const std::string& name);
 vector<string> split(const string& text, char delimiter);

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" } });

tests/CMakeLists.txt

@@ -4,6 +4,7 @@ if(ENABLE_TESTING)
     include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
     include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
     include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
+    include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
     set(TEST_SOURCES BayesModels.cc BayesNetwork.cc ${BayesNet_SOURCE_DIR}/src/Platform/platformUtils.cc ${BayesNet_SOURCES})
     add_executable(${TEST_MAIN} ${TEST_SOURCES})
     target_link_libraries(${TEST_MAIN} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain)