Check min number of nested folds

Reviewed-on: #14

.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

@@ -31,7 +31,10 @@
 *.exe
 *.out
 *.app
-build/
+build/**
+build_*/**
 *.dSYM/**
 cmake-build*/**
 .idea
+puml/**
+.vscode/settings.json

.gitmodules

@@ -1,12 +1,25 @@
 [submodule "lib/mdlp"]
 	path = lib/mdlp
 	url = https://github.com/rmontanana/mdlp
+	main = main
+	update = merge
 [submodule "lib/catch2"]
 	path = lib/catch2
+        main  = v2.x
+	update = merge
 	url = https://github.com/catchorg/Catch2.git
 [submodule "lib/argparse"]
 	path = lib/argparse
 	url = https://github.com/p-ranav/argparse
+	master = master
+	update = merge
 [submodule "lib/json"]
 	path = lib/json
 	url = https://github.com/nlohmann/json.git
+        master = master
+	update = merge
+[submodule "lib/libxlsxwriter"]
+	path = lib/libxlsxwriter
+	url = https://github.com/jmcnamara/libxlsxwriter.git
+        main = main
+	update = merge

.vscode/c_cpp_properties.json

@@ -0,0 +1,18 @@
+{
+    "configurations": [
+        {
+            "name": "Mac",
+            "includePath": [
+                "${workspaceFolder}/**"
+            ],
+            "defines": [],
+            "macFrameworkPath": [
+                "/Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk/System/Library/Frameworks"
+            ],
+            "cStandard": "c17",
+            "cppStandard": "c++17",
+            "compileCommands": "${workspaceFolder}/cmake-build-release/compile_commands.json"
+        }
+    ],
+    "version": 4
+}

.vscode/launch.json

@@ -5,12 +5,12 @@
             "type": "lldb",
             "request": "launch",
             "name": "sample",
-            "program": "${workspaceFolder}/build/sample/BayesNetSample",
+            "program": "${workspaceFolder}/build_debug/sample/BayesNetSample",
             "args": [
                 "-d",
                 "iris",
                 "-m",
-                "KDB",
+                "TANLd",
                 "-s",
                 "271",
                 "-p",
@@ -21,24 +21,103 @@
         {
             "type": "lldb",
             "request": "launch",
-            "name": "experiment",
-            "program": "${workspaceFolder}/build/src/Platform/main",
+            "name": "experimentPy",
+            "program": "${workspaceFolder}/build_debug/src/Platform/b_main",
             "args": [
                 "-m",
-                "AODELd",
-                "-p",
-                "/Users/rmontanana/Code/discretizbench/datasets",
+                "STree",
                 "--stratified",
                 "-d",
-                "iris"
+                "iris",
+                //"--discretize"
+                // "--hyperparameters",
+                // "{\"repeatSparent\": true, \"maxModels\": 12}"
             ],
-            "cwd": "/Users/rmontanana/Code/discretizbench",
+            "cwd": "${workspaceFolder}/../discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "gridsearch",
+            "program": "${workspaceFolder}/build_debug/src/Platform/b_grid",
+            "args": [
+                "-m",
+                "KDB",
+                "--discretize",
+                "--continue",
+                "glass",
+                "--only",
+                "--compute"
+            ],
+            "cwd": "${workspaceFolder}/../discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "experimentBayes",
+            "program": "${workspaceFolder}/build_debug/src/Platform/b_main",
+            "args": [
+                "-m",
+                "TAN",
+                "--stratified",
+                "--discretize",
+                "-d",
+                "iris",
+                "--hyperparameters",
+                "{\"repeatSparent\": true, \"maxModels\": 12}"
+            ],
+            "cwd": "/home/rmontanana/Code/discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "best",
+            "program": "${workspaceFolder}/build_debug/src/Platform/b_best",
+            "args": [
+                "-m",
+                "BoostAODE",
+                "-s",
+                "accuracy",
+                "--build",
+            ],
+            "cwd": "${workspaceFolder}/../discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "manage",
+            "program": "${workspaceFolder}/build_debug/src/Platform/b_manage",
+            "args": [
+                "-n",
+                "20"
+            ],
+            "cwd": "${workspaceFolder}/../discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "list",
+            "program": "${workspaceFolder}/build_debug/src/Platform/b_list",
+            "args": [],
+            //"cwd": "/Users/rmontanana/Code/discretizbench",
+            "cwd": "${workspaceFolder}/../discretizbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "test",
+            "program": "${workspaceFolder}/build_debug/tests/unit_tests",
+            "args": [
+                "-c=\"Metrics Test\"",
+                // "-s",
+            ],
+            "cwd": "${workspaceFolder}/build/tests",
         },
         {
             "name": "Build & debug active file",
             "type": "cppdbg",
             "request": "launch",
-            "program": "${workspaceFolder}/build/bayesnet",
+            "program": "${workspaceFolder}/build_debug/bayesnet",
             "args": [],
             "stopAtEntry": false,
             "cwd": "${workspaceFolder}",

.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

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(BayesNet
-  VERSION 0.1.0
+  VERSION 0.2.0
   DESCRIPTION "Bayesian Network and basic classifiers Library."
   HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
   LANGUAGES CXX
@@ -24,24 +24,44 @@ set(CMAKE_CXX_STANDARD_REQUIRED            ON)
 set(CMAKE_CXX_EXTENSIONS                  OFF)
 set(CMAKE_EXPORT_COMPILE_COMMANDS          ON)
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
-
+SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
 # Options
 # -------
 option(ENABLE_CLANG_TIDY "Enable to add clang tidy."              OFF)
 option(ENABLE_TESTING "Unit testing build"                        OFF)
 option(CODE_COVERAGE "Collect coverage from test library"         OFF)
+option(MPI_ENABLED "Enable MPI options"                           ON)
+
+if (MPI_ENABLED)
+  find_package(MPI REQUIRED)
+  message("MPI_CXX_LIBRARIES=${MPI_CXX_LIBRARIES}")
+  message("MPI_CXX_INCLUDE_DIRS=${MPI_CXX_INCLUDE_DIRS}")
+endif (MPI_ENABLED)
+
+# Boost Library
+set(Boost_USE_STATIC_LIBS OFF) 
+set(Boost_USE_MULTITHREADED ON)  
+set(Boost_USE_STATIC_RUNTIME OFF) 
+find_package(Boost 1.66.0 REQUIRED COMPONENTS python3 numpy3) 
+if(Boost_FOUND)
+    message("Boost_INCLUDE_DIRS=${Boost_INCLUDE_DIRS}")
+    include_directories(${Boost_INCLUDE_DIRS}) 
+endif()
+
+# Python
+find_package(Python3 3.11...3.11.9 COMPONENTS Interpreter Development REQUIRED)
+message("Python3_LIBRARIES=${Python3_LIBRARIES}")
 
 # CMakes modules
 # --------------
 set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
-
 include(AddGitSubmodule)
+
 if (CODE_COVERAGE)
     enable_testing()
     include(CodeCoverage)
     MESSAGE("Code coverage enabled")
-    set(CMAKE_C_FLAGS " ${CMAKE_C_FLAGS} -fprofile-arcs -ftest-coverage")
-    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage")
+    set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage -O0 -g")
     SET(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
 endif (CODE_COVERAGE)
 
@@ -56,15 +76,21 @@ add_git_submodule("lib/mdlp")
 add_git_submodule("lib/argparse")
 add_git_submodule("lib/json")
 
+
+find_library(XLSXWRITER_LIB NAMES libxlsxwriter.dylib libxlsxwriter.so PATHS ${BayesNet_SOURCE_DIR}/lib/libxlsxwriter/lib)
+message("XLSXWRITER_LIB=${XLSXWRITER_LIB}")
+
+
 # Subdirectories
 # --------------
 add_subdirectory(config)
 add_subdirectory(lib/Files)
 add_subdirectory(src/BayesNet)
 add_subdirectory(src/Platform)
+add_subdirectory(src/PyClassifiers)
 add_subdirectory(sample)
 
-file(GLOB BayesNet_HEADERS CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/BayesNet/*.h ${BayesNet_SOURCE_DIR}/BayesNet/*.hpp)
+file(GLOB BayesNet_HEADERS CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/BayesNet/*.h ${BayesNet_SOURCE_DIR}/BayesNet/*.h)
 file(GLOB BayesNet_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/BayesNet/*.cc ${BayesNet_SOURCE_DIR}/src/BayesNet/*.cpp)
 file(GLOB Platform_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/Platform/*.cc ${BayesNet_SOURCE_DIR}/src/Platform/*.cpp)
 
@@ -74,7 +100,6 @@ file(GLOB Platform_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/Platform
 if (ENABLE_TESTING)
   MESSAGE("Testing enabled")
   add_git_submodule("lib/catch2")  
-  
   include(CTest)
   add_subdirectory(tests)
 endif (ENABLE_TESTING)

Makefile

@@ -1,6 +1,26 @@
 SHELL := /bin/bash
 .DEFAULT_GOAL := help
-.PHONY: coverage setup help build test
+.PHONY: coverage setup help build test clean debug release
+
+f_release = build_release
+f_debug = build_debug
+app_targets = b_best b_list b_main b_manage b_grid
+test_targets = unit_tests_bayesnet unit_tests_platform
+n_procs = -j 16
+
+define ClearTests
+	@for t in $(test_targets); do \
+		if [ -f $(f_debug)/tests/$$t ]; then \
+			echo ">>> Cleaning $$t..." ; \
+			rm -f $(f_debug)/tests/$$t ; \
+		fi ; \
+	done
+	@nfiles="$(find . -name "*.gcda" -print0)" ; \
+	if test "${nfiles}" != "" ; then \
+		find . -name "*.gcda" -print0 | xargs -0 rm 2>/dev/null ;\
+	fi ; 
+endef
+
 
 setup: ## Install dependencies for tests and coverage
 	@if [ "$(shell uname)" = "Darwin" ]; then \
@@ -11,49 +31,87 @@ setup: ## Install dependencies for tests and coverage
 		pip install gcovr; \
 	fi
 
+dest ?= ${HOME}/bin
+install: ## Copy binary files to bin folder
+	@echo "Destination folder: $(dest)"
+	make buildr
+	@echo "*******************************************"
+	@echo ">>> Copying files to $(dest)"
+	@echo "*******************************************"
+	@for item in $(app_targets); do \
+		echo ">>> Copying $$item" ; \
+		cp $(f_release)/src/Platform/$$item $(dest) ; \
+	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
+	@echo ">>> Creating dependency graph diagram of the project...";
+	$(MAKE) debug
+	cd $(f_debug) && cmake .. --graphviz=dependency.dot && dot -Tpng dependency.dot -o dependency.png
 
-build: ## Build the main and BayesNetSample
-	cmake --build build -t main -t BayesNetSample -j 32
+buildd: ## Build the debug targets
+	cmake --build $(f_debug) -t $(app_targets) BayesNetSample $(n_procs)
 
-clean: ## Clean the debug info
-	@echo ">>> Cleaning Debug BayesNet ...";
-	find . -name "*.gcda" -print0 | xargs -0 rm
+buildr: ## Build the release targets
+	cmake --build $(f_release) -t $(app_targets) BayesNetSample $(n_procs)
+
+clean: ## Clean the tests info
+	@echo ">>> Cleaning Debug BayesNet tests...";
+	$(call ClearTests)
 	@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 -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CODE_COVERAGE=ON; \
-	cmake --build build -j 32;
+	@if [ -d ./$(f_debug) ]; then rm -rf ./$(f_debug); fi
+	@mkdir $(f_debug); 
+	@cmake -S . -B $(f_debug) -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CODE_COVERAGE=ON
 	@echo ">>> Done";
 
 release: ## Build a Release version of the project
 	@echo ">>> Building Release BayesNet...";
-	@if [ -d ./build ]; then rm -rf ./build; fi
-	@mkdir build; 
-	cmake -S . -B build -D CMAKE_BUILD_TYPE=Release; \
-	cmake --build build -t main -t BayesNetSample -j 32;
+	@if [ -d ./$(f_release) ]; then rm -rf ./$(f_release); fi
+	@mkdir $(f_release); 
+	@cmake -S . -B $(f_release) -D CMAKE_BUILD_TYPE=Release
 	@echo ">>> Done";	
 
-test: ## Run tests
-	@echo "* Running tests...";
-	find . -name "*.gcda" -print0 | xargs -0 rm
-	@cd build; \
-	cmake --build . --target unit_tests ;
-	@cd build/tests; \
-	./unit_tests;
+opt = ""
+test: ## Run tests (opt="-s") to verbose output the tests, (opt="-c='Test Maximum Spanning Tree'") to run only that section
+	@echo ">>> Running BayesNet & Platform tests...";
+	@$(MAKE) clean
+	@cmake --build $(f_debug) -t $(test_targets) $(n_procs)
+	@for t in $(test_targets); do \
+		if [ -f $(f_debug)/tests/$$t ]; then \
+			cd $(f_debug)/tests ; \
+			./$$t $(opt) ; \
+		fi ; \
+	done
+	@echo ">>> Done";
+
+opt = ""
+testp: ## Run platform tests (opt="-s") to verbose output the tests, (opt="-c='Stratified Fold Test'") to run only that section
+	@echo ">>> Running Platform tests...";
+	@$(MAKE) clean
+	@cmake --build $(f_debug) --target unit_tests_platform $(n_procs)
+	@if [ -f $(f_debug)/tests/unit_tests_platform ]; then cd $(f_debug)/tests ; ./unit_tests_platform $(opt) ; fi ; 
+	@echo ">>> Done";
+
+opt = ""
+testb: ## Run BayesNet tests (opt="-s") to verbose output the tests, (opt="-c='Test Maximum Spanning Tree'") to run only that section
+	@echo ">>> Running BayesNet tests...";
+	@$(MAKE) clean
+	@cmake --build $(f_debug) --target unit_tests_bayesnet $(n_procs)
+	@if [ -f $(f_debug)/tests/unit_tests_bayesnet ]; then cd $(f_debug)/tests ; ./unit_tests_bayesnet $(opt) ; fi ; 
+	@echo ">>> Done";
 
 coverage: ## Run tests and generate coverage report (build/index.html)
-	@echo "*Building tests...";
-	find . -name "*.gcda" -print0 | xargs -0 rm
-	@cd build; \
-	cmake --build . --target unit_tests ;
-	@cd build/tests; \
-	./unit_tests;
-	gcovr ;
+	@echo ">>> Building tests with coverage...";
+	@$(MAKE) test
+	@cd $(f_debug) ; \
+	gcovr --config ../gcovr.cfg tests ;
+	@echo ">>> Done";	
+
 
 help: ## Show help message
 	@IFS=$$'\n' ; \

README.md

@@ -1,5 +1,91 @@
 # BayesNet
 
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
 Bayesian Network Classifier with libtorch from scratch
 
+## 0. Setup
+
+Before compiling BayesNet.
+
+### Miniconda
+
+To be able to run Python Classifiers such as STree, ODTE, SVC, etc. it is needed to install Miniconda. To do so, download the installer from [Miniconda](https://docs.conda.io/en/latest/miniconda.html) and run it. It is recommended to install it in the home folder.
+
+In Linux sometimes the library libstdc++ is mistaken from the miniconda installation and produces the next message when running the b_xxxx executables:
+
+```bash
+libstdc++.so.6: version `GLIBCXX_3.4.32' not found (required by b_xxxx)
+```
+
+The solution is to erase the libstdc++ library from the miniconda installation:
+
+### MPI
+
+In Linux just install openmpi & openmpi-devel packages. Only if cmake can't find openmpi installation (like in Oracle Linux) set the following variable:
+
+```bash
+export MPI_HOME="/usr/lib64/openmpi"
+```
+
+In Mac OS X, install mpich with brew and if cmake doesn't find it, edit mpicxx wrapper to remove the ",-commons,use_dylibs" from final_ldflags
+
+```bash
+vi /opt/homebrew/bin/mpicx
+```
+
+### boost library
+
+[Getting Started](<https://www.boost.org/doc/libs/1_83_0/more/getting_started/index.html>)
+
+The best option is install the packages that the Linux distribution have in its repository. If this is the case:
+
+```bash
+sudo dnf install boost-devel
+```
+
+If this is not possible and the compressed packaged is installed, the following environment variable has to be set pointing to the folder where it was unzipped to:
+
+```bash
+export BOOST_ROOT=/path/to/library/
+```
+
+In some cases, it is needed to build the library, to do so:
+
+```bash
+cd /path/to/library
+mkdir own
+./bootstrap.sh --prefix=/path/to/library/own
+./b2 install
+export BOOST_ROOT=/path/to/library/own/
+```
+
+Don't forget to add the export BOOST_ROOT statement to .bashrc or wherever it is meant to be.
+
+### libxlswriter
+
+```bash
+cd lib/libxlsxwriter
+make
+make install DESTDIR=/home/rmontanana/Code PREFIX=
+```
+
+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

TAN_iris.dot

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

data/_TAN_cpp_accuracy__.json

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

grid_stree.json

@@ -0,0 +1,162 @@
+{
+    "balance-scale": {
+        "C": 10000.0,
+        "gamma": 0.1,
+        "kernel": "rbf",
+        "max_iter": 10000
+    },
+    "balloons": {
+        "C": 7,
+        "gamma": 0.1,
+        "kernel": "rbf",
+        "max_iter": 10000
+    },
+    "breast-cancer-wisc-diag": {
+        "C": 0.2,
+        "max_iter": 10000
+    },
+    "breast-cancer-wisc-prog": {
+        "C": 0.2,
+        "max_iter": 10000
+    },
+    "breast-cancer-wisc": {},
+    "breast-cancer": {},
+    "cardiotocography-10clases": {},
+    "cardiotocography-3clases": {},
+    "conn-bench-sonar-mines-rocks": {},
+    "cylinder-bands": {},
+    "dermatology": {
+        "C": 55,
+        "max_iter": 10000
+    },
+    "echocardiogram": {
+        "C": 7,
+        "gamma": 0.1,
+        "kernel": "poly",
+        "max_features": "auto",
+        "max_iter": 10000
+    },
+    "fertility": {
+        "C": 0.05,
+        "max_features": "auto",
+        "max_iter": 10000
+    },
+    "haberman-survival": {},
+    "heart-hungarian": {
+        "C": 0.05,
+        "max_iter": 10000
+    },
+    "hepatitis": {
+        "C": 7,
+        "gamma": 0.1,
+        "kernel": "rbf",
+        "max_iter": 10000
+    },
+    "ilpd-indian-liver": {},
+    "ionosphere": {
+        "C": 7,
+        "gamma": 0.1,
+        "kernel": "rbf",
+        "max_iter": 10000
+    },
+    "iris": {},
+    "led-display": {},
+    "libras": {
+        "C": 0.08,
+        "max_iter": 10000
+    },
+    "low-res-spect": {
+        "C": 0.05,
+        "max_iter": 10000
+    },
+    "lymphography": {
+        "C": 0.05,
+        "max_iter": 10000
+    },
+    "mammographic": {},
+    "molec-biol-promoter": {
+        "C": 0.05,
+        "gamma": 0.1,
+        "kernel": "poly",
+        "max_iter": 10000
+    },
+    "musk-1": {
+        "C": 0.05,
+        "gamma": 0.1,
+        "kernel": "poly",
+        "max_iter": 10000
+    },
+    "oocytes_merluccius_nucleus_4d": {
+        "C": 8.25,
+        "gamma": 0.1,
+        "kernel": "poly"
+    },
+    "oocytes_merluccius_states_2f": {},
+    "oocytes_trisopterus_nucleus_2f": {},
+    "oocytes_trisopterus_states_5b": {
+        "C": 0.11,
+        "max_iter": 10000
+    },
+    "parkinsons": {},
+    "pima": {},
+    "pittsburg-bridges-MATERIAL": {
+        "C": 7,
+        "gamma": 0.1,
+        "kernel": "rbf",
+        "max_iter": 10000
+    },
+    "pittsburg-bridges-REL-L": {},
+    "pittsburg-bridges-SPAN": {
+        "C": 0.05,
+        "max_iter": 10000
+    },
+    "pittsburg-bridges-T-OR-D": {},
+    "planning": {
+        "C": 7,
+        "gamma": 10.0,
+        "kernel": "rbf",
+        "max_iter": 10000
+    },
+    "post-operative": {
+        "C": 55,
+        "degree": 5,
+        "gamma": 0.1,
+        "kernel": "poly",
+        "max_iter": 10000
+    },
+    "seeds": {
+        "C": 10000.0,
+        "max_iter": 10000
+    },
+    "statlog-australian-credit": {
+        "C": 0.05,
+        "max_features": "auto",
+        "max_iter": 10000
+    },
+    "statlog-german-credit": {},
+    "statlog-heart": {},
+    "statlog-image": {
+        "C": 7,
+        "max_iter": 10000
+    },
+    "statlog-vehicle": {},
+    "synthetic-control": {
+        "C": 0.55,
+        "max_iter": 10000
+    },
+    "tic-tac-toe": {
+        "C": 0.2,
+        "gamma": 0.1,
+        "kernel": "poly",
+        "max_iter": 10000
+    },
+    "vertebral-column-2clases": {},
+    "wine": {
+        "C": 0.55,
+        "max_iter": 10000
+    },
+    "zoo": {
+        "C": 0.1,
+        "max_iter": 10000
+    }
+}

lib/Files/ArffFiles.cc

@@ -4,11 +4,9 @@
 #include <map>
 #include <iostream>
 
-using namespace std;
-
 ArffFiles::ArffFiles() = default;
 
-vector<string> ArffFiles::getLines() const
+std::vector<std::string> ArffFiles::getLines() const
 {
     return lines;
 }
@@ -18,48 +16,48 @@ unsigned long int ArffFiles::getSize() const
     return lines.size();
 }
 
-vector<pair<string, string>> ArffFiles::getAttributes() const
+std::vector<std::pair<std::string, std::string>> ArffFiles::getAttributes() const
 {
     return attributes;
 }
 
-string ArffFiles::getClassName() const
+std::string ArffFiles::getClassName() const
 {
     return className;
 }
 
-string ArffFiles::getClassType() const
+std::string ArffFiles::getClassType() const
 {
     return classType;
 }
 
-vector<vector<float>>& ArffFiles::getX()
+std::vector<std::vector<float>>& ArffFiles::getX()
 {
     return X;
 }
 
-vector<int>& ArffFiles::getY()
+std::vector<int>& ArffFiles::getY()
 {
     return y;
 }
 
-void ArffFiles::loadCommon(string fileName)
+void ArffFiles::loadCommon(std::string fileName)
 {
-    ifstream file(fileName);
+    std::ifstream file(fileName);
     if (!file.is_open()) {
-        throw invalid_argument("Unable to open file");
+        throw std::invalid_argument("Unable to open file");
     }
-    string line;
-    string keyword;
-    string attribute;
-    string type;
-    string type_w;
+    std::string line;
+    std::string keyword;
+    std::string attribute;
+    std::string type;
+    std::string type_w;
     while (getline(file, line)) {
         if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
             continue;
         }
-        if (line.find("@attribute") != string::npos || line.find("@ATTRIBUTE") != string::npos) {
-            stringstream ss(line);
+        if (line.find("@attribute") != std::string::npos || line.find("@ATTRIBUTE") != std::string::npos) {
+            std::stringstream ss(line);
             ss >> keyword >> attribute;
             type = "";
             while (ss >> type_w)
@@ -74,35 +72,35 @@ void ArffFiles::loadCommon(string fileName)
     }
     file.close();
     if (attributes.empty())
-        throw invalid_argument("No attributes found");
+        throw std::invalid_argument("No attributes found");
 }
 
-void ArffFiles::load(const string& fileName, bool classLast)
+void ArffFiles::load(const std::string& fileName, bool classLast)
 {
     int labelIndex;
     loadCommon(fileName);
     if (classLast) {
-        className = get<0>(attributes.back());
-        classType = get<1>(attributes.back());
+        className = std::get<0>(attributes.back());
+        classType = std::get<1>(attributes.back());
         attributes.pop_back();
         labelIndex = static_cast<int>(attributes.size());
     } else {
-        className = get<0>(attributes.front());
-        classType = get<1>(attributes.front());
+        className = std::get<0>(attributes.front());
+        classType = std::get<1>(attributes.front());
         attributes.erase(attributes.begin());
         labelIndex = 0;
     }
     generateDataset(labelIndex);
 }
-void ArffFiles::load(const string& fileName, const string& name)
+void ArffFiles::load(const std::string& fileName, const std::string& name)
 {
     int labelIndex;
     loadCommon(fileName);
     bool found = false;
     for (int i = 0; i < attributes.size(); ++i) {
         if (attributes[i].first == name) {
-            className = get<0>(attributes[i]);
-            classType = get<1>(attributes[i]);
+            className = std::get<0>(attributes[i]);
+            classType = std::get<1>(attributes[i]);
             attributes.erase(attributes.begin() + i);
             labelIndex = i;
             found = true;
@@ -110,19 +108,19 @@ void ArffFiles::load(const string& fileName, const string& name)
         }
     }
     if (!found) {
-        throw invalid_argument("Class name not found");
+        throw std::invalid_argument("Class name not found");
     }
     generateDataset(labelIndex);
 }
 
 void ArffFiles::generateDataset(int labelIndex)
 {
-    X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
-    auto yy = vector<string>(lines.size(), "");
-    auto removeLines = vector<int>(); // Lines with missing values
+    X = std::vector<std::vector<float>>(attributes.size(), std::vector<float>(lines.size()));
+    auto yy = std::vector<std::string>(lines.size(), "");
+    auto removeLines = std::vector<int>(); // Lines with missing values
     for (size_t i = 0; i < lines.size(); i++) {
-        stringstream ss(lines[i]);
-        string value;
+        std::stringstream ss(lines[i]);
+        std::string value;
         int pos = 0;
         int xIndex = 0;
         while (getline(ss, value, ',')) {
@@ -146,21 +144,21 @@ void ArffFiles::generateDataset(int labelIndex)
     y = factorize(yy);
 }
 
-string ArffFiles::trim(const string& source)
+std::string ArffFiles::trim(const std::string& source)
 {
-    string s(source);
+    std::string s(source);
     s.erase(0, s.find_first_not_of(" '\n\r\t"));
     s.erase(s.find_last_not_of(" '\n\r\t") + 1);
     return s;
 }
 
-vector<int> ArffFiles::factorize(const vector<string>& labels_t)
+std::vector<int> ArffFiles::factorize(const std::vector<std::string>& labels_t)
 {
-    vector<int> yy;
+    std::vector<int> yy;
     yy.reserve(labels_t.size());
-    map<string, int> labelMap;
+    std::map<std::string, int> labelMap;
     int i = 0;
-    for (const string& label : labels_t) {
+    for (const std::string& label : labels_t) {
         if (labelMap.find(label) == labelMap.end()) {
             labelMap[label] = i++;
         }

lib/Files/ArffFiles.h

@@ -4,31 +4,29 @@
 #include <string>
 #include <vector>
 
-using namespace std;
-
 class ArffFiles {
 private:
-    vector<string> lines;
-    vector<pair<string, string>> attributes;
-    string className;
-    string classType;
-    vector<vector<float>> X;
-    vector<int> y;
+    std::vector<std::string> lines;
+    std::vector<std::pair<std::string, std::string>> attributes;
+    std::string className;
+    std::string classType;
+    std::vector<std::vector<float>> X;
+    std::vector<int> y;
     void generateDataset(int);
-    void loadCommon(string);
+    void loadCommon(std::string);
 public:
     ArffFiles();
-    void load(const string&, bool = true);
-    void load(const string&, const string&);
-    vector<string> getLines() const;
+    void load(const std::string&, bool = true);
+    void load(const std::string&, const std::string&);
+    std::vector<std::string> getLines() const;
     unsigned long int getSize() const;
-    string getClassName() const;
-    string getClassType() const;
-    static string trim(const string&);
-    vector<vector<float>>& getX();
-    vector<int>& getY();
-    vector<pair<string, string>> getAttributes() const;
-    static vector<int> factorize(const vector<string>& labels_t);
+    std::string getClassName() const;
+    std::string getClassType() const;
+    static std::string trim(const std::string&);
+    std::vector<std::vector<float>>& getX();
+    std::vector<int>& getY();
+    std::vector<std::pair<std::string, std::string>> getAttributes() const;
+    static std::vector<int> factorize(const std::vector<std::string>& labels_t);
 };
 
 #endif

lib/Files/CMakeLists.txt

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

sample/CMakeLists.txt

@@ -1,7 +1,10 @@
 include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
 include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
+include_directories(${BayesNet_SOURCE_DIR}/src/PyClassifiers)
+include_directories(${Python3_INCLUDE_DIRS})
 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}")
+target_link_libraries(BayesNetSample BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}" PyWrap)

sample/sample.cc

@@ -3,22 +3,21 @@
 #include <string>
 #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>
 
+const std::string PATH = "../../data/";
 
-using namespace std;
-
-const string PATH = "../../data/";
-
-pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features)
+pair<std::vector<mdlp::labels_t>, map<std::string, int>> discretize(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y, std::vector<std::string> features)
 {
-    vector<mdlp::labels_t>Xd;
-    map<string, int> maxes;
+    std::vector<mdlp::labels_t>Xd;
+    map<std::string, int> maxes;
 
     auto fimdlp = mdlp::CPPFImdlp();
     for (int i = 0; i < X.size(); i++) {
@@ -39,12 +38,12 @@ bool file_exists(const std::string& name)
         return false;
     }
 }
-pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vector<vector<int>> X, vector<int> y)
+pair<std::vector<std::vector<int>>, std::vector<int>> extract_indices(std::vector<int> indices, std::vector<std::vector<int>> X, std::vector<int> y)
 {
-    vector<vector<int>> Xr; // nxm
-    vector<int> yr;
+    std::vector<std::vector<int>> Xr; // nxm
+    std::vector<int> yr;
     for (int col = 0; col < X.size(); ++col) {
-        Xr.push_back(vector<int>());
+        Xr.push_back(std::vector<int>());
     }
     for (auto index : indices) {
         for (int col = 0; col < X.size(); ++col) {
@@ -57,7 +56,7 @@ pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vect
 
 int main(int argc, char** argv)
 {
-    map<string, bool> datasets = {
+    map<std::string, bool> datasets = {
             {"diabetes",           true},
             {"ecoli",              true},
             {"glass",              true},
@@ -67,9 +66,9 @@ int main(int argc, char** argv)
             {"liver-disorders",    true},
             {"mfeat-factors",      true},
     };
-    auto valid_datasets = vector<string>();
+    auto valid_datasets = std::vector<std::string>();
     transform(datasets.begin(), datasets.end(), back_inserter(valid_datasets),
-        [](const pair<string, bool>& pair) { return pair.first; });
+        [](const pair<std::string, bool>& pair) { return pair.first; });
     argparse::ArgumentParser program("BayesNetSample");
     program.add_argument("-d", "--dataset")
         .help("Dataset file name")
@@ -82,23 +81,23 @@ int main(int argc, char** argv)
     );
     program.add_argument("-p", "--path")
         .help(" folder where the data files are located, default")
-        .default_value(string{ PATH }
+        .default_value(std::string{ PATH }
     );
     program.add_argument("-m", "--model")
-        .help("Model to use " + platform::Models::instance()->toString())
+        .help("Model to use " + platform::Models::instance()->tostring())
         .action([](const std::string& value) {
-        static const vector<string> choices = platform::Models::instance()->getNames();
+        static const std::vector<std::string> choices = platform::Models::instance()->getNames();
         if (find(choices.begin(), choices.end(), value) != choices.end()) {
             return value;
         }
-        throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
+        throw runtime_error("Model must be one of " + platform::Models::instance()->tostring());
             }
     );
     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) {
+    program.add_argument("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const std::string& value) {
         try {
             auto k = stoi(value);
             if (k < 2) {
@@ -114,13 +113,13 @@ int main(int argc, char** argv)
         }});
     program.add_argument("-s", "--seed").help("Random seed").default_value(-1).scan<'i', int>();
     bool class_last, stratified, tensors, dump_cpt;
-    string model_name, file_name, path, complete_file_name;
+    std::string model_name, file_name, path, complete_file_name;
     int nFolds, seed;
     try {
         program.parse_args(argc, argv);
-        file_name = program.get<string>("dataset");
-        path = program.get<string>("path");
-        model_name = program.get<string>("model");
+        file_name = program.get<std::string>("dataset");
+        path = program.get<std::string>("path");
+        model_name = program.get<std::string>("model");
         complete_file_name = path + file_name + ".arff";
         stratified = program.get<bool>("stratified");
         tensors = program.get<bool>("tensors");
@@ -133,7 +132,7 @@ int main(int argc, char** argv)
         }
     }
     catch (const exception& err) {
-        cerr << err.what() << endl;
+        cerr << err.what() << std::endl;
         cerr << program;
         exit(1);
     }
@@ -144,93 +143,93 @@ int main(int argc, char** argv)
     auto handler = ArffFiles();
     handler.load(complete_file_name, class_last);
     // Get Dataset X, y
-    vector<mdlp::samples_t>& X = handler.getX();
+    std::vector<mdlp::samples_t>& X = handler.getX();
     mdlp::labels_t& y = handler.getY();
     // Get className & Features
     auto className = handler.getClassName();
-    vector<string> features;
+    std::vector<std::string> features;
     auto attributes = handler.getAttributes();
     transform(attributes.begin(), attributes.end(), back_inserter(features),
-        [](const pair<string, string>& item) { return item.first; });
+        [](const pair<std::string, std::string>& item) { return item.first; });
     // Discretize Dataset
     auto [Xd, maxes] = discretize(X, y, features);
     maxes[className] = *max_element(y.begin(), y.end()) + 1;
-    map<string, vector<int>> states;
+    map<std::string, std::vector<int>> states;
     for (auto feature : features) {
-        states[feature] = vector<int>(maxes[feature]);
+        states[feature] = std::vector<int>(maxes[feature]);
     }
-    states[className] = vector<int>(maxes[className]);
+    states[className] = std::vector<int>(maxes[className]);
     auto clf = platform::Models::instance()->create(model_name);
     clf->fit(Xd, y, features, className, states);
     if (dump_cpt) {
-        cout << "--- CPT Tables ---" << endl;
+        std::cout << "--- CPT Tables ---" << std::endl;
         clf->dump_cpt();
     }
     auto lines = clf->show();
     for (auto line : lines) {
-        cout << line << endl;
+        std::cout << line << std::endl;
     }
-    cout << "--- Topological Order ---" << endl;
+    std::cout << "--- Topological Order ---" << std::endl;
     auto order = clf->topological_order();
     for (auto name : order) {
-        cout << name << ", ";
+        std::cout << name << ", ";
     }
-    cout << "end." << endl;
+    std::cout << "end." << std::endl;
     auto score = clf->score(Xd, y);
-    cout << "Score: " << score << endl;
-    // auto graph = clf->graph();
-    // auto dot_file = model_name + "_" + file_name;
-    // ofstream file(dot_file + ".dot");
-    // file << graph;
-    // file.close();
-    // cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
-    // cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
-    // string stratified_string = stratified ? " Stratified" : "";
-    // cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
-    // cout << "==========================================" << endl;
-    // torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
-    // torch::Tensor yt = torch::tensor(y, torch::kInt32);
-    // for (int i = 0; i < features.size(); ++i) {
-    //     Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
-    // }
-    // float total_score = 0, total_score_train = 0, score_train, score_test;
-    // Fold* fold;
-    // if (stratified)
-    //     fold = new StratifiedKFold(nFolds, y, seed);
-    // else
-    //     fold = new KFold(nFolds, y.size(), seed);
-    // for (auto i = 0; i < nFolds; ++i) {
-    //     auto [train, test] = fold->getFold(i);
-    //     cout << "Fold: " << i + 1 << endl;
-    //     if (tensors) {
-    //         auto ttrain = torch::tensor(train, torch::kInt64);
-    //         auto ttest = torch::tensor(test, torch::kInt64);
-    //         torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
-    //         torch::Tensor ytraint = yt.index({ ttrain });
-    //         torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
-    //         torch::Tensor ytestt = yt.index({ ttest });
-    //         clf->fit(Xtraint, ytraint, features, className, states);
-    //         auto temp = clf->predict(Xtraint);
-    //         score_train = clf->score(Xtraint, ytraint);
-    //         score_test = clf->score(Xtestt, ytestt);
-    //     } else {
-    //         auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
-    //         auto [Xtest, ytest] = extract_indices(test, Xd, y);
-    //         clf->fit(Xtrain, ytrain, features, className, states);
-    //         score_train = clf->score(Xtrain, ytrain);
-    //         score_test = clf->score(Xtest, ytest);
-    //     }
-    //     if (dump_cpt) {
-    //         cout << "--- CPT Tables ---" << endl;
-    //         clf->dump_cpt();
-    //     }
-    //     total_score_train += score_train;
-    //     total_score += score_test;
-    //     cout << "Score Train: " << score_train << endl;
-    //     cout << "Score Test : " << score_test << endl;
-    //     cout << "-------------------------------------------------------------------------------" << endl;
-    // }
-    // cout << "**********************************************************************************" << endl;
-    // cout << "Average Score Train: " << total_score_train / nFolds << endl;
-    // cout << "Average Score Test : " << total_score / nFolds << endl;return 0;
+    std::cout << "Score: " << score << std::endl;
+    auto graph = clf->graph();
+    auto dot_file = model_name + "_" + file_name;
+    ofstream file(dot_file + ".dot");
+    file << graph;
+    file.close();
+    std::cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << std::endl;
+    std::cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << std::endl;
+    std::string stratified_string = stratified ? " Stratified" : "";
+    std::cout << nFolds << " Folds" << stratified_string << " Cross validation" << std::endl;
+    std::cout << "==========================================" << std::endl;
+    torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
+    torch::Tensor yt = torch::tensor(y, torch::kInt32);
+    for (int i = 0; i < features.size(); ++i) {
+        Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
+    }
+    float total_score = 0, total_score_train = 0, score_train, score_test;
+    platform::Fold* fold;
+    if (stratified)
+        fold = new platform::StratifiedKFold(nFolds, y, seed);
+    else
+        fold = new platform::KFold(nFolds, y.size(), seed);
+    for (auto i = 0; i < nFolds; ++i) {
+        auto [train, test] = fold->getFold(i);
+        std::cout << "Fold: " << i + 1 << std::endl;
+        if (tensors) {
+            auto ttrain = torch::tensor(train, torch::kInt64);
+            auto ttest = torch::tensor(test, torch::kInt64);
+            torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
+            torch::Tensor ytraint = yt.index({ ttrain });
+            torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
+            torch::Tensor ytestt = yt.index({ ttest });
+            clf->fit(Xtraint, ytraint, features, className, states);
+            auto temp = clf->predict(Xtraint);
+            score_train = clf->score(Xtraint, ytraint);
+            score_test = clf->score(Xtestt, ytestt);
+        } else {
+            auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
+            auto [Xtest, ytest] = extract_indices(test, Xd, y);
+            clf->fit(Xtrain, ytrain, features, className, states);
+            score_train = clf->score(Xtrain, ytrain);
+            score_test = clf->score(Xtest, ytest);
+        }
+        if (dump_cpt) {
+            std::cout << "--- CPT Tables ---" << std::endl;
+            clf->dump_cpt();
+        }
+        total_score_train += score_train;
+        total_score += score_test;
+        std::cout << "Score Train: " << score_train << std::endl;
+        std::cout << "Score Test : " << score_test << std::endl;
+        std::cout << "-------------------------------------------------------------------------------" << std::endl;
+    }
+    std::cout << "**********************************************************************************" << std::endl;
+    std::cout << "Average Score Train: " << total_score_train / nFolds << std::endl;
+    std::cout << "Average Score Test : " << total_score / nFolds << std::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 = std::vector<double>(n_models, 1.0);
     }
-    vector<string> AODE::graph(const string& title)
+    std::vector<std::string> AODE::graph(const std::string& title) const
     {
         return Ensemble::graph(title);
     }

src/BayesNet/AODE.h

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

src/BayesNet/AODELd.cc

@@ -1,33 +1,38 @@
 #include "AODELd.h"
 
 namespace bayesnet {
-    using namespace std;
-    AODELd::AODELd() : Ensemble(), Proposal(Ensemble::Xv, Ensemble::yv, features, className) {}
-    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
+    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
     {
+        checkInput(X_, y_);
         features = features_;
         className = className_;
-        states = states_;
-        train();
-        for (const auto& model : models) {
-            model->fit(X_, y_, features_, className_, states_);
-        }
-        n_models = models.size();
-        fitted = true;
+        Xf = X_;
+        y = y_;
+        // Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal TAN structure, TAN::fit initializes the base Bayesian network
+        Ensemble::fit(dataset, features, className, states);
         return *this;
+
     }
-    void AODELd::train()
+    void AODELd::buildModel(const torch::Tensor& weights)
     {
         models.clear();
         for (int i = 0; i < features.size(); ++i) {
             models.push_back(std::make_unique<SPODELd>(i));
         }
+        n_models = models.size();
+        significanceModels = std::vector<double>(n_models, 1.0);
     }
-    Tensor AODELd::predict(Tensor& X)
+    void AODELd::trainModel(const torch::Tensor& weights)
     {
-        return Ensemble::predict(X);
+        for (const auto& model : models) {
+            model->fit(Xf, y, features, className, states);
         }
-    vector<string> AODELd::graph(const string& name)
+    }
+    std::vector<std::string> AODELd::graph(const std::string& name) const
     {
         return Ensemble::graph(name);
     }

src/BayesNet/AODELd.h

@@ -5,16 +5,16 @@
 #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 std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_) override;
         virtual ~AODELd() = default;
-        AODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        vector<string> graph(const string& name = "AODE") override;
-        Tensor predict(Tensor& X) override;
-        void train() override;
-        static inline string version() { return "0.0.1"; };
+        std::vector<std::string> graph(const std::string& name = "AODELd") const override;
+        static inline std::string version() { return "0.0.1"; };
     };
 }
 #endif // !AODELD_H

src/BayesNet/BaseClassifier.h

@@ -1,28 +1,37 @@
 #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 {
     public:
-        // X is nxm vector, y is nx1 vector
-        virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        // X is nxm std::vector, y is nx1 std::vector
+        virtual BaseClassifier& fit(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) = 0;
         // X is nxm tensor, y is nx1 tensor
-        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights) = 0;
         virtual ~BaseClassifier() = default;
         torch::Tensor virtual predict(torch::Tensor& X) = 0;
-        vector<int> virtual predict(vector<vector<int>>& X) = 0;
-        float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
+        std::vector<int> virtual predict(std::vector<std::vector<int >>& X) = 0;
+        status_t virtual getStatus() const = 0;
+        float virtual score(std::vector<std::vector<int>>& X, std::vector<int>& y) = 0;
         float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
-        int virtual getNumberOfNodes() = 0;
-        int virtual getNumberOfEdges() = 0;
-        int virtual getNumberOfStates() = 0;
-        vector<string> virtual show() = 0;
-        vector<string> virtual graph(const string& title = "") = 0;
-        const string inline getVersion() const { return "0.1.0"; };
-        vector<string> virtual topological_order() = 0;
-        void virtual dump_cpt() = 0;
+        int virtual getNumberOfNodes()const = 0;
+        int virtual getNumberOfEdges()const = 0;
+        int virtual getNumberOfStates() const = 0;
+        std::vector<std::string> virtual show() const = 0;
+        std::vector<std::string> virtual graph(const std::string& title = "") const = 0;
+        virtual std::string getVersion() = 0;
+        std::vector<std::string> virtual topological_order() = 0;
+        void virtual dump_cpt()const = 0;
+        virtual void setHyperparameters(const nlohmann::json& hyperparameters) = 0;
+        std::vector<std::string>& getValidHyperparameters() { return validHyperparameters; }
+    protected:
+        virtual void trainModel(const torch::Tensor& weights) = 0;
+        std::vector<std::string> validHyperparameters;
     };
 }
 #endif

src/BayesNet/BayesMetrics.cc

@@ -1,16 +1,16 @@
 #include "BayesMetrics.h"
 #include "Mst.h"
 namespace bayesnet {
-    //samples is nxm tensor used to fit the model
-    Metrics::Metrics(torch::Tensor& samples, vector<string>& features, string& className, int classNumStates)
+    //samples is n+1xm tensor used to fit the model
+    Metrics::Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::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)
+    //samples is nxm std::vector used to fit the model
+    Metrics::Metrics(const std::vector<std::vector<int>>& vsamples, const std::vector<int>& labels, const std::vector<std::string>& features, const std::string& className, const int classNumStates)
         : features(features)
         , className(className)
         , classNumStates(classNumStates)
@@ -21,28 +21,57 @@ namespace bayesnet {
         }
         samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
     }
-    vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
+    std::vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
     {
-        vector<pair<string, string>> result;
-        for (int i = 0; i < source.size(); ++i) {
-            string temp = source[i];
-            for (int j = i + 1; j < source.size(); ++j) {
-                result.push_back({ temp, source[j] });
+        // 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());
                 }
             }
-        return result;
+        } 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);
         }
-    torch::Tensor Metrics::conditionalEdge()
+        return featuresKBest;
+    }
+    std::vector<double> Metrics::getScoresKBest() const
     {
-        auto result = vector<double>();
-        auto source = vector<string>(features);
+        return scoresKBest;
+    }
+
+    torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
+    {
+        auto result = std::vector<double>();
+        auto source = std::vector<std::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.size(1);
+            margin[value] = mask.sum().item<double>() / samples.size(1);
         }
         for (auto [first, second] : combinations) {
             int index_first = find(features.begin(), features.end(), first) - features.begin();
@@ -52,8 +81,9 @@ namespace bayesnet {
                 auto mask = samples.index({ -1, "..." }) == value;
                 auto first_dataset = samples.index({ index_first, mask });
                 auto second_dataset = samples.index({ index_second, mask });
-                auto mi = mutualInformation(first_dataset, second_dataset);
-                auto pb = margin[value].item<float>();
+                auto weights_dataset = weights.index({ mask });
+                auto mi = mutualInformation(first_dataset, second_dataset, weights_dataset);
+                auto pb = margin[value].item<double>();
                 accumulated += pb * mi;
             }
             result.push_back(accumulated);
@@ -70,31 +100,32 @@ namespace bayesnet {
         return matrix;
     }
     // To use in Python
-    vector<float> Metrics::conditionalEdgeWeights()
+    std::vector<float> Metrics::conditionalEdgeWeights(std::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();
-        unordered_map<int, unordered_map<int, double>> jointCounts;
+        torch::Tensor featureCounts = secondFeature.bincount(weights);
+        std::unordered_map<int, std::unordered_map<int, double>> jointCounts;
         double totalWeight = 0;
         for (auto i = 0; i < numSamples; i++) {
-            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += 1;
-            totalWeight += 1;
+            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
+            totalWeight += weights[i].item<float>();
         }
         if (totalWeight == 0)
             return 0;
@@ -115,16 +146,16 @@ 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)
+    std::vector<std::pair<int, int>> Metrics::maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root)
     {
         auto mst = MST(features, weights, root);
         return mst.maximumSpanningTree();

src/BayesNet/BayesMetrics.h

@@ -4,25 +4,46 @@
 #include <vector>
 #include <string>
 namespace bayesnet {
-    using namespace std;
-    using namespace torch;
     class Metrics {
     private:
-        Tensor samples; // nxm tensor used to fit the model
-        vector<string> features;
-        string className;
         int classNumStates = 0;
+        std::vector<double> scoresKBest;
+        std::vector<int> featuresKBest; // sorted indices of the features
+        double conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights);
+    protected:
+        torch::Tensor samples; // n+1xm torch::Tensor used to fit the model where samples[-1] is the y std::vector
+        std::string className;
+        double entropy(const torch::Tensor& feature, const torch::Tensor& weights);
+        std::vector<std::string> features;
+        template <class T>
+        std::vector<std::pair<T, T>> doCombinations(const std::vector<T>& source)
+        {
+            std::vector<std::pair<T, T>> result;
+            for (int i = 0; i < source.size(); ++i) {
+                T temp = source[i];
+                for (int j = i + 1; j < source.size(); ++j) {
+                    result.push_back({ temp, source[j] });
+                }
+            }
+            return result;
+        }
+        template <class T>
+        T pop_first(std::vector<T>& v)
+        {
+            T temp = v[0];
+            v.erase(v.begin());
+            return temp;
+        }
     public:
         Metrics() = default;
-        Metrics(Tensor&, vector<string>&, string&, int);
-        Metrics(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const int);
-        double entropy(Tensor&);
-        double conditionalEntropy(Tensor&, Tensor&);
-        double mutualInformation(Tensor&, Tensor&);
-        vector<float> conditionalEdgeWeights(); // To use in Python
-        Tensor conditionalEdge();
-        vector<pair<string, string>> doCombinations(const vector<string>&);
-        vector<pair<int, int>> maximumSpanningTree(vector<string> features, Tensor& weights, int root);
+        Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int classNumStates);
+        Metrics(const std::vector<std::vector<int>>& vsamples, const std::vector<int>& labels, const std::vector<std::string>& features, const std::string& className, const int classNumStates);
+        std::vector<int> SelectKBestWeighted(const torch::Tensor& weights, bool ascending = false, unsigned k = 0);
+        std::vector<double> getScoresKBest() const;
+        double mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights);
+        std::vector<float> conditionalEdgeWeights(std::vector<float>& weights); // To use in Python
+        torch::Tensor conditionalEdge(const torch::Tensor& weights);
+        std::vector<std::pair<int, int>> maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root);
     };
 }
 #endif

src/BayesNet/BoostAODE.cc

@@ -0,0 +1,209 @@
+#include <set>
+#include <functional>
+#include <limits.h>
+#include "BoostAODE.h"
+#include "Colors.h"
+#include "Folding.h"
+#include "Paths.h"
+#include "CFS.h"
+#include "FCBF.h"
+#include "IWSS.h"
+
+namespace bayesnet {
+    BoostAODE::BoostAODE() : Ensemble()
+    {
+        validHyperparameters = { "repeatSparent", "maxModels", "ascending", "convergence", "threshold", "select_features", "tolerance" };
+
+    }
+    void BoostAODE::buildModel(const torch::Tensor& weights)
+    {
+        // Models shall be built in trainModel
+        models.clear();
+        n_models = 0;
+        // Prepare the validation dataset
+        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::setHyperparameters(const nlohmann::json& hyperparameters_)
+    {
+        auto hyperparameters = hyperparameters_;
+        if (hyperparameters.contains("repeatSparent")) {
+            repeatSparent = hyperparameters["repeatSparent"];
+            hyperparameters.erase("repeatSparent");
+        }
+        if (hyperparameters.contains("maxModels")) {
+            maxModels = hyperparameters["maxModels"];
+            hyperparameters.erase("maxModels");
+        }
+        if (hyperparameters.contains("ascending")) {
+            ascending = hyperparameters["ascending"];
+            hyperparameters.erase("ascending");
+        }
+        if (hyperparameters.contains("convergence")) {
+            convergence = hyperparameters["convergence"];
+            hyperparameters.erase("convergence");
+        }
+        if (hyperparameters.contains("threshold")) {
+            threshold = hyperparameters["threshold"];
+            hyperparameters.erase("threshold");
+        }
+        if (hyperparameters.contains("tolerance")) {
+            tolerance = hyperparameters["tolerance"];
+            hyperparameters.erase("tolerance");
+        }
+        if (hyperparameters.contains("select_features")) {
+            auto selectedAlgorithm = hyperparameters["select_features"];
+            std::vector<std::string> algos = { "IWSS", "FCBF", "CFS" };
+            selectFeatures = true;
+            algorithm = selectedAlgorithm;
+            if (std::find(algos.begin(), algos.end(), selectedAlgorithm) == algos.end()) {
+                throw std::invalid_argument("Invalid selectFeatures value [IWSS, FCBF, CFS]");
+            }
+            hyperparameters.erase("select_features");
+        }
+        if (!hyperparameters.empty()) {
+            throw std::invalid_argument("Invalid hyperparameters" + hyperparameters.dump());
+        }
+    }
+    std::unordered_set<int> BoostAODE::initializeModels()
+    {
+        std::unordered_set<int> featuresUsed;
+        torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
+        int maxFeatures = 0;
+        if (algorithm == "CFS") {
+            featureSelector = new CFS(dataset, features, className, maxFeatures, states.at(className).size(), weights_);
+        } else if (algorithm == "IWSS") {
+            if (threshold < 0 || threshold >0.5) {
+                throw std::invalid_argument("Invalid threshold value for IWSS [0, 0.5]");
+            }
+            featureSelector = new IWSS(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
+        } else if (algorithm == "FCBF") {
+            if (threshold < 1e-7 || threshold > 1) {
+                throw std::invalid_argument("Invalid threshold value [1e-7, 1]");
+            }
+            featureSelector = new FCBF(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
+        }
+        featureSelector->fit();
+        auto cfsFeatures = featureSelector->getFeatures();
+        for (const int& feature : cfsFeatures) {
+            // std::cout << "Feature: [" << feature << "] " << feature << " " << features.at(feature) << std::endl;
+            featuresUsed.insert(feature);
+            std::unique_ptr<Classifier> model = std::make_unique<SPODE>(feature);
+            model->fit(dataset, features, className, states, weights_);
+            models.push_back(std::move(model));
+            significanceModels.push_back(1.0);
+            n_models++;
+        }
+        delete featureSelector;
+        return featuresUsed;
+    }
+    void BoostAODE::trainModel(const torch::Tensor& weights)
+    {
+        std::unordered_set<int> featuresUsed;
+        if (selectFeatures) {
+            featuresUsed = initializeModels();
+        }
+        if (maxModels == 0)
+            maxModels = .1 * n > 10 ? .1 * n : n;
+        torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
+        bool exitCondition = false;
+        // Variables to control the accuracy finish condition
+        double priorAccuracy = 0.0;
+        double delta = 1.0;
+        double threshold = 1e-4;
+        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
+        // epsilon 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
+            std::unique_ptr<Classifier> model;
+            auto feature = featureSelection[0];
+            if (!repeatSparent || featuresUsed.size() < featureSelection.size()) {
+                bool used = true;
+                for (const auto& feat : featureSelection) {
+                    if (std::find(featuresUsed.begin(), featuresUsed.end(), feat) != featuresUsed.end()) {
+                        continue;
+                    }
+                    used = false;
+                    feature = feat;
+                    break;
+                }
+                if (used) {
+                    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;
+        }
+    }
+    std::vector<std::string> BoostAODE::graph(const std::string& title) const
+    {
+        return Ensemble::graph(title);
+    }
+}

src/BayesNet/BoostAODE.h

@@ -0,0 +1,33 @@
+#ifndef BOOSTAODE_H
+#define BOOSTAODE_H
+#include "Ensemble.h"
+#include <map>
+#include "SPODE.h"
+#include "FeatureSelect.h"
+namespace bayesnet {
+    class BoostAODE : public Ensemble {
+    public:
+        BoostAODE();
+        virtual ~BoostAODE() = default;
+        std::vector<std::string> graph(const std::string& title = "BoostAODE") const override;
+        void setHyperparameters(const 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;
+        std::unordered_set<int> initializeModels();
+        // Hyperparameters
+        bool repeatSparent = false; // if true, a feature can be selected more than once
+        int maxModels = 0;
+        int tolerance = 0;
+        bool ascending = false; //Process KBest features ascending or descending order
+        bool convergence = false; //if true, stop when the model does not improve
+        bool selectFeatures = false; // if true, use feature selection
+        std::string algorithm = ""; // Selected feature selection algorithm
+        FeatureSelect* featureSelector = nullptr;
+        double threshold = -1;
+    };
+}
+#endif

src/BayesNet/CFS.cc

@@ -0,0 +1,72 @@
+#include "CFS.h"
+#include <limits>
+#include "bayesnetUtils.h"
+namespace bayesnet {
+    void CFS::fit()
+    {
+        initialize();
+        computeSuLabels();
+        auto featureOrder = argsort(suLabels); // sort descending order
+        auto continueCondition = true;
+        auto feature = featureOrder[0];
+        selectedFeatures.push_back(feature);
+        selectedScores.push_back(suLabels[feature]);
+        selectedFeatures.erase(selectedFeatures.begin());
+        while (continueCondition) {
+            double merit = std::numeric_limits<double>::lowest();
+            int bestFeature = -1;
+            for (auto feature : featureOrder) {
+                selectedFeatures.push_back(feature);
+                // Compute merit with selectedFeatures
+                auto meritNew = computeMeritCFS();
+                if (meritNew > merit) {
+                    merit = meritNew;
+                    bestFeature = feature;
+                }
+                selectedFeatures.pop_back();
+            }
+            if (bestFeature == -1) {
+                // meritNew has to be nan due to constant features
+                break;
+            }
+            selectedFeatures.push_back(bestFeature);
+            selectedScores.push_back(merit);
+            featureOrder.erase(remove(featureOrder.begin(), featureOrder.end(), bestFeature), featureOrder.end());
+            continueCondition = computeContinueCondition(featureOrder);
+        }
+        fitted = true;
+    }
+    bool CFS::computeContinueCondition(const std::vector<int>& featureOrder)
+    {
+        if (selectedFeatures.size() == maxFeatures || featureOrder.size() == 0) {
+            return false;
+        }
+        if (selectedScores.size() >= 5) {
+            /*
+            "To prevent the best first search from exploring the entire
+            feature subset search space, a stopping criterion is imposed.
+            The search will terminate if five consecutive fully expanded
+            subsets show no improvement over the current best subset."
+            as stated in Mark A.Hall Thesis
+            */
+            double item_ant = std::numeric_limits<double>::lowest();
+            int num = 0;
+            std::vector<double> lastFive(selectedScores.end() - 5, selectedScores.end());
+            for (auto item : lastFive) {
+                if (item_ant == std::numeric_limits<double>::lowest()) {
+                    item_ant = item;
+                }
+                if (item > item_ant) {
+                    break;
+                } else {
+                    num++;
+                    item_ant = item;
+                }
+            }
+            if (num == 5) {
+                return false;
+            }
+        }
+        return true;
+    }
+}

src/BayesNet/CFS.h

@@ -0,0 +1,20 @@
+#ifndef CFS_H
+#define CFS_H
+#include <torch/torch.h>
+#include <vector>
+#include "FeatureSelect.h"
+namespace bayesnet {
+    class CFS : public FeatureSelect {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
+        CFS(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :
+            FeatureSelect(samples, features, className, maxFeatures, classNumStates, weights)
+        {
+        }
+        virtual ~CFS() {};
+        void fit() override;
+    private:
+        bool computeContinueCondition(const std::vector<int>& featureOrder);
+    };
+}
+#endif

src/BayesNet/CMakeLists.txt

@@ -1,5 +1,12 @@
 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(${BayesNet_SOURCE_DIR}/src/Platform)
+include_directories(${BayesNet_SOURCE_DIR}/src/PyClassifiers)
+include_directories(${Python3_INCLUDE_DIRS})
+
 add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 
-    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc)
-target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")
+    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc BoostAODE.cc 
+    Mst.cc Proposal.cc CFS.cc FCBF.cc IWSS.cc FeatureSelect.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
+target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")

src/BayesNet/Classifier.cc

@@ -2,113 +2,125 @@
 #include "bayesnetUtils.h"
 
 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 std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
     {
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
         this->features = features;
         this->className = className;
         this->states = states;
+        m = dataset.size(1);
+        n = dataset.size(0) - 1;
         checkFitParameters();
-        auto n_classes = states[className].size();
-        metrics = Metrics(samples, features, className, n_classes);
+        auto n_classes = states.at(className).size();
+        metrics = Metrics(dataset, features, className, n_classes);
         model.initialize();
-        train();
-        if (Xv.empty()) {
-            // fit with tensors
-            model.fit(X, y, features, className);
-        } else {
-            // fit with vectors
-            model.fit(Xv, yv, features, className);
-        }
+        buildModel(weights);
+        trainModel(weights);
         fitted = true;
         return *this;
     }
-    // X is nxm where n is the number of features and m the number of samples
-    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    void Classifier::buildDataset(torch::Tensor& ytmp)
     {
-        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);
+        try {
+            auto yresized = torch::transpose(ytmp.view({ ytmp.size(0), 1 }), 0, 1);
+            dataset = torch::cat({ dataset, yresized }, 0);
         }
-    void Classifier::generateTensorXFromVector()
+        catch (const std::exception& e) {
+            std::cerr << e.what() << '\n';
+            std::cout << "X dimensions: " << dataset.sizes() << "\n";
+            std::cout << "y dimensions: " << ytmp.sizes() << "\n";
+            exit(1);
+        }
+    }
+    void Classifier::trainModel(const torch::Tensor& weights)
     {
-        X = torch::zeros({ static_cast<int>(Xv.size()), static_cast<int>(Xv[0].size()) }, kInt32);
-        for (int i = 0; i < Xv.size(); ++i) {
-            X.index_put_({ i, "..." }, torch::tensor(Xv[i], kInt32));
-        }
+        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(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
     {
-        Xv = X;
-        generateTensorXFromVector();
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, 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(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
+    {
+        dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, torch::kInt32);
+        for (int i = 0; i < X.size(); ++i) {
+            dataset.index_put_({ i, "..." }, torch::tensor(X[i], torch::kInt32));
+        }
+        auto ytmp = torch::tensor(y, torch::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 std::vector<std::string>& features, const std::string& className, std::map<std::string, std::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 std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
+    {
+        this->dataset = dataset;
+        return build(features, className, states, weights);
     }
     void Classifier::checkFitParameters()
     {
-        auto sizes = X.sizes();
-        m = sizes[1];
-        n = sizes[0];
-        if (m != y.size(0)) {
-            throw invalid_argument("X and y must have the same number of samples");
+        if (torch::is_floating_point(dataset)) {
+            throw std::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 std::invalid_argument("Classifier: X " + std::to_string(n) + " and features " + std::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");
+            throw std::invalid_argument("className not found in states");
         }
         for (auto feature : features) {
             if (states.find(feature) == states.end()) {
-                throw invalid_argument("feature [" + feature + "] not found in states");
+                throw std::invalid_argument("feature [" + feature + "] not found in states");
             }
         }
     }
-    Tensor Classifier::predict(Tensor& X)
+    torch::Tensor Classifier::predict(torch::Tensor& X)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::logic_error("Classifier has not been fitted");
         }
         return model.predict(X);
     }
-    vector<int> Classifier::predict(vector<vector<int>>& X)
+    std::vector<int> Classifier::predict(std::vector<std::vector<int>>& X)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::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));
+        std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
         for (auto i = 0; i < n_; i++) {
-            Xd[i] = vector<int>(X[i].begin(), X[i].end());
+            Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
         }
         auto yp = model.predict(Xd);
         return yp;
     }
-    float Classifier::score(Tensor& X, Tensor& y)
+    float Classifier::score(torch::Tensor& X, torch::Tensor& y)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::logic_error("Classifier has not been fitted");
         }
-        Tensor y_pred = predict(X);
+        torch::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)
+    float Classifier::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::logic_error("Classifier has not been fitted");
         }
         return model.score(X, y);
     }
-    vector<string> Classifier::show()
+    std::vector<std::string> Classifier::show() const
     {
         return model.show();
     }
@@ -120,26 +132,29 @@ namespace bayesnet {
         }
         model.addNode(className);
     }
-    int Classifier::getNumberOfNodes()
+    int Classifier::getNumberOfNodes() const
     {
         // Features does not include class
-        return fitted ? model.getFeatures().size() + 1 : 0;
+        return fitted ? model.getFeatures().size() : 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()
+    std::vector<std::string> Classifier::topological_order()
     {
         return model.topological_sort();
     }
-    void Classifier::dump_cpt()
+    void Classifier::dump_cpt() const
     {
         model.dump_cpt();
     }
-
+    void Classifier::setHyperparameters(const nlohmann::json& hyperparameters)
+    {
+        //For classifiers that don't have hyperparameters
+    }
 }

src/BayesNet/Classifier.h

@@ -4,45 +4,46 @@
 #include "BaseClassifier.h"
 #include "Network.h"
 #include "BayesMetrics.h"
-using namespace std;
-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 std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
     protected:
-        Network model;
+        bool fitted;
         int m, n; // m: number of samples, n: number of features
-        Tensor X; // nxm tensor
-        vector<vector<int>> Xv; // nxm vector
-        Tensor y;
-        vector<int> yv;
-        Tensor samples; // (n+1)xm tensor
+        Network model;
         Metrics metrics;
-        vector<string> features;
-        string className;
-        map<string, vector<int>> states;
+        std::vector<std::string> features;
+        std::string className;
+        std::map<std::string, std::vector<int>> states;
+        torch::Tensor dataset; // (n+1)xm tensor
+        status_t status = NORMAL;
         void checkFitParameters();
-        void generateTensorXFromVector();
-        virtual void train() = 0;
+        virtual void buildModel(const torch::Tensor& weights) = 0;
+        void trainModel(const torch::Tensor& weights) override;
+        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(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights) override;
         void addNodes();
-        int getNumberOfNodes() override;
-        int getNumberOfEdges() override;
-        int getNumberOfStates() override;
-        Tensor predict(Tensor& X) override;
-        vector<int> predict(vector<vector<int>>& X) override;
-        float score(Tensor& X, Tensor& y) override;
-        float score(vector<vector<int>>& X, vector<int>& y) override;
-        vector<string> show() override;
-        vector<string> topological_order() override;
-        void dump_cpt() override;
+        int getNumberOfNodes() const override;
+        int getNumberOfEdges() const override;
+        int getNumberOfStates() const override;
+        torch::Tensor predict(torch::Tensor& X) override;
+        status_t getStatus() const override { return status; }
+        std::string getVersion() override { return "0.2.0"; };
+        std::vector<int> predict(std::vector<std::vector<int>>& X) override;
+        float score(torch::Tensor& X, torch::Tensor& y) override;
+        float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
+        std::vector<std::string> show() const override;
+        std::vector<std::string> topological_order()  override;
+        void dump_cpt() const override;
+        void setHyperparameters(const nlohmann::json& hyperparameters) override; //For classifiers that don't have hyperparameters
     };
 }
 #endif

src/BayesNet/Ensemble.cc

@@ -1,65 +1,29 @@
 #include "Ensemble.h"
 
 namespace bayesnet {
-    using namespace torch;
 
-    Ensemble::Ensemble() : n_models(0), metrics(Metrics()), fitted(false) {}
-    Ensemble& Ensemble::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
+
+    void Ensemble::trainModel(const torch::Tensor& weights)
     {
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        this->features = features;
-        this->className = className;
-        this->states = states;
-        auto n_classes = states[className].size();
-        metrics = Metrics(samples, features, className, n_classes);
-        // Build models
-        train();
-        // Train models
         n_models = models.size();
         for (auto i = 0; i < n_models; ++i) {
-            if (Xv.empty()) {
-                // fit with tensors
-                models[i]->fit(X, y, features, className, states);
-            } else {
-                // fit with vectors
-                models[i]->fit(Xv, yv, features, className, states);
+            // fit with std::vectors
+            models[i]->fit(dataset, features, className, states);
         }
     }
-        fitted = true;
-        return *this;
-    }
-    void Ensemble::generateTensorXFromVector()
-    {
-        X = torch::zeros({ static_cast<int>(Xv.size()), static_cast<int>(Xv[0].size()) }, kInt32);
-        for (int i = 0; i < Xv.size(); ++i) {
-            X.index_put_({ i, "..." }, torch::tensor(Xv[i], kInt32));
-        }
-    }
-    Ensemble& Ensemble::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
-    {
-        this->X = X;
-        this->y = y;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        return build(features, className, states);
-    }
-    Ensemble& Ensemble::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
-    {
-        Xv = X;
-        generateTensorXFromVector();
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, states);
-    }
-    vector<int> Ensemble::voting(Tensor& y_pred)
+    std::vector<int> Ensemble::voting(torch::Tensor& y_pred)
     {
         auto y_pred_ = y_pred.accessor<int, 2>();
-        vector<int> y_pred_final;
+        std::vector<int> y_pred_final;
+        int numClasses = states.at(className).size();
+        // y_pred is m x n_models with the prediction of every model for each sample
         for (int i = 0; i < y_pred.size(0); ++i) {
-            vector<float> votes(y_pred.size(1), 0);
-            for (int j = 0; j < y_pred.size(1); ++j) {
-                votes[y_pred_[i][j]] += 1;
+            // 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
+            std::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);
@@ -67,19 +31,18 @@ namespace bayesnet {
         }
         return y_pred_final;
     }
-    Tensor Ensemble::predict(Tensor& X)
+    torch::Tensor Ensemble::predict(torch::Tensor& X)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
-        Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
-        //Create a threadpool
-        auto threads{ vector<thread>() };
-        mutex mtx;
+        torch::Tensor y_pred = torch::zeros({ X.size(1), n_models }, torch::kInt32);
+        auto threads{ std::vector<std::thread>() };
+        std::mutex mtx;
         for (auto i = 0; i < n_models; ++i) {
-            threads.push_back(thread([&, i]() {
+            threads.push_back(std::thread([&, i]() {
                 auto ypredict = models[i]->predict(X);
-                lock_guard<mutex> lock(mtx);
+                std::lock_guard<std::mutex> lock(mtx);
                 y_pred.index_put_({ "...", i }, ypredict);
                 }));
         }
@@ -88,27 +51,27 @@ namespace bayesnet {
         }
         return torch::tensor(voting(y_pred));
     }
-    vector<int> Ensemble::predict(vector<vector<int>>& X)
+    std::vector<int> Ensemble::predict(std::vector<std::vector<int>>& X)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
         long m_ = X[0].size();
         long n_ = X.size();
-        vector<vector<int>> Xd(n_, vector<int>(m_, 0));
+        std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
         for (auto i = 0; i < n_; i++) {
-            Xd[i] = vector<int>(X[i].begin(), X[i].end());
+            Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
         }
-        Tensor y_pred = torch::zeros({ m_, n_models }, kInt32);
+        torch::Tensor y_pred = torch::zeros({ m_, n_models }, torch::kInt32);
         for (auto i = 0; i < n_models; ++i) {
-            y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), kInt32));
+            y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), torch::kInt32));
         }
         return voting(y_pred);
     }
-    float Ensemble::score(Tensor& X, Tensor& y)
+    float Ensemble::score(torch::Tensor& X, torch::Tensor& y)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
         auto y_pred = predict(X);
         int correct = 0;
@@ -119,10 +82,10 @@ namespace bayesnet {
         }
         return (double)correct / y_pred.size(0);
     }
-    float Ensemble::score(vector<vector<int>>& X, vector<int>& y)
+    float Ensemble::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
         auto y_pred = predict(X);
         int correct = 0;
@@ -132,27 +95,26 @@ namespace bayesnet {
             }
         }
         return (double)correct / y_pred.size();
-
     }
-    vector<string> Ensemble::show()
+    std::vector<std::string> Ensemble::show() const
     {
-        auto result = vector<string>();
+        auto result = std::vector<std::string>();
         for (auto i = 0; i < n_models; ++i) {
             auto res = models[i]->show();
             result.insert(result.end(), res.begin(), res.end());
         }
         return result;
     }
-    vector<string> Ensemble::graph(const string& title)
+    std::vector<std::string> Ensemble::graph(const std::string& title) const
     {
-        auto result = vector<string>();
+        auto result = std::vector<std::string>();
         for (auto i = 0; i < n_models; ++i) {
-            auto res = models[i]->graph(title + "_" + to_string(i));
+            auto res = models[i]->graph(title + "_" + std::to_string(i));
             result.insert(result.end(), res.begin(), res.end());
         }
         return result;
     }
-    int Ensemble::getNumberOfNodes()
+    int Ensemble::getNumberOfNodes() const
     {
         int nodes = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -160,7 +122,7 @@ namespace bayesnet {
         }
         return nodes;
     }
-    int Ensemble::getNumberOfEdges()
+    int Ensemble::getNumberOfEdges() const
     {
         int edges = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -168,7 +130,7 @@ 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

@@ -4,48 +4,34 @@
 #include "Classifier.h"
 #include "BayesMetrics.h"
 #include "bayesnetUtils.h"
-using namespace std;
-using namespace torch;
 
 namespace bayesnet {
-    class Ensemble : public BaseClassifier {
+    class Ensemble : public Classifier {
     private:
-        Ensemble& build(vector<string>& features, string className, map<string, vector<int>>& states);
+        Ensemble& build(std::vector<std::string>& features, std::string className, std::map<std::string, std::vector<int>>& states);
     protected:
         unsigned n_models;
-        bool fitted;
-        vector<unique_ptr<Classifier>> models;
-        Tensor X;
-        vector<vector<int>> Xv;
-        Tensor y;
-        vector<int> yv;
-        Tensor samples;
-        Metrics metrics;
-        vector<string> features;
-        string className;
-        map<string, vector<int>> states;
-        void virtual train() = 0;
-        vector<int> voting(Tensor& y_pred);
-        void generateTensorXFromVector();
+        std::vector<std::unique_ptr<Classifier>> models;
+        std::vector<double> significanceModels;
+        void trainModel(const torch::Tensor& weights) override;
+        std::vector<int> voting(torch::Tensor& y_pred);
     public:
         Ensemble();
         virtual ~Ensemble() = default;
-        Ensemble& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Ensemble& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Tensor predict(Tensor& X) override;
-        vector<int> predict(vector<vector<int>>& X) override;
-        float score(Tensor& X, Tensor& y) override;
-        float score(vector<vector<int>>& X, vector<int>& y) override;
-        int getNumberOfNodes() override;
-        int getNumberOfEdges() override;
-        int getNumberOfStates() override;
-        vector<string> show() override;
-        vector<string> graph(const string& title) override;
-        vector<string> topological_order() override
+        torch::Tensor predict(torch::Tensor& X) override;
+        std::vector<int> predict(std::vector<std::vector<int>>& X) override;
+        float score(torch::Tensor& X, torch::Tensor& y) override;
+        float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
+        int getNumberOfNodes() const override;
+        int getNumberOfEdges() const override;
+        int getNumberOfStates() const override;
+        std::vector<std::string> show() const override;
+        std::vector<std::string> graph(const std::string& title) const override;
+        std::vector<std::string> topological_order()  override
         {
-            return vector<string>();
+            return std::vector<std::string>();
         }
-        void dump_cpt() override
+        void dump_cpt() const override
         {
         }
     };

src/BayesNet/FCBF.cc

@@ -0,0 +1,44 @@
+#include "bayesnetUtils.h"
+#include "FCBF.h"
+namespace bayesnet {
+
+    FCBF::FCBF(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold) :
+        FeatureSelect(samples, features, className, maxFeatures, classNumStates, weights), threshold(threshold)
+    {
+        if (threshold < 1e-7) {
+            throw std::invalid_argument("Threshold cannot be less than 1e-7");
+        }
+    }
+    void FCBF::fit()
+    {
+        initialize();
+        computeSuLabels();
+        auto featureOrder = argsort(suLabels); // sort descending order
+        auto featureOrderCopy = featureOrder;
+        for (const auto& feature : featureOrder) {
+            // Don't self compare
+            featureOrderCopy.erase(featureOrderCopy.begin());
+            if (suLabels.at(feature) == 0.0) {
+                // The feature has been removed from the list
+                continue;
+            }
+            if (suLabels.at(feature) < threshold) {
+                break;
+            }
+            // Remove redundant features
+            for (const auto& featureCopy : featureOrderCopy) {
+                double value = computeSuFeatures(feature, featureCopy);
+                if (value >= suLabels.at(featureCopy)) {
+                    // Remove feature from list
+                    suLabels[featureCopy] = 0.0;
+                }
+            }
+            selectedFeatures.push_back(feature);
+            selectedScores.push_back(suLabels[feature]);
+            if (selectedFeatures.size() == maxFeatures) {
+                break;
+            }
+        }
+        fitted = true;
+    }
+}

src/BayesNet/FCBF.h

@@ -0,0 +1,17 @@
+#ifndef FCBF_H
+#define FCBF_H
+#include <torch/torch.h>
+#include <vector>
+#include "FeatureSelect.h"
+namespace bayesnet {
+    class FCBF : public FeatureSelect {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
+        FCBF(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold);
+        virtual ~FCBF() {};
+        void fit() override;
+    private:
+        double threshold = -1;
+    };
+}
+#endif

src/BayesNet/FeatureSelect.cc

@@ -0,0 +1,79 @@
+#include "FeatureSelect.h"
+#include <limits>
+#include "bayesnetUtils.h"
+namespace bayesnet {
+    FeatureSelect::FeatureSelect(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights) :
+        Metrics(samples, features, className, classNumStates), maxFeatures(maxFeatures == 0 ? samples.size(0) - 1 : maxFeatures), weights(weights)
+
+    {
+    }
+    void FeatureSelect::initialize()
+    {
+        selectedFeatures.clear();
+        selectedScores.clear();
+    }
+    double FeatureSelect::symmetricalUncertainty(int a, int b)
+    {
+        /*
+        Compute symmetrical uncertainty. Normalize* information gain (mutual
+        information) with the entropies of the features in order to compensate
+        the bias due to high cardinality features. *Range [0, 1]
+        (https://www.sciencedirect.com/science/article/pii/S0020025519303603)
+        */
+        auto x = samples.index({ a, "..." });
+        auto y = samples.index({ b, "..." });
+        auto mu = mutualInformation(x, y, weights);
+        auto hx = entropy(x, weights);
+        auto hy = entropy(y, weights);
+        return 2.0 * mu / (hx + hy);
+    }
+    void FeatureSelect::computeSuLabels()
+    {
+        // Compute Simmetrical Uncertainty between features and labels
+        // https://en.wikipedia.org/wiki/Symmetric_uncertainty
+        for (int i = 0; i < features.size(); ++i) {
+            suLabels.push_back(symmetricalUncertainty(i, -1));
+        }
+    }
+    double FeatureSelect::computeSuFeatures(const int firstFeature, const int secondFeature)
+    {
+        // Compute Simmetrical Uncertainty between features
+        // https://en.wikipedia.org/wiki/Symmetric_uncertainty
+        try {
+            return suFeatures.at({ firstFeature, secondFeature });
+        }
+        catch (const std::out_of_range& e) {
+            double result = symmetricalUncertainty(firstFeature, secondFeature);
+            suFeatures[{firstFeature, secondFeature}] = result;
+            return result;
+        }
+    }
+    double FeatureSelect::computeMeritCFS()
+    {
+        double result;
+        double rcf = 0;
+        for (auto feature : selectedFeatures) {
+            rcf += suLabels[feature];
+        }
+        double rff = 0;
+        int n = selectedFeatures.size();
+        for (const auto& item : doCombinations(selectedFeatures)) {
+            rff += computeSuFeatures(item.first, item.second);
+        }
+        return rcf / sqrt(n + (n * n - n) * rff);
+    }
+    std::vector<int> FeatureSelect::getFeatures() const
+    {
+        if (!fitted) {
+            throw std::runtime_error("FeatureSelect not fitted");
+        }
+        return selectedFeatures;
+    }
+    std::vector<double> FeatureSelect::getScores() const
+    {
+        if (!fitted) {
+            throw std::runtime_error("FeatureSelect not fitted");
+        }
+        return selectedScores;
+    }
+}

src/BayesNet/FeatureSelect.h

@@ -0,0 +1,30 @@
+#ifndef FEATURE_SELECT_H
+#define FEATURE_SELECT_H
+#include <torch/torch.h>
+#include <vector>
+#include "BayesMetrics.h"
+namespace bayesnet {
+    class FeatureSelect : public Metrics {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
+        FeatureSelect(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights);
+        virtual ~FeatureSelect() {};
+        virtual void fit() = 0;
+        std::vector<int> getFeatures() const;
+        std::vector<double> getScores() const;
+    protected:
+        void initialize();
+        void computeSuLabels();
+        double computeSuFeatures(const int a, const int b);
+        double symmetricalUncertainty(int a, int b);
+        double computeMeritCFS();
+        const torch::Tensor& weights;
+        int maxFeatures;
+        std::vector<int> selectedFeatures;
+        std::vector<double> selectedScores;
+        std::vector<double> suLabels;
+        std::map<std::pair<int, int>, double> suFeatures;
+        bool fitted = false;
+    };
+}
+#endif

src/BayesNet/IWSS.cc

@@ -0,0 +1,47 @@
+#include "IWSS.h"
+#include <limits>
+#include "bayesnetUtils.h"
+namespace bayesnet {
+    IWSS::IWSS(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold) :
+        FeatureSelect(samples, features, className, maxFeatures, classNumStates, weights), threshold(threshold)
+    {
+        if (threshold < 0 || threshold > .5) {
+            throw std::invalid_argument("Threshold has to be in [0, 0.5]");
+        }
+    }
+    void IWSS::fit()
+    {
+        initialize();
+        computeSuLabels();
+        auto featureOrder = argsort(suLabels); // sort descending order
+        auto featureOrderCopy = featureOrder;
+        // Add first and second features to result
+        //     First with its own score
+        auto first_feature = pop_first(featureOrderCopy);
+        selectedFeatures.push_back(first_feature);
+        selectedScores.push_back(suLabels.at(first_feature));
+        //     Second with the score of the candidates
+        selectedFeatures.push_back(pop_first(featureOrderCopy));
+        auto merit = computeMeritCFS();
+        selectedScores.push_back(merit);
+        for (const auto feature : featureOrderCopy) {
+            selectedFeatures.push_back(feature);
+            // Compute merit with selectedFeatures
+            auto meritNew = computeMeritCFS();
+            double delta = merit != 0.0 ? abs(merit - meritNew) / merit : 0.0;
+            if (meritNew > merit || delta < threshold) {
+                if (meritNew > merit) {
+                    merit = meritNew;
+                }
+                selectedScores.push_back(meritNew);
+            } else {
+                selectedFeatures.pop_back();
+                break;
+            }
+            if (selectedFeatures.size() == maxFeatures) {
+                break;
+            }
+        }
+        fitted = true;
+    }
+}

src/BayesNet/IWSS.h

@@ -0,0 +1,17 @@
+#ifndef IWSS_H
+#define IWSS_H
+#include <torch/torch.h>
+#include <vector>
+#include "FeatureSelect.h"
+namespace bayesnet {
+    class IWSS : public FeatureSelect {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y std::vector
+        IWSS(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights, const double threshold);
+        virtual ~IWSS() {};
+        void fit() override;
+    private:
+        double threshold = -1;
+    };
+}
+#endif

src/BayesNet/KDB.cc

@@ -1,10 +1,21 @@
 #include "KDB.h"
 
 namespace bayesnet {
-    using namespace torch;
+    KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta)
+    {
+        validHyperparameters = { "k", "theta" };
 
-    KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
-    void KDB::train()
+    }
+    void KDB::setHyperparameters(const nlohmann::json& 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),
@@ -28,15 +39,16 @@ namespace bayesnet {
         // 1. For each feature Xi, compute mutual information, I(X;C),
         // where C is the class.
         addNodes();
-        vector <float> mi;
+        const torch::Tensor& y = dataset.index({ -1, "..." });
+        std::vector<double> mi;
         for (auto i = 0; i < features.size(); i++) {
-            Tensor firstFeature = X.index({ i, "..." });
-            mi.push_back(metrics.mutualInformation(firstFeature, y));
+            torch::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;
+        std::vector<int> S;
         // 4. Let the DAG network being constructed, BN, begin with a single
         // class node, C.
         // 5. Repeat until S includes all domain features
@@ -54,9 +66,9 @@ namespace bayesnet {
             S.push_back(idx);
         }
     }
-    void KDB::add_m_edges(int idx, vector<int>& S, Tensor& weights)
+    void KDB::add_m_edges(int idx, std::vector<int>& S, torch::Tensor& weights)
     {
-        auto n_edges = min(k, static_cast<int>(S.size()));
+        auto n_edges = std::min(k, static_cast<int>(S.size()));
         auto cond_w = clone(weights);
         bool exit_cond = k == 0;
         int num = 0;
@@ -68,7 +80,7 @@ namespace bayesnet {
                     model.addEdge(features[max_minfo], features[idx]);
                     num++;
                 }
-                catch (const invalid_argument& e) {
+                catch (const std::invalid_argument& e) {
                     // Loops are not allowed
                 }
             }
@@ -78,11 +90,11 @@ namespace bayesnet {
             exit_cond = num == n_edges || candidates.size(0) == 0;
         }
     }
-    vector<string> KDB::graph(const string& title)
+    std::vector<std::string> KDB::graph(const std::string& title) const
     {
-        string header{ title };
+        std::string header{ title };
         if (title == "KDB") {
-            header += " (k=" + to_string(k) + ", theta=" + to_string(theta) + ")";
+            header += " (k=" + std::to_string(k) + ", theta=" + std::to_string(theta) + ")";
         }
         return model.graph(header);
     }

src/BayesNet/KDB.h

@@ -1,21 +1,21 @@
 #ifndef KDB_H
 #define KDB_H
+#include <torch/torch.h>
 #include "Classifier.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
-    using namespace std;
-    using namespace torch;
     class KDB : public Classifier {
     private:
         int k;
         float theta;
-        void add_m_edges(int idx, vector<int>& S, Tensor& weights);
+        void add_m_edges(int idx, std::vector<int>& S, torch::Tensor& weights);
     protected:
-        void train() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         explicit KDB(int k, float theta = 0.03);
-        virtual ~KDB() {};
-        vector<string> graph(const string& name = "KDB") override;
+        virtual ~KDB() = default;
+        void setHyperparameters(const nlohmann::json& hyperparameters) override;
+        std::vector<std::string> graph(const std::string& name = "KDB") const override;
     };
 }
 #endif

src/BayesNet/KDBLd.cc

@@ -1,34 +1,28 @@
 #include "KDBLd.h"
 
 namespace bayesnet {
-    using namespace std;
-    KDBLd::KDBLd(int k) : KDB(k), Proposal(KDB::Xv, KDB::yv, features, className) {}
-    KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    KDBLd::KDBLd(int k) : KDB(k), Proposal(dataset, features, className) {}
+    KDBLd& KDBLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
         y = y_;
-        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
-        fit_local_discretization(states, y);
-        generateTensorXFromVector();
+        // Fills std::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(KDB::Xv, KDB::yv, features, className, states);
-        localDiscretizationProposal(states, model);
-        generateTensorXFromVector();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        model.fit(KDB::Xv, KDB::yv, features, className);
+        KDB::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
         return *this;
     }
-    Tensor KDBLd::predict(Tensor& X)
+    torch::Tensor KDBLd::predict(torch::Tensor& X)
     {
         auto Xt = prepareX(X);
         return KDB::predict(Xt);
     }
-    vector<string> KDBLd::graph(const string& name)
+    std::vector<std::string> KDBLd::graph(const std::string& name) const
     {
         return KDB::graph(name);
     }

src/BayesNet/KDBLd.h

@@ -4,16 +4,15 @@
 #include "Proposal.h"
 
 namespace bayesnet {
-    using namespace std;
     class KDBLd : public KDB, public Proposal {
     private:
     public:
         explicit KDBLd(int k);
         virtual ~KDBLd() = default;
-        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        vector<string> graph(const string& name = "KDB") override;
-        Tensor predict(Tensor& X) override;
-        static inline string version() { return "0.0.1"; };
+        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
+        std::vector<std::string> graph(const std::string& name = "KDB") const override;
+        torch::Tensor predict(torch::Tensor& X) override;
+        static inline std::string version() { return "0.0.1"; };
     };
 }
 #endif // !KDBLD_H

src/BayesNet/Mst.cc

@@ -1,13 +1,13 @@
 #include "Mst.h"
 #include <vector>
+#include <list>
 /*
     Based on the code from https://www.softwaretestinghelp.com/minimum-spanning-tree-tutorial/
 
 */
 
 namespace bayesnet {
-    using namespace std;
-    Graph::Graph(int V) : V(V), parent(vector<int>(V))
+    Graph::Graph(int V) : V(V), parent(std::vector<int>(V))
     {
         for (int i = 0; i < V; i++)
             parent[i] = i;
@@ -34,36 +34,45 @@ namespace bayesnet {
     void Graph::kruskal_algorithm()
     {
         // sort the edges ordered on decreasing weight
-        sort(G.begin(), G.end(), [](const auto& left, const auto& right) {return left.first > right.first;});
+        stable_sort(G.begin(), G.end(), [](const auto& left, const auto& right) {return left.first > right.first;});
         for (int i = 0; i < G.size(); i++) {
             int uSt, vEd;
             uSt = find_set(G[i].second.first);
             vEd = find_set(G[i].second.second);
             if (uSt != vEd) {
-                T.push_back(G[i]); // add to mst vector
+                T.push_back(G[i]); // add to mst std::vector
                 union_set(uSt, vEd);
             }
         }
     }
     void Graph::display_mst()
     {
-        cout << "Edge :" << " Weight" << endl;
+        std::cout << "Edge :" << " Weight" << std::endl;
         for (int i = 0; i < T.size(); i++) {
-            cout << T[i].second.first << " - " << T[i].second.second << " : "
+            std::cout << T[i].second.first << " - " << T[i].second.second << " : "
                 << T[i].first;
-            cout << endl;
+            std::cout << std::endl;
         }
     }
 
-    vector<pair<int, int>> reorder(vector<pair<float, pair<int, int>>> T, int root_original)
+    void insertElement(std::list<int>& variables, int variable)
     {
-        auto result = vector<pair<int, int>>();
-        auto visited = vector<int>();
-        auto nextVariables = unordered_set<int>();
-        nextVariables.emplace(root_original);
+        if (std::find(variables.begin(), variables.end(), variable) == variables.end()) {
+            variables.push_front(variable);
+        }
+    }
+
+    std::vector<std::pair<int, int>> reorder(std::vector<std::pair<float, std::pair<int, int>>> T, int root_original)
+    {
+        // Create the edges of a DAG from the MST
+        // replacing unordered_set with list because unordered_set cannot guarantee the order of the elements inserted
+        auto result = std::vector<std::pair<int, int>>();
+        auto visited = std::vector<int>();
+        auto nextVariables = std::list<int>();
+        nextVariables.push_front(root_original);
         while (nextVariables.size() > 0) {
-            int root = *nextVariables.begin();
-            nextVariables.erase(nextVariables.begin());
+            int root = nextVariables.front();
+            nextVariables.pop_front();
             for (int i = 0; i < T.size(); ++i) {
                 auto [weight, edge] = T[i];
                 auto [from, to] = edge;
@@ -71,10 +80,10 @@ namespace bayesnet {
                     visited.insert(visited.begin(), i);
                     if (from == root) {
                         result.push_back({ from, to });
-                        nextVariables.emplace(to);
+                        insertElement(nextVariables, to);
                     } else {
                         result.push_back({ to, from });
-                        nextVariables.emplace(from);
+                        insertElement(nextVariables, from);
                     }
                 }
             }
@@ -94,12 +103,11 @@ namespace bayesnet {
         return result;
     }
 
-    MST::MST(vector<string>& features, Tensor& weights, int root) : features(features), weights(weights), root(root) {}
-    vector<pair<int, int>> MST::maximumSpanningTree()
+    MST::MST(const std::vector<std::string>& features, const torch::Tensor& weights, const int root) : features(features), weights(weights), root(root) {}
+    std::vector<std::pair<int, int>> MST::maximumSpanningTree()
     {
         auto num_features = features.size();
         Graph g(num_features);
-
         // Make a complete graph
         for (int i = 0; i < num_features - 1; ++i) {
             for (int j = i + 1; j < num_features; ++j) {

src/BayesNet/Mst.h

@@ -4,24 +4,22 @@
 #include <vector>
 #include <string>
 namespace bayesnet {
-    using namespace std;
-    using namespace torch;
     class MST {
     private:
-        Tensor weights;
-        vector<string> features;
+        torch::Tensor weights;
+        std::vector<std::string> features;
         int root = 0;
     public:
         MST() = default;
-        MST(vector<string>& features, Tensor& weights, int root);
-        vector<pair<int, int>> maximumSpanningTree();
+        MST(const std::vector<std::string>& features, const torch::Tensor& weights, const int root);
+        std::vector<std::pair<int, int>> maximumSpanningTree();
     };
     class Graph {
     private:
         int V;      // number of nodes in graph
-        vector <pair<float, pair<int, int>>> G; // vector for graph
-        vector <pair<float, pair<int, int>>> T; // vector for mst
-        vector<int> parent;
+        std::vector <std::pair<float, std::pair<int, int>>> G; // std::vector for graph
+        std::vector <std::pair<float, std::pair<int, int>>> T; // std::vector for mst
+        std::vector<int> parent;
     public:
         explicit Graph(int V);
         void addEdge(int u, int v, float wt);
@@ -29,7 +27,7 @@ namespace bayesnet {
         void union_set(int u, int v);
         void kruskal_algorithm();
         void display_mst();
-        vector <pair<float, pair<int, int>>> get_mst() { return T; }
+        std::vector <std::pair<float, std::pair<int, int>>> get_mst() { return T; }
     };
 }
 #endif

src/BayesNet/Network.cc

@@ -3,24 +3,22 @@
 #include "Network.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
-    Network::Network() : features(vector<string>()), className(""), classNumStates(0), fitted(false) {}
-    Network::Network(float maxT) : features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
-    Network::Network(float maxT, int smoothing) : laplaceSmoothing(smoothing), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
+    Network::Network() : features(std::vector<std::string>()), className(""), classNumStates(0), fitted(false), laplaceSmoothing(0) {}
+    Network::Network(float maxT) : features(std::vector<std::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);
+        for (const auto& node : other.nodes) {
+            nodes[node.first] = std::make_unique<Node>(*node.second);
         }
     }
     void Network::initialize()
     {
-        features = vector<string>();
+        features = std::vector<std::string>();
         className = "";
         classNumStates = 0;
         fitted = false;
         nodes.clear();
-        dataset.clear();
         samples = torch::Tensor();
     }
     float Network::getmaxThreads()
@@ -31,10 +29,10 @@ namespace bayesnet {
     {
         return samples;
     }
-    void Network::addNode(const string& name)
+    void Network::addNode(const std::string& name)
     {
         if (name == "") {
-            throw invalid_argument("Node name cannot be empty");
+            throw std::invalid_argument("Node name cannot be empty");
         }
         if (nodes.find(name) != nodes.end()) {
             return;
@@ -44,15 +42,15 @@ namespace bayesnet {
         }
         nodes[name] = std::make_unique<Node>(name);
     }
-    vector<string> Network::getFeatures()
+    std::vector<std::string> Network::getFeatures() const
     {
         return features;
     }
-    int Network::getClassNumStates()
+    int Network::getClassNumStates() const
     {
         return classNumStates;
     }
-    int Network::getStates()
+    int Network::getStates() const
     {
         int result = 0;
         for (auto& node : nodes) {
@@ -60,11 +58,11 @@ namespace bayesnet {
         }
         return result;
     }
-    string Network::getClassName()
+    std::string Network::getClassName() const
     {
         return className;
     }
-    bool Network::isCyclic(const string& nodeId, unordered_set<string>& visited, unordered_set<string>& recStack)
+    bool Network::isCyclic(const std::string& nodeId, std::unordered_set<std::string>& visited, std::unordered_set<std::string>& recStack)
     {
         if (visited.find(nodeId) == visited.end()) // if node hasn't been visited yet
         {
@@ -80,124 +78,107 @@ namespace bayesnet {
         recStack.erase(nodeId); // remove node from recursion stack before function ends
         return false;
     }
-    void Network::addEdge(const string& parent, const string& child)
+    void Network::addEdge(const std::string& parent, const std::string& child)
     {
         if (nodes.find(parent) == nodes.end()) {
-            throw invalid_argument("Parent node " + parent + " does not exist");
+            throw std::invalid_argument("Parent node " + parent + " does not exist");
         }
         if (nodes.find(child) == nodes.end()) {
-            throw invalid_argument("Child node " + child + " does not exist");
+            throw std::invalid_argument("Child node " + child + " does not exist");
         }
         // Temporarily add edge to check for cycles
         nodes[parent]->addChild(nodes[child].get());
         nodes[child]->addParent(nodes[parent].get());
-        unordered_set<string> visited;
-        unordered_set<string> recStack;
+        std::unordered_set<std::string> visited;
+        std::unordered_set<std::string> recStack;
         if (isCyclic(nodes[child]->getName(), visited, recStack)) // if adding this edge forms a cycle
         {
             // remove problematic edge
             nodes[parent]->removeChild(nodes[child].get());
             nodes[child]->removeParent(nodes[parent].get());
-            throw invalid_argument("Adding this edge forms a cycle in the graph.");
+            throw std::invalid_argument("Adding this edge forms a cycle in the graph.");
         }
     }
-    map<string, std::unique_ptr<Node>>& Network::getNodes()
+    std::map<std::string, std::unique_ptr<Node>>& Network::getNodes()
     {
         return nodes;
     }
-    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className)
+    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
     {
+        if (weights.size(0) != n_samples) {
+            throw std::invalid_argument("Weights (" + std::to_string(weights.size(0)) + ") must have the same number of elements as samples (" + std::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) + ")");
+            throw std::invalid_argument("X and y must have the same number of samples in Network::fit (" + std::to_string(n_samples) + " != " + std::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()) + ")");
+            throw std::invalid_argument("X and features must have the same number of features in Network::fit (" + std::to_string(n_features) + " != " + std::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) + ")");
+            throw std::invalid_argument("X and local features must have the same number of features in Network::fit (" + std::to_string(n_features) + " != " + std::to_string(features.size() - 1) + ")");
         }
         if (find(features.begin(), features.end(), className) == features.end()) {
-            throw invalid_argument("className not found in Network::features");
+            throw std::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");
+                throw std::invalid_argument("Feature " + feature + " not found in Network::features");
+            }
+            if (states.find(feature) == states.end()) {
+                throw std::invalid_argument("Feature " + feature + " not found in states");
             }
         }
     }
-    void Network::setStates()
+    void Network::setStates(const std::map<std::string, std::vector<int>>& states)
     {
         // Set states to every Node in the network
-        for (int i = 0; i < features.size(); ++i) {
-            nodes[features[i]]->setNumStates(static_cast<int>(torch::max(samples.index({ i, "..." })).item<int>()) + 1);
-        }
-        classNumStates = nodes[className]->getNumStates();
+        for_each(features.begin(), features.end(), [this, &states](const std::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(torch::Tensor& X, torch::Tensor& y, const vector<string>& featureNames, const string& className)
+    void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states)
     {
-        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className);
+        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states, weights);
         this->className = className;
-        dataset.clear();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
+        torch::Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
         samples = torch::cat({ X , ytmp }, 0);
         for (int i = 0; i < featureNames.size(); ++i) {
             auto row_feature = X.index({ i, "..." });
-            dataset[featureNames[i]] = vector<int>(row_feature.data_ptr<int>(), row_feature.data_ptr<int>() + row_feature.size(0));;
         }
-        dataset[className] = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        completeFit();
+        completeFit(states, weights);
+    }
+    void Network::fit(const torch::Tensor& samples, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states)
+    {
+        checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states, weights);
+        this->className = className;
+        this->samples = samples;
+        completeFit(states, weights);
     }
     // input_data comes in nxm, where n is the number of features and m the number of samples
-    void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className)
+    void Network::fit(const std::vector<std::vector<int>>& input_data, const std::vector<int>& labels, const std::vector<double>& weights_, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states)
     {
-        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className);
+        const torch::Tensor weights = torch::tensor(weights_, torch::kFloat64);
+        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states, weights);
         this->className = className;
-        dataset.clear();
-        // Build dataset & tensor of samples (nxm) (n+1 because of the class)
+        // Build tensor of samples (nxm) (n+1 because of the class)
         samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
         for (int i = 0; i < featureNames.size(); ++i) {
-            dataset[featureNames[i]] = input_data[i];
             samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
         }
-        dataset[className] = labels;
         samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
-        completeFit();
+        completeFit(states, weights);
     }
-    void Network::completeFit()
+    void Network::completeFit(const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
     {
-        setStates();
-        int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
-        if (maxThreadsRunning < 1) {
-            maxThreadsRunning = 1;
-        }
-        vector<thread> threads;
-        mutex mtx;
-        condition_variable cv;
-        int activeThreads = 0;
-        int nextNodeIndex = 0;
-        while (nextNodeIndex < nodes.size()) {
-            unique_lock<mutex> lock(mtx);
-            cv.wait(lock, [&activeThreads, &maxThreadsRunning]() { return activeThreads < maxThreadsRunning; });
-            threads.emplace_back([this, &nextNodeIndex, &mtx, &cv, &activeThreads]() {
-                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();
+        setStates(states);
+        laplaceSmoothing = 1.0 / samples.size(1); // To use in CPT computation
+        std::vector<std::thread> threads;
+        for (auto& node : nodes) {
+            threads.emplace_back([this, &node, &weights]() {
+                node.second->computeCPT(samples, features, laplaceSmoothing, weights);
                 });
-            ++activeThreads;
         }
         for (auto& thread : threads) {
             thread.join();
@@ -207,12 +188,12 @@ namespace bayesnet {
     torch::Tensor Network::predict_tensor(const torch::Tensor& samples, const bool proba)
     {
         if (!fitted) {
-            throw logic_error("You must call fit() before calling predict()");
+            throw std::logic_error("You must call fit() before calling predict()");
         }
         torch::Tensor result;
         result = torch::zeros({ samples.size(1), classNumStates }, torch::kFloat64);
         for (int i = 0; i < samples.size(1); ++i) {
-            auto sample = samples.index({ "...", i });
+            const torch::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));
@@ -220,36 +201,35 @@ namespace bayesnet {
         }
         if (proba)
             return result;
-        else
         return result.argmax(1);
     }
     // Return mxn tensor of probabilities
-    Tensor Network::predict_proba(const Tensor& samples)
+    torch::Tensor Network::predict_proba(const torch::Tensor& samples)
     {
         return predict_tensor(samples, true);
     }
 
     // Return mxn tensor of probabilities
-    Tensor Network::predict(const Tensor& samples)
+    torch::Tensor Network::predict(const torch::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)
+    // Return mx1 std::vector of predictions
+    // tsamples is nxm std::vector of samples
+    std::vector<int> Network::predict(const std::vector<std::vector<int>>& tsamples)
     {
         if (!fitted) {
-            throw logic_error("You must call fit() before calling predict()");
+            throw std::logic_error("You must call fit() before calling predict()");
         }
-        vector<int> predictions;
-        vector<int> sample;
+        std::vector<int> predictions;
+        std::vector<int> sample;
         for (int row = 0; row < tsamples[0].size(); ++row) {
             sample.clear();
             for (int col = 0; col < tsamples.size(); ++col) {
                 sample.push_back(tsamples[col][row]);
             }
-            vector<double> classProbabilities = predict_sample(sample);
+            std::vector<double> classProbabilities = predict_sample(sample);
             // Find the class with the maximum posterior probability
             auto maxElem = max_element(classProbabilities.begin(), classProbabilities.end());
             int predictedClass = distance(classProbabilities.begin(), maxElem);
@@ -257,14 +237,14 @@ namespace bayesnet {
         }
         return predictions;
     }
-    // Return mxn vector of probabilities
-    vector<vector<double>> Network::predict_proba(const vector<vector<int>>& tsamples)
+    // Return mxn std::vector of probabilities
+    std::vector<std::vector<double>> Network::predict_proba(const std::vector<std::vector<int>>& tsamples)
     {
         if (!fitted) {
-            throw logic_error("You must call fit() before calling predict_proba()");
+            throw std::logic_error("You must call fit() before calling predict_proba()");
         }
-        vector<vector<double>> predictions;
-        vector<int> sample;
+        std::vector<std::vector<double>> predictions;
+        std::vector<int> sample;
         for (int row = 0; row < tsamples[0].size(); ++row) {
             sample.clear();
             for (int col = 0; col < tsamples.size(); ++col) {
@@ -274,9 +254,9 @@ namespace bayesnet {
         }
         return predictions;
     }
-    double Network::score(const vector<vector<int>>& tsamples, const vector<int>& labels)
+    double Network::score(const std::vector<std::vector<int>>& tsamples, const std::vector<int>& labels)
     {
-        vector<int> y_pred = predict(tsamples);
+        std::vector<int> y_pred = predict(tsamples);
         int correct = 0;
         for (int i = 0; i < y_pred.size(); ++i) {
             if (y_pred[i] == labels[i]) {
@@ -285,35 +265,35 @@ namespace bayesnet {
         }
         return (double)correct / y_pred.size();
     }
-    // Return 1xn vector of probabilities
-    vector<double> Network::predict_sample(const vector<int>& sample)
+    // Return 1xn std::vector of probabilities
+    std::vector<double> Network::predict_sample(const std::vector<int>& sample)
     {
         // Ensure the sample size is equal to the number of features
         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() - 1) + ")");
+            throw std::invalid_argument("Sample size (" + std::to_string(sample.size()) +
+                ") does not match the number of features (" + std::to_string(features.size() - 1) + ")");
         }
-        map<string, int> evidence;
+        std::map<std::string, int> evidence;
         for (int i = 0; i < sample.size(); ++i) {
             evidence[features[i]] = sample[i];
         }
         return exactInference(evidence);
     }
-    // Return 1xn vector of probabilities
-    vector<double> Network::predict_sample(const Tensor& sample)
+    // Return 1xn std::vector of probabilities
+    std::vector<double> Network::predict_sample(const torch::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) + ")");
+            throw std::invalid_argument("Sample size (" + std::to_string(sample.size(0)) +
+                ") does not match the number of features (" + std::to_string(features.size() - 1) + ")");
         }
-        map<string, int> evidence;
+        std::map<std::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 Network::computeFactor(std::map<std::string, int>& completeEvidence)
     {
         double result = 1.0;
         for (auto& node : getNodes()) {
@@ -321,17 +301,17 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<double> Network::exactInference(map<string, int>& evidence)
+    std::vector<double> Network::exactInference(std::map<std::string, int>& evidence)
     {
-        vector<double> result(classNumStates, 0.0);
-        vector<thread> threads;
-        mutex mtx;
+        std::vector<double> result(classNumStates, 0.0);
+        std::vector<std::thread> threads;
+        std::mutex mtx;
         for (int i = 0; i < classNumStates; ++i) {
             threads.emplace_back([this, &result, &evidence, i, &mtx]() {
-            auto completeEvidence = map<string, int>(evidence);
+                auto completeEvidence = std::map<std::string, int>(evidence);
                 completeEvidence[getClassName()] = i;
                 double factor = computeFactor(completeEvidence);
-                lock_guard<mutex> lock(mtx);
+                std::lock_guard<std::mutex> lock(mtx);
                 result[i] = factor;
                 });
         }
@@ -340,15 +320,15 @@ namespace bayesnet {
         }
         // 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()
+    std::vector<std::string> Network::show() const
     {
-        vector<string> result;
+        std::vector<std::string> result;
         // Draw the network
         for (auto& node : nodes) {
-            string line = node.first + " -> ";
+            std::string line = node.first + " -> ";
             for (auto child : node.second->getChildren()) {
                 line += child->getName() + ", ";
             }
@@ -356,12 +336,12 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<string> Network::graph(const string& title)
+    std::vector<std::string> Network::graph(const std::string& title) const
     {
-        auto output = vector<string>();
+        auto output = std::vector<std::string>();
         auto prefix = "digraph BayesNet {\nlabel=<BayesNet ";
         auto suffix = ">\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n";
-        string header = prefix + title + suffix;
+        std::string header = prefix + title + suffix;
         output.push_back(header);
         for (auto& node : nodes) {
             auto result = node.second->graph(className);
@@ -370,9 +350,9 @@ namespace bayesnet {
         output.push_back("}\n");
         return output;
     }
-    vector<pair<string, string>> Network::getEdges()
+    std::vector<std::pair<std::string, std::string>> Network::getEdges() const
     {
-        auto edges = vector<pair<string, string>>();
+        auto edges = std::vector<std::pair<std::string, std::string>>();
         for (const auto& node : nodes) {
             auto head = node.first;
             for (const auto& child : node.second->getChildren()) {
@@ -382,13 +362,16 @@ namespace bayesnet {
         }
         return edges;
     }
-    vector<string> Network::topological_sort()
+    int Network::getNumEdges() const
+    {
+        return getEdges().size();
+    }
+    std::vector<std::string> Network::topological_sort()
     {
         /* Check if al the fathers of every node are before the node */
         auto result = features;
         result.erase(remove(result.begin(), result.end(), className), result.end());
         bool ending{ false };
-        int idx = 0;
         while (!ending) {
             ending = true;
             for (auto feature : features) {
@@ -410,20 +393,21 @@ namespace bayesnet {
                                 ending = false;
                             }
                         } else {
-                            throw logic_error("Error in topological sort because of node " + feature + " is not in result");
+                            throw std::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");
+                        throw std::logic_error("Error in topological sort because of node father " + fatherName + " is not in result");
                     }
                 }
             }
         }
         return result;
     }
-    void Network::dump_cpt()
+    void Network::dump_cpt() const
     {
         for (auto& node : nodes) {
-            cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
+            std::cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << std::endl;
+            std::cout << node.second->getCPT() << std::endl;
         }
     }
 }

src/BayesNet/Network.h

@@ -7,58 +7,56 @@
 namespace bayesnet {
     class Network {
     private:
-        map<string, unique_ptr<Node>> nodes;
-        map<string, vector<int>> dataset;
+        std::map<std::string, std::unique_ptr<Node>> nodes;
         bool fitted;
         float maxThreads = 0.95;
         int classNumStates;
-        vector<string> features; // Including class
-        string className;
-        int laplaceSmoothing = 1;
+        std::vector<std::string> features; // Including classname
+        std::string className;
+        double laplaceSmoothing;
         torch::Tensor samples; // nxm tensor used to fit the model
         bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
-        vector<double> predict_sample(const vector<int>&);
-        vector<double> predict_sample(const torch::Tensor&);
-        vector<double> exactInference(map<string, int>&);
-        double computeFactor(map<string, int>&);
-        double mutual_info(torch::Tensor&, torch::Tensor&);
-        double entropy(torch::Tensor&);
-        double conditionalEntropy(torch::Tensor&, torch::Tensor&);
-        double mutualInformation(torch::Tensor&, torch::Tensor&);
-        void completeFit();
-        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className);
-        void setStates();
+        std::vector<double> predict_sample(const std::vector<int>&);
+        std::vector<double> predict_sample(const torch::Tensor&);
+        std::vector<double> exactInference(std::map<std::string, int>&);
+        double computeFactor(std::map<std::string, int>&);
+        void completeFit(const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
+        void checkFitData(int n_features, int n_samples, int n_samples_y, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
+        void setStates(const std::map<std::string, std::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&);
-        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>>&); // Return mx1 vector of predictions
+        void addNode(const std::string&);
+        void addEdge(const std::string&, const std::string&);
+        std::map<std::string, std::unique_ptr<Node>>& getNodes();
+        std::vector<std::string> getFeatures() const;
+        int getStates() const;
+        std::vector<std::pair<std::string, std::string>> getEdges() const;
+        int getNumEdges() const;
+        int getClassNumStates() const;
+        std::string getClassName() const;
+        /*
+        Notice: Nodes have to be inserted in the same order as they are in the dataset, i.e., first node is first column and so on.
+        */
+        void fit(const std::vector<std::vector<int>>& input_data, const std::vector<int>& labels, const std::vector<double>& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
+        void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
+        void fit(const torch::Tensor& samples, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
+        std::vector<int> predict(const std::vector<std::vector<int>>&); // Return mx1 std::vector of predictions
         torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
-        //Computes the conditional edge weight of variable index u and v conditioned on class_node
-        torch::Tensor conditionalEdgeWeight();
         torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
-        vector<vector<double>> predict_proba(const vector<vector<int>>&); // Return mxn vector of probabilities
+        std::vector<std::vector<double>> predict_proba(const std::vector<std::vector<int>>&); // Return mxn std::vector of probabilities
         torch::Tensor predict_proba(const torch::Tensor&); // Return mxn tensor of probabilities
-        double score(const vector<vector<int>>&, const vector<int>&);
-        vector<string> topological_sort();
-        vector<string> show();
-        vector<string> graph(const string& title); // Returns a vector of strings representing the graph in graphviz format
+        double score(const std::vector<std::vector<int>>&, const std::vector<int>&);
+        std::vector<std::string> topological_sort();
+        std::vector<std::string> show() const;
+        std::vector<std::string> graph(const std::string& title) const; // Returns a std::vector of std::strings representing the graph in graphviz format
         void initialize();
-        void dump_cpt();
-        inline string version() { return "0.1.0"; }
+        void dump_cpt() const;
+        inline std::string version() { return "0.2.0"; }
     };
 }
 #endif

src/BayesNet/Node.cc

@@ -3,7 +3,7 @@
 namespace bayesnet {
 
     Node::Node(const std::string& name)
-        : name(name), numStates(0), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
+        : name(name), numStates(0), cpTable(torch::Tensor()), parents(std::vector<Node*>()), children(std::vector<Node*>())
     {
     }
     void Node::clear()
@@ -14,7 +14,7 @@ namespace bayesnet {
         dimensions.clear();
         numStates = 0;
     }
-    string Node::getName() const
+    std::string Node::getName() const
     {
         return name;
     }
@@ -34,11 +34,11 @@ namespace bayesnet {
     {
         children.push_back(child);
     }
-    vector<Node*>& Node::getParents()
+    std::vector<Node*>& Node::getParents()
     {
         return parents;
     }
-    vector<Node*>& Node::getChildren()
+    std::vector<Node*>& Node::getChildren()
     {
         return children;
     }
@@ -63,28 +63,28 @@ namespace bayesnet {
     */
     unsigned Node::minFill()
     {
-        unordered_set<string> neighbors;
+        std::unordered_set<std::string> neighbors;
         for (auto child : children) {
             neighbors.emplace(child->getName());
         }
         for (auto parent : parents) {
             neighbors.emplace(parent->getName());
         }
-        auto source = vector<string>(neighbors.begin(), neighbors.end());
+        auto source = std::vector<std::string>(neighbors.begin(), neighbors.end());
         return combinations(source).size();
     }
-    vector<pair<string, string>> Node::combinations(const vector<string>& source)
+    std::vector<std::pair<std::string, std::string>> Node::combinations(const std::vector<std::string>& source)
     {
-        vector<pair<string, string>> result;
+        std::vector<std::pair<std::string, std::string>> result;
         for (int i = 0; i < source.size(); ++i) {
-            string temp = source[i];
+            std::string temp = source[i];
             for (int j = i + 1; j < source.size(); ++j) {
                 result.push_back({ temp, source[j] });
             }
         }
         return result;
     }
-    void Node::computeCPT(map<string, vector<int>>& dataset, const int laplaceSmoothing)
+    void Node::computeCPT(const torch::Tensor& dataset, const std::vector<std::string>& features, const double laplaceSmoothing, const torch::Tensor& weights)
     {
         dimensions.clear();
         // Get dimensions of the CPT
@@ -94,27 +94,39 @@ 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 std::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 std::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)
+    float Node::getFactorValue(std::map<std::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(), std::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)
+    std::vector<std::string> Node::graph(const std::string& className)
     {
-        auto output = vector<string>();
+        auto output = std::vector<std::string>();
         auto suffix = name == className ? ", fontcolor=red, fillcolor=lightblue, style=filled " : "";
         output.push_back(name + " [shape=circle" + suffix + "] \n");
         transform(children.begin(), children.end(), back_inserter(output), [this](const auto& child) { return name + " -> " + child->getName(); });

src/BayesNet/Node.h

@@ -5,33 +5,32 @@
 #include <vector>
 #include <string>
 namespace bayesnet {
-    using namespace std;
     class Node {
     private:
-        string name;
-        vector<Node*> parents;
-        vector<Node*> children;
+        std::string name;
+        std::vector<Node*> parents;
+        std::vector<Node*> children;
         int numStates; // number of states of the variable
         torch::Tensor cpTable; // Order of indices is 0-> node variable, 1-> 1st parent, 2-> 2nd parent, ...
-        vector<int64_t> dimensions; // dimensions of the cpTable
+        std::vector<int64_t> dimensions; // dimensions of the cpTable
+        std::vector<std::pair<std::string, std::string>> combinations(const std::vector<std::string>&);
     public:
-        vector<pair<string, string>> combinations(const vector<string>&);
-        explicit Node(const string&);
+        explicit Node(const std::string&);
         void clear();
         void addParent(Node*);
         void addChild(Node*);
         void removeParent(Node*);
         void removeChild(Node*);
-        string getName() const;
-        vector<Node*>& getParents();
-        vector<Node*>& getChildren();
+        std::string getName() const;
+        std::vector<Node*>& getParents();
+        std::vector<Node*>& getChildren();
         torch::Tensor& getCPT();
-        void computeCPT(map<string, vector<int>>&, const int);
+        void computeCPT(const torch::Tensor& dataset, const std::vector<std::string>& features, const double laplaceSmoothing, const torch::Tensor& weights);
         int getNumStates() const;
         void setNumStates(int);
         unsigned minFill();
-        vector<string> graph(const string& clasName); // Returns a vector of strings representing the graph in graphviz format
-        float getFactorValue(map<string, int>&);
+        std::vector<std::string> graph(const std::string& clasName); // Returns a std::vector of std::strings representing the graph in graphviz format
+        float getFactorValue(std::map<std::string, int>&);
     };
 }
 #endif

src/BayesNet/Proposal.cc

@@ -2,21 +2,30 @@
 #include "ArffFiles.h"
 
 namespace bayesnet {
-    Proposal::Proposal(vector<vector<int>>& Xv_, vector<int>& yv_, vector<string>& features_, string& className_) : Xv(Xv_), yv(yv_), pFeatures(features_), pClassName(className_) {}
+    Proposal::Proposal(torch::Tensor& dataset_, std::vector<std::string>& features_, std::string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_) {}
     Proposal::~Proposal()
     {
         for (auto& [key, value] : discretizers) {
             delete value;
         }
     }
-    void Proposal::localDiscretizationProposal(map<string, vector<int>>& states, Network& model)
+    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<std::string, std::vector<int>> Proposal::localDiscretizationProposal(const map<std::string, std::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();
-        vector<int> indicesToReDiscretize;
-        auto n_samples = Xf.size(1);
+        map<std::string, std::vector<int>> states = oldStates;
+        std::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();
@@ -24,76 +33,75 @@ namespace bayesnet {
             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;
+            std::vector<std::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;
+            std::vector<int> indices;
+            indices.push_back(-1); // Add class index
             transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(pFeatures.begin(), pFeatures.end(), p) - pFeatures.begin(); });
             // Now we fit the discretizer of the feature, conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
-            vector<string> yJoinParents;
-            transform(yv.begin(), yv.end(), back_inserter(yJoinParents), [&](const auto& p) {return to_string(p); });
+            std::vector<std::string> yJoinParents(Xf.size(1));
             for (auto idx : indices) {
-                for (int i = 0; i < n_samples; ++i) {
-                    yJoinParents[i] += to_string(Xv[idx][i]);
+                for (int i = 0; i < Xf.size(1); ++i) {
+                    yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
                 }
             }
             auto arff = ArffFiles();
             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));
+            auto xvf = std::vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
             discretizers[feature]->fit(xvf, yxv);
-            //
-            //
-            //
-            // auto tmp = discretizers[feature]->transform(xvf);
-            // Xv[index] = tmp;
-            // auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
-            // iota(xStates.begin(), xStates.end(), 0);
-            // //Update new states of the feature/node
-            // states[feature] = xStates;
         }
         if (upgrade) {
             // Discretize again X (only the affected indices) with the new fitted discretizers
             for (auto index : indicesToReDiscretize) {
                 auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
-                auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
-                Xv[index] = discretizers[pFeatures[index]]->transform(Xt);
-                auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
+                auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+                pDataset.index_put_({ index, "..." }, torch::tensor(discretizers[pFeatures[index]]->transform(Xt)));
+                auto xStates = std::vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
                 iota(xStates.begin(), xStates.end(), 0);
                 //Update new states of the feature/node
                 states[pFeatures[index]] = xStates;
             }
+            const torch::Tensor weights = torch::full({ pDataset.size(1) }, 1.0 / pDataset.size(1), torch::kDouble);
+            model.fit(pDataset, weights, pFeatures, pClassName, states);
         }
+        return states;
     }
-    void Proposal::fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y)
+    map<std::string, std::vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
     {
-        // Sharing Xv and yv with Classifier
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        // Discretize the continuous input data and build pDataset (Classifier::dataset)
+        int m = Xf.size(1);
+        int n = Xf.size(0);
+        map<std::string, std::vector<int>> states;
+        pDataset = torch::zeros({ n + 1, m }, torch::kInt32);
+        auto yv = std::vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
         // discretize input data by feature(row)
-        for (int i = 0; i < pFeatures.size(); ++i) {
+        for (auto i = 0; i < pFeatures.size(); ++i) {
             auto* discretizer = new mdlp::CPPFImdlp();
             auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
-            auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+            auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
             discretizer->fit(Xt, yv);
-            Xv.push_back(discretizer->transform(Xt));
-            auto xStates = vector<int>(discretizer->getCutPoints().size() + 1);
+            pDataset.index_put_({ i, "..." }, torch::tensor(discretizer->transform(Xt)));
+            auto xStates = std::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);
+        auto yStates = std::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 Xt = std::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));
         }

src/BayesNet/Proposal.h

@@ -10,19 +10,20 @@
 namespace bayesnet {
     class Proposal {
     public:
-        Proposal(vector<vector<int>>& Xv_, vector<int>& yv_, vector<string>& features_, string& className_);
+        Proposal(torch::Tensor& pDataset, std::vector<std::string>& features_, std::string& className_);
         virtual ~Proposal();
     protected:
+        void checkInput(const torch::Tensor& X, const torch::Tensor& y);
         torch::Tensor prepareX(torch::Tensor& X);
-        void localDiscretizationProposal(map<string, vector<int>>& states, Network& model);
-        void fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y);
+        map<std::string, std::vector<int>> localDiscretizationProposal(const map<std::string, std::vector<int>>& states, Network& model);
+        map<std::string, std::vector<int>> fit_local_discretization(const torch::Tensor& y);
         torch::Tensor Xf; // X continuous nxm tensor
-        map<string, mdlp::CPPFImdlp*> discretizers;
+        torch::Tensor y; // y discrete nx1 tensor
+        map<std::string, mdlp::CPPFImdlp*> discretizers;
     private:
-        vector<string>& pFeatures;
-        string& pClassName;
-        vector<vector<int>>& Xv; // X discrete nxm vector
-        vector<int>& yv;
+        torch::Tensor& pDataset; // (n+1)xm tensor
+        std::vector<std::string>& pFeatures;
+        std::string& pClassName;
     };
 }
 

src/BayesNet/SPODE.cc

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

src/BayesNet/SPODE.h

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

src/BayesNet/SPODELd.cc

@@ -1,34 +1,46 @@
 #include "SPODELd.h"
 
 namespace bayesnet {
-    using namespace std;
-    SPODELd::SPODELd(int root) : SPODE(root), Proposal(SPODE::Xv, SPODE::yv, features, className) {}
-    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
+    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
         y = y_;
-        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
-        fit_local_discretization(states, y);
-        generateTensorXFromVector();
+        // Fills std::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(SPODE::Xv, SPODE::yv, features, className, states);
-        localDiscretizationProposal(states, model);
-        generateTensorXFromVector();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        model.fit(SPODE::Xv, SPODE::yv, features, className);
+        SPODE::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
         return *this;
     }
-    Tensor SPODELd::predict(Tensor& X)
+    SPODELd& SPODELd::fit(torch::Tensor& dataset, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::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 std::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;
+    }
+
+    torch::Tensor SPODELd::predict(torch::Tensor& X)
     {
         auto Xt = prepareX(X);
         return SPODE::predict(Xt);
     }
-    vector<string> SPODELd::graph(const string& name)
+    std::vector<std::string> SPODELd::graph(const std::string& name) const
     {
         return SPODE::graph(name);
     }

src/BayesNet/SPODELd.h

@@ -4,16 +4,15 @@
 #include "Proposal.h"
 
 namespace bayesnet {
-    using namespace std;
     class SPODELd : public SPODE, public Proposal {
-    private:
     public:
         explicit SPODELd(int root);
         virtual ~SPODELd() = default;
-        SPODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        vector<string> graph(const string& name = "SPODE") override;
-        Tensor predict(Tensor& X) override;
-        static inline string version() { return "0.0.1"; };
+        SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
+        SPODELd& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
+        std::vector<std::string> graph(const std::string& name = "SPODE") const override;
+        torch::Tensor predict(torch::Tensor& X) override;
+        static inline std::string version() { return "0.0.1"; };
     };
 }
 #endif // !SPODELD_H

src/BayesNet/TAN.cc

@@ -1,29 +1,27 @@
 #include "TAN.h"
 
 namespace bayesnet {
-    using namespace torch;
-
     TAN::TAN() : Classifier(Network()) {}
 
-    void TAN::train()
+    void TAN::buildModel(const torch::Tensor& weights)
     {
         // 0. Add all nodes to the model
         addNodes();
         // 1. Compute mutual information between each feature and the class and set the root node
         // as the highest mutual information with the class
-        auto mi = vector <pair<int, float >>();
-        Tensor class_dataset = samples.index({ -1, "..." });
+        auto mi = std::vector <std::pair<int, float >>();
+        torch::Tensor class_dataset = dataset.index({ -1, "..." });
         for (int i = 0; i < static_cast<int>(features.size()); ++i) {
-            Tensor feature_dataset = samples.index({ i, "..." });
-            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
+            torch::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 +32,7 @@ namespace bayesnet {
             model.addEdge(className, feature);
         }
     }
-    vector<string> TAN::graph(const string& title)
+    std::vector<std::string> TAN::graph(const std::string& title) const
     {
         return model.graph(title);
     }

src/BayesNet/TAN.h

@@ -2,16 +2,14 @@
 #define TAN_H
 #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(const string& name = "TAN") override;
+        virtual ~TAN() = default;
+        std::vector<std::string> graph(const std::string& name = "TAN") const override;
     };
 }
 #endif

src/BayesNet/TANLd.cc

@@ -1,34 +1,29 @@
 #include "TANLd.h"
 
 namespace bayesnet {
-    using namespace std;
-    TANLd::TANLd() : TAN(), Proposal(TAN::Xv, TAN::yv, features, className) {}
-    TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    TANLd::TANLd() : TAN(), Proposal(dataset, features, className) {}
+    TANLd& TANLd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
         y = y_;
-        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
-        fit_local_discretization(states, y);
-        generateTensorXFromVector();
+        // Fills std::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(TAN::Xv, TAN::yv, features, className, states);
-        localDiscretizationProposal(states, model);
-        generateTensorXFromVector();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        model.fit(TAN::Xv, TAN::yv, features, className);
+        TAN::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
         return *this;
+
     }
-    Tensor TANLd::predict(Tensor& X)
+    torch::Tensor TANLd::predict(torch::Tensor& X)
     {
         auto Xt = prepareX(X);
         return TAN::predict(Xt);
     }
-    vector<string> TANLd::graph(const string& name)
+    std::vector<std::string> TANLd::graph(const std::string& name) const
     {
         return TAN::graph(name);
     }

src/BayesNet/TANLd.h

@@ -4,16 +4,15 @@
 #include "Proposal.h"
 
 namespace bayesnet {
-    using namespace std;
     class TANLd : public TAN, public Proposal {
     private:
     public:
         TANLd();
         virtual ~TANLd() = default;
-        TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        vector<string> graph(const string& name = "TAN") override;
-        Tensor predict(Tensor& X) override;
-        static inline string version() { return "0.0.1"; };
+        TANLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states) override;
+        std::vector<std::string> graph(const std::string& name = "TAN") const override;
+        torch::Tensor predict(torch::Tensor& X) override;
+        static inline std::string version() { return "0.0.1"; };
     };
 }
 #endif // !TANLD_H

src/BayesNet/bayesnetUtils.cc

@@ -1,25 +1,23 @@
 
 #include "bayesnetUtils.h"
 namespace bayesnet {
-    using namespace std;
-    using namespace torch;
     // Return the indices in descending order
-    vector<int> argsort(vector<float>& nums)
+    std::vector<int> argsort(std::vector<double>& nums)
     {
         int n = nums.size();
-        vector<int> indices(n);
+        std::vector<int> indices(n);
         iota(indices.begin(), indices.end(), 0);
         sort(indices.begin(), indices.end(), [&nums](int i, int j) {return nums[i] > nums[j];});
         return indices;
     }
-    vector<vector<int>> tensorToVector(Tensor& tensor)
+    std::vector<std::vector<int>> tensorToVector(torch::Tensor& tensor)
     {
-        // convert mxn tensor to nxm vector
-        vector<vector<int>> result;
+        // convert mxn tensor to nxm std::vector
+        std::vector<std::vector<int>> result;
         // Iterate over cols
         for (int i = 0; i < tensor.size(1); ++i) {
             auto col_tensor = tensor.index({ "...", i });
-            auto col = vector<int>(col_tensor.data_ptr<int>(), col_tensor.data_ptr<int>() + tensor.size(0));
+            auto col = std::vector<int>(col_tensor.data_ptr<int>(), col_tensor.data_ptr<int>() + tensor.size(0));
             result.push_back(col);
         }
         return result;

src/BayesNet/bayesnetUtils.h

@@ -3,9 +3,7 @@
 #include <torch/torch.h>
 #include <vector>
 namespace bayesnet {
-    using namespace std;
-    using namespace torch;
-    vector<int> argsort(vector<float>& nums);
-    vector<vector<int>> tensorToVector(Tensor& tensor);
+    std::vector<int> argsort(std::vector<double>& nums);
+    std::vector<std::vector<int>> tensorToVector(torch::Tensor& tensor);
 }
 #endif //BAYESNET_UTILS_H

src/Platform/BestResults.cc

@@ -0,0 +1,343 @@
+#include <filesystem>
+#include <set>
+#include <fstream>
+#include <iostream>
+#include <sstream>
+#include <algorithm>
+#include "BestResults.h"
+#include "Result.h"
+#include "Colors.h"
+#include "Statistics.h"
+#include "BestResultsExcel.h"
+#include "CLocale.h"
+
+
+namespace fs = std::filesystem;
+// function ftime_to_std::string, Code taken from 
+// https://stackoverflow.com/a/58237530/1389271
+template <typename TP>
+std::string ftime_to_string(TP tp)
+{
+    auto sctp = std::chrono::time_point_cast<std::chrono::system_clock::duration>(tp - TP::clock::now()
+        + std::chrono::system_clock::now());
+    auto tt = std::chrono::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 {
+    std::string BestResults::build()
+    {
+        auto files = loadResultFiles();
+        if (files.size() == 0) {
+            std::cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << std::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;
+                // Check if results file contains only one dataset
+                auto datasetName = item.at("dataset").get<std::string>();
+                if (bests.contains(datasetName)) {
+                    if (item.at("score").get<double>() > bests[datasetName].at(0).get<double>()) {
+                        update = true;
+                    }
+                } else {
+                    update = true;
+                }
+                if (update) {
+                    bests[datasetName] = { item.at("score").get<double>(), item.at("hyperparameters"), file };
+                }
+            }
+        }
+        std::string bestFileName = path + bestResultFile();
+        if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+            fclose(fileTest);
+            std::cout << Colors::MAGENTA() << "File " << bestFileName << " already exists and it shall be overwritten." << Colors::RESET() << std::endl;
+        }
+        std::ofstream file(bestFileName);
+        file << bests;
+        file.close();
+        return bestFileName;
+    }
+    std::string BestResults::bestResultFile()
+    {
+        return "best_results_" + score + "_" + model + ".json";
+    }
+    std::pair<std::string, std::string> getModelScore(std::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);
+        std::string score = name.substr(pos + 1, pos2 - pos - 1);
+        pos = name.find("_", pos2 + 1);
+        std::string model = name.substr(pos2 + 1, pos - pos2 - 1);
+        return { model, score };
+    }
+    std::vector<std::string> BestResults::loadResultFiles()
+    {
+        std::vector<std::string> files;
+        using std::filesystem::directory_iterator;
+        std::string fileModel, fileScore;
+        for (const auto& file : directory_iterator(path)) {
+            auto fileName = file.path().filename().string();
+            if (fileName.find(".json") != std::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 std::string& fileName)
+    {
+        std::ifstream resultData(fileName);
+        if (resultData.is_open()) {
+            json data = json::parse(resultData);
+            return data;
+        }
+        throw std::invalid_argument("Unable to open result file. [" + fileName + "]");
+    }
+    std::vector<std::string> BestResults::getModels()
+    {
+        std::set<std::string> models;
+        std::vector<std::string> result;
+        auto files = loadResultFiles();
+        if (files.size() == 0) {
+            std::cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << std::endl;
+            exit(1);
+        }
+        std::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 std::vector of models
+            models.insert(fileModel);
+        }
+        result = std::vector<std::string>(models.begin(), models.end());
+        return result;
+    }
+    std::vector<std::string> BestResults::getDatasets(json table)
+    {
+        std::vector<std::string> datasets;
+        for (const auto& dataset : table.items()) {
+            datasets.push_back(dataset.key());
+        }
+        return datasets;
+    }
+    void BestResults::buildAll()
+    {
+        auto models = getModels();
+        for (const auto& model : models) {
+            std::cout << "Building best results for model: " << model << std::endl;
+            this->model = model;
+            build();
+        }
+        model = "any";
+    }
+    void BestResults::listFile()
+    {
+        std::string bestFileName = path + bestResultFile();
+        if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+            fclose(fileTest);
+        } else {
+            std::cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << std::endl;
+            exit(1);
+        }
+        auto temp = ConfigLocale();
+        auto date = ftime_to_string(std::filesystem::last_write_time(bestFileName));
+        auto data = loadFile(bestFileName);
+        auto datasets = getDatasets(data);
+        int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
+        int maxFileName = 0;
+        int maxHyper = 15;
+        for (auto const& item : data.items()) {
+            maxHyper = std::max(maxHyper, (int)item.value().at(1).dump().size());
+            maxFileName = std::max(maxFileName, (int)item.value().at(2).get<std::string>().size());
+        }
+        std::stringstream oss;
+        oss << Colors::GREEN() << "Best results for " << model << " as of " << date << std::endl;
+        std::cout << oss.str();
+        std::cout << std::string(oss.str().size() - 8, '-') << std::endl;
+        std::cout << Colors::GREEN() << " #  " << std::setw(maxDatasetName + 1) << std::left << "Dataset" << "Score       " << std::setw(maxFileName) << "File" << " Hyperparameters" << std::endl;
+        std::cout << "=== " << std::string(maxDatasetName, '=') << " =========== " << std::string(maxFileName, '=') << " " << std::string(maxHyper, '=') << std::endl;
+        auto i = 0;
+        bool odd = true;
+        double total = 0;
+        for (auto const& item : data.items()) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            double value = item.value().at(0).get<double>();
+            std::cout << color << std::setw(3) << std::fixed << std::right << i++ << " ";
+            std::cout << std::setw(maxDatasetName) << std::left << item.key() << " ";
+            std::cout << std::setw(11) << std::setprecision(9) << std::fixed << value << " ";
+            std::cout << std::setw(maxFileName) << item.value().at(2).get<std::string>() << " ";
+            std::cout << item.value().at(1) << " ";
+            std::cout << std::endl;
+            total += value;
+            odd = !odd;
+        }
+        std::cout << Colors::GREEN() << "=== " << std::string(maxDatasetName, '=') << " ===========" << std::endl;
+        std::cout << std::setw(5 + maxDatasetName) << "Total.................. " << std::setw(11) << std::setprecision(8) << std::fixed << total << std::endl;
+    }
+    json BestResults::buildTableResults(std::vector<std::string> models)
+    {
+        json table;
+        auto maxDate = std::filesystem::file_time_type::max();
+        for (const auto& model : models) {
+            this->model = model;
+            std::string bestFileName = path + bestResultFile();
+            if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+                fclose(fileTest);
+            } else {
+                std::cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << std::endl;
+                exit(1);
+            }
+            auto dateWrite = std::filesystem::last_write_time(bestFileName);
+            if (dateWrite < maxDate) {
+                maxDate = dateWrite;
+            }
+            auto data = loadFile(bestFileName);
+            table[model] = data;
+        }
+        table["dateTable"] = ftime_to_string(maxDate);
+        return table;
+    }
+    void BestResults::printTableResults(std::vector<std::string> models, json table)
+    {
+        std::stringstream oss;
+        oss << Colors::GREEN() << "Best results for " << score << " as of " << table.at("dateTable").get<std::string>() << std::endl;
+        std::cout << oss.str();
+        std::cout << std::string(oss.str().size() - 8, '-') << std::endl;
+        std::cout << Colors::GREEN() << " #  " << std::setw(maxDatasetName + 1) << std::left << std::string("Dataset");
+        for (const auto& model : models) {
+            std::cout << std::setw(maxModelName) << std::left << model << " ";
+        }
+        std::cout << std::endl;
+        std::cout << "=== " << std::string(maxDatasetName, '=') << " ";
+        for (const auto& model : models) {
+            std::cout << std::string(maxModelName, '=') << " ";
+        }
+        std::cout << std::endl;
+        auto i = 0;
+        bool odd = true;
+        std::map<std::string, double> totals;
+        int nDatasets = table.begin().value().size();
+        for (const auto& model : models) {
+            totals[model] = 0.0;
+        }
+        auto datasets = getDatasets(table.begin().value());
+        for (auto const& dataset : datasets) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            std::cout << color << std::setw(3) << std::fixed << std::right << i++ << " ";
+            std::cout << std::setw(maxDatasetName) << std::left << dataset << " ";
+            double maxValue = 0;
+            // Find out the max value for this dataset
+            for (const auto& model : models) {
+                double value = table[model].at(dataset).at(0).get<double>();
+                if (value > maxValue) {
+                    maxValue = value;
+                }
+            }
+            // Print the row with red colors on max values
+            for (const auto& model : models) {
+                std::string efectiveColor = color;
+                double value = table[model].at(dataset).at(0).get<double>();
+                if (value == maxValue) {
+                    efectiveColor = Colors::RED();
+                }
+                totals[model] += value;
+                std::cout << efectiveColor << std::setw(maxModelName) << std::setprecision(maxModelName - 2) << std::fixed << value << " ";
+            }
+            std::cout << std::endl;
+            odd = !odd;
+        }
+        std::cout << Colors::GREEN() << "=== " << std::string(maxDatasetName, '=') << " ";
+        for (const auto& model : models) {
+            std::cout << std::string(maxModelName, '=') << " ";
+        }
+        std::cout << std::endl;
+        std::cout << Colors::GREEN() << std::setw(5 + maxDatasetName) << "    Totals...................";
+        double max = 0.0;
+        for (const auto& total : totals) {
+            if (total.second > max) {
+                max = total.second;
+            }
+        }
+        for (const auto& model : models) {
+            std::string efectiveColor = Colors::GREEN();
+            if (totals[model] == max) {
+                efectiveColor = Colors::RED();
+            }
+            std::cout << efectiveColor << std::right << std::setw(maxModelName) << std::setprecision(maxModelName - 4) << std::fixed << totals[model] << " ";
+        }
+        std::cout << std::endl;
+    }
+    void BestResults::reportSingle(bool excel)
+    {
+        listFile();
+        if (excel) {
+            auto models = getModels();
+            // Build the table of results
+            json table = buildTableResults(models);
+            std::vector<std::string> datasets = getDatasets(table.begin().value());
+            BestResultsExcel excel(score, datasets);
+            excel.reportSingle(model, path + bestResultFile());
+            messageExcelFile(excel.getFileName());
+        }
+    }
+    void BestResults::reportAll(bool excel)
+    {
+        auto models = getModels();
+        // Build the table of results
+        json table = buildTableResults(models);
+        std::vector<std::string> datasets = getDatasets(table.begin().value());
+        maxModelName = (*max_element(models.begin(), models.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
+        maxModelName = std::max(12, maxModelName);
+        maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
+        maxDatasetName = std::max(25, maxDatasetName);
+        // Print the table of results
+        printTableResults(models, table);
+        // Compute the Friedman test
+        std::map<std::string, std::map<std::string, float>> ranksModels;
+        if (friedman) {
+            Statistics stats(models, datasets, table, significance);
+            auto result = stats.friedmanTest();
+            stats.postHocHolmTest(result);
+            ranksModels = stats.getRanks();
+        }
+        if (excel) {
+            BestResultsExcel excel(score, datasets);
+            excel.reportAll(models, table, ranksModels, friedman, significance);
+            if (friedman) {
+                int idx = -1;
+                double min = 2000;
+                // Find out the control model
+                auto totals = std::vector<double>(models.size(), 0.0);
+                for (const auto& dataset : datasets) {
+                    for (int i = 0; i < models.size(); ++i) {
+                        totals[i] += ranksModels[dataset][models[i]];
+                    }
+                }
+                for (int i = 0; i < models.size(); ++i) {
+                    if (totals[i] < min) {
+                        min = totals[i];
+                        idx = i;
+                    }
+                }
+                model = models.at(idx);
+                excel.reportSingle(model, path + bestResultFile());
+            }
+            messageExcelFile(excel.getFileName());
+        }
+    }
+    void BestResults::messageExcelFile(const std::string& fileName)
+    {
+        std::cout << Colors::YELLOW() << "** Excel file generated: " << fileName << Colors::RESET() << std::endl;
+    }
+}

src/Platform/BestResults.h

@@ -0,0 +1,36 @@
+#ifndef BESTRESULTS_H
+#define BESTRESULTS_H
+#include <string>
+#include <nlohmann/json.hpp>
+using json = nlohmann::json;
+namespace platform {
+    class BestResults {
+    public:
+        explicit BestResults(const std::string& path, const std::string& score, const std::string& model, bool friedman, double significance = 0.05)
+            : path(path), score(score), model(model), friedman(friedman), significance(significance)
+        {
+        }
+        std::string build();
+        void reportSingle(bool excel);
+        void reportAll(bool excel);
+        void buildAll();
+    private:
+        std::vector<std::string> getModels();
+        std::vector<std::string> getDatasets(json table);
+        std::vector<std::string> loadResultFiles();
+        void messageExcelFile(const std::string& fileName);
+        json buildTableResults(std::vector<std::string> models);
+        void printTableResults(std::vector<std::string> models, json table);
+        std::string bestResultFile();
+        json loadFile(const std::string& fileName);
+        void listFile();
+        std::string path;
+        std::string score;
+        std::string model;
+        bool friedman;
+        double significance;
+        int maxModelName = 0;
+        int maxDatasetName = 0;
+    };
+}
+#endif //BESTRESULTS_H

src/Platform/BestResultsExcel.cc

@@ -0,0 +1,300 @@
+#include <sstream>
+#include "BestResultsExcel.h"
+#include "Paths.h"
+#include <map>
+#include <nlohmann/json.hpp>
+#include "Statistics.h"
+#include "ReportExcel.h"
+
+namespace platform {
+    json loadResultData(const std::string& fileName)
+    {
+        json data;
+        std::ifstream resultData(fileName);
+        if (resultData.is_open()) {
+            data = json::parse(resultData);
+        } else {
+            throw std::invalid_argument("Unable to open result file. [" + fileName + "]");
+        }
+        return data;
+    }
+    std::string getColumnName(int colNum)
+    {
+        std::string columnName = "";
+        if (colNum == 0)
+            return "A";
+        while (colNum > 0) {
+            int modulo = colNum % 26;
+            columnName = char(65 + modulo) + columnName;
+            colNum = (int)((colNum - modulo) / 26);
+        }
+        return columnName;
+    }
+    BestResultsExcel::BestResultsExcel(const std::string& score, const std::vector<std::string>& datasets) : score(score), datasets(datasets)
+    {
+        workbook = workbook_new((Paths::excel() + fileName).c_str());
+        setProperties("Best Results");
+        int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
+        datasetNameSize = std::max(datasetNameSize, maxDatasetName);
+        createFormats();
+    }
+    void BestResultsExcel::reportAll(const std::vector<std::string>& models, const json& table, const std::map<std::string, std::map<std::string, float>>& ranks, bool friedman, double significance)
+    {
+        this->table = table;
+        this->models = models;
+        ranksModels = ranks;
+        this->friedman = friedman;
+        this->significance = significance;
+        worksheet = workbook_add_worksheet(workbook, "Best Results");
+        int maxModelName = (*std::max_element(models.begin(), models.end(), [](const std::string& a, const std::string& b) { return a.size() < b.size(); })).size();
+        modelNameSize = std::max(modelNameSize, maxModelName);
+        formatColumns();
+        build();
+    }
+    void BestResultsExcel::reportSingle(const std::string& model, const std::string& fileName)
+    {
+        worksheet = workbook_add_worksheet(workbook, "Report");
+        if (FILE* fileTest = fopen(fileName.c_str(), "r")) {
+            fclose(fileTest);
+        } else {
+            std::cerr << "File " << fileName << " doesn't exist." << std::endl;
+            exit(1);
+        }
+        json data = loadResultData(fileName);
+
+        std::string title = "Best results for " + model;
+        worksheet_merge_range(worksheet, 0, 0, 0, 4, title.c_str(), styles["headerFirst"]);
+        // Body header
+        row = 3;
+        int col = 1;
+        writeString(row, 0, "Nº", "bodyHeader");
+        writeString(row, 1, "Dataset", "bodyHeader");
+        writeString(row, 2, "Score", "bodyHeader");
+        writeString(row, 3, "File", "bodyHeader");
+        writeString(row, 4, "Hyperparameters", "bodyHeader");
+        auto i = 0;
+        std::string hyperparameters;
+        int hypSize = 22;
+        std::map<std::string, std::string> files; // map of files imported and their tabs
+        for (auto const& item : data.items()) {
+            row++;
+            writeInt(row, 0, i++, "ints");
+            writeString(row, 1, item.key().c_str(), "text");
+            writeDouble(row, 2, item.value().at(0).get<double>(), "result");
+            auto fileName = item.value().at(2).get<std::string>();
+            std::string hyperlink = "";
+            try {
+                hyperlink = files.at(fileName);
+            }
+            catch (const std::out_of_range& oor) {
+                auto tabName = "table_" + std::to_string(i);
+                auto worksheetNew = workbook_add_worksheet(workbook, tabName.c_str());
+                json data = loadResultData(Paths::results() + fileName);
+                auto report = ReportExcel(data, false, workbook, worksheetNew);
+                report.show();
+                hyperlink = "#table_" + std::to_string(i);
+                files[fileName] = hyperlink;
+            }
+            hyperlink += "!H" + std::to_string(i + 6);
+            std::string fileNameText = "=HYPERLINK(\"" + hyperlink + "\",\"" + fileName + "\")";
+            worksheet_write_formula(worksheet, row, 3, fileNameText.c_str(), efectiveStyle("text"));
+            hyperparameters = item.value().at(1).dump();
+            if (hyperparameters.size() > hypSize) {
+                hypSize = hyperparameters.size();
+            }
+            writeString(row, 4, hyperparameters, "text");
+        }
+        row++;
+        // Set Totals
+        writeString(row, 1, "Total", "bodyHeader");
+        std::stringstream oss;
+        auto colName = getColumnName(2);
+        oss << "=sum(" << colName << "5:" << colName << row << ")";
+        worksheet_write_formula(worksheet, row, 2, oss.str().c_str(), styles["bodyHeader_odd"]);
+        // Set format
+        worksheet_freeze_panes(worksheet, 4, 2);
+        std::vector<int> columns_sizes = { 5, datasetNameSize, modelNameSize, 66, hypSize + 1 };
+        for (int i = 0; i < columns_sizes.size(); ++i) {
+            worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
+        }
+    }
+    BestResultsExcel::~BestResultsExcel()
+    {
+        workbook_close(workbook);
+    }
+    void BestResultsExcel::formatColumns()
+    {
+        worksheet_freeze_panes(worksheet, 4, 2);
+        std::vector<int> columns_sizes = { 5, datasetNameSize };
+        for (int i = 0; i < models.size(); ++i) {
+            columns_sizes.push_back(modelNameSize);
+        }
+        for (int i = 0; i < columns_sizes.size(); ++i) {
+            worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
+        }
+    }
+    void BestResultsExcel::addConditionalFormat(std::string formula)
+    {
+        // Add conditional format for max/min values in scores/ranks sheets
+        lxw_format* custom_format = workbook_add_format(workbook);
+        format_set_bg_color(custom_format, 0xFFC7CE);
+        format_set_font_color(custom_format, 0x9C0006);
+        // Create a conditional format object. A static object would also work.
+        lxw_conditional_format* conditional_format = (lxw_conditional_format*)calloc(1, sizeof(lxw_conditional_format));
+        conditional_format->type = LXW_CONDITIONAL_TYPE_FORMULA;
+        std::string col = getColumnName(models.size() + 1);
+        std::stringstream oss;
+        oss << "=C5=" << formula << "($C5:$" << col << "5)";
+        auto formulaValue = oss.str();
+        conditional_format->value_string = formulaValue.c_str();
+        conditional_format->format = custom_format;
+        worksheet_conditional_format_range(worksheet, 4, 2, datasets.size() + 3, models.size() + 1, conditional_format);
+    }
+    void BestResultsExcel::build()
+    {
+        // Create Sheet with scores
+        header(false);
+        body(false);
+        // Add conditional format for max values
+        addConditionalFormat("max");
+        footer(false);
+        if (friedman) {
+            // Create Sheet with ranks
+            worksheet = workbook_add_worksheet(workbook, "Ranks");
+            formatColumns();
+            header(true);
+            body(true);
+            addConditionalFormat("min");
+            footer(true);
+            // Create Sheet with Friedman Test
+            doFriedman();
+        }
+    }
+    std::string BestResultsExcel::getFileName()
+    {
+        return Paths::excel() + fileName;
+    }
+    void BestResultsExcel::header(bool ranks)
+    {
+        row = 0;
+        std::string message = ranks ? "Ranks for score " + score : "Best results for " + score;
+        worksheet_merge_range(worksheet, 0, 0, 0, 1 + models.size(), message.c_str(), styles["headerFirst"]);
+        // Body header
+        row = 3;
+        int col = 1;
+        writeString(row, 0, "Nº", "bodyHeader");
+        writeString(row, 1, "Dataset", "bodyHeader");
+        for (const auto& model : models) {
+            writeString(row, ++col, model.c_str(), "bodyHeader");
+        }
+    }
+    void BestResultsExcel::body(bool ranks)
+    {
+        row = 4;
+        int i = 0;
+        json origin = table.begin().value();
+        for (auto const& item : origin.items()) {
+            writeInt(row, 0, i++, "ints");
+            writeString(row, 1, item.key().c_str(), "text");
+            int col = 1;
+            for (const auto& model : models) {
+                double value = ranks ? ranksModels[item.key()][model] : table[model].at(item.key()).at(0).get<double>();
+                writeDouble(row, ++col, value, "result");
+            }
+            ++row;
+        }
+    }
+    void BestResultsExcel::footer(bool ranks)
+    {
+        // Set Totals
+        writeString(row, 1, "Total", "bodyHeader");
+        int col = 1;
+        for (const auto& model : models) {
+            std::stringstream oss;
+            auto colName = getColumnName(col + 1);
+            oss << "=SUM(" << colName << "5:" << colName << row << ")";
+            worksheet_write_formula(worksheet, row, ++col, oss.str().c_str(), styles["bodyHeader_odd"]);
+        }
+        if (ranks) {
+            row++;
+            writeString(row, 1, "Average ranks", "bodyHeader");
+            int col = 1;
+            for (const auto& model : models) {
+                auto colName = getColumnName(col + 1);
+                std::stringstream oss;
+                oss << "=SUM(" << colName << "5:" << colName << row - 1 << ")/" << datasets.size();
+                worksheet_write_formula(worksheet, row, ++col, oss.str().c_str(), styles["bodyHeader_odd"]);
+            }
+        }
+    }
+    void BestResultsExcel::doFriedman()
+    {
+        worksheet = workbook_add_worksheet(workbook, "Friedman");
+        std::vector<int> columns_sizes = { 5, datasetNameSize };
+        for (int i = 0; i < models.size(); ++i) {
+            columns_sizes.push_back(modelNameSize);
+        }
+        for (int i = 0; i < columns_sizes.size(); ++i) {
+            worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
+        }
+        worksheet_merge_range(worksheet, 0, 0, 0, 1 + models.size(), "Friedman Test", styles["headerFirst"]);
+        row = 2;
+        Statistics stats(models, datasets, table, significance, false);
+        auto result = stats.friedmanTest();
+        stats.postHocHolmTest(result);
+        auto friedmanResult = stats.getFriedmanResult();
+        auto holmResult = stats.getHolmResult();
+        worksheet_merge_range(worksheet, row, 0, row, 1 + models.size(), "Null hypothesis: H0 'There is no significant differences between all the classifiers.'", styles["headerSmall"]);
+        row += 2;
+        writeString(row, 1, "Friedman Q", "bodyHeader");
+        writeDouble(row, 2, friedmanResult.statistic, "bodyHeader");
+        row++;
+        writeString(row, 1, "Critical χ2 value", "bodyHeader");
+        writeDouble(row, 2, friedmanResult.criticalValue, "bodyHeader");
+        row++;
+        writeString(row, 1, "p-value", "bodyHeader");
+        writeDouble(row, 2, friedmanResult.pvalue, "bodyHeader");
+        writeString(row, 3, friedmanResult.reject ? "<" : ">", "bodyHeader");
+        writeDouble(row, 4, significance, "bodyHeader");
+        writeString(row, 5, friedmanResult.reject ? "Reject H0" : "Accept H0", "bodyHeader");
+        row += 3;
+        worksheet_merge_range(worksheet, row, 0, row, 1 + models.size(), "Holm Test", styles["headerFirst"]);
+        row += 2;
+        worksheet_merge_range(worksheet, row, 0, row, 1 + models.size(), "Null hypothesis: H0 'There is no significant differences between the control model and the other models.'", styles["headerSmall"]);
+        row += 2;
+        std::string controlModel = "Control Model: " + holmResult.model;
+        worksheet_merge_range(worksheet, row, 1, row, 7, controlModel.c_str(), styles["bodyHeader_odd"]);
+        row++;
+        writeString(row, 1, "Model", "bodyHeader");
+        writeString(row, 2, "p-value", "bodyHeader");
+        writeString(row, 3, "Rank", "bodyHeader");
+        writeString(row, 4, "Win", "bodyHeader");
+        writeString(row, 5, "Tie", "bodyHeader");
+        writeString(row, 6, "Loss", "bodyHeader");
+        writeString(row, 7, "Reject H0", "bodyHeader");
+        row++;
+        bool first = true;
+        for (const auto& item : holmResult.holmLines) {
+            writeString(row, 1, item.model, "text");
+            if (first) {
+                // Control model info
+                first = false;
+                writeString(row, 2, "", "text");
+                writeDouble(row, 3, item.rank, "result");
+                writeString(row, 4, "", "text");
+                writeString(row, 5, "", "text");
+                writeString(row, 6, "", "text");
+                writeString(row, 7, "", "textCentered");
+            } else {
+                // Rest of the models info
+                writeDouble(row, 2, item.pvalue, "result");
+                writeDouble(row, 3, item.rank, "result");
+                writeInt(row, 4, item.wtl.win, "ints");
+                writeInt(row, 5, item.wtl.tie, "ints");
+                writeInt(row, 6, item.wtl.loss, "ints");
+                writeString(row, 7, item.reject ? "Yes" : "No", "textCentered");
+            }
+            row++;
+        }
+    }
+}

src/Platform/BestResultsExcel.h

@@ -0,0 +1,39 @@
+#ifndef BESTRESULTS_EXCEL_H
+#define BESTRESULTS_EXCEL_H
+#include "ExcelFile.h"
+#include <vector>
+#include <map>
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+
+namespace platform {
+
+    class BestResultsExcel : ExcelFile {
+    public:
+        BestResultsExcel(const std::string& score, const std::vector<std::string>& datasets);
+        ~BestResultsExcel();
+        void reportAll(const std::vector<std::string>& models, const json& table, const std::map<std::string, std::map<std::string, float>>& ranks, bool friedman, double significance);
+        void reportSingle(const std::string& model, const std::string& fileName);
+        std::string getFileName();
+    private:
+        void build();
+        void header(bool ranks);
+        void body(bool ranks);
+        void footer(bool ranks);
+        void formatColumns();
+        void doFriedman();
+        void addConditionalFormat(std::string formula);
+        const std::string fileName = "BestResults.xlsx";
+        std::string score;
+        std::vector<std::string> models;
+        std::vector<std::string> datasets;
+        json table;
+        std::map<std::string, std::map<std::string, float>> ranksModels;
+        bool friedman;
+        double significance;
+        int modelNameSize = 12; // Min size of the column
+        int datasetNameSize = 25; // Min size of the column
+    };
+}
+#endif //BESTRESULTS_EXCEL_H

src/Platform/BestScore.h

@@ -0,0 +1,28 @@
+#ifndef BESTSCORE_H
+#define BESTSCORE_H
+#include <string>
+#include <map>
+#include <utility>
+#include "DotEnv.h"
+namespace platform {
+    class BestScore {
+    public:
+        static std::pair<std::string, double> getScore(const std::string& metric)
+        {
+            static std::map<std::pair<std::string, std::string>, std::pair<std::string, double>> data = {
+               {{"discretiz", "accuracy"}, {"STree_default (linear-ovo)",  22.109799}},
+               {{"odte", "accuracy"}, {"STree_default (linear-ovo)",  22.109799}},
+            };
+            auto env = platform::DotEnv();
+            std::string experiment = env.get("experiment");
+            try {
+                return data[{experiment, metric}];
+            }
+            catch (...) {
+                return { "", 0.0 };
+            }
+        }
+    };
+}
+
+#endif

src/Platform/CLocale.h

@@ -0,0 +1,22 @@
+#ifndef LOCALE_H
+#define LOCALE_H
+#include <locale>
+#include <iostream>
+#include <string>
+namespace platform {
+    struct separation : std::numpunct<char> {
+        char do_decimal_point() const { return ','; }
+        char do_thousands_sep() const { return '.'; }
+        std::string do_grouping() const { return "\03"; }
+    };
+    class ConfigLocale {
+    public:
+        explicit ConfigLocale()
+        {
+            std::locale mylocale(std::cout.getloc(), new separation);
+            std::locale::global(mylocale);
+            std::cout.imbue(mylocale);
+        }
+    };
+}
+#endif 

src/Platform/CMakeLists.txt

@@ -1,8 +1,22 @@
 include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
 include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
+include_directories(${BayesNet_SOURCE_DIR}/src/PyClassifiers)
 include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
 include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
-add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc Report.cc)
-target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
+include_directories(${BayesNet_SOURCE_DIR}/lib/libxlsxwriter/include)
+include_directories(${Python3_INCLUDE_DIRS})
+include_directories(${MPI_CXX_INCLUDE_DIRS})
+
+add_executable(b_best b_best.cc BestResults.cc Result.cc Statistics.cc BestResultsExcel.cc ReportExcel.cc ReportBase.cc Datasets.cc Dataset.cc ExcelFile.cc)
+add_executable(b_grid b_grid.cc GridSearch.cc GridData.cc HyperParameters.cc Folding.cc Datasets.cc Dataset.cc)
+add_executable(b_list b_list.cc Datasets.cc Dataset.cc)
+add_executable(b_main b_main.cc Folding.cc Experiment.cc Datasets.cc Dataset.cc Models.cc HyperParameters.cc ReportConsole.cc ReportBase.cc)
+add_executable(b_manage b_manage.cc Results.cc ManageResults.cc CommandParser.cc Result.cc ReportConsole.cc ReportExcel.cc ReportBase.cc Datasets.cc Dataset.cc ExcelFile.cc)
+
+target_link_libraries(b_best Boost::boost "${XLSXWRITER_LIB}" "${TORCH_LIBRARIES}" ArffFiles mdlp)
+target_link_libraries(b_grid BayesNet PyWrap ${MPI_CXX_LIBRARIES})
+target_link_libraries(b_list ArffFiles mdlp "${TORCH_LIBRARIES}")
+target_link_libraries(b_main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}" PyWrap)
+target_link_libraries(b_manage "${TORCH_LIBRARIES}" "${XLSXWRITER_LIB}" ArffFiles mdlp)

src/Platform/Colors.h

@@ -0,0 +1,15 @@
+#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 IBLUE() { return "\033[0;94m"; }
+    static std::string RESET() { return "\033[0m"; }
+};
+#endif // COLORS_H

src/Platform/CommandParser.cc

@@ -0,0 +1,87 @@
+#include "CommandParser.h"
+#include <iostream>
+#include <sstream>
+#include <algorithm>
+#include "Colors.h"
+#include "Utils.h"
+
+namespace platform {
+    void CommandParser::messageError(const std::string& message)
+    {
+        std::cout << Colors::RED() << message << Colors::RESET() << std::endl;
+    }
+    std::pair<char, int> CommandParser::parse(const std::string& color, const std::vector<std::tuple<std::string, char, bool>>& options, const char defaultCommand, const int maxIndex)
+    {
+        bool finished = false;
+        while (!finished) {
+            std::stringstream oss;
+            std::string line;
+            oss << color << "Choose option (";
+            bool first = true;
+            for (auto& option : options) {
+                if (first) {
+                    first = false;
+                } else {
+                    oss << ", ";
+                }
+                oss << std::get<char>(option) << "=" << std::get<std::string>(option);
+            }
+            oss << "): ";
+            std::cout << oss.str();
+            getline(std::cin, line);
+            std::cout << Colors::RESET();
+            line = trim(line);
+            if (line.size() == 0)
+                continue;
+            if (all_of(line.begin(), line.end(), ::isdigit)) {
+                command = defaultCommand;
+                index = stoi(line);
+                if (index > maxIndex || index < 0) {
+                    messageError("Index out of range");
+                    continue;
+                }
+                finished = true;
+                break;
+            }
+            bool found = false;
+            for (auto& option : options) {
+                if (line[0] == std::get<char>(option)) {
+                    found = true;
+                    // it's a match
+                    line.erase(line.begin());
+                    line = trim(line);
+                    if (std::get<bool>(option)) {
+                        // The option requires a value
+                        if (line.size() == 0) {
+                            messageError("Option " + std::get<std::string>(option) + " requires a value");
+                            break;
+                        }
+                        try {
+                            index = stoi(line);
+                            if (index > maxIndex || index < 0) {
+                                messageError("Index out of range");
+                                break;
+                            }
+                        }
+                        catch (const std::invalid_argument& ia) {
+                            messageError("Invalid value: " + line);
+                            break;
+                        }
+                    } else {
+                        if (line.size() > 0) {
+                            messageError("option " + std::get<std::string>(option) + " doesn't accept values");
+                            break;
+                        }
+                    }
+                    command = std::get<char>(option);
+                    finished = true;
+                    break;
+                }
+            }
+            if (!found) {
+                messageError("I don't know " + line);
+            }
+        }
+        return { command, index };
+    }
+} /* namespace platform */

src/Platform/CommandParser.h

@@ -0,0 +1,20 @@
+#ifndef COMMAND_PARSER_H
+#define COMMAND_PARSER_H
+#include <string>
+#include <vector>
+#include <tuple>
+
+namespace platform {
+    class CommandParser {
+    public:
+        CommandParser() = default;
+        std::pair<char, int> parse(const std::string& color, const std::vector<std::tuple<std::string, char, bool>>& options, const char defaultCommand, const int maxIndex);
+        char getCommand() const { return command; };
+        int getIndex() const { return index; };
+    private:
+        void messageError(const std::string& message);
+        char command;
+        int index;
+    };
+} /* namespace platform */
+#endif /* COMMAND_PARSER_H */

src/Platform/Dataset.cc

@@ -0,0 +1,215 @@
+#include "Dataset.h"
+#include "ArffFiles.h"
+#include <fstream>
+namespace platform {
+    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)
+    {
+    }
+    std::string Dataset::getName() const
+    {
+        return name;
+    }
+    std::string Dataset::getClassName() const
+    {
+        return className;
+    }
+    std::vector<std::string> Dataset::getFeatures() const
+    {
+        if (loaded) {
+            return features;
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    int Dataset::getNFeatures() const
+    {
+        if (loaded) {
+            return n_features;
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    int Dataset::getNSamples() const
+    {
+        if (loaded) {
+            return n_samples;
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    std::map<std::string, std::vector<int>> Dataset::getStates() const
+    {
+        if (loaded) {
+            return states;
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    pair<std::vector<std::vector<float>>&, std::vector<int>&> Dataset::getVectors()
+    {
+        if (loaded) {
+            return { Xv, yv };
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    pair<std::vector<std::vector<int>>&, std::vector<int>&> Dataset::getVectorsDiscretized()
+    {
+        if (loaded) {
+            return { Xd, yv };
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    pair<torch::Tensor&, torch::Tensor&> Dataset::getTensors()
+    {
+        if (loaded) {
+            buildTensors();
+            return { X, y };
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    void Dataset::load_csv()
+    {
+        ifstream file(path + "/" + name + ".csv");
+        if (file.is_open()) {
+            std::string line;
+            getline(file, line);
+            std::vector<std::string> tokens = split(line, ',');
+            features = std::vector<std::string>(tokens.begin(), tokens.end() - 1);
+            if (className == "-1") {
+                className = tokens.back();
+            }
+            for (auto i = 0; i < features.size(); ++i) {
+                Xv.push_back(std::vector<float>());
+            }
+            while (getline(file, line)) {
+                tokens = split(line, ',');
+                for (auto i = 0; i < features.size(); ++i) {
+                    Xv[i].push_back(stof(tokens[i]));
+                }
+                yv.push_back(stoi(tokens.back()));
+            }
+            file.close();
+        } else {
+            throw std::invalid_argument("Unable to open dataset file.");
+        }
+    }
+    void Dataset::computeStates()
+    {
+        for (int i = 0; i < features.size(); ++i) {
+            states[features[i]] = std::vector<int>(*max_element(Xd[i].begin(), Xd[i].end()) + 1);
+            auto item = states.at(features[i]);
+            iota(begin(item), end(item), 0);
+        }
+        states[className] = std::vector<int>(*max_element(yv.begin(), yv.end()) + 1);
+        iota(begin(states.at(className)), end(states.at(className)), 0);
+    }
+    void Dataset::load_arff()
+    {
+        auto arff = ArffFiles();
+        arff.load(path + "/" + name + ".arff", className);
+        // Get Dataset X, y
+        Xv = arff.getX();
+        yv = arff.getY();
+        // Get className & Features
+        className = arff.getClassName();
+        auto attributes = arff.getAttributes();
+        transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& attribute) { return attribute.first; });
+    }
+    std::vector<std::string> tokenize(std::string line)
+    {
+        std::vector<std::string> tokens;
+        for (auto i = 0; i < line.size(); ++i) {
+            if (line[i] == ' ' || line[i] == '\t' || line[i] == '\n') {
+                std::string token = line.substr(0, i);
+                tokens.push_back(token);
+                line.erase(line.begin(), line.begin() + i + 1);
+                i = 0;
+                while (line[i] == ' ' || line[i] == '\t' || line[i] == '\n')
+                    line.erase(line.begin(), line.begin() + i + 1);
+            }
+        }
+        if (line.size() > 0) {
+            tokens.push_back(line);
+        }
+        return tokens;
+    }
+    void Dataset::load_rdata()
+    {
+        ifstream file(path + "/" + name + "_R.dat");
+        if (file.is_open()) {
+            std::string line;
+            getline(file, line);
+            line = ArffFiles::trim(line);
+            std::vector<std::string> tokens = tokenize(line);
+            transform(tokens.begin(), tokens.end() - 1, back_inserter(features), [](const auto& attribute) { return ArffFiles::trim(attribute); });
+            if (className == "-1") {
+                className = ArffFiles::trim(tokens.back());
+            }
+            for (auto i = 0; i < features.size(); ++i) {
+                Xv.push_back(std::vector<float>());
+            }
+            while (getline(file, line)) {
+                tokens = tokenize(line);
+                // We have to skip the first token, which is the instance number.
+                for (auto i = 1; i < features.size() + 1; ++i) {
+                    const float value = stof(tokens[i]);
+                    Xv[i - 1].push_back(value);
+                }
+                yv.push_back(stoi(tokens.back()));
+            }
+            file.close();
+        } else {
+            throw std::invalid_argument("Unable to open dataset file.");
+        }
+    }
+    void Dataset::load()
+    {
+        if (loaded) {
+            return;
+        }
+        if (fileType == CSV) {
+            load_csv();
+        } else if (fileType == ARFF) {
+            load_arff();
+        } else if (fileType == RDATA) {
+            load_rdata();
+        }
+        if (discretize) {
+            Xd = discretizeDataset(Xv, yv);
+            computeStates();
+        }
+        n_samples = Xv[0].size();
+        n_features = Xv.size();
+        loaded = true;
+    }
+    void Dataset::buildTensors()
+    {
+        if (discretize) {
+            X = torch::zeros({ static_cast<int>(n_features), static_cast<int>(n_samples) }, torch::kInt32);
+        } else {
+            X = torch::zeros({ static_cast<int>(n_features), static_cast<int>(n_samples) }, torch::kFloat32);
+        }
+        for (int i = 0; i < features.size(); ++i) {
+            if (discretize) {
+                X.index_put_({ i,  "..." }, torch::tensor(Xd[i], torch::kInt32));
+            } else {
+                X.index_put_({ i,  "..." }, torch::tensor(Xv[i], torch::kFloat32));
+            }
+        }
+        y = torch::tensor(yv, torch::kInt32);
+    }
+    std::vector<mdlp::labels_t> Dataset::discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y)
+    {
+        std::vector<mdlp::labels_t> Xd;
+        auto fimdlp = mdlp::CPPFImdlp();
+        for (int i = 0; i < X.size(); i++) {
+            fimdlp.fit(X[i], y);
+            mdlp::labels_t& xd = fimdlp.transform(X[i]);
+            Xd.push_back(xd);
+        }
+        return Xd;
+    }
+}

src/Platform/Dataset.h

@@ -0,0 +1,78 @@
+#ifndef DATASET_H
+#define DATASET_H
+#include <torch/torch.h>
+#include <map>
+#include <vector>
+#include <string>
+#include "CPPFImdlp.h"
+#include "Utils.h"
+namespace platform {
+    enum fileType_t { CSV, ARFF, RDATA };
+    class SourceData {
+    public:
+        SourceData(std::string source)
+        {
+            if (source == "Surcov") {
+                path = "datasets/";
+                fileType = CSV;
+            } else if (source == "Arff") {
+                path = "datasets/";
+                fileType = ARFF;
+            } else if (source == "Tanveer") {
+                path = "data/";
+                fileType = RDATA;
+            } else {
+                throw std::invalid_argument("Unknown source.");
+            }
+        }
+        std::string getPath()
+        {
+            return path;
+        }
+        fileType_t getFileType()
+        {
+            return fileType;
+        }
+    private:
+        std::string path;
+        fileType_t fileType;
+    };
+    class Dataset {
+    private:
+        std::string path;
+        std::string name;
+        fileType_t fileType;
+        std::string className;
+        int n_samples{ 0 }, n_features{ 0 };
+        std::vector<std::string> features;
+        std::map<std::string, std::vector<int>> states;
+        bool loaded;
+        bool discretize;
+        torch::Tensor X, y;
+        std::vector<std::vector<float>> Xv;
+        std::vector<std::vector<int>> Xd;
+        std::vector<int> yv;
+        void buildTensors();
+        void load_csv();
+        void load_arff();
+        void load_rdata();
+        void computeStates();
+        std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y);
+    public:
+        Dataset(const std::string& path, const std::string& name, const std::string& className, bool discretize, fileType_t fileType) : path(path), name(name), className(className), discretize(discretize), loaded(false), fileType(fileType) {};
+        explicit Dataset(const Dataset&);
+        std::string getName() const;
+        std::string getClassName() const;
+        std::vector<string> getFeatures() const;
+        std::map<std::string, std::vector<int>> getStates() const;
+        std::pair<vector<std::vector<float>>&, std::vector<int>&> getVectors();
+        std::pair<vector<std::vector<int>>&, std::vector<int>&> getVectorsDiscretized();
+        std::pair<torch::Tensor&, torch::Tensor&> getTensors();
+        int getNFeatures() const;
+        int getNSamples() const;
+        void load();
+        const bool inline isLoaded() const { return loaded; };
+    };
+};
+
+#endif

src/Platform/Datasets.cc

@@ -1,231 +1,129 @@
 #include "Datasets.h"
-#include "platformUtils.h"
-#include "ArffFiles.h"
+#include <fstream>
 namespace platform {
     void Datasets::load()
     {
-        ifstream catalog(path + "/all.txt");
+        auto sd = SourceData(sfileType);
+        fileType = sd.getFileType();
+        path = sd.getPath();
+        ifstream catalog(path + "all.txt");
         if (catalog.is_open()) {
-            string line;
+            std::string line;
             while (getline(catalog, line)) {
-                vector<string> tokens = split(line, ',');
-                string name = tokens[0];
-                string className = tokens[1];
+                if (line.empty() || line[0] == '#') {
+                    continue;
+                }
+                std::vector<std::string> tokens = split(line, ',');
+                std::string name = tokens[0];
+                std::string className;
+                if (tokens.size() == 1) {
+                    className = "-1";
+                } else {
+                    className = tokens[1];
+                }
                 datasets[name] = make_unique<Dataset>(path, name, className, discretize, fileType);
             }
             catalog.close();
         } else {
-            throw invalid_argument("Unable to open catalog file. [" + path + "/all.txt" + "]");
+            throw std::invalid_argument("Unable to open catalog file. [" + path + "all.txt" + "]");
         }
     }
-    vector<string> Datasets::getNames()
+    std::vector<std::string> Datasets::getNames()
     {
-        vector<string> result;
+        std::vector<std::string> result;
         transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
         return result;
     }
-    vector<string> Datasets::getFeatures(string name)
+    std::vector<std::string> Datasets::getFeatures(const std::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.");
+            throw std::invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Datasets::getStates(string name)
+    map<std::string, std::vector<int>> Datasets::getStates(const std::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.");
+            throw std::invalid_argument("Dataset not loaded.");
         }
     }
-    string Datasets::getClassName(string name)
+    void Datasets::loadDataset(const std::string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getClassName();
+        if (datasets.at(name)->isLoaded()) {
+            return;
         } else {
-            throw invalid_argument("Dataset not loaded.");
+            datasets.at(name)->load();
         }
     }
-    int Datasets::getNSamples(string name)
+    std::string Datasets::getClassName(const std::string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getNSamples();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getClassName();
         } else {
-            throw invalid_argument("Dataset not loaded.");
+            throw std::invalid_argument("Dataset not loaded.");
         }
     }
-    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
+    int Datasets::getNSamples(const std::string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getNSamples();
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    int Datasets::getNClasses(const std::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 *std::max_element(yv.begin(), yv.end()) + 1;
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    std::vector<int> Datasets::getClassesCounts(const std::string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto [Xv, yv] = datasets.at(name)->getVectors();
+            std::vector<int> counts(*std::max_element(yv.begin(), yv.end()) + 1);
+            for (auto y : yv) {
+                counts[y]++;
+            }
+            return counts;
+        } else {
+            throw std::invalid_argument("Dataset not loaded.");
+        }
+    }
+    pair<std::vector<std::vector<float>>&, std::vector<int>&> Datasets::getVectors(const std::string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectors();
     }
-    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(string name)
+    pair<std::vector<std::vector<int>>&, std::vector<int>&> Datasets::getVectorsDiscretized(const std::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 std::string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getTensors();
     }
-    bool Datasets::isDataset(const string& name)
+    bool Datasets::isDataset(const std::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()
-    {
-        return name;
-    }
-    string Dataset::getClassName()
-    {
-        return className;
-    }
-    vector<string> Dataset::getFeatures()
-    {
-        if (loaded) {
-            return features;
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    int Dataset::getNFeatures()
-    {
-        if (loaded) {
-            return n_features;
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    int Dataset::getNSamples()
-    {
-        if (loaded) {
-            return n_samples;
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    map<string, vector<int>> Dataset::getStates()
-    {
-        if (loaded) {
-            return states;
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    pair<vector<vector<float>>&, vector<int>&> Dataset::getVectors()
-    {
-        if (loaded) {
-            return { Xv, yv };
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    pair<vector<vector<int>>&, vector<int>&> Dataset::getVectorsDiscretized()
-    {
-        if (loaded) {
-            return { Xd, yv };
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    pair<torch::Tensor&, torch::Tensor&> Dataset::getTensors()
-    {
-        if (loaded) {
-            buildTensors();
-            return { X, y };
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    void Dataset::load_csv()
-    {
-        ifstream file(path + "/" + name + ".csv");
-        if (file.is_open()) {
-            string line;
-            getline(file, line);
-            vector<string> tokens = split(line, ',');
-            features = vector<string>(tokens.begin(), tokens.end() - 1);
-            className = tokens.back();
-            for (auto i = 0; i < features.size(); ++i) {
-                Xv.push_back(vector<float>());
-            }
-            while (getline(file, line)) {
-                tokens = split(line, ',');
-                for (auto i = 0; i < features.size(); ++i) {
-                    Xv[i].push_back(stof(tokens[i]));
-                }
-                yv.push_back(stoi(tokens.back()));
-            }
-            file.close();
-        } else {
-            throw invalid_argument("Unable to open dataset file.");
-        }
-    }
-    void Dataset::computeStates()
-    {
-        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);
-        }
-        states[className] = vector<int>(*max_element(yv.begin(), yv.end()) + 1);
-        iota(begin(states[className]), end(states[className]), 0);
-    }
-    void Dataset::load_arff()
-    {
-        auto arff = ArffFiles();
-        arff.load(path + "/" + name + ".arff", className);
-        // Get Dataset X, y
-        Xv = arff.getX();
-        yv = arff.getY();
-        // Get className & Features
-        className = arff.getClassName();
-        auto attributes = arff.getAttributes();
-        transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& attribute) { return attribute.first; });
-    }
-    void Dataset::load()
-    {
-        if (loaded) {
-            return;
-        }
-        if (fileType == CSV) {
-            load_csv();
-        } else if (fileType == ARFF) {
-            load_arff();
-        }
-        if (discretize) {
-            Xd = discretizeDataset(Xv, yv);
-            computeStates();
-        }
-        n_samples = Xv[0].size();
-        n_features = Xv.size();
-        loaded = true;
-    }
-    void Dataset::buildTensors()
-    {
-        if (discretize) {
-            X = torch::zeros({ static_cast<int>(n_features), static_cast<int>(n_samples) }, torch::kInt32);
-        } else {
-            X = torch::zeros({ static_cast<int>(n_features), static_cast<int>(n_samples) }, torch::kFloat32);
-        }
-        for (int i = 0; i < features.size(); ++i) {
-            if (discretize) {
-                X.index_put_({ i,  "..." }, torch::tensor(Xd[i], torch::kInt32));
-            } else {
-                X.index_put_({ i,  "..." }, torch::tensor(Xv[i], torch::kFloat32));
-            }
-        }
-        y = torch::tensor(yv, torch::kInt32);
-    }
 }

src/Platform/Datasets.h

@@ -1,64 +1,29 @@
 #ifndef DATASETS_H
 #define DATASETS_H
-#include <torch/torch.h>
-#include <map>
-#include <vector>
-#include <string>
+#include "Dataset.h"
 namespace platform {
-    using namespace std;
-    enum fileType_t { CSV, ARFF };
-    class Dataset {
-    private:
-        string path;
-        string name;
-        fileType_t fileType;
-        string className;
-        int n_samples{ 0 }, n_features{ 0 };
-        vector<string> features;
-        map<string, vector<int>> states;
-        bool loaded;
-        bool discretize;
-        torch::Tensor X, y;
-        vector<vector<float>> Xv;
-        vector<vector<int>> Xd;
-        vector<int> yv;
-        void buildTensors();
-        void load_csv();
-        void load_arff();
-        void computeStates();
-    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();
-        pair<vector<vector<float>>&, vector<int>&> getVectors();
-        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized();
-        pair<torch::Tensor&, torch::Tensor&> getTensors();
-        int getNFeatures();
-        int getNSamples();
-        void load();
-        const bool inline isLoaded() const { return loaded; };
-    };
     class Datasets {
     private:
-        string path;
+        std::string path;
         fileType_t fileType;
-        map<string, unique_ptr<Dataset>> datasets;
+        std::string sfileType;
+        std::map<std::string, std::unique_ptr<Dataset>> datasets;
         bool discretize;
         void load(); // Loads the list of datasets
     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);
+        explicit Datasets(bool discretize, std::string sfileType) : discretize(discretize), sfileType(sfileType) { load(); };
+        std::vector<string> getNames();
+        std::vector<string> getFeatures(const std::string& name) const;
+        int getNSamples(const std::string& name) const;
+        std::string getClassName(const std::string& name) const;
+        int getNClasses(const std::string& name);
+        std::vector<int> getClassesCounts(const std::string& name) const;
+        std::map<std::string, std::vector<int>> getStates(const std::string& name) const;
+        std::pair<std::vector<std::vector<float>>&, std::vector<int>&> getVectors(const std::string& name);
+        std::pair<std::vector<std::vector<int>>&, std::vector<int>&> getVectorsDiscretized(const std::string& name);
+        std::pair<torch::Tensor&, torch::Tensor&> getTensors(const std::string& name);
+        bool isDataset(const std::string& name) const;
+        void loadDataset(const std::string& name) const;
     };
 };
 

src/Platform/DotEnv.h

@@ -4,22 +4,15 @@
 #include <map>
 #include <fstream>
 #include <sstream>
-#include "platformUtils.h"
+#include <algorithm>
+#include <iostream>
+#include "Utils.h"
+
+//#include "Dataset.h"
 namespace platform {
     class DotEnv {
     private:
         std::map<std::string, std::string> env;
-        std::string trim(const std::string& str)
-        {
-            std::string result = str;
-            result.erase(result.begin(), std::find_if(result.begin(), result.end(), [](int ch) {
-                return !std::isspace(ch);
-                }));
-            result.erase(std::find_if(result.rbegin(), result.rend(), [](int ch) {
-                return !std::isspace(ch);
-                }).base(), result.end());
-            return result;
-        }
     public:
         DotEnv()
         {
@@ -43,7 +36,7 @@ namespace platform {
         }
         std::string get(const std::string& key)
         {
-            return env[key];
+            return env.at(key);
         }
         std::vector<int> getSeeds()
         {

src/Platform/ExcelFile.cc

@@ -0,0 +1,168 @@
+#include "ExcelFile.h"
+
+namespace platform {
+    ExcelFile::ExcelFile()
+    {
+        setDefault();
+    }
+    ExcelFile::ExcelFile(lxw_workbook* workbook) : workbook(workbook)
+    {
+        setDefault();
+    }
+    ExcelFile::ExcelFile(lxw_workbook* workbook, lxw_worksheet* worksheet) : workbook(workbook), worksheet(worksheet)
+    {
+        setDefault();
+    }
+    void ExcelFile::setDefault()
+    {
+        normalSize = 14; //font size for report body
+        row = 0;
+        colorTitle = 0xB1A0C7;
+        colorOdd = 0xDCE6F1;
+        colorEven = 0xFDE9D9;
+    }
+
+    lxw_workbook* ExcelFile::getWorkbook()
+    {
+        return workbook;
+    }
+    void ExcelFile::setProperties(std::string title)
+    {
+        char line[title.size() + 1];
+        strcpy(line, title.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);
+    }
+    lxw_format* ExcelFile::efectiveStyle(const std::string& style)
+    {
+        lxw_format* efectiveStyle = NULL;
+        if (style != "") {
+            std::string suffix = row % 2 ? "_odd" : "_even";
+            try {
+                efectiveStyle = styles.at(style + suffix);
+            }
+            catch (const std::out_of_range& oor) {
+                try {
+                    efectiveStyle = styles.at(style);
+                }
+                catch (const std::out_of_range& oor) {
+                    throw std::invalid_argument("Style " + style + " not found");
+                }
+            }
+        }
+        return efectiveStyle;
+    }
+    void ExcelFile::writeString(int row, int col, const std::string& text, const std::string& style)
+    {
+        worksheet_write_string(worksheet, row, col, text.c_str(), efectiveStyle(style));
+    }
+    void ExcelFile::writeInt(int row, int col, const int number, const std::string& style)
+    {
+        worksheet_write_number(worksheet, row, col, number, efectiveStyle(style));
+    }
+    void ExcelFile::writeDouble(int row, int col, const double number, const std::string& style)
+    {
+        worksheet_write_number(worksheet, row, col, number, efectiveStyle(style));
+    }
+    void ExcelFile::addColor(lxw_format* style, bool odd)
+    {
+        uint32_t efectiveColor = odd ? colorEven : colorOdd;
+        format_set_bg_color(style, lxw_color_t(efectiveColor));
+    }
+    void ExcelFile::createStyle(const std::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 ExcelFile::createFormats()
+    {
+        auto styleNames = { "text", "textCentered", "bodyHeader", "result", "time", "ints", "floats" };
+        lxw_format* style;
+        for (std::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;
+    }
+}

src/Platform/ExcelFile.h

@@ -0,0 +1,43 @@
+#ifndef EXCELFILE_H
+#define EXCELFILE_H
+#include <locale>
+#include <string>
+#include <map>
+#include "xlsxwriter.h"
+
+namespace platform {
+    struct separated : std::numpunct<char> {
+        char do_decimal_point() const { return ','; }
+
+        char do_thousands_sep() const { return '.'; }
+
+        std::string do_grouping() const { return "\03"; }
+    };
+    class ExcelFile {
+    public:
+        ExcelFile();
+        ExcelFile(lxw_workbook* workbook);
+        ExcelFile(lxw_workbook* workbook, lxw_worksheet* worksheet);
+        lxw_workbook* getWorkbook();
+    protected:
+        void setProperties(std::string title);
+        void writeString(int row, int col, const std::string& text, const std::string& style = "");
+        void writeInt(int row, int col, const int number, const std::string& style = "");
+        void writeDouble(int row, int col, const double number, const std::string& style = "");
+        void createFormats();
+        void createStyle(const std::string& name, lxw_format* style, bool odd);
+        void addColor(lxw_format* style, bool odd);
+        lxw_format* efectiveStyle(const std::string& name);
+        lxw_workbook* workbook;
+        lxw_worksheet* worksheet;
+        std::map<std::string, lxw_format*> styles;
+        int row;
+        int normalSize; //font size for report body
+        uint32_t colorTitle;
+        uint32_t colorOdd;
+        uint32_t colorEven;
+    private:
+        void setDefault();
+    };
+}
+#endif // !EXCELFILE_H

src/Platform/Experiment.cc

@@ -1,11 +1,12 @@
+#include <fstream>
 #include "Experiment.h"
 #include "Datasets.h"
 #include "Models.h"
-#include "Report.h"
-
+#include "ReportConsole.h"
+#include "Paths.h"
 namespace platform {
     using json = nlohmann::json;
-    string get_date()
+    std::string get_date()
     {
         time_t rawtime;
         tm* timeinfo;
@@ -15,7 +16,7 @@ namespace platform {
         oss << std::put_time(timeinfo, "%Y-%m-%d");
         return oss.str();
     }
-    string get_time()
+    std::string get_time()
     {
         time_t rawtime;
         tm* timeinfo;
@@ -25,9 +26,9 @@ namespace platform {
         oss << std::put_time(timeinfo, "%H:%M:%S");
         return oss.str();
     }
-    string Experiment::get_file_name()
+    std::string Experiment::get_file_name()
     {
-        string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
+        std::string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
         return result;
     }
 
@@ -79,7 +80,7 @@ namespace platform {
         }
         return result;
     }
-    void Experiment::save(const string& path)
+    void Experiment::save(const std::string& path)
     {
         json data = build_json();
         ofstream file(path + "/" + get_file_name());
@@ -90,40 +91,64 @@ namespace platform {
     void Experiment::report()
     {
         json data = build_json();
-        Report report(data);
+        ReportConsole report(data);
         report.show();
     }
 
     void Experiment::show()
     {
         json data = build_json();
-        cout << data.dump(4) << endl;
+        std::cout << data.dump(4) << std::endl;
     }
 
-    void Experiment::go(vector<string> filesToProcess, const string& path)
+    void Experiment::go(std::vector<std::string> filesToProcess, bool quiet)
     {
-        cout << "*** Starting experiment: " << title << " ***" << endl;
+        std::cout << "*** Starting experiment: " << title << " ***" << std::endl;
         for (auto fileName : filesToProcess) {
-            cout << "- " << setw(20) << left << fileName << " " << right << flush;
-            cross_validation(path, fileName);
-            cout << endl;
+            std::cout << "- " << setw(20) << left << fileName << " " << right << flush;
+            cross_validation(fileName, quiet);
+            std::cout << std::endl;
         }
     }
 
-    void Experiment::cross_validation(const string& path, const string& fileName)
+    std::string getColor(bayesnet::status_t status)
     {
-        auto datasets = platform::Datasets(path, discretized, platform::ARFF);
+        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 std::string& color, const std::string& phase)
+    {
+        std::string prefix = phase == "a" ? "" : "\b\b\b\b";
+        std::cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
+
+    }
+    void Experiment::cross_validation(const std::string& fileName, bool quiet)
+    {
+        auto datasets = Datasets(discretized, Paths::datasets());
         // Get dataset
         auto [X, y] = datasets.getTensors(fileName);
         auto states = datasets.getStates(fileName);
         auto features = datasets.getFeatures(fileName);
         auto samples = datasets.getNSamples(fileName);
         auto className = datasets.getClassName(fileName);
-        cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
+        if (!quiet) {
+            std::cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
+        }
         // Prepare Result
         auto result = Result();
         auto [values, counts] = at::_unique(y);
         result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
+        result.setHyperparameters(hyperparameters.get(fileName));
+        // Initialize results std::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);
@@ -135,7 +160,8 @@ namespace platform {
         Timer train_timer, test_timer;
         int item = 0;
         for (auto seed : randomSeeds) {
-            cout << "(" << seed << ") doing Fold: " << flush;
+            if (!quiet)
+                std::cout << "(" << seed << ") doing Fold: " << flush;
             Fold* fold;
             if (stratified)
                 fold = new StratifiedKFold(nfolds, y, seed);
@@ -144,6 +170,10 @@ namespace platform {
             for (int nfold = 0; nfold < nfolds; nfold++) {
                 auto clf = Models::instance()->create(model);
                 setModelVersion(clf->getVersion());
+                auto valid = clf->getValidHyperparameters();
+                hyperparameters.check(valid, fileName);
+                clf->setHyperparameters(hyperparameters.get(fileName));
+                // Split train - test dataset
                 train_timer.start();
                 auto [train, test] = fold->getFold(nfold);
                 auto train_t = torch::tensor(train);
@@ -152,31 +182,43 @@ 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;
+                if (!quiet)
+                    showProgress(nfold + 1, getColor(clf->getStatus()), "a");
+                // Train model
                 clf->fit(X_train, y_train, features, className, states);
+                if (!quiet)
+                    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
+                if (!quiet)
+                    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;
-                // Store results and times in vector
+                if (!quiet)
+                    std::cout << "\b\b\b, " << flush;
+                // Store results and times in std::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++;
             }
-            cout << "end. " << flush;
+            if (!quiet)
+                std::cout << "end. " << flush;
             delete fold;
         }
         result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
         result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
         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

@@ -3,41 +3,28 @@
 #include <torch/torch.h>
 #include <nlohmann/json.hpp>
 #include <string>
-#include <chrono>
 #include "Folding.h"
 #include "BaseClassifier.h"
+#include "HyperParameters.h"
 #include "TAN.h"
 #include "KDB.h"
 #include "AODE.h"
+#include "Timer.h"
 
-using namespace std;
 namespace platform {
     using json = nlohmann::json;
-    class Timer {
-    private:
-        chrono::high_resolution_clock::time_point begin;
-    public:
-        Timer() = default;
-        ~Timer() = default;
-        void start() { begin = chrono::high_resolution_clock::now(); }
-        double getDuration()
-        {
-            chrono::high_resolution_clock::time_point end = chrono::high_resolution_clock::now();
-            chrono::duration<double> time_span = chrono::duration_cast<chrono::duration<double>>(end - begin);
-            return time_span.count();
-        }
-    };
     class Result {
     private:
-        string dataset, hyperparameters, model_version;
+        std::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 };
-        vector<double> scores_train, scores_test, times_train, times_test;
+        std::vector<double> scores_train, scores_test, times_train, times_test;
     public:
         Result() = default;
-        Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
-        Result& setHyperparameters(const string& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
+        Result& setDataset(const std::string& dataset) { this->dataset = dataset; 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; }
@@ -58,8 +45,8 @@ namespace platform {
         Result& addTimeTest(double time) { times_test.push_back(time); return *this; }
         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 std::string& getDataset() const { return dataset; }
+        const json& getHyperparameters() const { return hyperparameters; }
         const int getSamples() const { return samples; }
         const int getFeatures() const { return features; }
         const int getClasses() const { return classes; }
@@ -74,41 +61,43 @@ namespace platform {
         const float getNodes() const { return nodes; }
         const float getLeaves() const { return leaves; }
         const float getDepth() const { return depth; }
-        const vector<double>& getScoresTrain() const { return scores_train; }
-        const vector<double>& getScoresTest() const { return scores_test; }
-        const vector<double>& getTimesTrain() const { return times_train; }
-        const vector<double>& getTimesTest() const { return times_test; }
+        const std::vector<double>& getScoresTrain() const { return scores_train; }
+        const std::vector<double>& getScoresTest() const { return scores_test; }
+        const std::vector<double>& getTimesTrain() const { return times_train; }
+        const std::vector<double>& getTimesTest() const { return times_test; }
     };
     class Experiment {
-    private:
-        string title, model, platform, score_name, model_version, language_version, language;
-        bool discretized{ false }, stratified{ false };
-        vector<Result> results;
-        vector<int> randomSeeds;
-        int nfolds{ 0 };
-        float duration{ 0 };
-        json build_json();
     public:
         Experiment() = default;
-        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; }
-        Experiment& setScoreName(const string& score_name) { this->score_name = score_name; return *this; }
-        Experiment& setModelVersion(const string& model_version) { this->model_version = model_version; return *this; }
-        Experiment& setLanguage(const string& language) { this->language = language; return *this; }
-        Experiment& setLanguageVersion(const string& language_version) { this->language_version = language_version; return *this; }
+        Experiment& setTitle(const std::string& title) { this->title = title; return *this; }
+        Experiment& setModel(const std::string& model) { this->model = model; return *this; }
+        Experiment& setPlatform(const std::string& platform) { this->platform = platform; return *this; }
+        Experiment& setScoreName(const std::string& score_name) { this->score_name = score_name; return *this; }
+        Experiment& setModelVersion(const std::string& model_version) { this->model_version = model_version; return *this; }
+        Experiment& setLanguage(const std::string& language) { this->language = language; return *this; }
+        Experiment& setLanguageVersion(const std::string& language_version) { this->language_version = language_version; return *this; }
         Experiment& setDiscretized(bool discretized) { this->discretized = discretized; return *this; }
         Experiment& setStratified(bool stratified) { this->stratified = stratified; return *this; }
         Experiment& setNFolds(int nfolds) { this->nfolds = nfolds; return *this; }
         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; }
-        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);
+        Experiment& setHyperparameters(const HyperParameters& hyperparameters_) { this->hyperparameters = hyperparameters_; return *this; }
+        std::string get_file_name();
+        void save(const std::string& path);
+        void cross_validation(const std::string& fileName, bool quiet);
+        void go(std::vector<std::string> filesToProcess, bool quiet);
         void show();
         void report();
+    private:
+        std::string title, model, platform, score_name, model_version, language_version, language;
+        bool discretized{ false }, stratified{ false };
+        std::vector<Result> results;
+        std::vector<int> randomSeeds;
+        HyperParameters hyperparameters;
+        int nfolds{ 0 };
+        float duration{ 0 };
+        json build_json();
     };
 }
 #endif

src/Platform/Folding.cc

@@ -1,25 +1,26 @@
 #include "Folding.h"
 #include <algorithm>
 #include <map>
+namespace platform {
     Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
     {
-    random_device rd;
-    random_seed = default_random_engine(seed == -1 ? rd() : seed);
-    srand(seed == -1 ? time(0) : seed);
+        std::random_device rd;
+        random_seed = std::default_random_engine(seed == -1 ? rd() : seed);
+        std::srand(seed == -1 ? time(0) : seed);
     }
-KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
+    KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(std::vector<int>(n))
     {
-    iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
+        std::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)
+    std::pair<std::vector<int>, std::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) + ")");
+            throw std::out_of_range("nFold (" + std::to_string(nFold) + ") must be less than k (" + std::to_string(k) + ")");
         }
         int nTest = n / k;
-    auto train = vector<int>();
-    auto test = vector<int>();
+        auto train = std::vector<int>();
+        auto test = std::vector<int>();
         for (int i = 0; i < n; i++) {
             if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
                 test.push_back(indices[i]);
@@ -32,10 +33,10 @@ pair<vector<int>, vector<int>> KFold::getFold(int nFold)
     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);
+        this->y = std::vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
         build();
     }
-StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
+    StratifiedKFold::StratifiedKFold(int k, const std::vector<int>& y, int seed)
         : Fold(k, y.size(), seed)
     {
         this->y = y;
@@ -44,11 +45,12 @@ StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
     }
     void StratifiedKFold::build()
     {
-    stratified_indices = vector<vector<int>>(k);
+        stratified_indices = std::vector<std::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);
+        auto class_indices = std::map<int, std::vector<int>>();
+        std::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);
@@ -59,20 +61,26 @@ void StratifiedKFold::build()
         }
         // 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)
+            auto num_samples_to_take = class_counts.at(label) / k;
+            if (num_samples_to_take == 0) {
+                std::cerr << "Warning! The number of samples in class " << label << " (" << class_counts.at(label)
+                    << ") is less than the number of folds (" << k << ")." << std::endl;
+                faulty = true;
                 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);
             }
+            auto chosen = std::vector<bool>(k, false);
             while (remainder_samples_to_take > 0) {
                 int fold = (rand() % static_cast<int>(k));
-            if (stratified_indices[fold].size() == fold_size + 1) {
+                if (chosen.at(fold)) {
                     continue;
                 }
+                chosen[fold] = true;
                 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);
@@ -80,16 +88,17 @@ void StratifiedKFold::build()
             }
         }
     }
-pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
+    std::pair<std::vector<int>, std::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) + ")");
+            throw std::out_of_range("nFold (" + std::to_string(nFold) + ") must be less than k (" + std::to_string(k) + ")");
         }
-    vector<int> test_indices = stratified_indices[nFold];
-    vector<int> train_indices;
+        std::vector<int> test_indices = stratified_indices[nFold];
+        std::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

@@ -3,35 +3,37 @@
 #include <torch/torch.h>
 #include <vector>
 #include <random> 
-using namespace std;
-
+namespace platform {
     class Fold {
     protected:
         int k;
         int n;
         int seed;
-    default_random_engine random_seed;
+        std::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 std::pair<std::vector<int>, std::vector<int>> getFold(int nFold) = 0;
         virtual ~Fold() = default;
         int getNumberOfFolds() { return k; }
     };
     class KFold : public Fold {
     private:
-    vector<int> indices;
+        std::vector<int> indices;
     public:
         KFold(int k, int n, int seed = -1);
-    pair<vector<int>, vector<int>> getFold(int nFold) override;
+        std::pair<std::vector<int>, std::vector<int>> getFold(int nFold) override;
     };
     class StratifiedKFold : public Fold {
     private:
-    vector<int> y;
-    vector<vector<int>> stratified_indices;
+        std::vector<int> y;
+        std::vector<std::vector<int>> stratified_indices;
         void build();
+        bool faulty = false; // Only true if the number of samples of any class is less than the number of folds.
     public:
-    StratifiedKFold(int k, const vector<int>& y, int seed = -1);
+        StratifiedKFold(int k, const std::vector<int>& y, int seed = -1);
         StratifiedKFold(int k, torch::Tensor& y, int seed = -1);
-    pair<vector<int>, vector<int>> getFold(int nFold) override;
+        std::pair<std::vector<int>, std::vector<int>> getFold(int nFold) override;
+        bool isFaulty() { return faulty; }
     };
+}
 #endif

src/Platform/GridData.cc

@@ -0,0 +1,75 @@
+#include "GridData.h"
+#include <fstream>
+
+namespace platform {
+    GridData::GridData(const std::string& fileName)
+    {
+        json grid_file;
+        std::ifstream resultData(fileName);
+        if (resultData.is_open()) {
+            grid_file = json::parse(resultData);
+        } else {
+            throw std::invalid_argument("Unable to open input file. [" + fileName + "]");
+        }
+        for (const auto& item : grid_file.items()) {
+            auto key = item.key();
+            auto value = item.value();
+            grid[key] = value;
+        }
+
+    }
+    int GridData::computeNumCombinations(const json& line)
+    {
+        int numCombinations = 1;
+        for (const auto& item : line.items()) {
+            numCombinations *= item.value().size();
+        }
+        return numCombinations;
+    }
+    int GridData::getNumCombinations(const std::string& dataset)
+    {
+        int numCombinations = 0;
+        auto selected = decide_dataset(dataset);
+        for (const auto& line : grid.at(selected)) {
+            numCombinations += computeNumCombinations(line);
+        }
+        return numCombinations;
+    }
+    json GridData::generateCombinations(json::iterator index, const json::iterator last, std::vector<json>& output, json currentCombination)
+    {
+        if (index == last) {
+            // If we reached the end of input, store the current combination
+            output.push_back(currentCombination);
+            return  currentCombination;
+        }
+        const auto& key = index.key();
+        const auto& values = index.value();
+        for (const auto& value : values) {
+            auto combination = currentCombination;
+            combination[key] = value;
+            json::iterator nextIndex = index;
+            generateCombinations(++nextIndex, last, output, combination);
+        }
+        return currentCombination;
+    }
+    std::vector<json> GridData::getGrid(const std::string& dataset)
+    {
+        auto selected = decide_dataset(dataset);
+        auto result = std::vector<json>();
+        for (json line : grid.at(selected)) {
+            generateCombinations(line.begin(), line.end(), result, json({}));
+        }
+        return result;
+    }
+    json& GridData::getInputGrid(const std::string& dataset)
+    {
+        auto selected = decide_dataset(dataset);
+        return grid.at(selected);
+    }
+    std::string GridData::decide_dataset(const std::string& dataset)
+    {
+        if (grid.find(dataset) != grid.end())
+            return dataset;
+        return ALL_DATASETS;
+    }
+} /* namespace platform */

src/Platform/GridData.h

@@ -0,0 +1,26 @@
+#ifndef GRIDDATA_H
+#define GRIDDATA_H
+#include <string>
+#include <vector>
+#include <map>
+#include <nlohmann/json.hpp>
+
+namespace platform {
+    using json = nlohmann::json;
+    const std::string ALL_DATASETS = "all";
+    class GridData {
+    public:
+        explicit GridData(const std::string& fileName);
+        ~GridData() = default;
+        std::vector<json> getGrid(const std::string& dataset = ALL_DATASETS);
+        int getNumCombinations(const std::string& dataset = ALL_DATASETS);
+        json& getInputGrid(const std::string& dataset = ALL_DATASETS);
+        std::map<std::string, json>& getGridFile() { return grid; }
+    private:
+        std::string decide_dataset(const std::string& dataset);
+        json generateCombinations(json::iterator index, const json::iterator last, std::vector<json>& output, json currentCombination);
+        int computeNumCombinations(const json& line);
+        std::map<std::string, json> grid;
+    };
+} /* namespace platform */
+#endif /* GRIDDATA_H */

src/Platform/GridSearch.cc

@@ -0,0 +1,441 @@
+#include <iostream>
+#include <cstddef>
+#include <torch/torch.h>
+#include "GridSearch.h"
+#include "Models.h"
+#include "Paths.h"
+#include "Folding.h"
+#include "Colors.h"
+
+namespace platform {
+    std::string get_date()
+    {
+        time_t rawtime;
+        tm* timeinfo;
+        time(&rawtime);
+        timeinfo = std::localtime(&rawtime);
+        std::ostringstream oss;
+        oss << std::put_time(timeinfo, "%Y-%m-%d");
+        return oss.str();
+    }
+    std::string get_time()
+    {
+        time_t rawtime;
+        tm* timeinfo;
+        time(&rawtime);
+        timeinfo = std::localtime(&rawtime);
+        std::ostringstream oss;
+        oss << std::put_time(timeinfo, "%H:%M:%S");
+        return oss.str();
+    }
+    std::string get_color_rank(int rank)
+    {
+        auto colors = { Colors::WHITE(), Colors::RED(), Colors::GREEN(),  Colors::BLUE(), Colors::MAGENTA(), Colors::CYAN() };
+        return *(colors.begin() + rank % colors.size());
+    }
+    GridSearch::GridSearch(struct ConfigGrid& config) : config(config)
+    {
+    }
+    json GridSearch::loadResults()
+    {
+        std::ifstream file(Paths::grid_output(config.model));
+        if (file.is_open()) {
+            return json::parse(file);
+        }
+        return json();
+    }
+    std::vector<std::string> GridSearch::filterDatasets(Datasets& datasets) const
+    {
+        // Load datasets
+        auto datasets_names = datasets.getNames();
+        if (config.continue_from != NO_CONTINUE()) {
+            // Continue previous execution:
+            if (std::find(datasets_names.begin(), datasets_names.end(), config.continue_from) == datasets_names.end()) {
+                throw std::invalid_argument("Dataset " + config.continue_from + " not found");
+            }
+            // Remove datasets already processed
+            std::vector<string>::iterator it = datasets_names.begin();
+            while (it != datasets_names.end()) {
+                if (*it != config.continue_from) {
+                    it = datasets_names.erase(it);
+                } else {
+                    if (config.only)
+                        ++it;
+                    else
+                        break;
+                }
+            }
+        }
+        // Exclude datasets
+        for (const auto& name : config.excluded) {
+            auto dataset = name.get<std::string>();
+            auto it = std::find(datasets_names.begin(), datasets_names.end(), dataset);
+            if (it == datasets_names.end()) {
+                throw std::invalid_argument("Dataset " + dataset + " already excluded or doesn't exist!");
+            }
+            datasets_names.erase(it);
+        }
+        return datasets_names;
+    }
+    json GridSearch::build_tasks_mpi(int rank)
+    {
+        auto tasks = json::array();
+        auto grid = GridData(Paths::grid_input(config.model));
+        auto datasets = Datasets(false, Paths::datasets());
+        auto all_datasets = datasets.getNames();
+        auto datasets_names = filterDatasets(datasets);
+        for (int idx_dataset = 0; idx_dataset < datasets_names.size(); ++idx_dataset) {
+            auto dataset = datasets_names[idx_dataset];
+            for (const auto& seed : config.seeds) {
+                auto combinations = grid.getGrid(dataset);
+                for (int n_fold = 0; n_fold < config.n_folds; n_fold++) {
+                    json task = {
+                        { "dataset", dataset },
+                        { "idx_dataset", idx_dataset},
+                        { "seed", seed },
+                        { "fold", n_fold},
+                    };
+                    tasks.push_back(task);
+                }
+            }
+        }
+        // Shuffle the array so heavy datasets are spread across the workers
+        std::mt19937 g{ 271 }; // Use fixed seed to obtain the same shuffle
+        std::shuffle(tasks.begin(), tasks.end(), g);
+        std::cout << get_color_rank(rank) << "* Number of tasks: " << tasks.size() << std::endl;
+        std::cout << "|";
+        for (int i = 0; i < tasks.size(); ++i) {
+            std::cout << (i + 1) % 10;
+        }
+        std::cout << "|" << std::endl << "|" << std::flush;
+        return tasks;
+    }
+    void process_task_mpi_consumer(struct ConfigGrid& config, struct ConfigMPI& config_mpi, json& tasks, int n_task, Datasets& datasets, Task_Result* result)
+    {
+        // initialize
+        Timer timer;
+        timer.start();
+        json task = tasks[n_task];
+        auto model = config.model;
+        auto grid = GridData(Paths::grid_input(model));
+        auto dataset = task["dataset"].get<std::string>();
+        auto idx_dataset = task["idx_dataset"].get<int>();
+        auto seed = task["seed"].get<int>();
+        auto n_fold = task["fold"].get<int>();
+        bool stratified = config.stratified;
+        // Generate the hyperparamters combinations
+        auto combinations = grid.getGrid(dataset);
+        auto [X, y] = datasets.getTensors(dataset);
+        auto states = datasets.getStates(dataset);
+        auto features = datasets.getFeatures(dataset);
+        auto className = datasets.getClassName(dataset);
+        //
+        // Start working on task
+        //
+        Fold* fold;
+        if (stratified)
+            fold = new StratifiedKFold(config.n_folds, y, seed);
+        else
+            fold = new KFold(config.n_folds, y.size(0), seed);
+        auto [train, test] = fold->getFold(n_fold);
+        auto train_t = torch::tensor(train);
+        auto test_t = torch::tensor(test);
+        auto X_train = X.index({ "...", train_t });
+        auto y_train = y.index({ train_t });
+        auto X_test = X.index({ "...", test_t });
+        auto y_test = y.index({ test_t });
+        double best_fold_score = 0.0;
+        int best_idx_combination = -1;
+        json best_fold_hyper;
+        for (int idx_combination = 0; idx_combination < combinations.size(); ++idx_combination) {
+            auto hyperparam_line = combinations[idx_combination];
+            auto hyperparameters = platform::HyperParameters(datasets.getNames(), hyperparam_line);
+            Fold* nested_fold;
+            if (config.stratified)
+                nested_fold = new StratifiedKFold(config.nested, y_train, seed);
+            else
+                nested_fold = new KFold(config.nested, y_train.size(0), seed);
+            double score = 0.0;
+            for (int n_nested_fold = 0; n_nested_fold < config.nested; n_nested_fold++) {
+                // Nested level fold
+                auto [train_nested, test_nested] = nested_fold->getFold(n_nested_fold);
+                auto train_nested_t = torch::tensor(train_nested);
+                auto test_nested_t = torch::tensor(test_nested);
+                auto X_nested_train = X_train.index({ "...", train_nested_t });
+                auto y_nested_train = y_train.index({ train_nested_t });
+                auto X_nested_test = X_train.index({ "...", test_nested_t });
+                auto y_nested_test = y_train.index({ test_nested_t });
+                // Build Classifier with selected hyperparameters
+                auto clf = Models::instance()->create(config.model);
+                auto valid = clf->getValidHyperparameters();
+                hyperparameters.check(valid, dataset);
+                clf->setHyperparameters(hyperparameters.get(dataset));
+                // Train model
+                clf->fit(X_nested_train, y_nested_train, features, className, states);
+                // Test model
+                score += clf->score(X_nested_test, y_nested_test);
+            }
+            delete nested_fold;
+            score /= config.nested;
+            if (score > best_fold_score) {
+                best_fold_score = score;
+                best_idx_combination = idx_combination;
+                best_fold_hyper = hyperparam_line;
+            }
+        }
+        delete fold;
+        // Build Classifier with the best hyperparameters to obtain the best score
+        auto hyperparameters = platform::HyperParameters(datasets.getNames(), best_fold_hyper);
+        auto clf = Models::instance()->create(config.model);
+        auto valid = clf->getValidHyperparameters();
+        hyperparameters.check(valid, dataset);
+        clf->setHyperparameters(best_fold_hyper);
+        clf->fit(X_train, y_train, features, className, states);
+        best_fold_score = clf->score(X_test, y_test);
+        // Return the result
+        result->idx_dataset = task["idx_dataset"].get<int>();
+        result->idx_combination = best_idx_combination;
+        result->score = best_fold_score;
+        result->n_fold = n_fold;
+        result->time = timer.getDuration();
+        // Update progress bar
+        std::cout << get_color_rank(config_mpi.rank) << "*" << std::flush;
+    }
+    json store_result(std::vector<std::string>& names, Task_Result& result, json& results)
+    {
+        json json_result = {
+            { "score", result.score },
+            { "combination", result.idx_combination },
+            { "fold", result.n_fold },
+            { "time", result.time },
+            { "dataset", result.idx_dataset }
+        };
+        auto name = names[result.idx_dataset];
+        if (!results.contains(name)) {
+            results[name] = json::array();
+        }
+        results[name].push_back(json_result);
+        return results;
+    }
+    json producer(std::vector<std::string>& names, json& tasks, struct ConfigMPI& config_mpi, MPI_Datatype& MPI_Result)
+    {
+        Task_Result result;
+        json results;
+        int num_tasks = tasks.size();
+
+        //
+        // 2a.1 Producer will loop to send all the tasks to the consumers and receive the results
+        //
+        for (int i = 0; i < num_tasks; ++i) {
+            MPI_Status status;
+            MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
+            if (status.MPI_TAG == TAG_RESULT) {
+                //Store result
+                store_result(names, result, results);
+            }
+            MPI_Send(&i, 1, MPI_INT, status.MPI_SOURCE, TAG_TASK, MPI_COMM_WORLD);
+        }
+        //
+        // 2a.2 Producer will send the end message to all the consumers
+        //
+        for (int i = 0; i < config_mpi.n_procs - 1; ++i) {
+            MPI_Status status;
+            MPI_Recv(&result, 1, MPI_Result, MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
+            if (status.MPI_TAG == TAG_RESULT) {
+                //Store result
+                store_result(names, result, results);
+            }
+            MPI_Send(&i, 1, MPI_INT, status.MPI_SOURCE, TAG_END, MPI_COMM_WORLD);
+        }
+        return results;
+    }
+    void select_best_results_folds(json& results, json& all_results, std::string& model)
+    {
+        Timer timer;
+        auto grid = GridData(Paths::grid_input(model));
+        //
+        // Select the best result of the computed outer folds
+        //
+        for (const auto& result : all_results.items()) {
+            // each result has the results of all the outer folds as each one were a different task
+            double best_score = 0.0;
+            json best;
+            for (const auto& result_fold : result.value()) {
+                double score = result_fold["score"].get<double>();
+                if (score > best_score) {
+                    best_score = score;
+                    best = result_fold;
+                }
+            }
+            auto dataset = result.key();
+            auto combinations = grid.getGrid(dataset);
+            json json_best = {
+                    { "score", best_score },
+                    { "hyperparameters", combinations[best["combination"].get<int>()] },
+                    { "date", get_date() + " " + get_time() },
+                    { "grid", grid.getInputGrid(dataset) },
+                    { "duration", timer.translate2String(best["time"].get<double>()) }
+            };
+            results[dataset] = json_best;
+        }
+    }
+    void consumer(Datasets& datasets, json& tasks, struct ConfigGrid& config, struct ConfigMPI& config_mpi, MPI_Datatype& MPI_Result)
+    {
+        Task_Result result;
+        //
+        // 2b.1 Consumers announce to the producer that they are ready to receive a task
+        //
+        MPI_Send(&result, 1, MPI_Result, config_mpi.manager, TAG_QUERY, MPI_COMM_WORLD);
+        int task;
+        while (true) {
+            MPI_Status status;
+            //
+            // 2b.2 Consumers receive the task from the producer and process it
+            //
+            MPI_Recv(&task, 1, MPI_INT, config_mpi.manager, MPI_ANY_TAG, MPI_COMM_WORLD, &status);
+            if (status.MPI_TAG == TAG_END) {
+                break;
+            }
+            process_task_mpi_consumer(config, config_mpi, tasks, task, datasets, &result);
+            //
+            // 2b.3 Consumers send the result to the producer
+            //
+            MPI_Send(&result, 1, MPI_Result, config_mpi.manager, TAG_RESULT, MPI_COMM_WORLD);
+        }
+    }
+    void GridSearch::go(struct ConfigMPI& config_mpi)
+    {
+        /*
+        * Each task is a json object with the following structure:
+        * {
+        *   "dataset": "dataset_name",
+        *   "idx_dataset": idx_dataset, // used to identify the dataset in the results
+        *    // this index is relative to the used datasets in the actual run not to the whole datasets
+        *   "seed": # of seed to use,
+        *   "Fold": # of fold to process
+        * }
+        *
+        * The overall process consists in these steps:
+           * 0. Create the MPI result type & tasks
+           * 0.1 Create the MPI result type
+           * 0.2 Manager creates the tasks
+           * 1. Manager will broadcast the tasks to all the processes
+           * 1.1 Broadcast the number of tasks
+           * 1.2 Broadcast the length of the following string
+           * 1.2 Broadcast the tasks as a char* string
+           * 2a. Producer delivers the tasks to the consumers
+           * 2a.1 Producer will loop to send all the tasks to the consumers and receive the results
+           * 2a.2 Producer will send the end message to all the consumers
+           * 2b. Consumers process the tasks and send the results to the producer
+           * 2b.1 Consumers announce to the producer that they are ready to receive a task
+           * 2b.2 Consumers receive the task from the producer and process it
+           * 2b.3 Consumers send the result to the producer
+           * 3. Manager select the bests sccores for each dataset
+           * 3.1 Loop thru all the results obtained from each outer fold (task) and select the best
+           * 3.2 Save the results
+        */
+        //
+        // 0.1 Create the MPI result type
+        //
+        Task_Result result;
+        int tasks_size;
+        MPI_Datatype MPI_Result;
+        MPI_Datatype type[5] = { MPI_UNSIGNED, MPI_UNSIGNED, MPI_INT, MPI_DOUBLE, MPI_DOUBLE };
+        int blocklen[5] = { 1, 1, 1, 1, 1 };
+        MPI_Aint disp[5];
+        disp[0] = offsetof(Task_Result, idx_dataset);
+        disp[1] = offsetof(Task_Result, idx_combination);
+        disp[2] = offsetof(Task_Result, n_fold);
+        disp[3] = offsetof(Task_Result, score);
+        disp[4] = offsetof(Task_Result, time);
+        MPI_Type_create_struct(5, blocklen, disp, type, &MPI_Result);
+        MPI_Type_commit(&MPI_Result);
+        //
+        // 0.2 Manager creates the tasks
+        //
+        char* msg;
+        json tasks;
+        if (config_mpi.rank == config_mpi.manager) {
+            timer.start();
+            tasks = build_tasks_mpi(config_mpi.rank);
+            auto tasks_str = tasks.dump();
+            tasks_size = tasks_str.size();
+            msg = new char[tasks_size + 1];
+            strcpy(msg, tasks_str.c_str());
+        }
+        //
+        // 1. Manager will broadcast the tasks to all the processes
+        //
+        MPI_Bcast(&tasks_size, 1, MPI_INT, config_mpi.manager, MPI_COMM_WORLD);
+        if (config_mpi.rank != config_mpi.manager) {
+            msg = new char[tasks_size + 1];
+        }
+        MPI_Bcast(msg, tasks_size + 1, MPI_CHAR, config_mpi.manager, MPI_COMM_WORLD);
+        tasks = json::parse(msg);
+        delete[] msg;
+        auto datasets = Datasets(config.discretize, Paths::datasets());
+        if (config_mpi.rank == config_mpi.manager) {
+            //
+            // 2a. Producer delivers the tasks to the consumers
+            //
+            auto datasets_names = filterDatasets(datasets);
+            json all_results = producer(datasets_names, tasks, config_mpi, MPI_Result);
+            std::cout << get_color_rank(config_mpi.rank) << "|" << std::endl;
+            //
+            // 3. Manager select the bests sccores for each dataset
+            //
+            auto results = initializeResults();
+            select_best_results_folds(results, all_results, config.model);
+            //
+            // 3.2 Save the results
+            //
+            save(results);
+        } else {
+            //
+            // 2b. Consumers process the tasks and send the results to the producer
+            //
+            consumer(datasets, tasks, config, config_mpi, MPI_Result);
+        }
+    }
+    json GridSearch::initializeResults()
+    {
+        // Load previous results if continue is set
+        json results;
+        if (config.continue_from != NO_CONTINUE()) {
+            if (!config.quiet)
+                std::cout << "* Loading previous results" << std::endl;
+            try {
+                std::ifstream file(Paths::grid_output(config.model));
+                if (file.is_open()) {
+                    results = json::parse(file);
+                    results = results["results"];
+                }
+            }
+            catch (const std::exception& e) {
+                std::cerr << "* There were no previous results" << std::endl;
+                std::cerr << "* Initizalizing new results" << std::endl;
+                results = json();
+            }
+        }
+        return results;
+    }
+    void GridSearch::save(json& results)
+    {
+        std::ofstream file(Paths::grid_output(config.model));
+        json output = {
+            { "model", config.model },
+            { "score", config.score },
+            { "discretize", config.discretize },
+            { "stratified", config.stratified },
+            { "n_folds", config.n_folds },
+            { "seeds", config.seeds },
+            { "date", get_date() + " " + get_time()},
+            { "nested", config.nested},
+            { "platform", config.platform },
+            { "duration", timer.getDurationString(true)},
+            { "results", results }
+
+        };
+        file << output.dump(4);
+    }
+} /* namespace platform */

src/Platform/GridSearch.h

@@ -0,0 +1,60 @@
+#ifndef GRIDSEARCH_H
+#define GRIDSEARCH_H
+#include <string>
+#include <map>
+#include <mpi.h>
+#include <nlohmann/json.hpp>
+#include "Datasets.h"
+#include "HyperParameters.h"
+#include "GridData.h"
+#include "Timer.h"
+
+namespace platform {
+    using json = nlohmann::json;
+    struct ConfigGrid {
+        std::string model;
+        std::string score;
+        std::string continue_from;
+        std::string platform;
+        bool quiet;
+        bool only; // used with continue_from to only compute that dataset
+        bool discretize;
+        bool stratified;
+        int nested;
+        int n_folds;
+        json excluded;
+        std::vector<int> seeds;
+    };
+    struct ConfigMPI {
+        int rank;
+        int n_procs;
+        int manager;
+    };
+    typedef struct {
+        uint idx_dataset;
+        uint idx_combination;
+        int n_fold;
+        double score;
+        double time;
+    } Task_Result;
+    const int TAG_QUERY = 1;
+    const int TAG_RESULT = 2;
+    const int TAG_TASK = 3;
+    const int TAG_END = 4;
+    class GridSearch {
+    public:
+        explicit GridSearch(struct ConfigGrid& config);
+        void go(struct ConfigMPI& config_mpi);
+        ~GridSearch() = default;
+        json loadResults();
+        static inline std::string NO_CONTINUE() { return "NO_CONTINUE"; }
+    private:
+        void save(json& results);
+        json initializeResults();
+        std::vector<std::string> filterDatasets(Datasets& datasets) const;
+        struct ConfigGrid config;
+        json build_tasks_mpi(int rank);
+        Timer timer; // used to measure the time of the whole process
+    };
+} /* namespace platform */
+#endif /* GRIDSEARCH_H */

src/Platform/HyperParameters.cc

@@ -0,0 +1,55 @@
+#include "HyperParameters.h"
+#include <fstream>
+#include <sstream>
+#include <iostream>
+
+namespace platform {
+    HyperParameters::HyperParameters(const std::vector<std::string>& datasets, const json& hyperparameters_)
+    {
+        // Initialize all datasets with the given hyperparameters
+        for (const auto& item : datasets) {
+            hyperparameters[item] = hyperparameters_;
+        }
+    }
+    // https://www.techiedelight.com/implode-a-vector-of-strings-into-a-comma-separated-string-in-cpp/
+    std::string join(std::vector<std::string> const& strings, std::string delim)
+    {
+        std::stringstream ss;
+        std::copy(strings.begin(), strings.end(),
+            std::ostream_iterator<std::string>(ss, delim.c_str()));
+        return ss.str();
+    }
+    HyperParameters::HyperParameters(const std::vector<std::string>& datasets, const std::string& hyperparameters_file)
+    {
+        // Check if file exists
+        std::ifstream file(hyperparameters_file);
+        if (!file.is_open()) {
+            throw std::runtime_error("File " + hyperparameters_file + " not found");
+        }
+        // Check if file is a json
+        json input_hyperparameters = json::parse(file);
+        // Check if hyperparameters are valid
+        for (const auto& dataset : datasets) {
+            if (!input_hyperparameters.contains(dataset)) {
+                std::cerr << "*Warning: Dataset " << dataset << " not found in hyperparameters file" << " assuming default hyperparameters" << std::endl;
+                hyperparameters[dataset] = json({});
+                continue;
+            }
+            hyperparameters[dataset] = input_hyperparameters[dataset]["hyperparameters"].get<json>();
+        }
+    }
+    void HyperParameters::check(const std::vector<std::string>& valid, const std::string& fileName)
+    {
+        json result = hyperparameters.at(fileName);
+        for (const auto& item : result.items()) {
+            if (find(valid.begin(), valid.end(), item.key()) == valid.end()) {
+                throw std::invalid_argument("Hyperparameter " + item.key() + " is not valid. Passed Hyperparameters are: "
+                    + result.dump(4) + "\n Valid hyperparameters are: {" + join(valid, ",") + "}");
+            }
+        }
+    }
+    json HyperParameters::get(const std::string& fileName)
+    {
+        return hyperparameters.at(fileName);
+    }
+} /* namespace platform */

src/Platform/HyperParameters.h

@@ -0,0 +1,23 @@
+#ifndef HYPERPARAMETERS_H
+#define HYPERPARAMETERS_H
+#include <string>
+#include <map>
+#include <vector>
+#include <nlohmann/json.hpp>
+
+namespace platform {
+    using json = nlohmann::json;
+    class HyperParameters {
+    public:
+        HyperParameters() = default;
+        explicit HyperParameters(const std::vector<std::string>& datasets, const json& hyperparameters_);
+        explicit HyperParameters(const std::vector<std::string>& datasets, const std::string& hyperparameters_file);
+        ~HyperParameters() = default;
+        bool notEmpty(const std::string& key) const { return !hyperparameters.at(key).empty(); }
+        void check(const std::vector<std::string>& valid, const std::string& fileName);
+        json get(const std::string& fileName);
+    private:
+        std::map<std::string, json> hyperparameters;
+    };
+} /* namespace platform */
+#endif /* HYPERPARAMETERS_H */

src/Platform/ManageResults.cc

@@ -0,0 +1,213 @@
+#include "ManageResults.h"
+#include "CommandParser.h"
+#include <filesystem>
+#include <tuple>
+#include "Colors.h"
+#include "CLocale.h"
+#include "Paths.h"
+#include "ReportConsole.h"
+#include "ReportExcel.h"
+
+namespace platform {
+
+    ManageResults::ManageResults(int numFiles, const std::string& model, const std::string& score, bool complete, bool partial, bool compare) :
+        numFiles{ numFiles }, complete{ complete }, partial{ partial }, compare{ compare }, results(Results(Paths::results(), model, score, complete, partial))
+    {
+        indexList = true;
+        openExcel = false;
+        workbook = NULL;
+        if (numFiles == 0) {
+            this->numFiles = results.size();
+        }
+    }
+    void ManageResults::doMenu()
+    {
+        if (results.empty()) {
+            std::cout << Colors::MAGENTA() << "No results found!" << Colors::RESET() << std::endl;
+            return;
+        }
+        results.sortDate();
+        list();
+        menu();
+        if (openExcel) {
+            workbook_close(workbook);
+        }
+        std::cout << Colors::RESET() << "Done!" << std::endl;
+    }
+    void ManageResults::list()
+    {
+        auto temp = ConfigLocale();
+        std::string suffix = numFiles != results.size() ? " of " + std::to_string(results.size()) : "";
+        std::stringstream oss;
+        oss << "Results on screen: " << numFiles << suffix;
+        std::cout << Colors::GREEN() << oss.str() << std::endl;
+        std::cout << std::string(oss.str().size(), '-') << std::endl;
+        if (complete) {
+            std::cout << Colors::MAGENTA() << "Only listing complete results" << std::endl;
+        }
+        if (partial) {
+            std::cout << Colors::MAGENTA() << "Only listing partial results" << std::endl;
+        }
+        auto i = 0;
+        int maxModel = results.maxModelSize();
+        std::cout << Colors::GREEN() << " #  Date       " << std::setw(maxModel) << std::left << "Model" << " Score Name  Score       C/P Duration  Title" << std::endl;
+        std::cout << "=== ========== " << std::string(maxModel, '=') << " =========== =========== === ========= =============================================================" << std::endl;
+        bool odd = true;
+        for (auto& result : results) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            std::cout << color << std::setw(3) << std::fixed << std::right << i++ << " ";
+            std::cout << result.to_string(maxModel) << std::endl;
+            if (i == numFiles) {
+                break;
+            }
+            odd = !odd;
+        }
+    }
+    bool ManageResults::confirmAction(const std::string& intent, const std::string& fileName) const
+    {
+        std::string color;
+        if (intent == "delete") {
+            color = Colors::RED();
+        } else {
+            color = Colors::YELLOW();
+        }
+        std::string line;
+        bool finished = false;
+        while (!finished) {
+            std::cout << color << "Really want to " << intent << " " << fileName << "? (y/n): ";
+            getline(std::cin, line);
+            finished = line.size() == 1 && (tolower(line[0]) == 'y' || tolower(line[0] == 'n'));
+        }
+        if (tolower(line[0]) == 'y') {
+            return true;
+        }
+        std::cout << "Not done!" << std::endl;
+        return false;
+    }
+    void ManageResults::report(const int index, const bool excelReport)
+    {
+        std::cout << Colors::YELLOW() << "Reporting " << results.at(index).getFilename() << std::endl;
+        auto data = results.at(index).load();
+        if (excelReport) {
+            ReportExcel reporter(data, compare, workbook);
+            reporter.show();
+            openExcel = true;
+            workbook = reporter.getWorkbook();
+            std::cout << "Adding sheet to " << Paths::excel() + Paths::excelResults() << std::endl;
+        } else {
+            ReportConsole reporter(data, compare);
+            reporter.show();
+        }
+    }
+    void ManageResults::showIndex(const int index, const int idx)
+    {
+        // Show a dataset result inside a report
+        auto data = results.at(index).load();
+        std::cout << Colors::YELLOW() << "Showing " << results.at(index).getFilename() << std::endl;
+        ReportConsole reporter(data, compare, idx);
+        reporter.show();
+    }
+    void ManageResults::sortList()
+    {
+        std::cout << Colors::YELLOW() << "Choose sorting field (date='d', score='s', duration='u', model='m'): ";
+        std::string line;
+        char option;
+        getline(std::cin, line);
+        if (line.size() == 0)
+            return;
+        if (line.size() > 1) {
+            std::cout << "Invalid option" << std::endl;
+            return;
+        }
+        option = line[0];
+        switch (option) {
+            case 'd':
+                results.sortDate();
+                break;
+            case 's':
+                results.sortScore();
+                break;
+            case 'u':
+                results.sortDuration();
+                break;
+            case 'm':
+                results.sortModel();
+                break;
+            default:
+                std::cout << "Invalid option" << std::endl;
+        }
+    }
+    void ManageResults::menu()
+    {
+        char option;
+        int index, subIndex;
+        bool finished = false;
+        std::string filename;
+        // tuple<Option, digit, requires value>
+        std::vector<std::tuple<std::string, char, bool>>  mainOptions = {
+            {"quit", 'q', false},
+            {"list", 'l', false},
+            {"delete", 'd', true},
+            {"hide", 'h', true},
+            {"sort", 's', false},
+            {"report", 'r', true},
+            {"excel", 'e', true}
+        };
+        std::vector<std::tuple<std::string, char, bool>> listOptions = {
+            {"report", 'r', true},
+            {"list", 'l', false},
+            {"quit", 'q', false}
+        };
+        auto parser = CommandParser();
+        while (!finished) {
+            if (indexList) {
+                std::tie(option, index) = parser.parse(Colors::GREEN(), mainOptions, 'r', numFiles - 1);
+            } else {
+                std::tie(option, subIndex) = parser.parse(Colors::MAGENTA(), listOptions, 'r', results.at(index).load()["results"].size() - 1);
+            }
+            switch (option) {
+                case 'q':
+                    finished = true;
+                    break;
+                case 'l':
+                    list();
+                    indexList = true;
+                    break;
+                case 'd':
+                    filename = results.at(index).getFilename();
+                    if (!confirmAction("delete", filename))
+                        break;
+                    std::cout << "Deleting " << filename << std::endl;
+                    results.deleteResult(index);
+                    std::cout << "File: " + filename + " deleted!" << std::endl;
+                    list();
+                    break;
+                case 'h':
+                    filename = results.at(index).getFilename();
+                    if (!confirmAction("hide", filename))
+                        break;
+                    filename = results.at(index).getFilename();
+                    std::cout << "Hiding " << filename << std::endl;
+                    results.hideResult(index, Paths::hiddenResults());
+                    std::cout << "File: " + filename + " hidden! (moved to " << Paths::hiddenResults() << ")" << std::endl;
+                    list();
+                    break;
+                case 's':
+                    sortList();
+                    list();
+                    break;
+                case 'r':
+                    if (indexList) {
+                        report(index, false);
+                        indexList = false;
+                    } else {
+                        showIndex(index, subIndex);
+                    }
+                    break;
+                case 'e':
+                    report(index, true);
+                    break;
+            }
+        }
+    }
+} /* namespace platform */

src/Platform/ManageResults.h

@@ -0,0 +1,31 @@
+#ifndef MANAGE_RESULTS_H
+#define MANAGE_RESULTS_H
+#include "Results.h"
+#include "xlsxwriter.h"
+
+namespace platform {
+    class ManageResults {
+    public:
+        ManageResults(int numFiles, const std::string& model, const std::string& score, bool complete, bool partial, bool compare);
+        ~ManageResults() = default;
+        void doMenu();
+    private:
+        void list();
+        bool confirmAction(const std::string& intent, const std::string& fileName) const;
+        void report(const int index, const bool excelReport);
+        void showIndex(const int index, const int idx);
+        void sortList();
+        void menu();
+        int numFiles;
+        bool indexList;
+        bool openExcel;
+        bool complete;
+        bool partial;
+        bool compare;
+        Results results;
+        lxw_workbook* workbook;
+    };
+
+}
+
+#endif /* MANAGE_RESULTS_H */

src/Platform/Models.cc

@@ -1,6 +1,5 @@
 #include "Models.h"
 namespace platform {
-    using namespace std;
     // Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
     Models* Models::factory = nullptr;;
     Models* Models::instance()
@@ -10,13 +9,13 @@ namespace platform {
             factory = new Models();
         return factory;
     }
-    void Models::registerFactoryFunction(const string& name,
+    void Models::registerFactoryFunction(const std::string& name,
         function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
     {
         // register the class factory function
         functionRegistry[name] = classFactoryFunction;
     }
-    shared_ptr<bayesnet::BaseClassifier> Models::create(const string& name)
+    shared_ptr<bayesnet::BaseClassifier> Models::create(const std::string& name)
     {
         bayesnet::BaseClassifier* instance = nullptr;
 
@@ -26,27 +25,26 @@ 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;
     }
-    vector<string> Models::getNames()
+    std::vector<std::string> Models::getNames()
     {
-        vector<string> names;
+        std::vector<std::string> names;
         transform(functionRegistry.begin(), functionRegistry.end(), back_inserter(names),
-            [](const pair<string, function<bayesnet::BaseClassifier* (void)>>& pair) { return pair.first; });
+            [](const pair<std::string, function<bayesnet::BaseClassifier* (void)>>& pair) { return pair.first; });
         return names;
     }
-    string Models::toString()
+    std::string Models::tostring()
     {
-        string result = "";
+        std::string result = "";
         for (const auto& pair : functionRegistry) {
             result += pair.first + ", ";
         }
         return "{" + result.substr(0, result.size() - 2) + "}";
     }
-
-    Registrar::Registrar(const string& name, function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
+    Registrar::Registrar(const std::string& name, function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
     {
         // register the class factory function 
         Models::instance()->registerFactoryFunction(name, classFactoryFunction);

src/Platform/Models.h

@@ -10,10 +10,15 @@
 #include "KDBLd.h"
 #include "SPODELd.h"
 #include "AODELd.h"
+#include "BoostAODE.h"
+#include "STree.h"
+#include "ODTE.h"
+#include "SVC.h"
+#include "RandomForest.h"
 namespace platform {
     class Models {
     private:
-        map<string, function<bayesnet::BaseClassifier* (void)>> functionRegistry;
+        map<std::string, function<bayesnet::BaseClassifier* (void)>> functionRegistry;
         static Models* factory; //singleton
         Models() {};
     public:
@@ -21,16 +26,16 @@ namespace platform {
         void operator=(const Models&) = delete;
         // Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
         static Models* instance();
-        shared_ptr<bayesnet::BaseClassifier> create(const string& name);
-        void registerFactoryFunction(const string& name,
+        shared_ptr<bayesnet::BaseClassifier> create(const std::string& name);
+        void registerFactoryFunction(const std::string& name,
             function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
-        vector<string> getNames();
-        string toString();
+        std::vector<string> getNames();
+        std::string tostring();
 
     };
     class Registrar {
     public:
-        Registrar(const string& className, function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
+        Registrar(const std::string& className, function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
     };
 }
 #endif

src/Platform/Paths.h

@@ -0,0 +1,39 @@
+#ifndef PATHS_H
+#define PATHS_H
+#include <string>
+#include <filesystem>
+#include "DotEnv.h"
+namespace platform {
+    class Paths {
+    public:
+        static std::string results() { return "results/"; }
+        static std::string hiddenResults() { return "hidden_results/"; }
+        static std::string excel() { return "excel/"; }
+        static std::string grid() { return "grid/"; }
+        static std::string datasets()
+        {
+            auto env = platform::DotEnv();
+            return env.get("source_data");
+        }
+        static void createPath(const std::string& path)
+        {
+            // Create directory if it does not exist
+            try {
+                std::filesystem::create_directory(path);
+            }
+            catch (std::exception& e) {
+                throw std::runtime_error("Could not create directory " + path);
+            }
+        }
+        static std::string excelResults() { return "some_results.xlsx"; }
+        static std::string grid_input(const std::string& model)
+        {
+            return grid() + "grid_" + model + "_input.json";
+        }
+        static std::string grid_output(const std::string& model)
+        {
+            return grid() + "grid_" + model + "_output.json";
+        }
+    };
+}
+#endif