Fix xlsx library finding

Reviewed-on: #10

.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 +31,11 @@
 *.exe
 *.out
 *.app
-build/
+build/**
+build_debug/**
+build_release/**
 *.dSYM/**
 cmake-build*/**
 .idea
+puml/**
+.vscode/settings.json

.gitmodules

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

.vscode/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

@@ -10,7 +10,7 @@
                 "-d",
                 "iris",
                 "-m",
-                "KDB",
+                "TANLd",
                 "-s",
                 "271",
                 "-p",
@@ -22,15 +22,30 @@
             "type": "lldb",
             "request": "launch",
             "name": "experiment",
-            "program": "${workspaceFolder}/build/src/Platform/main",
+            "program": "${workspaceFolder}/build/src/Platform/b_main",
             "args": [
                 "-m",
-                "SPODELd",
-                "-p",
-                "/Users/rmontanana/Code/discretizbench/datasets",
+                "TAN",
                 "--stratified",
                 "-d",
-                "iris"
+                "zoo",
+                "--discretize"
+                // "--hyperparameters",
+                // "{\"repeatSparent\": true, \"maxModels\": 12}"
+            ],
+            "cwd": "/Users/rmontanana/Code/odtebench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "best",
+            "program": "${workspaceFolder}/build/src/Platform/b_best",
+            "args": [
+                "-m",
+                "BoostAODE",
+                "-s",
+                "accuracy",
+                "--build",
             ],
             "cwd": "/Users/rmontanana/Code/discretizbench",
         },
@@ -38,13 +53,33 @@
             "type": "lldb",
             "request": "launch",
             "name": "manage",
-            "program": "${workspaceFolder}/build/src/Platform/manage",
+            "program": "${workspaceFolder}/build/src/Platform/b_manage",
             "args": [
                 "-n",
                 "20"
             ],
             "cwd": "/Users/rmontanana/Code/discretizbench",
         },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "list",
+            "program": "${workspaceFolder}/build/src/Platform/b_list",
+            "args": [],
+            //"cwd": "/Users/rmontanana/Code/discretizbench",
+            "cwd": "/home/rmontanana/Code/covbench",
+        },
+        {
+            "type": "lldb",
+            "request": "launch",
+            "name": "test",
+            "program": "${workspaceFolder}/build/tests/unit_tests",
+            "args": [
+                "-c=\"Metrics Test\"",
+                // "-s",
+            ],
+            "cwd": "${workspaceFolder}/build/tests",
+        },
         {
             "name": "Build & debug active file",
             "type": "cppdbg",

.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
@@ -31,17 +31,26 @@ 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)
 
+# 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) 
+if(Boost_FOUND)
+    message("Boost_INCLUDE_DIRS=${Boost_INCLUDE_DIRS}")
+    include_directories(${Boost_INCLUDE_DIRS}) 
+endif()
+
+SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
 # CMakes modules
 # --------------
 set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
-
 include(AddGitSubmodule)
 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)
 
@@ -56,6 +65,11 @@ 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)
@@ -64,7 +78,7 @@ add_subdirectory(src/BayesNet)
 add_subdirectory(src/Platform)
 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 +88,6 @@ 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
+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 +31,85 @@ 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 ">>> Copying files to $(dest)"
+	@cp $(f_release)/src/Platform/b_main $(dest)
+	@cp $(f_release)/src/Platform/b_list $(dest)
+	@cp $(f_release)/src/Platform/b_manage $(dest)
+	@cp $(f_release)/src/Platform/b_best $(dest)
+
 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) $(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) $(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;
+	@echo ">>> Building Debug BayesNet...";
+	@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;
+	@echo ">>> Building Release BayesNet...";
+	@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

@@ -2,4 +2,50 @@
 
 Bayesian Network Classifier with libtorch from scratch
 
+## 0. Setup
+
+Before compiling BayesNet.
+
+### 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:
+
+```bash
+export BOOST_ROOT=/path/to/library/
+```
+
+### 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

lib/Files/CMakeLists.txt

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

mac_mst.txt

@@ -0,0 +1,33 @@
+Weights matrix: 
+ 0.0000000,   0.0384968,   0.0795434,   0.1546867,  -0.0000000,   0.1788104,   0.2214721,   0.0323837,   0.0366549,  
+ 0.0384968,   0.0000000,   0.0200662,   0.0200937,  -0.0000000,   0.0637224,   0.0183005,   0.0127657,   0.0136054,  
+ 0.0795434,   0.0200662,   0.0000000,   0.0605489,  -0.0000000,   0.0894469,   0.1689408,   0.0321602,   0.0223184,  
+ 0.1546867,   0.0200937,   0.0605489,   0.0000000,  -0.0000000,   0.1150757,   0.1332292,   0.0422865,   0.0191138,  
+-0.0000000,  -0.0000000,  -0.0000000,  -0.0000000,   0.0000000,   0.0000000,   0.0000000,   0.0000000,   0.0000000,  
+ 0.1788104,   0.0637224,   0.0894469,   0.1150757,   0.0000000,   0.0000000,   0.1407102,   0.0406590,   0.0366986,  
+ 0.2214721,   0.0183005,   0.1689408,   0.1332292,   0.0000000,   0.1407102,   0.0000000,   0.0427515,   0.0349965,  
+ 0.0323837,   0.0127657,   0.0321602,   0.0422865,   0.0000000,   0.0406590,   0.0427515,   0.0000000,   0.0343376,  
+ 0.0366549,   0.0136054,   0.0223184,   0.0191138,   0.0000000,   0.0366986,   0.0349965,   0.0343376,   0.0000000,  
+Edge : Weight
+0 - 6 : 0.2214721
+0 - 5 : 0.1788104
+2 - 6 : 0.1689408
+0 - 3 : 0.1546867
+1 - 5 : 0.0637224
+6 - 7 : 0.0427515
+5 - 8 : 0.0366986
+4 - 5 : 0.0000000
+-------------------------------------------------------------------------------
+Metrics Test
+  Test Maximum Spanning Tree
+-------------------------------------------------------------------------------
+/Users/rmontanana/Code/BayesNet/tests/TestBayesMetrics.cc:58
+...............................................................................
+
+/Users/rmontanana/Code/BayesNet/tests/TestBayesMetrics.cc:69: PASSED:
+  REQUIRE( result == resultsMST.at(file_name) )
+with expansion:
+  (0, 6) (0, 5) (0, 3) (5, 1) (5, 8) (5, 4) (6, 2) (6, 7)
+  ==
+  (0, 6) (0, 5) (0, 3) (5, 1) (5, 8) (5, 4) (6, 2) (6, 7)
+

sample/CMakeLists.txt

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

sample/sample.cc

@@ -3,13 +3,14 @@
 #include <string>
 #include <map>
 #include <argparse/argparse.hpp>
-#include "ArffFiles.h"
+#include <nlohmann/json.hpp>
+#include "ArffFiles.h"v
 #include "BayesMetrics.h"
 #include "CPPFImdlp.h"
 #include "Folding.h"
 #include "Models.h"
 #include "modelRegister.h"
-
+#include <fstream>
 
 using namespace std;
 
@@ -178,59 +179,59 @@ int main(int argc, char** argv)
     cout << "end." << endl;
     auto score = clf->score(Xd, y);
     cout << "Score: " << score << endl;
-    // auto graph = clf->graph();
-    // auto dot_file = model_name + "_" + file_name;
-    // ofstream file(dot_file + ".dot");
-    // file << graph;
-    // 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;
+    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;
+    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);
+        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;
 }

src/BayesNet/AODE.cc

@@ -2,12 +2,14 @@
 
 namespace bayesnet {
     AODE::AODE() : Ensemble() {}
-    void AODE::buildModel()
+    void AODE::buildModel(const torch::Tensor& weights)
     {
         models.clear();
         for (int i = 0; i < features.size(); ++i) {
             models.push_back(std::make_unique<SPODE>(i));
         }
+        n_models = models.size();
+        significanceModels = vector<double>(n_models, 1.0);
     }
     vector<string> AODE::graph(const string& title) const
     {

src/BayesNet/AODE.h

@@ -5,7 +5,7 @@
 namespace bayesnet {
     class AODE : public Ensemble {
     protected:
-        void buildModel() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         AODE();
         virtual ~AODE() {};

src/BayesNet/AODELd.cc

@@ -4,9 +4,9 @@
 namespace bayesnet {
     using namespace std;
     AODELd::AODELd() : Ensemble(), Proposal(dataset, features, className) {}
-    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    AODELd& AODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
@@ -19,15 +19,16 @@ namespace bayesnet {
         return *this;
 
     }
-    void AODELd::buildModel()
+    void AODELd::buildModel(const torch::Tensor& weights)
     {
         models.clear();
         for (int i = 0; i < features.size(); ++i) {
             models.push_back(std::make_unique<SPODELd>(i));
         }
         n_models = models.size();
+        significanceModels = vector<double>(n_models, 1.0);
     }
-    void AODELd::trainModel()
+    void AODELd::trainModel(const torch::Tensor& weights)
     {
         for (const auto& model : models) {
             model->fit(Xf, y, features, className, states);

src/BayesNet/AODELd.h

@@ -8,13 +8,13 @@ namespace bayesnet {
     using namespace std;
     class AODELd : public Ensemble, public Proposal {
     protected:
-        void trainModel() override;
-        void buildModel() override;
+        void trainModel(const torch::Tensor& weights) override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         AODELd();
-        AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_) override;
+        AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_) override;
         virtual ~AODELd() = default;
-        vector<string> graph(const string& name = "AODE") const override;
+        vector<string> graph(const string& name = "AODELd") const override;
         static inline string version() { return "0.0.1"; };
     };
 }

src/BayesNet/BaseClassifier.h

@@ -1,21 +1,25 @@
 #ifndef BASE_H
 #define BASE_H
 #include <torch/torch.h>
+#include <nlohmann/json.hpp>
 #include <vector>
 namespace bayesnet {
     using namespace std;
+    enum status_t { NORMAL, WARNING, ERROR };
     class BaseClassifier {
     protected:
-        virtual void trainModel() = 0;
+        virtual void trainModel(const torch::Tensor& weights) = 0;
     public:
         // X is nxm vector, y is nx1 vector
-        virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
         // X is nxm tensor, y is nx1 tensor
-        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
-        virtual BaseClassifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights) = 0;
         virtual ~BaseClassifier() = default;
         torch::Tensor virtual predict(torch::Tensor& X) = 0;
         vector<int> virtual predict(vector<vector<int>>& X) = 0;
+        status_t virtual getStatus() const = 0;
         float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
         float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
         int virtual getNumberOfNodes()const = 0;
@@ -23,9 +27,10 @@ namespace bayesnet {
         int virtual getNumberOfStates() const = 0;
         vector<string> virtual show() const = 0;
         vector<string> virtual graph(const string& title = "") const = 0;
-        const string inline getVersion() const { return "0.1.0"; };
+        const string inline getVersion() const { return "0.2.0"; };
         vector<string> virtual topological_order() = 0;
         void virtual dump_cpt()const = 0;
+        virtual void setHyperparameters(nlohmann::json& hyperparameters) = 0;
     };
 }
 #endif

src/BayesNet/BayesMetrics.cc

@@ -1,7 +1,7 @@
 #include "BayesMetrics.h"
 #include "Mst.h"
 namespace bayesnet {
-    //samples is nxm tensor used to fit the model
+    //samples is n+1xm tensor used to fit the model
     Metrics::Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates)
         : samples(samples)
         , features(features)
@@ -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)
+    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;
         }
-        return result;
+        // compute scores
+        scoresKBest.clear();
+        featuresKBest.clear();
+        auto label = samples.index({ -1, "..." });
+        for (int i = 0; i < n; ++i) {
+            scoresKBest.push_back(mutualInformation(label, samples.index({ i, "..." }), weights));
+            featuresKBest.push_back(i);
+        }
+        // sort & reduce scores and features
+        if (ascending) {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] < scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::less<double>());
+            if (k < n) {
+                for (int i = 0; i < n - k; ++i) {
+                    featuresKBest.erase(featuresKBest.begin());
+                    scoresKBest.erase(scoresKBest.begin());
+                }
+            }
+        } else {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] > scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::greater<double>());
+            featuresKBest.resize(k);
+            scoresKBest.resize(k);
+        }
+        return featuresKBest;
     }
-    torch::Tensor Metrics::conditionalEdge()
+    vector<double> Metrics::getScoresKBest() const
+    {
+        return scoresKBest;
+    }
+
+    torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
     {
         auto result = vector<double>();
         auto source = vector<string>(features);
         source.push_back(className);
         auto combinations = doCombinations(source);
         // Compute class prior
-        auto margin = torch::zeros({ classNumStates });
+        auto margin = torch::zeros({ classNumStates }, torch::kFloat);
         for (int value = 0; value < classNumStates; ++value) {
             auto mask = samples.index({ -1,  "..." }) == value;
-            margin[value] = mask.sum().item<float>() / samples.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()
+    vector<float> Metrics::conditionalEdgeWeights(vector<float>& weights_)
     {
-        auto matrix = conditionalEdge();
+        const torch::Tensor weights = torch::tensor(weights_);
+        auto matrix = conditionalEdge(weights);
         std::vector<float> v(matrix.data_ptr<float>(), matrix.data_ptr<float>() + matrix.numel());
         return v;
     }
-    double Metrics::entropy(const 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(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature)
+    double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
     {
         int numSamples = firstFeature.sizes()[0];
-        torch::Tensor featureCounts = secondFeature.bincount();
+        torch::Tensor featureCounts = secondFeature.bincount(weights);
         unordered_map<int, unordered_map<int, double>> jointCounts;
         double totalWeight = 0;
         for (auto i = 0; i < numSamples; i++) {
-            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += 1;
-            totalWeight += 1;
+            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
+            totalWeight += weights[i].item<float>();
         }
         if (totalWeight == 0)
             return 0;
@@ -115,9 +146,9 @@ namespace bayesnet {
         return entropyValue;
     }
     // I(X;Y) = H(Y) - H(Y|X)
-    double Metrics::mutualInformation(const torch::Tensor& firstFeature, const 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

src/BayesNet/BayesMetrics.h

@@ -8,20 +8,43 @@ namespace bayesnet {
     using namespace torch;
     class Metrics {
     private:
-        Tensor samples; // nxm tensor used to fit the model
-        vector<string> features;
-        string className;
         int classNumStates = 0;
+        vector<double> scoresKBest;
+        vector<int> featuresKBest; // sorted indices of the features
+        double conditionalEntropy(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
+    protected:
+        Tensor samples; // n+1xm tensor used to fit the model where samples[-1] is the y vector
+        string className;
+        double entropy(const Tensor& feature, const Tensor& weights);
+        vector<string> features;
+        template <class T>
+        vector<pair<T, T>> doCombinations(const vector<T>& source)
+        {
+            vector<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(vector<T>& v)
+        {
+            T temp = v[0];
+            v.erase(v.begin());
+            return temp;
+        }
     public:
         Metrics() = default;
-        Metrics(const Tensor&, const vector<string>&, const string&, const int);
-        Metrics(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const int);
-        double entropy(const Tensor&);
-        double conditionalEntropy(const Tensor&, const Tensor&);
-        double mutualInformation(const Tensor&, const Tensor&);
-        vector<float> conditionalEdgeWeights(); // To use in Python
-        Tensor conditionalEdge();
-        vector<pair<string, string>> doCombinations(const vector<string>&);
+        Metrics(const torch::Tensor& samples, const vector<string>& features, const string& className, const int classNumStates);
+        Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates);
+        vector<int> SelectKBestWeighted(const torch::Tensor& weights, bool ascending = false, unsigned k = 0);
+        vector<double> getScoresKBest() const;
+        double mutualInformation(const Tensor& firstFeature, const Tensor& secondFeature, const Tensor& weights);
+        vector<float> conditionalEdgeWeights(vector<float>& weights); // To use in Python
+        Tensor conditionalEdge(const torch::Tensor& weights);
         vector<pair<int, int>> maximumSpanningTree(const vector<string>& features, const Tensor& weights, const int root);
     };
 }

src/BayesNet/BoostAODE.cc

@@ -0,0 +1,195 @@
+#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() {}
+    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(nlohmann::json& hyperparameters)
+    {
+        // Check if hyperparameters are valid
+        const vector<string> validKeys = { "repeatSparent", "maxModels", "ascending", "convergence", "threshold", "select_features" };
+        checkHyperparameters(validKeys, hyperparameters);
+        if (hyperparameters.contains("repeatSparent")) {
+            repeatSparent = hyperparameters["repeatSparent"];
+        }
+        if (hyperparameters.contains("maxModels")) {
+            maxModels = hyperparameters["maxModels"];
+        }
+        if (hyperparameters.contains("ascending")) {
+            ascending = hyperparameters["ascending"];
+        }
+        if (hyperparameters.contains("convergence")) {
+            convergence = hyperparameters["convergence"];
+        }
+        if (hyperparameters.contains("threshold")) {
+            threshold = hyperparameters["threshold"];
+        }
+        if (hyperparameters.contains("select_features")) {
+            auto selectedAlgorithm = hyperparameters["select_features"];
+            vector<string> algos = { "IWSS", "FCBF", "CFS" };
+            selectFeatures = true;
+            algorithm = selectedAlgorithm;
+            if (find(algos.begin(), algos.end(), selectedAlgorithm) == algos.end()) {
+                throw invalid_argument("Invalid selectFeatures value [IWSS, FCBF, CFS]");
+            }
+        }
+    }
+    unordered_set<int> BoostAODE::initializeModels()
+    {
+        unordered_set<int> featuresUsed;
+        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 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 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) {
+            // cout << "Feature: [" << feature << "] " << feature << " " << features.at(feature) << endl;
+            featuresUsed.insert(feature);
+            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)
+    {
+        unordered_set<int> featuresUsed;
+        if (selectFeatures) {
+            featuresUsed = initializeModels();
+        }
+        if (maxModels == 0)
+            maxModels = .1 * n > 10 ? .1 * n : n;
+        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 tolerance = 5; // number of times the accuracy can be lower than the threshold
+        int count = 0; // number of times the accuracy is lower than the threshold
+        fitted = true; // to enable predict
+        // Step 0: Set the finish condition
+        // if not repeatSparent a finish condition is run out of features
+        // n_models == maxModels
+        // epsiolon sub t > 0.5 => inverse the weights policy
+        // validation error is not decreasing
+        while (!exitCondition) {
+            // Step 1: Build ranking with mutual information
+            auto featureSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted
+            unique_ptr<Classifier> model;
+            auto feature = featureSelection[0];
+            if (!repeatSparent || featuresUsed.size() < featureSelection.size()) {
+                bool used = true;
+                for (const auto& feat : featureSelection) {
+                    if (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;
+        }
+    }
+    vector<string> BoostAODE::graph(const string& title) const
+    {
+        return Ensemble::graph(title);
+    }
+}

src/BayesNet/BoostAODE.h

@@ -0,0 +1,32 @@
+#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() {};
+        vector<string> graph(const string& title = "BoostAODE") const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
+    protected:
+        void buildModel(const torch::Tensor& weights) override;
+        void trainModel(const torch::Tensor& weights) override;
+    private:
+        torch::Tensor dataset_;
+        torch::Tensor X_train, y_train, X_test, y_test;
+        unordered_set<int> initializeModels();
+        // Hyperparameters
+        bool repeatSparent = false; // if true, a feature can be selected more than once
+        int maxModels = 0;
+        bool ascending = false; //Process KBest features ascending or descending order
+        bool convergence = false; //if true, stop when the model does not improve
+        bool selectFeatures = false; // if true, use feature selection
+        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 = 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 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 = numeric_limits<double>::lowest();
+            int num = 0;
+            vector<double> lastFive(selectedScores.end() - 5, selectedScores.end());
+            for (auto item : lastFive) {
+                if (item_ant == 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 +1,21 @@
+#ifndef CFS_H
+#define CFS_H
+#include <torch/torch.h>
+#include <vector>
+#include "FeatureSelect.h"
+using namespace std;
+namespace bayesnet {
+    class CFS : public FeatureSelect {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
+        CFS(const torch::Tensor& samples, const vector<string>& features, const 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 vector<int>& featureOrder);
+    };
+}
+#endif

src/BayesNet/CMakeLists.txt

@@ -1,7 +1,9 @@
 include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
 include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
+include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
 include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
 include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
 add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 
-    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc)
-target_link_libraries(BayesNet mdlp ArffFiles "${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

@@ -5,7 +5,7 @@ namespace bayesnet {
     using namespace torch;
 
     Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
-    Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
     {
         this->features = features;
         this->className = className;
@@ -13,15 +13,14 @@ namespace bayesnet {
         m = dataset.size(1);
         n = dataset.size(0) - 1;
         checkFitParameters();
-        auto n_classes = states[className].size();
+        auto n_classes = states.at(className).size();
         metrics = Metrics(dataset, features, className, n_classes);
         model.initialize();
-        buildModel();
-        trainModel();
+        buildModel(weights);
+        trainModel(weights);
         fitted = true;
         return *this;
     }
-
     void Classifier::buildDataset(Tensor& ytmp)
     {
         try {
@@ -35,19 +34,20 @@ namespace bayesnet {
             exit(1);
         }
     }
-    void Classifier::trainModel()
+    void Classifier::trainModel(const torch::Tensor& weights)
     {
-        model.fit(dataset, features, className, states);
+        model.fit(dataset, weights, features, className, states);
     }
     // X is nxm where n is the number of features and m the number of samples
-    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
     {
         dataset = X;
         buildDataset(y);
-        return build(features, className, states);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
     }
     // X is nxm where n is the number of features and m the number of samples
-    Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states)
     {
         dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, kInt32);
         for (int i = 0; i < X.size(); ++i) {
@@ -55,17 +55,27 @@ namespace bayesnet {
         }
         auto ytmp = torch::tensor(y, kInt32);
         buildDataset(ytmp);
-        return build(features, className, states);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
     }
-    Classifier& Classifier::fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states)
     {
         this->dataset = dataset;
-        return build(features, className, states);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    Classifier& Classifier::fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights)
+    {
+        this->dataset = dataset;
+        return build(features, className, states, weights);
     }
     void Classifier::checkFitParameters()
     {
+        if (torch::is_floating_point(dataset)) {
+            throw invalid_argument("dataset (X, y) must be of type Integer");
+        }
         if (n != features.size()) {
-            throw invalid_argument("X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
+            throw invalid_argument("Classifier: X " + to_string(n) + " and features " + to_string(features.size()) + " must have the same number of features");
         }
         if (states.find(className) == states.end()) {
             throw invalid_argument("className not found in states");
@@ -145,4 +155,18 @@ namespace bayesnet {
     {
         model.dump_cpt();
     }
+    void Classifier::checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters)
+    {
+        for (const auto& item : hyperparameters.items()) {
+            if (find(validKeys.begin(), validKeys.end(), item.key()) == validKeys.end()) {
+                throw invalid_argument("Hyperparameter " + item.key() + " is not valid");
+            }
+        }
+    }
+    void Classifier::setHyperparameters(nlohmann::json& hyperparameters)
+    {
+        // Check if hyperparameters are valid, default is no hyperparameters
+        const vector<string> validKeys = { };
+        checkHyperparameters(validKeys, hyperparameters);
+    }
 }

src/BayesNet/Classifier.h

@@ -10,37 +10,42 @@ using namespace torch;
 namespace bayesnet {
     class Classifier : public BaseClassifier {
     private:
-        void buildDataset(torch::Tensor& y);
-        Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states);
+        Classifier& build(const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights);
     protected:
         bool fitted;
-        Network model;
         int m, n; // m: number of samples, n: number of features
-        Tensor dataset; // (n+1)xm tensor
+        Network model;
         Metrics metrics;
         vector<string> features;
         string className;
         map<string, vector<int>> states;
+        Tensor dataset; // (n+1)xm tensor
+        status_t status = NORMAL;
         void checkFitParameters();
-        virtual void buildModel() = 0;
-        void trainModel() override;
+        virtual void buildModel(const torch::Tensor& weights) = 0;
+        void trainModel(const torch::Tensor& weights) override;
+        void checkHyperparameters(const vector<string>& validKeys, nlohmann::json& hyperparameters);
+        void buildDataset(torch::Tensor& y);
     public:
         Classifier(Network model);
         virtual ~Classifier() = default;
-        Classifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Classifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Classifier& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        Classifier& fit(vector<vector<int>>& X, vector<int>& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states, const torch::Tensor& weights) override;
         void addNodes();
         int getNumberOfNodes() const override;
         int getNumberOfEdges() const override;
         int getNumberOfStates() const override;
         Tensor predict(Tensor& X) override;
+        status_t getStatus() const override { return status; }
         vector<int> predict(vector<vector<int>>& X) override;
         float score(Tensor& X, Tensor& y) override;
         float score(vector<vector<int>>& X, vector<int>& y) override;
         vector<string> show() const override;
         vector<string> topological_order()  override;
         void dump_cpt() const override;
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
     };
 }
 #endif

src/BayesNet/Ensemble.cc

@@ -3,9 +3,9 @@
 namespace bayesnet {
     using namespace torch;
 
-    Ensemble::Ensemble() : Classifier(Network()) {}
+    Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
 
-    void Ensemble::trainModel()
+    void Ensemble::trainModel(const torch::Tensor& weights)
     {
         n_models = models.size();
         for (auto i = 0; i < n_models; ++i) {
@@ -17,10 +17,14 @@ namespace bayesnet {
     {
         auto y_pred_ = y_pred.accessor<int, 2>();
         vector<int> y_pred_final;
+        int numClasses = states.at(className).size();
+        // y_pred is m x n_models with the prediction of every model for each sample
         for (int i = 0; i < y_pred.size(0); ++i) {
-            vector<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
+            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);
@@ -34,7 +38,6 @@ namespace bayesnet {
             throw logic_error("Ensemble has not been fitted");
         }
         Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
-        //Create a threadpool
         auto threads{ vector<thread>() };
         mutex mtx;
         for (auto i = 0; i < n_models; ++i) {

src/BayesNet/Ensemble.h

@@ -14,7 +14,8 @@ namespace bayesnet {
     protected:
         unsigned n_models;
         vector<unique_ptr<Classifier>> models;
-        void trainModel() override;
+        vector<double> significanceModels;
+        void trainModel(const torch::Tensor& weights) override;
         vector<int> voting(Tensor& y_pred);
     public:
         Ensemble();

src/BayesNet/FCBF.cc

@@ -0,0 +1,44 @@
+#include "bayesnetUtils.h"
+#include "FCBF.h"
+namespace bayesnet {
+
+    FCBF::FCBF(const torch::Tensor& samples, const vector<string>& features, const 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 +1,18 @@
+#ifndef FCBF_H
+#define FCBF_H
+#include <torch/torch.h>
+#include <vector>
+#include "FeatureSelect.h"
+using namespace std;
+namespace bayesnet {
+    class FCBF : public FeatureSelect {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
+        FCBF(const torch::Tensor& samples, const vector<string>& features, const 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 vector<string>& features, const 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 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);
+    }
+    vector<int> FeatureSelect::getFeatures() const
+    {
+        if (!fitted) {
+            throw runtime_error("FeatureSelect not fitted");
+        }
+        return selectedFeatures;
+    }
+    vector<double> FeatureSelect::getScores() const
+    {
+        if (!fitted) {
+            throw runtime_error("FeatureSelect not fitted");
+        }
+        return selectedScores;
+    }
+}

src/BayesNet/FeatureSelect.h

@@ -0,0 +1,31 @@
+#ifndef FEATURE_SELECT_H
+#define FEATURE_SELECT_H
+#include <torch/torch.h>
+#include <vector>
+#include "BayesMetrics.h"
+using namespace std;
+namespace bayesnet {
+    class FeatureSelect : public Metrics {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
+        FeatureSelect(const torch::Tensor& samples, const vector<string>& features, const string& className, const int maxFeatures, const int classNumStates, const torch::Tensor& weights);
+        virtual ~FeatureSelect() {};
+        virtual void fit() = 0;
+        vector<int> getFeatures() const;
+        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;
+        vector<int> selectedFeatures;
+        vector<double> selectedScores;
+        vector<double> suLabels;
+        map<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 vector<string>& features, const 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 +1,18 @@
+#ifndef IWSS_H
+#define IWSS_H
+#include <torch/torch.h>
+#include <vector>
+#include "FeatureSelect.h"
+using namespace std;
+namespace bayesnet {
+    class IWSS : public FeatureSelect {
+    public:
+        // dataset is a n+1xm tensor of integers where dataset[-1] is the y vector
+        IWSS(const torch::Tensor& samples, const vector<string>& features, const 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

@@ -4,7 +4,19 @@ namespace bayesnet {
     using namespace torch;
 
     KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
-    void KDB::buildModel()
+    void KDB::setHyperparameters(nlohmann::json& hyperparameters)
+    {
+        // Check if hyperparameters are valid
+        const vector<string> validKeys = { "k", "theta" };
+        checkHyperparameters(validKeys, hyperparameters);
+        if (hyperparameters.contains("k")) {
+            k = hyperparameters["k"];
+        }
+        if (hyperparameters.contains("theta")) {
+            theta = hyperparameters["theta"];
+        }
+    }
+    void KDB::buildModel(const torch::Tensor& weights)
     {
         /*
         1. For each feature Xi, compute mutual information, I(X;C),
@@ -29,13 +41,13 @@ namespace bayesnet {
         // where C is the class.
         addNodes();
         const Tensor& y = dataset.index({ -1, "..." });
-        vector <float> mi;
+        vector<double> mi;
         for (auto i = 0; i < features.size(); i++) {
             Tensor firstFeature = dataset.index({ i, "..." });
-            mi.push_back(metrics.mutualInformation(firstFeature, y));
+            mi.push_back(metrics.mutualInformation(firstFeature, y, weights));
         }
         // 2. Compute class conditional mutual information I(Xi;XjIC), f or each
-        auto conditionalEdgeWeights = metrics.conditionalEdge();
+        auto conditionalEdgeWeights = metrics.conditionalEdge(weights);
         // 3. Let the used variable list, S, be empty.
         vector<int> S;
         // 4. Let the DAG network being constructed, BN, begin with a single

src/BayesNet/KDB.h

@@ -1,5 +1,6 @@
 #ifndef KDB_H
 #define KDB_H
+#include <torch/torch.h>
 #include "Classifier.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
@@ -11,10 +12,11 @@ namespace bayesnet {
         float theta;
         void add_m_edges(int idx, vector<int>& S, Tensor& weights);
     protected:
-        void buildModel() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         explicit KDB(int k, float theta = 0.03);
         virtual ~KDB() {};
+        void setHyperparameters(nlohmann::json& hyperparameters) override;
         vector<string> graph(const string& name = "KDB") const override;
     };
 }

src/BayesNet/KDBLd.cc

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

src/BayesNet/KDBLd.h

@@ -10,7 +10,7 @@ namespace bayesnet {
     public:
         explicit KDBLd(int k);
         virtual ~KDBLd() = default;
-        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "KDB") const override;
         Tensor predict(Tensor& X) override;
         static inline string version() { return "0.0.1"; };

src/BayesNet/Mst.cc

@@ -1,5 +1,6 @@
 #include "Mst.h"
 #include <vector>
+#include <list>
 /*
     Based on the code from https://www.softwaretestinghelp.com/minimum-spanning-tree-tutorial/
 
@@ -34,7 +35,7 @@ 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);
@@ -55,15 +56,24 @@ namespace bayesnet {
         }
     }
 
+    void insertElement(list<int>& variables, int variable)
+    {
+        if (find(variables.begin(), variables.end(), variable) == variables.end()) {
+            variables.push_front(variable);
+        }
+    }
+
     vector<pair<int, int>> reorder(vector<pair<float, 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 = vector<pair<int, int>>();
         auto visited = vector<int>();
-        auto nextVariables = unordered_set<int>();
-        nextVariables.emplace(root_original);
+        auto nextVariables = 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 +81,10 @@ 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);
                     }
                 }
             }
@@ -99,7 +109,6 @@ namespace bayesnet {
     {
         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/Network.cc

@@ -3,9 +3,8 @@
 #include "Network.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
-    Network::Network() : features(vector<string>()), className(""), classNumStates(0), fitted(false) {}
-    Network::Network(float maxT) : features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
-    Network::Network(float maxT, int smoothing) : laplaceSmoothing(smoothing), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
+    Network::Network() : features(vector<string>()), className(""), classNumStates(0), fitted(false), laplaceSmoothing(0) {}
+    Network::Network(float maxT) : features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false), laplaceSmoothing(0) {}
     Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.
         getmaxThreads()), fitted(other.fitted)
     {
@@ -104,8 +103,11 @@ namespace bayesnet {
     {
         return nodes;
     }
-    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
+    void Network::checkFitData(int n_samples, int n_features, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights)
     {
+        if (weights.size(0) != n_samples) {
+            throw invalid_argument("Weights (" + to_string(weights.size(0)) + ") must have the same number of elements as samples (" + to_string(n_samples) + ") in Network::fit");
+        }
         if (n_samples != n_samples_y) {
             throw invalid_argument("X and y must have the same number of samples in Network::fit (" + to_string(n_samples) + " != " + to_string(n_samples_y) + ")");
         }
@@ -130,34 +132,35 @@ namespace bayesnet {
     void Network::setStates(const map<string, vector<int>>& states)
     {
         // Set states to every Node in the network
-        for (int i = 0; i < features.size(); ++i) {
-            nodes[features[i]]->setNumStates(states.at(features[i]).size());
-        }
-        classNumStates = nodes[className]->getNumStates();
+        for_each(features.begin(), features.end(), [this, &states](const string& feature) {
+            nodes.at(feature)->setNumStates(states.at(feature).size());
+            });
+        classNumStates = nodes.at(className)->getNumStates();
     }
     // X comes in nxm, where n is the number of features and m the number of samples
-    void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
+    void Network::fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
     {
-        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states);
+        checkFitData(X.size(1), X.size(0), y.size(0), featureNames, className, states, weights);
         this->className = className;
         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, "..." });
         }
-        completeFit(states);
+        completeFit(states, weights);
     }
-    void Network::fit(const torch::Tensor& samples, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
+    void Network::fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
     {
-        checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states);
+        checkFitData(samples.size(1), samples.size(0) - 1, samples.size(1), featureNames, className, states, weights);
         this->className = className;
         this->samples = samples;
-        completeFit(states);
+        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, const map<string, vector<int>>& states)
+    void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<double>& weights_, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states)
     {
-        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states);
+        const torch::Tensor weights = torch::tensor(weights_, torch::kFloat64);
+        checkFitData(input_data[0].size(), input_data.size(), labels.size(), featureNames, className, states, weights);
         this->className = className;
         // Build tensor of samples (nxm) (n+1 because of the class)
         samples = torch::zeros({ static_cast<int>(input_data.size() + 1), static_cast<int>(input_data[0].size()) }, torch::kInt32);
@@ -165,42 +168,17 @@ namespace bayesnet {
             samples.index_put_({ i, "..." }, torch::tensor(input_data[i], torch::kInt32));
         }
         samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
-        completeFit(states);
+        completeFit(states, weights);
     }
-    void Network::completeFit(const map<string, vector<int>>& states)
+    void Network::completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights)
     {
         setStates(states);
-        int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
-        if (maxThreadsRunning < 1) {
-            maxThreadsRunning = 1;
-        }
+        laplaceSmoothing = 1.0 / samples.size(1); // To use in CPT computation
         vector<thread> threads;
-        mutex mtx;
-        condition_variable cv;
-        int activeThreads = 0;
-        int nextNodeIndex = 0;
-        while (nextNodeIndex < nodes.size()) {
-            unique_lock<mutex> lock(mtx);
-            cv.wait(lock, [&activeThreads, &maxThreadsRunning]() { return activeThreads < maxThreadsRunning; });
-            threads.emplace_back([this, &nextNodeIndex, &mtx, &cv, &activeThreads]() {
-                while (true) {
-                    unique_lock<mutex> lock(mtx);
-                    if (nextNodeIndex >= nodes.size()) {
-                        break;  // No more work remaining
-                    }
-                    auto& pair = *std::next(nodes.begin(), nextNodeIndex);
-                    ++nextNodeIndex;
-                    lock.unlock();
-                    pair.second->computeCPT(samples, features, laplaceSmoothing);
-                    lock.lock();
-                    nodes[pair.first] = std::move(pair.second);
-                    lock.unlock();
-                }
-                lock_guard<mutex> lock(mtx);
-                --activeThreads;
-                cv.notify_one();
+        for (auto& node : nodes) {
+            threads.emplace_back([this, &node, &weights]() {
+                node.second->computeCPT(samples, features, laplaceSmoothing, weights);
                 });
-            ++activeThreads;
         }
         for (auto& thread : threads) {
             thread.join();
@@ -223,8 +201,7 @@ namespace bayesnet {
         }
         if (proba)
             return result;
-        else
-            return result.argmax(1);
+        return result.argmax(1);
     }
     // Return mxn tensor of probabilities
     Tensor Network::predict_proba(const Tensor& samples)
@@ -343,7 +320,7 @@ 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() const
@@ -395,7 +372,6 @@ namespace bayesnet {
         auto result = features;
         result.erase(remove(result.begin(), result.end(), className), result.end());
         bool ending{ false };
-        int idx = 0;
         while (!ending) {
             ending = true;
             for (auto feature : features) {
@@ -431,6 +407,7 @@ namespace bayesnet {
     {
         for (auto& node : nodes) {
             cout << "* " << node.first << ": (" << node.second->getNumStates() << ") : " << node.second->getCPT().sizes() << endl;
+            cout << node.second->getCPT() << endl;
         }
     }
 }

src/BayesNet/Network.h

@@ -13,21 +13,21 @@ namespace bayesnet {
         int classNumStates;
         vector<string> features; // Including classname
         string className;
-        int laplaceSmoothing = 1;
+        double laplaceSmoothing;
         torch::Tensor samples; // nxm tensor used to fit the model
         bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
         vector<double> predict_sample(const vector<int>&);
         vector<double> predict_sample(const torch::Tensor&);
         vector<double> exactInference(map<string, int>&);
         double computeFactor(map<string, int>&);
-        void completeFit(const map<string, vector<int>>&);
-        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>&);
+        void completeFit(const map<string, vector<int>>& states, const torch::Tensor& weights);
+        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states, const torch::Tensor& weights);
         void setStates(const map<string, vector<int>>&);
     public:
         Network();
-        explicit Network(float, int);
         explicit Network(float);
         explicit Network(Network&);
+        ~Network() = default;
         torch::Tensor& getSamples();
         float getmaxThreads();
         void addNode(const string&);
@@ -39,9 +39,12 @@ namespace bayesnet {
         int getNumEdges() const;
         int getClassNumStates() const;
         string getClassName() const;
-        void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&, const map<string, vector<int>>&);
-        void fit(const torch::Tensor&, const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
-        void fit(const torch::Tensor&, const vector<string>&, const string&, const map<string, vector<int>>&);
+        /*
+        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 vector<vector<int>>& input_data, const vector<int>& labels, const vector<double>& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
+        void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
+        void fit(const torch::Tensor& samples, const torch::Tensor& weights, const vector<string>& featureNames, const string& className, const map<string, vector<int>>& states);
         vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
         torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
         torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
@@ -53,7 +56,7 @@ namespace bayesnet {
         vector<string> graph(const string& title) const; // Returns a vector of strings representing the graph in graphviz format
         void initialize();
         void dump_cpt() const;
-        inline string version() { return "0.1.0"; }
+        inline string version() { return "0.2.0"; }
     };
 }
 #endif

src/BayesNet/Node.cc

@@ -84,7 +84,7 @@ namespace bayesnet {
         }
         return result;
     }
-    void Node::computeCPT(const torch::Tensor& dataset, const vector<string>& features, const int laplaceSmoothing)
+    void Node::computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights)
     {
         dimensions.clear();
         // Get dimensions of the CPT
@@ -100,7 +100,7 @@ namespace bayesnet {
         }
         int name_index = pos - features.begin();
         for (int n_sample = 0; n_sample < dataset.size(1); ++n_sample) {
-            torch::List<c10::optional<torch::Tensor>> coordinates;
+            c10::List<c10::optional<at::Tensor>> coordinates;
             coordinates.push_back(dataset.index({ name_index, n_sample }));
             for (auto parent : parents) {
                 pos = find(features.begin(), features.end(), parent->getName());
@@ -111,17 +111,17 @@ namespace bayesnet {
                 coordinates.push_back(dataset.index({ parent_index, n_sample }));
             }
             // Increment the count of the corresponding coordinate
-            cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + 1);
+            cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + weights.index({ n_sample }).item<double>());
         }
         // Normalize the counts
         cpTable = cpTable / cpTable.sum(0);
     }
     float Node::getFactorValue(map<string, int>& evidence)
     {
-        torch::List<c10::optional<torch::Tensor>> coordinates;
+        c10::List<c10::optional<at::Tensor>> coordinates;
         // following predetermined order of indices in the cpTable (see Node.h)
-        coordinates.push_back(torch::tensor(evidence[name]));
-        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return torch::tensor(evidence[parent->getName()]); });
+        coordinates.push_back(at::tensor(evidence[name]));
+        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return at::tensor(evidence[parent->getName()]); });
         return cpTable.index({ coordinates }).item<float>();
     }
     vector<string> Node::graph(const string& className)

src/BayesNet/Node.h

@@ -14,8 +14,8 @@ namespace bayesnet {
         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
-    public:
         vector<pair<string, string>> combinations(const vector<string>&);
+    public:
         explicit Node(const string&);
         void clear();
         void addParent(Node*);
@@ -26,7 +26,7 @@ namespace bayesnet {
         vector<Node*>& getParents();
         vector<Node*>& getChildren();
         torch::Tensor& getCPT();
-        void computeCPT(const torch::Tensor&, const vector<string>&, const int);
+        void computeCPT(const torch::Tensor& dataset, const vector<string>& features, const double laplaceSmoothing, const torch::Tensor& weights);
         int getNumStates() const;
         void setNumStates(int);
         unsigned minFill();

src/BayesNet/Proposal.cc

@@ -9,6 +9,15 @@ namespace bayesnet {
             delete value;
         }
     }
+    void Proposal::checkInput(const torch::Tensor& X, const torch::Tensor& y)
+    {
+        if (!torch::is_floating_point(X)) {
+            throw std::invalid_argument("X must be a floating point tensor");
+        }
+        if (torch::is_floating_point(y)) {
+            throw std::invalid_argument("y must be an integer tensor");
+        }
+    }
     map<string, vector<int>> Proposal::localDiscretizationProposal(const map<string, vector<int>>& oldStates, Network& model)
     {
         // order of local discretization is important. no good 0, 1, 2...
@@ -44,15 +53,6 @@ namespace bayesnet {
             auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
             auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
             discretizers[feature]->fit(xvf, yxv);
-            //
-            //
-            //
-            // auto tmp = discretizers[feature]->transform(xvf);
-            // Xv[index] = tmp;
-            // auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
-            // iota(xStates.begin(), xStates.end(), 0);
-            // //Update new states of the feature/node
-            // states[feature] = xStates;
         }
         if (upgrade) {
             // Discretize again X (only the affected indices) with the new fitted discretizers
@@ -65,7 +65,8 @@ namespace bayesnet {
                 //Update new states of the feature/node
                 states[pFeatures[index]] = xStates;
             }
-            model.fit(pDataset, pFeatures, pClassName, states);
+            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;
     }

src/BayesNet/Proposal.h

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

src/BayesNet/SPODE.cc

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

src/BayesNet/SPODE.h

@@ -7,7 +7,7 @@ namespace bayesnet {
     private:
         int root;
     protected:
-        void buildModel() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         explicit SPODE(int root);
         virtual ~SPODE() {};

src/BayesNet/SPODELd.cc

@@ -3,9 +3,9 @@
 namespace bayesnet {
     using namespace std;
     SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
-    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
@@ -18,12 +18,13 @@ namespace bayesnet {
         states = localDiscretizationProposal(states, model);
         return *this;
     }
-    SPODELd& SPODELd::fit(torch::Tensor& dataset, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    SPODELd& SPODELd::fit(torch::Tensor& dataset, const vector<string>& features_, const string& className_, map<string, vector<int>>& states_)
     {
+        if (!torch::is_floating_point(dataset)) {
+            throw std::runtime_error("Dataset must be a floating point tensor");
+        }
         Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
-        cout << "Xf " << Xf.sizes() << " dtype: " << Xf.dtype() << endl;
         y = dataset.index({ -1, "..." }).clone();
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
         features = features_;
         className = className_;
         // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y

src/BayesNet/SPODELd.h

@@ -9,8 +9,8 @@ namespace bayesnet {
     public:
         explicit SPODELd(int root);
         virtual ~SPODELd() = default;
-        SPODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        SPODELd& fit(torch::Tensor& dataset, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        SPODELd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
+        SPODELd& fit(torch::Tensor& dataset, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "SPODE") const override;
         Tensor predict(Tensor& X) override;
         static inline string version() { return "0.0.1"; };

src/BayesNet/TAN.cc

@@ -5,7 +5,7 @@ namespace bayesnet {
 
     TAN::TAN() : Classifier(Network()) {}
 
-    void TAN::buildModel()
+    void TAN::buildModel(const torch::Tensor& weights)
     {
         // 0. Add all nodes to the model
         addNodes();
@@ -15,15 +15,15 @@ namespace bayesnet {
         Tensor class_dataset = dataset.index({ -1, "..." });
         for (int i = 0; i < static_cast<int>(features.size()); ++i) {
             Tensor feature_dataset = dataset.index({ i, "..." });
-            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
+            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];

src/BayesNet/TAN.h

@@ -3,11 +3,10 @@
 #include "Classifier.h"
 namespace bayesnet {
     using namespace std;
-    using namespace torch;
     class TAN : public Classifier {
     private:
     protected:
-        void buildModel() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         TAN();
         virtual ~TAN() {};

src/BayesNet/TANLd.cc

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

src/BayesNet/TANLd.h

@@ -10,7 +10,7 @@ namespace bayesnet {
     public:
         TANLd();
         virtual ~TANLd() = default;
-        TANLd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        TANLd& fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& features, const string& className, map<string, vector<int>>& states) override;
         vector<string> graph(const string& name = "TAN") const override;
         Tensor predict(Tensor& X) override;
         static inline string version() { return "0.0.1"; };

src/BayesNet/bayesnetUtils.cc

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

src/BayesNet/bayesnetUtils.h

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

src/Platform/BestResults.cc

@@ -0,0 +1,300 @@
+#include <filesystem>
+#include <set>
+#include <fstream>
+#include <iostream>
+#include <sstream>
+#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_string, Code taken from 
+// https://stackoverflow.com/a/58237530/1389271
+template <typename TP>
+std::string ftime_to_string(TP tp)
+{
+    using namespace std::chrono;
+    auto sctp = time_point_cast<system_clock::duration>(tp - TP::clock::now()
+        + system_clock::now());
+    auto tt = system_clock::to_time_t(sctp);
+    std::tm* gmt = std::gmtime(&tt);
+    std::stringstream buffer;
+    buffer << std::put_time(gmt, "%Y-%m-%d %H:%M");
+    return buffer.str();
+}
+namespace platform {
+
+    string BestResults::build()
+    {
+        auto files = loadResultFiles();
+        if (files.size() == 0) {
+            cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << endl;
+            exit(1);
+        }
+        json bests;
+        for (const auto& file : files) {
+            auto result = Result(path, file);
+            auto data = result.load();
+            for (auto const& item : data.at("results")) {
+                bool update = false;
+                // Check if results file contains only one dataset
+                auto datasetName = item.at("dataset").get<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 };
+                }
+            }
+        }
+        string bestFileName = path + bestResultFile();
+        if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+            fclose(fileTest);
+            cout << Colors::MAGENTA() << "File " << bestFileName << " already exists and it shall be overwritten." << Colors::RESET() << endl;
+        }
+        ofstream file(bestFileName);
+        file << bests;
+        file.close();
+        return bestFileName;
+    }
+
+    string BestResults::bestResultFile()
+    {
+        return "best_results_" + score + "_" + model + ".json";
+    }
+
+    pair<string, string> getModelScore(string name)
+    {
+        // results_accuracy_BoostAODE_MacBookpro16_2023-09-06_12:27:00_1.json
+        int i = 0;
+        auto pos = name.find("_");
+        auto pos2 = name.find("_", pos + 1);
+        string score = name.substr(pos + 1, pos2 - pos - 1);
+        pos = name.find("_", pos2 + 1);
+        string model = name.substr(pos2 + 1, pos - pos2 - 1);
+        return { model, score };
+    }
+
+    vector<string> BestResults::loadResultFiles()
+    {
+        vector<string> files;
+        using std::filesystem::directory_iterator;
+        string fileModel, fileScore;
+        for (const auto& file : directory_iterator(path)) {
+            auto fileName = file.path().filename().string();
+            if (fileName.find(".json") != string::npos && fileName.find("results_") == 0) {
+                tie(fileModel, fileScore) = getModelScore(fileName);
+                if (score == fileScore && (model == fileModel || model == "any")) {
+                    files.push_back(fileName);
+                }
+            }
+        }
+        return files;
+    }
+
+    json BestResults::loadFile(const string& fileName)
+    {
+        ifstream resultData(fileName);
+        if (resultData.is_open()) {
+            json data = json::parse(resultData);
+            return data;
+        }
+        throw invalid_argument("Unable to open result file. [" + fileName + "]");
+    }
+    vector<string> BestResults::getModels()
+    {
+        set<string> models;
+        vector<string> result;
+        auto files = loadResultFiles();
+        if (files.size() == 0) {
+            cerr << Colors::MAGENTA() << "No result files were found!" << Colors::RESET() << endl;
+            exit(1);
+        }
+        string fileModel, fileScore;
+        for (const auto& file : files) {
+            // extract the model from the file name
+            tie(fileModel, fileScore) = getModelScore(file);
+            // add the model to the vector of models
+            models.insert(fileModel);
+        }
+        result = vector<string>(models.begin(), models.end());
+        return result;
+    }
+    vector<string> BestResults::getDatasets(json table)
+    {
+        vector<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) {
+            cout << "Building best results for model: " << model << endl;
+            this->model = model;
+            build();
+        }
+        model = "any";
+    }
+
+    void BestResults::reportSingle()
+    {
+        string bestFileName = path + bestResultFile();
+        if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+            fclose(fileTest);
+        } else {
+            cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << endl;
+            exit(1);
+        }
+        auto temp = ConfigLocale();
+        auto date = ftime_to_string(filesystem::last_write_time(bestFileName));
+        auto data = loadFile(bestFileName);
+        auto datasets = getDatasets(data);
+        int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
+        cout << Colors::GREEN() << "Best results for " << model << " and " << score << " as of " << date << endl;
+        cout << "--------------------------------------------------------" << endl;
+        cout << Colors::GREEN() << " #  " << setw(maxDatasetName + 1) << left << string("Dataset") << "Score       File                                                               Hyperparameters" << endl;
+        cout << "=== " << string(maxDatasetName, '=') << " =========== ================================================================== ================================================= " << endl;
+        auto i = 0;
+        bool odd = true;
+        for (auto const& item : data.items()) {
+            auto color = odd ? Colors::BLUE() : Colors::CYAN();
+            cout << color << setw(3) << fixed << right << i++ << " ";
+            cout << setw(maxDatasetName) << left << item.key() << " ";
+            cout << setw(11) << setprecision(9) << fixed << item.value().at(0).get<double>() << " ";
+            cout << setw(66) << item.value().at(2).get<string>() << " ";
+            cout << item.value().at(1) << " ";
+            cout << endl;
+            odd = !odd;
+        }
+    }
+    json BestResults::buildTableResults(vector<string> models)
+    {
+        json table;
+        auto maxDate = filesystem::file_time_type::max();
+        for (const auto& model : models) {
+            this->model = model;
+            string bestFileName = path + bestResultFile();
+            if (FILE* fileTest = fopen(bestFileName.c_str(), "r")) {
+                fclose(fileTest);
+            } else {
+                cerr << Colors::MAGENTA() << "File " << bestFileName << " doesn't exist." << Colors::RESET() << endl;
+                exit(1);
+            }
+            auto dateWrite = filesystem::last_write_time(bestFileName);
+            if (dateWrite < maxDate) {
+                maxDate = dateWrite;
+            }
+            auto data = loadFile(bestFileName);
+            table[model] = data;
+        }
+        table["dateTable"] = ftime_to_string(maxDate);
+        return table;
+    }
+
+    void BestResults::printTableResults(vector<string> models, json table)
+    {
+        cout << Colors::GREEN() << "Best results for " << score << " as of " << table.at("dateTable").get<string>() << endl;
+        cout << "------------------------------------------------" << endl;
+        cout << Colors::GREEN() << " #  " << setw(maxDatasetName + 1) << left << string("Dataset");
+        for (const auto& model : models) {
+            cout << setw(maxModelName) << left << model << " ";
+        }
+        cout << endl;
+        cout << "=== " << string(maxDatasetName, '=') << " ";
+        for (const auto& model : models) {
+            cout << string(maxModelName, '=') << " ";
+        }
+        cout << endl;
+        auto i = 0;
+        bool odd = true;
+        map<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();
+            cout << color << setw(3) << fixed << right << i++ << " ";
+            cout << setw(maxDatasetName) << 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) {
+                string efectiveColor = color;
+                double value = table[model].at(dataset).at(0).get<double>();
+                if (value == maxValue) {
+                    efectiveColor = Colors::RED();
+                }
+                totals[model] += value;
+                cout << efectiveColor << setw(maxModelName) << setprecision(maxModelName - 2) << fixed << value << " ";
+            }
+            cout << endl;
+            odd = !odd;
+        }
+        cout << Colors::GREEN() << "=== " << string(maxDatasetName, '=') << " ";
+        for (const auto& model : models) {
+            cout << string(maxModelName, '=') << " ";
+        }
+        cout << endl;
+        cout << Colors::GREEN() << 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) {
+            string efectiveColor = Colors::GREEN();
+            if (totals[model] == max) {
+                efectiveColor = Colors::RED();
+            }
+            cout << efectiveColor << right << setw(maxModelName) << setprecision(maxModelName - 4) << fixed << totals[model] << " ";
+        }
+        cout << endl;
+    }
+    void BestResults::reportAll(bool excel)
+    {
+        auto models = getModels();
+        // Build the table of results
+        json table = buildTableResults(models);
+        vector<string> datasets = getDatasets(table.begin().value());
+        maxModelName = (*max_element(models.begin(), models.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
+        maxModelName = max(12, maxModelName);
+        maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
+        maxDatasetName = max(25, maxDatasetName);
+        // Print the table of results
+        printTableResults(models, table);
+        // Compute the Friedman test
+        map<string, map<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, models, datasets, table, ranksModels, friedman, significance);
+            excel.build();
+            cout << Colors::YELLOW() << "** Excel file generated: " << excel.getFileName() << Colors::RESET() << endl;
+        }
+    }
+}

src/Platform/BestResults.h

@@ -0,0 +1,32 @@
+#ifndef BESTRESULTS_H
+#define BESTRESULTS_H
+#include <string>
+#include <nlohmann/json.hpp>
+using namespace std;
+using json = nlohmann::json;
+namespace platform {
+    class BestResults {
+    public:
+        explicit BestResults(const string& path, const string& score, const string& model, bool friedman, double significance = 0.05) : path(path), score(score), model(model), friedman(friedman), significance(significance) {}
+        string build();
+        void reportSingle();
+        void reportAll(bool excel);
+        void buildAll();
+    private:
+        vector<string> getModels();
+        vector<string> getDatasets(json table);
+        vector<string> loadResultFiles();
+        json buildTableResults(vector<string> models);
+        void printTableResults(vector<string> models, json table);
+        string bestResultFile();
+        json loadFile(const string& fileName);
+        string path;
+        string score;
+        string model;
+        bool friedman;
+        double significance;
+        int maxModelName = 0;
+        int maxDatasetName = 0;
+    };
+}
+#endif //BESTRESULTS_H

src/Platform/BestResultsExcel.cc

@@ -0,0 +1,177 @@
+#include <sstream>
+#include "BestResultsExcel.h"
+#include "Paths.h"
+#include "Statistics.h"
+
+namespace platform {
+    BestResultsExcel::BestResultsExcel(const string& score, const vector<string>& models, const vector<string>& datasets, const json& table, const map<string, map<string, float>>& ranksModels, bool friedman, double significance) :
+        score(score), models(models), datasets(datasets), table(table), ranksModels(ranksModels), friedman(friedman), significance(significance)
+    {
+        workbook = workbook_new((Paths::excel() + fileName).c_str());
+        worksheet = workbook_add_worksheet(workbook, "Best Results");
+        setProperties("Best Results");
+        createFormats();
+        int maxModelName = (*max_element(models.begin(), models.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
+        modelNameSize = max(modelNameSize, maxModelName);
+        int maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
+        datasetNameSize = max(datasetNameSize, maxDatasetName);
+        formatColumns();
+    }
+    BestResultsExcel::~BestResultsExcel()
+    {
+        workbook_close(workbook);
+    }
+    void BestResultsExcel::formatColumns()
+    {
+        worksheet_freeze_panes(worksheet, 4, 2);
+        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::build()
+    {
+        // Create Sheet with scores
+        header(false);
+        body(false);
+        footer(false);
+        if (friedman) {
+            // Create Sheet with ranks
+            worksheet = workbook_add_worksheet(workbook, "Ranks");
+            formatColumns();
+            header(true);
+            body(true);
+            footer(true);
+            // Create Sheet with Friedman Test
+            doFriedman();
+        }
+    }
+    string BestResultsExcel::getFileName()
+    {
+        return Paths::excel() + fileName;
+    }
+    void BestResultsExcel::header(bool ranks)
+    {
+        row = 0;
+        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) {
+            stringstream oss;
+            oss << "=sum(indirect(address(" << 5 << "," << col + 2 << ")):indirect(address(" << row << "," << col + 2 << ")))";
+            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) {
+                stringstream oss;
+                oss << "=sum(indirect(address(" << 5 << "," << col + 2 << ")):indirect(address(" << row - 1 << "," << col + 2 << ")))/" << datasets.size();
+                worksheet_write_formula(worksheet, row, ++col, oss.str().c_str(), styles["bodyHeader_odd"]);
+            }
+        }
+    }
+    void BestResultsExcel::doFriedman()
+    {
+        worksheet = workbook_add_worksheet(workbook, "Friedman");
+        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;
+        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 +1,37 @@
+#ifndef BESTRESULTS_EXCEL_H
+#define BESTRESULTS_EXCEL_H
+#include "ExcelFile.h"
+#include <vector>
+#include <map>
+#include <nlohmann/json.hpp>
+
+using namespace std;
+using json = nlohmann::json;
+
+namespace platform {
+
+    class BestResultsExcel : ExcelFile {
+    public:
+        BestResultsExcel(const string& score, const vector<string>& models, const vector<string>& datasets, const json& table, const map<string, map<string, float>>& ranks, bool friedman, double significance);
+        ~BestResultsExcel();
+        void build();
+        string getFileName();
+    private:
+        void header(bool ranks);
+        void body(bool ranks);
+        void footer(bool ranks);
+        void formatColumns();
+        void doFriedman();
+        const string fileName = "BestResults.xlsx";
+        string score;
+        vector<string> models;
+        vector<string> datasets;
+        json table;
+        map<string, map<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

@@ -1,7 +1,7 @@
-#ifndef BESTRESULT_H
-#define BESTRESULT_H
+#ifndef BESTSCORE_H
+#define BESTSCORE_H
 #include <string>
-class BestResult {
+class BestScore {
 public:
     static std::string title() { return "STree_default (linear-ovo)"; }
     static double score() { return 22.109799; }

src/Platform/CLocale.h

@@ -0,0 +1,24 @@
+#ifndef LOCALE_H
+#define LOCALE_H
+#include <locale>
+#include <iostream>
+#include <sstream>
+#include <string>
+using namespace std;
+namespace platform {
+    struct separation : numpunct<char> {
+        char do_decimal_point() const { return ','; }
+        char do_thousands_sep() const { return '.'; }
+        string do_grouping() const { return "\03"; }
+    };
+    class ConfigLocale {
+    public:
+        explicit ConfigLocale()
+        {
+            locale mylocale(cout.getloc(), new separation);
+            locale::global(mylocale);
+            cout.imbue(mylocale);
+        }
+    };
+}
+#endif 

src/Platform/CMakeLists.txt

@@ -4,7 +4,14 @@ 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)
-add_executable(manage manage.cc Results.cc Report.cc)
-target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
-target_link_libraries(manage "${TORCH_LIBRARIES}")
+include_directories(${BayesNet_SOURCE_DIR}/lib/libxlsxwriter/include)
+add_executable(b_main main.cc Folding.cc Experiment.cc Datasets.cc Dataset.cc Models.cc ReportConsole.cc ReportBase.cc)
+add_executable(b_manage manage.cc Results.cc Result.cc ReportConsole.cc ReportExcel.cc ReportBase.cc Datasets.cc Dataset.cc ExcelFile.cc)
+add_executable(b_list list.cc Datasets.cc Dataset.cc)
+add_executable(b_best best.cc BestResults.cc Result.cc Statistics.cc BestResultsExcel.cc ExcelFile.cc)
+add_executable(testx testx.cpp Datasets.cc Dataset.cc Folding.cc )
+target_link_libraries(b_main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")
+target_link_libraries(b_manage "${TORCH_LIBRARIES}" "${XLSXWRITER_LIB}" ArffFiles mdlp)
+target_link_libraries(b_best Boost::boost "${XLSXWRITER_LIB}")
+target_link_libraries(b_list ArffFiles mdlp "${TORCH_LIBRARIES}")
+target_link_libraries(testx ArffFiles BayesNet "${TORCH_LIBRARIES}")

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)
+    {
+    }
+    string Dataset::getName() const
+    {
+        return name;
+    }
+    string Dataset::getClassName() const
+    {
+        return className;
+    }
+    vector<string> Dataset::getFeatures() const
+    {
+        if (loaded) {
+            return features;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    int Dataset::getNFeatures() const
+    {
+        if (loaded) {
+            return n_features;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    int Dataset::getNSamples() const
+    {
+        if (loaded) {
+            return n_samples;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    map<string, vector<int>> Dataset::getStates() const
+    {
+        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);
+            if (className == "-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);
+            auto item = states.at(features[i]);
+            iota(begin(item), end(item), 0);
+        }
+        states[className] = vector<int>(*max_element(yv.begin(), yv.end()) + 1);
+        iota(begin(states.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; });
+    }
+    vector<string> tokenize(string line)
+    {
+        vector<string> tokens;
+        for (auto i = 0; i < line.size(); ++i) {
+            if (line[i] == ' ' || line[i] == '\t' || line[i] == '\n') {
+                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()) {
+            string line;
+            getline(file, line);
+            line = ArffFiles::trim(line);
+            vector<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(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 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);
+    }
+    vector<mdlp::labels_t> Dataset::discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y)
+    {
+        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 +1,80 @@
+#ifndef DATASET_H
+#define DATASET_H
+#include <torch/torch.h>
+#include <map>
+#include <vector>
+#include <string>
+#include "CPPFImdlp.h"
+#include "Utils.h"
+namespace platform {
+    using namespace std;
+
+    enum fileType_t { CSV, ARFF, RDATA };
+    class SourceData {
+    public:
+        SourceData(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 invalid_argument("Unknown source.");
+            }
+        }
+        string getPath()
+        {
+            return path;
+        }
+        fileType_t getFileType()
+        {
+            return fileType;
+        }
+    private:
+        string path;
+        fileType_t fileType;
+    };
+    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 load_rdata();
+        void computeStates();
+        vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y);
+    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() const;
+        string getClassName() const;
+        vector<string> getFeatures() const;
+        map<string, vector<int>> getStates() const;
+        pair<vector<vector<float>>&, vector<int>&> getVectors();
+        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized();
+        pair<torch::Tensor&, torch::Tensor&> getTensors();
+        int getNFeatures() const;
+        int getNSamples() const;
+        void load();
+        const bool inline isLoaded() const { return loaded; };
+    };
+};
+
+#endif

src/Platform/Datasets.cc

@@ -1,21 +1,31 @@
 #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;
             while (getline(catalog, line)) {
+                if (line.empty() || line[0] == '#') {
+                    continue;
+                }
                 vector<string> tokens = split(line, ',');
                 string name = tokens[0];
-                string className = tokens[1];
+                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 invalid_argument("Unable to open catalog file. [" + path + "all.txt" + "]");
         }
     }
     vector<string> Datasets::getNames()
@@ -24,208 +34,96 @@ namespace platform {
         transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
         return result;
     }
-    vector<string> Datasets::getFeatures(string name)
+    vector<string> Datasets::getFeatures(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getFeatures();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getFeatures();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    map<string, vector<int>> Datasets::getStates(string name)
+    map<string, vector<int>> Datasets::getStates(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getStates();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getStates();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    string Datasets::getClassName(string name)
+    void Datasets::loadDataset(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getClassName();
+        if (datasets.at(name)->isLoaded()) {
+            return;
+        } else {
+            datasets.at(name)->load();
+        }
+    }
+    string Datasets::getClassName(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getClassName();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    int Datasets::getNSamples(string name)
+    int Datasets::getNSamples(const string& name) const
     {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getNSamples();
+        if (datasets.at(name)->isLoaded()) {
+            return datasets.at(name)->getNSamples();
         } else {
             throw invalid_argument("Dataset not loaded.");
         }
     }
-    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
+    int Datasets::getNClasses(const string& name)
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto className = datasets.at(name)->getClassName();
+            if (discretize) {
+                auto states = getStates(name);
+                return states.at(className).size();
+            }
+            auto [Xv, yv] = getVectors(name);
+            return *max_element(yv.begin(), yv.end()) + 1;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    vector<int> Datasets::getClassesCounts(const string& name) const
+    {
+        if (datasets.at(name)->isLoaded()) {
+            auto [Xv, yv] = datasets.at(name)->getVectors();
+            vector<int> counts(*max_element(yv.begin(), yv.end()) + 1);
+            for (auto y : yv) {
+                counts[y]++;
+            }
+            return counts;
+        } else {
+            throw invalid_argument("Dataset not loaded.");
+        }
+    }
+    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectors();
     }
-    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(string name)
+    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getVectorsDiscretized();
     }
-    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(string name)
+    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(const string& name)
     {
         if (!datasets[name]->isLoaded()) {
             datasets[name]->load();
         }
         return datasets[name]->getTensors();
     }
-    bool Datasets::isDataset(const string& name)
+    bool Datasets::isDataset(const string& name) const
     {
         return datasets.find(name) != datasets.end();
     }
-    Dataset::Dataset(const Dataset& dataset) : path(dataset.path), name(dataset.name), className(dataset.className), n_samples(dataset.n_samples), n_features(dataset.n_features), features(dataset.features), states(dataset.states), loaded(dataset.loaded), discretize(dataset.discretize), X(dataset.X), y(dataset.y), Xv(dataset.Xv), Xd(dataset.Xd), yv(dataset.yv), fileType(dataset.fileType)
-    {
-    }
-    string Dataset::getName()
-    {
-        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 +1,30 @@
 #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;
         fileType_t fileType;
+        string sfileType;
         map<string, 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(); };
+        explicit Datasets(bool discretize, string sfileType) : discretize(discretize), sfileType(sfileType) { load(); };
         vector<string> getNames();
-        vector<string> getFeatures(string name);
-        int getNSamples(string name);
-        string getClassName(string name);
-        map<string, vector<int>> getStates(string name);
-        pair<vector<vector<float>>&, vector<int>&> getVectors(string name);
-        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(string name);
-        pair<torch::Tensor&, torch::Tensor&> getTensors(string name);
-        bool isDataset(const string& name);
+        vector<string> getFeatures(const string& name) const;
+        int getNSamples(const string& name) const;
+        string getClassName(const string& name) const;
+        int getNClasses(const string& name);
+        vector<int> getClassesCounts(const string& name) const;
+        map<string, vector<int>> getStates(const string& name) const;
+        pair<vector<vector<float>>&, vector<int>&> getVectors(const string& name);
+        pair<vector<vector<int>>&, vector<int>&> getVectorsDiscretized(const string& name);
+        pair<torch::Tensor&, torch::Tensor&> getTensors(const string& name);
+        bool isDataset(const string& name) const;
+        void loadDataset(const string& name) const;
     };
 };
 

src/Platform/DotEnv.h

@@ -4,7 +4,11 @@
 #include <map>
 #include <fstream>
 #include <sstream>
-#include "platformUtils.h"
+#include <algorithm>
+#include <iostream>
+#include "Utils.h"
+
+//#include "Dataset.h"
 namespace platform {
     class DotEnv {
     private:
@@ -43,7 +47,7 @@ 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 +1,164 @@
+#include "ExcelFile.h"
+
+namespace platform {
+    ExcelFile::ExcelFile()
+    {
+        setDefault();
+    }
+    ExcelFile::ExcelFile(lxw_workbook* workbook) : workbook(workbook)
+    {
+        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(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 string& style)
+    {
+        lxw_format* efectiveStyle = NULL;
+        if (style != "") {
+            string suffix = row % 2 ? "_odd" : "_even";
+            try {
+                efectiveStyle = styles.at(style + suffix);
+            }
+            catch (const out_of_range& oor) {
+                try {
+                    efectiveStyle = styles.at(style);
+                }
+                catch (const out_of_range& oor) {
+                    throw invalid_argument("Style " + style + " not found");
+                }
+            }
+        }
+        return efectiveStyle;
+    }
+    void ExcelFile::writeString(int row, int col, const string& text, const string& style)
+    {
+        worksheet_write_string(worksheet, row, col, text.c_str(), efectiveStyle(style));
+    }
+    void ExcelFile::writeInt(int row, int col, const int number, const string& style)
+    {
+        worksheet_write_number(worksheet, row, col, number, efectiveStyle(style));
+    }
+    void ExcelFile::writeDouble(int row, int col, const double number, const 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 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 (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"
+
+using namespace std;
+namespace platform {
+    struct separated : numpunct<char> {
+        char do_decimal_point() const { return ','; }
+
+        char do_thousands_sep() const { return '.'; }
+
+        string do_grouping() const { return "\03"; }
+    };
+    class ExcelFile {
+    public:
+        ExcelFile();
+        ExcelFile(lxw_workbook* workbook);
+        lxw_workbook* getWorkbook();
+    protected:
+        void setProperties(string title);
+        void writeString(int row, int col, const string& text, const string& style = "");
+        void writeInt(int row, int col, const int number, const string& style = "");
+        void writeDouble(int row, int col, const double number, const string& style = "");
+        void createFormats();
+        void createStyle(const string& name, lxw_format* style, bool odd);
+        void addColor(lxw_format* style, bool odd);
+        lxw_format* efectiveStyle(const string& name);
+        lxw_workbook* workbook;
+        lxw_worksheet* worksheet;
+        map<string, lxw_format*> styles;
+        int row;
+        int normalSize; //font size for report body
+        uint32_t colorTitle;
+        uint32_t colorOdd;
+        uint32_t colorEven;
+    private:
+        void setDefault();
+    };
+}
+#endif // !EXCELFILE_H

src/Platform/Experiment.cc

@@ -1,8 +1,9 @@
+#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()
@@ -25,6 +26,7 @@ namespace platform {
         oss << std::put_time(timeinfo, "%H:%M:%S");
         return oss.str();
     }
+    Experiment::Experiment() : hyperparameters(json::parse("{}")) {}
     string Experiment::get_file_name()
     {
         string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
@@ -90,7 +92,7 @@ namespace platform {
     void Experiment::report()
     {
         json data = build_json();
-        Report report(data);
+        ReportConsole report(data);
         report.show();
     }
 
@@ -100,19 +102,39 @@ namespace platform {
         cout << data.dump(4) << endl;
     }
 
-    void Experiment::go(vector<string> filesToProcess, const string& path)
+    void Experiment::go(vector<string> filesToProcess)
     {
         cout << "*** Starting experiment: " << title << " ***" << endl;
         for (auto fileName : filesToProcess) {
             cout << "- " << setw(20) << left << fileName << " " << right << flush;
-            cross_validation(path, fileName);
+            cross_validation(fileName);
             cout << endl;
         }
     }
 
-    void Experiment::cross_validation(const string& path, const string& fileName)
+    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 string& color, const string& phase)
+    {
+        string prefix = phase == "a" ? "" : "\b\b\b\b";
+        cout << prefix << color << fold << Colors::RESET() << "(" << color << phase << Colors::RESET() << ")" << flush;
+
+    }
+    void Experiment::cross_validation(const string& fileName)
+    {
+        auto datasets = platform::Datasets(discretized, Paths::datasets());
         // Get dataset
         auto [X, y] = datasets.getTensors(fileName);
         auto states = datasets.getStates(fileName);
@@ -124,6 +146,8 @@ namespace platform {
         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);
+        // Initialize results vectors
         int nResults = nfolds * static_cast<int>(randomSeeds.size());
         auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
         auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
@@ -144,6 +168,10 @@ namespace platform {
             for (int nfold = 0; nfold < nfolds; nfold++) {
                 auto clf = Models::instance()->create(model);
                 setModelVersion(clf->getVersion());
+                if (hyperparameters.size() != 0) {
+                    clf->setHyperparameters(hyperparameters);
+                }
+                // Split train - test dataset
                 train_timer.start();
                 auto [train, test] = fold->getFold(nfold);
                 auto train_t = torch::tensor(train);
@@ -152,24 +180,31 @@ namespace platform {
                 auto y_train = y.index({ train_t });
                 auto X_test = X.index({ "...", test_t });
                 auto y_test = y.index({ test_t });
-                cout << nfold + 1 << ", " << flush;
+                showProgress(nfold + 1, getColor(clf->getStatus()), "a");
+                // Train model
                 clf->fit(X_train, y_train, features, className, states);
+                showProgress(nfold + 1, getColor(clf->getStatus()), "b");
                 nodes[item] = clf->getNumberOfNodes();
                 edges[item] = clf->getNumberOfEdges();
                 num_states[item] = clf->getNumberOfStates();
                 train_time[item] = train_timer.getDuration();
+                // Score train
                 auto accuracy_train_value = clf->score(X_train, y_train);
+                // Test model
+                showProgress(nfold + 1, getColor(clf->getStatus()), "c");
                 test_timer.start();
                 auto accuracy_test_value = clf->score(X_test, y_test);
                 test_time[item] = test_timer.getDuration();
                 accuracy_train[item] = accuracy_train_value;
                 accuracy_test[item] = accuracy_test_value;
+                cout << "\b\b\b, " << flush;
                 // Store results and times in vector
                 result.addScoreTrain(accuracy_train_value);
                 result.addScoreTest(accuracy_test_value);
                 result.addTimeTrain(train_time[item].item<double>());
                 result.addTimeTest(test_time[item].item<double>());
                 item++;
+                clf.reset();
             }
             cout << "end. " << flush;
             delete fold;
@@ -177,6 +212,7 @@ namespace platform {
         result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
         result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
         result.setTrainTime(torch::mean(train_time).item<double>()).setTestTime(torch::mean(test_time).item<double>());
+        result.setTestTimeStd(torch::std(test_time).item<double>()).setTrainTimeStd(torch::std(train_time).item<double>());
         result.setNodes(torch::mean(nodes).item<double>()).setLeaves(torch::mean(edges).item<double>()).setDepth(torch::mean(num_states).item<double>());
         result.setDataset(fileName);
         addResult(result);

src/Platform/Experiment.h

@@ -29,7 +29,8 @@ namespace platform {
     };
     class Result {
     private:
-        string dataset, hyperparameters, model_version;
+        string dataset, model_version;
+        json hyperparameters;
         int samples{ 0 }, features{ 0 }, classes{ 0 };
         double score_train{ 0 }, score_test{ 0 }, score_train_std{ 0 }, score_test_std{ 0 }, train_time{ 0 }, train_time_std{ 0 }, test_time{ 0 }, test_time_std{ 0 };
         float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
@@ -37,7 +38,7 @@ namespace platform {
     public:
         Result() = default;
         Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
-        Result& setHyperparameters(const string& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
+        Result& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
         Result& setSamples(int samples) { this->samples = samples; return *this; }
         Result& setFeatures(int features) { this->features = features; return *this; }
         Result& setClasses(int classes) { this->classes = classes; return *this; }
@@ -59,7 +60,7 @@ namespace platform {
         const float get_score_train() const { return score_train; }
         float get_score_test() { return score_test; }
         const string& getDataset() const { return dataset; }
-        const string& getHyperparameters() const { return hyperparameters; }
+        const json& getHyperparameters() const { return hyperparameters; }
         const int getSamples() const { return samples; }
         const int getFeatures() const { return features; }
         const int getClasses() const { return classes; }
@@ -85,11 +86,12 @@ namespace platform {
         bool discretized{ false }, stratified{ false };
         vector<Result> results;
         vector<int> randomSeeds;
+        json hyperparameters = "{}";
         int nfolds{ 0 };
         float duration{ 0 };
         json build_json();
     public:
-        Experiment() = default;
+        Experiment();
         Experiment& setTitle(const string& title) { this->title = title; return *this; }
         Experiment& setModel(const string& model) { this->model = model; return *this; }
         Experiment& setPlatform(const string& platform) { this->platform = platform; return *this; }
@@ -103,10 +105,11 @@ namespace platform {
         Experiment& addResult(Result result) { results.push_back(result); return *this; }
         Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
         Experiment& setDuration(float duration) { this->duration = duration; return *this; }
+        Experiment& setHyperparameters(const json& hyperparameters) { this->hyperparameters = hyperparameters; return *this; }
         string get_file_name();
         void save(const string& path);
-        void cross_validation(const string& path, const string& fileName);
-        void go(vector<string> filesToProcess, const string& path);
+        void cross_validation(const string& fileName);
+        void go(vector<string> filesToProcess);
         void show();
         void report();
     };

src/Platform/Folding.cc

@@ -1,95 +1,104 @@
 #include "Folding.h"
 #include <algorithm>
 #include <map>
-Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
-{
-    random_device rd;
-    random_seed = default_random_engine(seed == -1 ? rd() : seed);
-    srand(seed == -1 ? time(0) : seed);
-}
-KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
-{
-    iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
-    shuffle(indices.begin(), indices.end(), random_seed);
-}
-pair<vector<int>, vector<int>> KFold::getFold(int nFold)
-{
-    if (nFold >= k || nFold < 0) {
-        throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
+namespace platform {
+    Fold::Fold(int k, int n, int seed) : k(k), n(n), seed(seed)
+    {
+        random_device rd;
+        random_seed = default_random_engine(seed == -1 ? rd() : seed);
+        srand(seed == -1 ? time(0) : seed);
     }
-    int nTest = n / k;
-    auto train = vector<int>();
-    auto test = vector<int>();
-    for (int i = 0; i < n; i++) {
-        if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
-            test.push_back(indices[i]);
-        } else {
-            train.push_back(indices[i]);
-        }
-    }
-    return { train, test };
-}
-StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
-{
-    n = y.numel();
-    this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
-    build();
-}
-StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
-    : Fold(k, y.size(), seed)
-{
-    this->y = y;
-    n = y.size();
-    build();
-}
-void StratifiedKFold::build()
-{
-    stratified_indices = vector<vector<int>>(k);
-    int fold_size = n / k;
-    // Compute class counts and indices
-    auto class_indices = map<int, vector<int>>();
-    vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
-    for (auto i = 0; i < n; ++i) {
-        class_counts[y[i]]++;
-        class_indices[y[i]].push_back(i);
-    }
-    // Shuffle class indices
-    for (auto& [cls, indices] : class_indices) {
+    KFold::KFold(int k, int n, int seed) : Fold(k, n, seed), indices(vector<int>(n))
+    {
+        iota(begin(indices), end(indices), 0); // fill with 0, 1, ..., n - 1
         shuffle(indices.begin(), indices.end(), random_seed);
     }
-    // Assign indices to folds
-    for (auto label = 0; label < class_counts.size(); ++label) {
-        auto num_samples_to_take = class_counts[label] / k;
-        if (num_samples_to_take == 0)
-            continue;
-        auto remainder_samples_to_take = class_counts[label] % k;
-        for (auto fold = 0; fold < k; ++fold) {
-            auto it = next(class_indices[label].begin(), num_samples_to_take);
-            move(class_indices[label].begin(), it, back_inserter(stratified_indices[fold]));  // ##
-            class_indices[label].erase(class_indices[label].begin(), it);
+    pair<vector<int>, vector<int>> KFold::getFold(int nFold)
+    {
+        if (nFold >= k || nFold < 0) {
+            throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
         }
-        while (remainder_samples_to_take > 0) {
-            int fold = (rand() % static_cast<int>(k));
-            if (stratified_indices[fold].size() == fold_size + 1) {
+        int nTest = n / k;
+        auto train = vector<int>();
+        auto test = vector<int>();
+        for (int i = 0; i < n; i++) {
+            if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
+                test.push_back(indices[i]);
+            } else {
+                train.push_back(indices[i]);
+            }
+        }
+        return { train, test };
+    }
+    StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
+    {
+        n = y.numel();
+        this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
+        build();
+    }
+    StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
+        : Fold(k, y.size(), seed)
+    {
+        this->y = y;
+        n = y.size();
+        build();
+    }
+    void StratifiedKFold::build()
+    {
+        stratified_indices = vector<vector<int>>(k);
+        int fold_size = n / k;
+
+        // Compute class counts and indices
+        auto class_indices = map<int, vector<int>>();
+        vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
+        for (auto i = 0; i < n; ++i) {
+            class_counts[y[i]]++;
+            class_indices[y[i]].push_back(i);
+        }
+        // Shuffle class indices
+        for (auto& [cls, indices] : class_indices) {
+            shuffle(indices.begin(), indices.end(), random_seed);
+        }
+        // Assign indices to folds
+        for (auto label = 0; label < class_counts.size(); ++label) {
+            auto num_samples_to_take = class_counts.at(label) / k;
+            if (num_samples_to_take == 0) {
+                cerr << "Warning! The number of samples in class " << label << " (" << class_counts.at(label)
+                    << ") is less than the number of folds (" << k << ")." << endl;
+                faulty = true;
                 continue;
             }
-            auto it = next(class_indices[label].begin(), 1);
-            stratified_indices[fold].push_back(*class_indices[label].begin());
-            class_indices[label].erase(class_indices[label].begin(), it);
-            remainder_samples_to_take--;
+            auto 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 = vector<bool>(k, false);
+            while (remainder_samples_to_take > 0) {
+                int fold = (rand() % static_cast<int>(k));
+                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);
+                remainder_samples_to_take--;
+            }
         }
     }
-}
-pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
-{
-    if (nFold >= k || nFold < 0) {
-        throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
+    pair<vector<int>, vector<int>> StratifiedKFold::getFold(int nFold)
+    {
+        if (nFold >= k || nFold < 0) {
+            throw out_of_range("nFold (" + to_string(nFold) + ") must be less than k (" + to_string(k) + ")");
+        }
+        vector<int> test_indices = stratified_indices[nFold];
+        vector<int> train_indices;
+        for (int i = 0; i < k; ++i) {
+            if (i == nFold) continue;
+            train_indices.insert(train_indices.end(), stratified_indices[i].begin(), stratified_indices[i].end());
+        }
+        return { train_indices, test_indices };
     }
-    vector<int> test_indices = stratified_indices[nFold];
-    vector<int> train_indices;
-    for (int i = 0; i < k; ++i) {
-        if (i == nFold) continue;
-        train_indices.insert(train_indices.end(), stratified_indices[i].begin(), stratified_indices[i].end());
-    }
-    return { train_indices, test_indices };
 }

src/Platform/Folding.h

@@ -4,34 +4,37 @@
 #include <vector>
 #include <random> 
 using namespace std;
-
-class Fold {
-protected:
-    int k;
-    int n;
-    int seed;
-    default_random_engine random_seed;
-public:
-    Fold(int k, int n, int seed = -1);
-    virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
-    virtual ~Fold() = default;
-    int getNumberOfFolds() { return k; }
-};
-class KFold : public Fold {
-private:
-    vector<int> indices;
-public:
-    KFold(int k, int n, int seed = -1);
-    pair<vector<int>, vector<int>> getFold(int nFold) override;
-};
-class StratifiedKFold : public Fold {
-private:
-    vector<int> y;
-    vector<vector<int>> stratified_indices;
-    void build();
-public:
-    StratifiedKFold(int k, const vector<int>& y, int seed = -1);
-    StratifiedKFold(int k, torch::Tensor& y, int seed = -1);
-    pair<vector<int>, vector<int>> getFold(int nFold) override;
-};
+namespace platform {
+    class Fold {
+    protected:
+        int k;
+        int n;
+        int seed;
+        default_random_engine random_seed;
+    public:
+        Fold(int k, int n, int seed = -1);
+        virtual pair<vector<int>, vector<int>> getFold(int nFold) = 0;
+        virtual ~Fold() = default;
+        int getNumberOfFolds() { return k; }
+    };
+    class KFold : public Fold {
+    private:
+        vector<int> indices;
+    public:
+        KFold(int k, int n, int seed = -1);
+        pair<vector<int>, vector<int>> getFold(int nFold) override;
+    };
+    class StratifiedKFold : public Fold {
+    private:
+        vector<int> y;
+        vector<vector<int>> stratified_indices;
+        void build();
+        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, torch::Tensor& y, int seed = -1);
+        pair<vector<int>, vector<int>> getFold(int nFold) override;
+        bool isFaulty() { return faulty; }
+    };
+}
 #endif

src/Platform/Models.cc

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

src/Platform/Models.h

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

src/Platform/Paths.h

@@ -1,10 +1,18 @@
 #ifndef PATHS_H
 #define PATHS_H
+#include <string>
+#include "DotEnv.h"
 namespace platform {
     class Paths {
     public:
-        static std::string datasets() { return "datasets/"; }
         static std::string results() { return "results/"; }
+        static std::string excel() { return "excel/"; }
+        static std::string cfs() { return "cfs/"; }
+        static std::string datasets()
+        {
+            auto env = platform::DotEnv();
+            return env.get("source_data");
+        }
     };
 }
 #endif

src/Platform/Report.cc

@@ -1,93 +0,0 @@
-#include "Report.h"
-#include "BestResult.h"
-
-namespace platform {
-    string headerLine(const string& text)
-    {
-        int n = MAXL - text.length() - 3;
-        n = n < 0 ? 0 : n;
-        return "* " + text + string(n, ' ') + "*\n";
-    }
-    string Report::fromVector(const string& key)
-    {
-        string result = "";
-
-        for (auto& item : data[key]) {
-            result += to_string(item) + ", ";
-        }
-        return "[" + result.substr(0, result.size() - 2) + "]";
-    }
-    string fVector(const json& data)
-    {
-        string result = "";
-        for (const auto& item : data) {
-            result += to_string(item) + ", ";
-        }
-        return "[" + result.substr(0, result.size() - 2) + "]";
-    }
-    void Report::show()
-    {
-        header();
-        body();
-        footer();
-    }
-    void Report::header()
-    {
-        cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
-        cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
-        cout << headerLine(data["title"].get<string>());
-        cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
-        cout << headerLine("Execution took  " + to_string(data["duration"].get<float>()) + " seconds,   " + to_string(data["duration"].get<float>() / 3600) + " hours, on " + data["platform"].get<string>());
-        cout << headerLine("Score is " + data["score_name"].get<string>());
-        cout << string(MAXL, '*') << endl;
-        cout << endl;
-    }
-    void Report::body()
-    {
-        cout << Colors::GREEN() << "Dataset                        Sampl. Feat. Cls Nodes   Edges   States  Score           Time               Hyperparameters" << endl;
-        cout << "============================== ====== ===== === ======= ======= ======= =============== ================== ===============" << endl;
-        json lastResult;
-        totalScore = 0;
-        bool odd = true;
-        for (const auto& r : data["results"]) {
-            auto color = odd ? Colors::CYAN() : Colors::BLUE();
-            cout << color << setw(30) << left << r["dataset"].get<string>() << " ";
-            cout << setw(6) << right << r["samples"].get<int>() << " ";
-            cout << setw(5) << right << r["features"].get<int>() << " ";
-            cout << setw(3) << right << r["classes"].get<int>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
-            cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>() << " ";
-            cout << setw(11) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
-            try {
-                cout << r["hyperparameters"].get<string>();
-            }
-            catch (const exception& err) {
-                cout << r["hyperparameters"];
-            }
-            cout << endl;
-            lastResult = r;
-            totalScore += r["score"].get<double>();
-            odd = !odd;
-        }
-        if (data["results"].size() == 1) {
-            cout << string(MAXL, '*') << endl;
-            cout << headerLine("Train scores: " + fVector(lastResult["scores_train"]));
-            cout << headerLine("Test  scores: " + fVector(lastResult["scores_test"]));
-            cout << headerLine("Train  times: " + fVector(lastResult["times_train"]));
-            cout << headerLine("Test   times: " + fVector(lastResult["times_test"]));
-            cout << string(MAXL, '*') << endl;
-        }
-    }
-    void Report::footer()
-    {
-        cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
-        auto score = data["score_name"].get<string>();
-        if (score == BestResult::scoreName()) {
-            cout << headerLine(score + " compared to " + BestResult::title() + " .:  " + to_string(totalScore / BestResult::score()));
-        }
-        cout << string(MAXL, '*') << endl << Colors::RESET();
-
-    }
-}

src/Platform/Report.h

@@ -1,26 +0,0 @@
-#ifndef REPORT_H
-#define REPORT_H
-#include <string>
-#include <iostream>
-#include <nlohmann/json.hpp>
-#include "Colors.h"
-
-using json = nlohmann::json;
-const int MAXL = 121;
-namespace platform {
-    using namespace std;
-    class Report {
-    public:
-        explicit Report(json data_) { data = data_; };
-        virtual ~Report() = default;
-        void show();
-    private:
-        void header();
-        void body();
-        void footer();
-        string fromVector(const string& key);
-        json data;
-        double totalScore; // Total score of all results in a report
-    };
-};
-#endif

src/Platform/ReportBase.cc

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

src/Platform/ReportBase.h

@@ -0,0 +1,37 @@
+#ifndef REPORTBASE_H
+#define REPORTBASE_H
+#include <string>
+#include <iostream>
+#include "Paths.h"
+#include "Symbols.h"
+#include <nlohmann/json.hpp>
+
+using json = nlohmann::json;
+namespace platform {
+    using namespace std;
+
+    class ReportBase {
+    public:
+        explicit ReportBase(json data_, bool compare);
+        virtual ~ReportBase() = default;
+        void show();
+    protected:
+        json data;
+        string fromVector(const string& key);
+        string fVector(const string& title, const json& data, const int width, const int precision);
+        bool getExistBestFile();
+        virtual void header() = 0;
+        virtual void body() = 0;
+        virtual void showSummary() = 0;
+        string compareResult(const string& dataset, double result);
+        map<string, int> summary;
+        double margin;
+        map<string, string> meaning;
+        bool compare;
+    private:
+        double bestResult(const string& dataset, const string& model);
+        json bestResults;
+        bool existBestFile = true;
+    };
+};
+#endif

src/Platform/ReportConsole.cc

@@ -0,0 +1,100 @@
+#include <sstream>
+#include <locale>
+#include "ReportConsole.h"
+#include "BestScore.h"
+#include "CLocale.h"
+
+namespace platform {
+    string ReportConsole::headerLine(const string& text, int utf = 0)
+    {
+        int n = MAXL - text.length() - 3;
+        n = n < 0 ? 0 : n;
+        return "* " + text + string(n + utf, ' ') + "*\n";
+    }
+
+    void ReportConsole::header()
+    {
+        stringstream oss;
+        cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
+        cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
+        cout << headerLine(data["title"].get<string>());
+        cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
+        oss << "Execution took  " << setprecision(2) << fixed << data["duration"].get<float>() << " seconds,   " << data["duration"].get<float>() / 3600 << " hours, on " << data["platform"].get<string>();
+        cout << headerLine(oss.str());
+        cout << headerLine("Score is " + data["score_name"].get<string>());
+        cout << string(MAXL, '*') << endl;
+        cout << endl;
+    }
+    void ReportConsole::body()
+    {
+        auto tmp = ConfigLocale();
+        cout << Colors::GREEN() << " #  Dataset                   Sampl. Feat. Cls Nodes     Edges     States    Score           Time                Hyperparameters" << endl;
+        cout << "=== ========================= ====== ===== === ========= ========= ========= =============== =================== ====================" << endl;
+        json lastResult;
+        double totalScore = 0.0;
+        bool odd = true;
+        int index = 0;
+        for (const auto& r : data["results"]) {
+            if (selectedIndex != -1 && index != selectedIndex) {
+                index++;
+                continue;
+            }
+            auto color = odd ? Colors::CYAN() : Colors::BLUE();
+            cout << color;
+            cout << setw(3) << index++ << " ";
+            cout << setw(25) << left << r["dataset"].get<string>() << " ";
+            cout << setw(6) << right << r["samples"].get<int>() << " ";
+            cout << setw(5) << right << r["features"].get<int>() << " ";
+            cout << setw(3) << right << r["classes"].get<int>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
+            cout << setw(9) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
+            cout << setw(8) << right << setprecision(6) << fixed << r["score"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_std"].get<double>();
+            const string status = compareResult(r["dataset"].get<string>(), r["score"].get<double>());
+            cout << status;
+            cout << setw(12) << right << setprecision(6) << fixed << r["time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["time_std"].get<double>() << " ";
+            cout << r["hyperparameters"].dump();
+            cout << endl;
+            cout << flush;
+            lastResult = r;
+            totalScore += r["score"].get<double>();
+            odd = !odd;
+        }
+        if (data["results"].size() == 1 || selectedIndex != -1) {
+            cout << string(MAXL, '*') << endl;
+            cout << headerLine(fVector("Train scores: ", lastResult["scores_train"], 14, 12));
+            cout << headerLine(fVector("Test  scores: ", lastResult["scores_test"], 14, 12));
+            cout << headerLine(fVector("Train  times: ", lastResult["times_train"], 10, 3));
+            cout << headerLine(fVector("Test   times: ", lastResult["times_test"], 10, 3));
+            cout << string(MAXL, '*') << endl;
+        } else {
+            footer(totalScore);
+        }
+    }
+    void ReportConsole::showSummary()
+    {
+        for (const auto& item : summary) {
+            stringstream oss;
+            oss << setw(3) << left << item.first;
+            oss << setw(3) << right << item.second << " ";
+            oss << left << meaning.at(item.first);
+            cout << headerLine(oss.str(), 2);
+        }
+    }
+
+    void ReportConsole::footer(double totalScore)
+    {
+        cout << Colors::MAGENTA() << string(MAXL, '*') << endl;
+        showSummary();
+        auto score = data["score_name"].get<string>();
+        if (score == BestScore::scoreName()) {
+            stringstream oss;
+            oss << score << " compared to " << BestScore::title() << " .:  " << totalScore / BestScore::score();
+            cout << headerLine(oss.str());
+        }
+        if (!getExistBestFile() && compare) {
+            cout << headerLine("*** Best Results File not found. Couldn't compare any result!");
+        }
+        cout << string(MAXL, '*') << endl << Colors::RESET();
+    }
+}

src/Platform/ReportConsole.h

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

src/Platform/ReportExcel.cc

@@ -0,0 +1,182 @@
+#include <sstream>
+#include <locale>
+#include "ReportExcel.h"
+#include "BestScore.h"
+
+
+namespace platform {
+
+    ReportExcel::ReportExcel(json data_, bool compare, lxw_workbook* workbook) : ReportBase(data_, compare), ExcelFile(workbook)
+    {
+        createFile();
+    }
+
+    void ReportExcel::formatColumns()
+    {
+        worksheet_freeze_panes(worksheet, 6, 1);
+        vector<int> columns_sizes = { 22, 10, 9, 7, 12, 12, 12, 12, 12, 3, 15, 12, 23 };
+        for (int i = 0; i < columns_sizes.size(); ++i) {
+            worksheet_set_column(worksheet, i, i, columns_sizes.at(i), NULL);
+        }
+    }
+
+    void ReportExcel::createFile()
+    {
+        if (workbook == NULL) {
+            workbook = workbook_new((Paths::excel() + fileName).c_str());
+        }
+        const string name = data["model"].get<string>();
+        string suffix = "";
+        string efectiveName;
+        int num = 1;
+        // Create a sheet with the name of the model
+        while (true) {
+            efectiveName = name + suffix;
+            if (workbook_get_worksheet_by_name(workbook, efectiveName.c_str())) {
+                suffix = to_string(++num);
+            } else {
+                worksheet = workbook_add_worksheet(workbook, efectiveName.c_str());
+                break;
+            }
+            if (num > 100) {
+                throw invalid_argument("Couldn't create sheet " + efectiveName);
+            }
+        }
+        cout << "Adding sheet " << efectiveName << " to " << Paths::excel() + fileName << endl;
+        setProperties(data["title"].get<string>());
+        createFormats();
+        formatColumns();
+    }
+
+    void ReportExcel::closeFile()
+    {
+        workbook_close(workbook);
+    }
+
+    void ReportExcel::header()
+    {
+        locale mylocale(cout.getloc(), new separated);
+        locale::global(mylocale);
+        cout.imbue(mylocale);
+        stringstream oss;
+        string message = data["model"].get<string>() + " ver. " + data["version"].get<string>() + " " +
+            data["language"].get<string>() + " ver. " + data["language_version"].get<string>() +
+            " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) +
+            " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>();
+        worksheet_merge_range(worksheet, 0, 0, 0, 12, message.c_str(), styles["headerFirst"]);
+        worksheet_merge_range(worksheet, 1, 0, 1, 12, data["title"].get<string>().c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 0, 3, 0, ("Score is " + data["score_name"].get<string>()).c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 1, 3, 3, "Execution time", styles["headerRest"]);
+        oss << setprecision(2) << fixed << data["duration"].get<float>() << " s";
+        worksheet_merge_range(worksheet, 2, 4, 2, 5, oss.str().c_str(), styles["headerRest"]);
+        oss.str("");
+        oss.clear();
+        oss << setprecision(2) << fixed << data["duration"].get<float>() / 3600 << " h";
+        worksheet_merge_range(worksheet, 3, 4, 3, 5, oss.str().c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 6, 3, 7, "Platform", styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 8, 3, 9, data["platform"].get<string>().c_str(), styles["headerRest"]);
+        worksheet_merge_range(worksheet, 2, 10, 2, 12, ("Random seeds: " + fromVector("seeds")).c_str(), styles["headerSmall"]);
+        oss.str("");
+        oss.clear();
+        oss << "Stratified: " << (data["stratified"].get<bool>() ? "True" : "False");
+        worksheet_merge_range(worksheet, 3, 10, 3, 11, oss.str().c_str(), styles["headerSmall"]);
+        oss.str("");
+        oss.clear();
+        oss << "Discretized: " << (data["discretized"].get<bool>() ? "True" : "False");
+        worksheet_write_string(worksheet, 3, 12, oss.str().c_str(), styles["headerSmall"]);
+    }
+
+    void ReportExcel::body()
+    {
+        auto head = vector<string>(
+            { "Dataset", "Samples", "Features", "Classes", "Nodes", "Edges", "States", "Score", "Score Std.", "St.", "Time",
+             "Time Std.", "Hyperparameters" });
+        int col = 0;
+        for (const auto& item : head) {
+            writeString(5, col++, item, "bodyHeader");
+        }
+        row = 6;
+        col = 0;
+        int hypSize = 22;
+        json lastResult;
+        double totalScore = 0.0;
+        string hyperparameters;
+        for (const auto& r : data["results"]) {
+            writeString(row, col, r["dataset"].get<string>(), "text");
+            writeInt(row, col + 1, r["samples"].get<int>(), "ints");
+            writeInt(row, col + 2, r["features"].get<int>(), "ints");
+            writeInt(row, col + 3, r["classes"].get<int>(), "ints");
+            writeDouble(row, col + 4, r["nodes"].get<float>(), "floats");
+            writeDouble(row, col + 5, r["leaves"].get<float>(), "floats");
+            writeDouble(row, col + 6, r["depth"].get<double>(), "floats");
+            writeDouble(row, col + 7, r["score"].get<double>(), "result");
+            writeDouble(row, col + 8, r["score_std"].get<double>(), "result");
+            const string status = compareResult(r["dataset"].get<string>(), r["score"].get<double>());
+            writeString(row, col + 9, status, "textCentered");
+            writeDouble(row, col + 10, r["time"].get<double>(), "time");
+            writeDouble(row, col + 11, r["time_std"].get<double>(), "time");
+            try {
+                hyperparameters = r["hyperparameters"].get<string>();
+            }
+            catch (const exception& err) {
+                stringstream oss;
+                oss << r["hyperparameters"];
+                hyperparameters = oss.str();
+            }
+            if (hyperparameters.size() > hypSize) {
+                hypSize = hyperparameters.size();
+            }
+            writeString(row, col + 12, hyperparameters, "text");
+            lastResult = r;
+            totalScore += r["score"].get<double>();
+            row++;
+
+        }
+        // Set the right column width of hyperparameters with the maximum length
+        worksheet_set_column(worksheet, 12, 12, hypSize + 5, NULL);
+        // Show totals if only one dataset is present in the result
+        if (data["results"].size() == 1) {
+            for (const string& group : { "scores_train", "scores_test", "times_train", "times_test" }) {
+                row++;
+                col = 1;
+                writeString(row, col, group, "text");
+                for (double item : lastResult[group]) {
+                    string style = group.find("scores") != string::npos ? "result" : "time";
+                    writeDouble(row, ++col, item, style);
+                }
+            }
+            // Set with of columns to show those totals completely
+            worksheet_set_column(worksheet, 1, 1, 12, NULL);
+            for (int i = 2; i < 7; ++i) {
+                // doesn't work with from col to col, so...
+                worksheet_set_column(worksheet, i, i, 15, NULL);
+            }
+        } else {
+            footer(totalScore, row);
+        }
+    }
+
+    void ReportExcel::showSummary()
+    {
+        for (const auto& item : summary) {
+            worksheet_write_string(worksheet, row + 2, 1, item.first.c_str(), styles["summaryStyle"]);
+            worksheet_write_number(worksheet, row + 2, 2, item.second, styles["summaryStyle"]);
+            worksheet_merge_range(worksheet, row + 2, 3, row + 2, 5, meaning.at(item.first).c_str(), styles["summaryStyle"]);
+            row += 1;
+        }
+    }
+
+    void ReportExcel::footer(double totalScore, int row)
+    {
+        showSummary();
+        row += 4 + summary.size();
+        auto score = data["score_name"].get<string>();
+        if (score == BestScore::scoreName()) {
+            worksheet_merge_range(worksheet, row, 1, row, 5, (score + " compared to " + BestScore::title() + " .:").c_str(), efectiveStyle("text"));
+            writeDouble(row, 6, totalScore / BestScore::score(), "result");
+        }
+        if (!getExistBestFile() && compare) {
+            worksheet_write_string(worksheet, row + 1, 0, "*** Best Results File not found. Couldn't compare any result!", styles["summaryStyle"]);
+        }
+    }
+}

src/Platform/ReportExcel.h

@@ -0,0 +1,25 @@
+#ifndef REPORTEXCEL_H
+#define REPORTEXCEL_H
+#include<map>
+#include "xlsxwriter.h"
+#include "ReportBase.h"
+#include "ExcelFile.h"
+#include "Colors.h"
+namespace platform {
+    using namespace std;
+    class ReportExcel : public ReportBase, public ExcelFile {
+    public:
+        explicit ReportExcel(json data_, bool compare, lxw_workbook* workbook);
+    private:
+        const string fileName = "some_results.xlsx";
+        void formatColumns();
+        void createFile();
+        void closeFile();
+        void header() override;
+        void body() override;
+        void showSummary() override;
+        void footer(double totalScore, int row);
+
+    };
+};
+#endif // !REPORTEXCEL_H

src/Platform/Result.cc

@@ -0,0 +1,56 @@
+#include <filesystem>
+#include <fstream>
+#include <sstream>
+#include "Result.h"
+#include "Colors.h"
+#include "BestScore.h"
+#include "CLocale.h"
+
+namespace platform {
+    Result::Result(const string& path, const string& filename)
+        : path(path)
+        , filename(filename)
+    {
+        auto data = load();
+        date = data["date"];
+        score = 0;
+        for (const auto& result : data["results"]) {
+            score += result["score"].get<double>();
+        }
+        scoreName = data["score_name"];
+        if (scoreName == BestScore::scoreName()) {
+            score /= BestScore::score();
+        }
+        title = data["title"];
+        duration = data["duration"];
+        model = data["model"];
+        complete = data["results"].size() > 1;
+    }
+
+    json Result::load() const
+    {
+        ifstream resultData(path + "/" + filename);
+        if (resultData.is_open()) {
+            json data = json::parse(resultData);
+            return data;
+        }
+        throw invalid_argument("Unable to open result file. [" + path + "/" + filename + "]");
+    }
+
+    string Result::to_string() const
+    {
+        auto tmp = ConfigLocale();
+        stringstream oss;
+        double durationShow = duration > 3600 ? duration / 3600 : duration > 60 ? duration / 60 : duration;
+        string durationUnit = duration > 3600 ? "h" : duration > 60 ? "m" : "s";
+        oss << date << " ";
+        oss << setw(12) << left << model << " ";
+        oss << setw(11) << left << scoreName << " ";
+        oss << right << setw(11) << setprecision(7) << fixed << score << " ";
+        auto completeString = isComplete() ? "C" : "P";
+        oss << setw(1) << " " << completeString << "  ";
+        oss << setw(7) << setprecision(2) << fixed << durationShow << " " << durationUnit << " ";
+        oss << setw(50) << left << title << " ";
+        return  oss.str();
+    }
+}

src/Platform/Result.h

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

src/Platform/Results.cc

@@ -1,37 +1,11 @@
 #include <filesystem>
-#include "platformUtils.h"
 #include "Results.h"
-#include "Report.h"
-#include "BestResult.h"
+#include "ReportConsole.h"
+#include "ReportExcel.h"
+#include "BestScore.h"
 #include "Colors.h"
+#include "CLocale.h"
 namespace platform {
-    Result::Result(const string& path, const string& filename)
-        : path(path)
-        , filename(filename)
-    {
-        auto data = load();
-        date = data["date"];
-        score = 0;
-        for (const auto& result : data["results"]) {
-            score += result["score"].get<double>();
-        }
-        scoreName = data["score_name"];
-        if (scoreName == BestResult::scoreName()) {
-            score /= BestResult::score();
-        }
-        title = data["title"];
-        duration = data["duration"];
-        model = data["model"];
-    }
-    json Result::load() const
-    {
-        ifstream resultData(path + "/" + filename);
-        if (resultData.is_open()) {
-            json data = json::parse(resultData);
-            return data;
-        }
-        throw invalid_argument("Unable to open result file. [" + path + "/" + filename + "]");
-    }
     void Results::load()
     {
         using std::filesystem::directory_iterator;
@@ -40,31 +14,30 @@ namespace platform {
             if (filename.find(".json") != string::npos && filename.find("results_") == 0) {
                 auto result = Result(path, filename);
                 bool addResult = true;
-                if (model != "any" && result.getModel() != model || scoreName != "any" && scoreName != result.getScoreName())
+                if (model != "any" && result.getModel() != model || scoreName != "any" && scoreName != result.getScoreName() || complete && !result.isComplete() || partial && result.isComplete())
                     addResult = false;
                 if (addResult)
                     files.push_back(result);
             }
         }
-    }
-    string Result::to_string() const
-    {
-        stringstream oss;
-        oss << date << " ";
-        oss << setw(12) << left << model << " ";
-        oss << setw(11) << left << scoreName << " ";
-        oss << right << setw(11) << setprecision(7) << fixed << score << " ";
-        oss << setw(9) << setprecision(3) << fixed << duration << " ";
-        oss << setw(50) << left << title << " ";
-        return  oss.str();
+        if (max == 0) {
+            max = files.size();
+        }
     }
     void Results::show() const
     {
+        auto temp = ConfigLocale();
         cout << Colors::GREEN() << "Results found: " << files.size() << endl;
         cout << "-------------------" << endl;
+        if (complete) {
+            cout << Colors::MAGENTA() << "Only listing complete results" << endl;
+        }
+        if (partial) {
+            cout << Colors::MAGENTA() << "Only listing partial results" << endl;
+        }
         auto i = 0;
-        cout << " #  Date       Model        Score Name  Score       Duration  Title" << endl;
-        cout << "=== ========== ============ =========== =========== ========= =============================================================" << endl;
+        cout << Colors::GREEN() << " #  Date       Model        Score Name  Score       C/P Duration  Title" << endl;
+        cout << "=== ========== ============ =========== =========== === ========= =============================================================" << endl;
         bool odd = true;
         for (const auto& result : files) {
             auto color = odd ? Colors::BLUE() : Colors::CYAN();
@@ -94,21 +67,51 @@ namespace platform {
         cout << "Invalid index" << endl;
         return -1;
     }
-    void Results::report(const int index) const
+    void Results::report(const int index, const bool excelReport)
     {
         cout << Colors::YELLOW() << "Reporting " << files.at(index).getFilename() << endl;
         auto data = files.at(index).load();
-        Report report(data);
-        report.show();
+        if (excelReport) {
+            ReportExcel reporter(data, compare, workbook);
+            reporter.show();
+            openExcel = true;
+            workbook = reporter.getWorkbook();
+        } else {
+            ReportConsole reporter(data, compare);
+            reporter.show();
+        }
+    }
+    void Results::showIndex(const int index, const int idx) const
+    {
+        auto data = files.at(index).load();
+        if (idx < 0 or idx >= static_cast<int>(data["results"].size())) {
+            cout << "Invalid index" << endl;
+            return;
+        }
+        cout << Colors::YELLOW() << "Showing " << files.at(index).getFilename() << endl;
+        ReportConsole reporter(data, compare, idx);
+        reporter.show();
     }
     void Results::menu()
     {
         char option;
         int index;
         bool finished = false;
-        string filename, line, options = "qldhsr";
+        string color, context;
+        string filename, line, options = "qldhsre";
         while (!finished) {
-            cout << Colors::RESET() << "Choose option (quit='q', list='l', delete='d', hide='h', sort='s', report='r'): ";
+            if (indexList) {
+                color = Colors::GREEN();
+                context = " (quit='q', list='l', delete='d', hide='h', sort='s', report='r', excel='e'): ";
+                options = "qldhsre";
+            } else {
+                color = Colors::MAGENTA();
+                context = " (quit='q', list='l'): ";
+                options = "ql";
+            }
+            cout << Colors::RESET() << color;
+
+            cout << "Choose option " << context;
             getline(cin, line);
             if (line.size() == 0)
                 continue;
@@ -119,12 +122,23 @@ namespace platform {
                 }
                 option = line[0];
             } else {
-                index = stoi(line);
-                if (index >= 0 && index < files.size()) {
-                    report(index);
-                } else {
-                    cout << "Invalid option" << endl;
+                if (all_of(line.begin(), line.end(), ::isdigit)) {
+                    int idx = stoi(line);
+                    if (indexList) {
+                        // The value is about the files list
+                        index = idx;
+                        if (index >= 0 && index < max) {
+                            report(index, false);
+                            indexList = false;
+                            continue;
+                        }
+                    } else {
+                        // The value is about the result showed on screen
+                        showIndex(index, idx);
+                        continue;
+                    }
                 }
+                cout << "Invalid option" << endl;
                 continue;
             }
             switch (option) {
@@ -133,6 +147,7 @@ namespace platform {
                     break;
                 case 'l':
                     show();
+                    indexList = true;
                     break;
                 case 'd':
                     index = getIndex("delete");
@@ -144,6 +159,7 @@ namespace platform {
                     files.erase(files.begin() + index);
                     cout << "File: " + filename + " deleted!" << endl;
                     show();
+                    indexList = true;
                     break;
                 case 'h':
                     index = getIndex("hide");
@@ -155,16 +171,26 @@ namespace platform {
                     files.erase(files.begin() + index);
                     show();
                     menu();
+                    indexList = true;
                     break;
                 case 's':
                     sortList();
+                    indexList = true;
                     show();
                     break;
                 case 'r':
                     index = getIndex("report");
                     if (index == -1)
                         break;
-                    report(index);
+                    indexList = false;
+                    report(index, false);
+                    break;
+                case 'e':
+                    index = getIndex("excel");
+                    if (index == -1)
+                        break;
+                    indexList = true;
+                    report(index, true);
                     break;
                 default:
                     cout << "Invalid option" << endl;
@@ -231,9 +257,13 @@ namespace platform {
             cout << "No results found!" << endl;
             exit(0);
         }
+        sortDate();
         show();
         menu();
-        cout << "Done!" << endl;
+        if (openExcel) {
+            workbook_close(workbook);
+        }
+        cout << Colors::RESET() << "Done!" << endl;
     }
 
 }

src/Platform/Results.h

@@ -1,48 +1,39 @@
 #ifndef RESULTS_H
 #define RESULTS_H
+#include "xlsxwriter.h"
 #include <map>
 #include <vector>
 #include <string>
 #include <nlohmann/json.hpp>
+#include "Result.h"
 namespace platform {
     using namespace std;
     using json = nlohmann::json;
 
-    class Result {
-    public:
-        Result(const string& path, const string& filename);
-        json load() const;
-        string to_string() const;
-        string getFilename() const { return filename; };
-        string getDate() const { return date; };
-        double getScore() const { return score; };
-        string getTitle() const { return title; };
-        double getDuration() const { return duration; };
-        string getModel() const { return model; };
-        string getScoreName() const { return scoreName; };
-    private:
-        string path;
-        string filename;
-        string date;
-        double score;
-        string title;
-        double duration;
-        string model;
-        string scoreName;
-    };
     class Results {
     public:
-        Results(const string& path, const int max, const string& model, const string& score) : path(path), max(max), model(model), scoreName(score) { load(); };
+        Results(const string& path, const int max, const string& model, const string& score, bool complete, bool partial, bool compare) :
+            path(path), max(max), model(model), scoreName(score), complete(complete), partial(partial), compare(compare)
+        {
+            load();
+        };
         void manage();
     private:
         string path;
         int max;
         string model;
         string scoreName;
+        bool complete;
+        bool partial;
+        bool indexList = true;
+        bool openExcel = false;
+        bool compare;
+        lxw_workbook* workbook = NULL;
         vector<Result> files;
         void load(); // Loads the list of results
         void show() const;
-        void report(const int index) const;
+        void report(const int index, const bool excelReport);
+        void showIndex(const int index, const int idx) const;
         int getIndex(const string& intent) const;
         void menu();
         void sortList();

src/Platform/Statistics.cc

@@ -0,0 +1,252 @@
+#include <sstream>
+#include "Statistics.h"
+#include "Colors.h"
+#include "Symbols.h"
+#include <boost/math/distributions/chi_squared.hpp>
+#include <boost/math/distributions/normal.hpp>
+#include "CLocale.h"
+
+
+namespace platform {
+
+    Statistics::Statistics(const vector<string>& models, const vector<string>& datasets, const json& data, double significance, bool output) :
+        models(models), datasets(datasets), data(data), significance(significance), output(output)
+    {
+        nModels = models.size();
+        nDatasets = datasets.size();
+        auto temp = ConfigLocale();
+    };
+
+    void Statistics::fit()
+    {
+        if (nModels < 3 || nDatasets < 3) {
+            cerr << "nModels: " << nModels << endl;
+            cerr << "nDatasets: " << nDatasets << endl;
+            throw runtime_error("Can't make the Friedman test with less than 3 models and/or less than 3 datasets.");
+        }
+        ranksModels.clear();
+        computeRanks();
+        // Set the control model as the one with the lowest average rank
+        controlIdx = distance(ranks.begin(), min_element(ranks.begin(), ranks.end(), [](const auto& l, const auto& r) { return l.second < r.second; }));
+        computeWTL();
+        maxModelName = (*max_element(models.begin(), models.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
+        maxDatasetName = (*max_element(datasets.begin(), datasets.end(), [](const string& a, const string& b) { return a.size() < b.size(); })).size();
+        fitted = true;
+    }
+    map<string, float> assignRanks(vector<pair<string, double>>& ranksOrder)
+    {
+        // sort the ranksOrder vector by value
+        sort(ranksOrder.begin(), ranksOrder.end(), [](const pair<string, double>& a, const pair<string, double>& b) {
+            return a.second > b.second;
+            });
+        //Assign ranks to  values and if they are the same they share the same averaged rank
+        map<string, float> ranks;
+        for (int i = 0; i < ranksOrder.size(); i++) {
+            ranks[ranksOrder[i].first] = i + 1.0;
+        }
+        int i = 0;
+        while (i < static_cast<int>(ranksOrder.size())) {
+            int j = i + 1;
+            int sumRanks = ranks[ranksOrder[i].first];
+            while (j < static_cast<int>(ranksOrder.size()) && ranksOrder[i].second == ranksOrder[j].second) {
+                sumRanks += ranks[ranksOrder[j++].first];
+            }
+            if (j > i + 1) {
+                float averageRank = (float)sumRanks / (j - i);
+                for (int k = i; k < j; k++) {
+                    ranks[ranksOrder[k].first] = averageRank;
+                }
+            }
+            i = j;
+        }
+        return ranks;
+    }
+    void Statistics::computeRanks()
+    {
+        map<string, float> ranksLine;
+        for (const auto& dataset : datasets) {
+            vector<pair<string, double>> ranksOrder;
+            for (const auto& model : models) {
+                double value = data[model].at(dataset).at(0).get<double>();
+                ranksOrder.push_back({ model, value });
+            }
+            // Assign the ranks
+            ranksLine = assignRanks(ranksOrder);
+            // Store the ranks of the dataset
+            ranksModels[dataset] = ranksLine;
+            if (ranks.size() == 0) {
+                ranks = ranksLine;
+            } else {
+                for (const auto& rank : ranksLine) {
+                    ranks[rank.first] += rank.second;
+                }
+            }
+        }
+        // Average the ranks
+        for (const auto& rank : ranks) {
+            ranks[rank.first] /= nDatasets;
+        }
+    }
+    void Statistics::computeWTL()
+    {
+        // Compute the WTL matrix
+        for (int i = 0; i < nModels; ++i) {
+            wtl[i] = { 0, 0, 0 };
+        }
+        json origin = data.begin().value();
+        for (auto const& item : origin.items()) {
+            auto controlModel = models.at(controlIdx);
+            double controlValue = data[controlModel].at(item.key()).at(0).get<double>();
+            for (int i = 0; i < nModels; ++i) {
+                if (i == controlIdx) {
+                    continue;
+                }
+                double value = data[models[i]].at(item.key()).at(0).get<double>();
+                if (value < controlValue) {
+                    wtl[i].win++;
+                } else if (value == controlValue) {
+                    wtl[i].tie++;
+                } else {
+                    wtl[i].loss++;
+                }
+            }
+        }
+    }
+
+    void Statistics::postHocHolmTest(bool friedmanResult)
+    {
+        if (!fitted) {
+            fit();
+        }
+        stringstream oss;
+        // Reference https://link.springer.com/article/10.1007/s44196-022-00083-8
+        // Post-hoc Holm test
+        // Calculate the p-value for the models paired with the control model
+        map<int, double> stats; // p-value of each model paired with the control model
+        boost::math::normal dist(0.0, 1.0);
+        double diff = sqrt(nModels * (nModels + 1) / (6.0 * nDatasets));
+        for (int i = 0; i < nModels; i++) {
+            if (i == controlIdx) {
+                stats[i] = 0.0;
+                continue;
+            }
+            double z = abs(ranks.at(models[controlIdx]) - ranks.at(models[i])) / diff;
+            double p_value = (long double)2 * (1 - cdf(dist, z));
+            stats[i] = p_value;
+        }
+        // Sort the models by p-value
+        vector<pair<int, double>> statsOrder;
+        for (const auto& stat : stats) {
+            statsOrder.push_back({ stat.first, stat.second });
+        }
+        sort(statsOrder.begin(), statsOrder.end(), [](const pair<int, double>& a, const pair<int, double>& b) {
+            return a.second < b.second;
+            });
+
+        // Holm adjustment
+        for (int i = 0; i < statsOrder.size(); ++i) {
+            auto item = statsOrder.at(i);
+            double before = i == 0 ? 0.0 : statsOrder.at(i - 1).second;
+            double p_value = min((double)1.0, item.second * (nModels - i));
+            p_value = max(before, p_value);
+            statsOrder[i] = { item.first, p_value };
+        }
+        holmResult.model = models.at(controlIdx);
+        auto color = friedmanResult ? Colors::CYAN() : Colors::YELLOW();
+        oss << color;
+        oss << "  *************************************************************************************************************" << endl;
+        oss << "  Post-hoc Holm test: H0: 'There is no significant differences between the control model and the other models.'" << endl;
+        oss << "  Control model: " << models.at(controlIdx) << endl;
+        oss << "  " << left << setw(maxModelName) << string("Model") << " p-value      rank      win tie loss Status" << endl;
+        oss << "  " << string(maxModelName, '=') << " ============ ========= === === ==== =============" << endl;
+        // sort ranks from lowest to highest
+        vector<pair<string, float>> ranksOrder;
+        for (const auto& rank : ranks) {
+            ranksOrder.push_back({ rank.first, rank.second });
+        }
+        sort(ranksOrder.begin(), ranksOrder.end(), [](const pair<string, float>& a, const pair<string, float>& b) {
+            return a.second < b.second;
+            });
+        // Show the control model info.
+        oss << "  " << Colors::BLUE() << left << setw(maxModelName) << ranksOrder.at(0).first << " ";
+        oss << setw(12) << " " << setprecision(7) << fixed << " " << ranksOrder.at(0).second << endl;
+        for (const auto& item : ranksOrder) {
+            auto idx = distance(models.begin(), find(models.begin(), models.end(), item.first));
+            double pvalue = 0.0;
+            for (const auto& stat : statsOrder) {
+                if (stat.first == idx) {
+                    pvalue = stat.second;
+                }
+            }
+            holmResult.holmLines.push_back({ item.first, pvalue, item.second, wtl.at(idx), pvalue < significance });
+            if (item.first == models.at(controlIdx)) {
+                continue;
+            }
+            auto colorStatus = pvalue > significance ? Colors::GREEN() : Colors::MAGENTA();
+            auto status = pvalue > significance ? Symbols::check_mark : Symbols::cross;
+            auto textStatus = pvalue > significance ? " accepted H0" : " rejected H0";
+            oss << "  " << colorStatus << left << setw(maxModelName) << item.first << " ";
+            oss << setprecision(6) << scientific << pvalue << setprecision(7) << fixed << " " << item.second;
+            oss << " " << right << setw(3) << wtl.at(idx).win << " " << setw(3) << wtl.at(idx).tie << " " << setw(4) << wtl.at(idx).loss;
+            oss << " " << status << textStatus << endl;
+        }
+        oss << color << "  *************************************************************************************************************" << endl;
+        oss << Colors::RESET();
+        if (output) {
+            cout << oss.str();
+        }
+    }
+    bool Statistics::friedmanTest()
+    {
+        if (!fitted) {
+            fit();
+        }
+        stringstream oss;
+        // Friedman test
+        // Calculate the Friedman statistic
+        oss << Colors::BLUE() << endl;
+        oss << "***************************************************************************************************************" << endl;
+        oss << Colors::GREEN() << "Friedman test: H0: 'There is no significant differences between all the classifiers.'" << Colors::BLUE() << endl;
+        double degreesOfFreedom = nModels - 1.0;
+        double sumSquared = 0;
+        for (const auto& rank : ranks) {
+            sumSquared += pow(rank.second, 2);
+        }
+        // Compute the Friedman statistic as in https://link.springer.com/article/10.1007/s44196-022-00083-8
+        double friedmanQ = 12.0 * nDatasets / (nModels * (nModels + 1)) * (sumSquared - (nModels * pow(nModels + 1, 2)) / 4);
+        // Calculate the critical value
+        boost::math::chi_squared chiSquared(degreesOfFreedom);
+        long double p_value = (long double)1.0 - cdf(chiSquared, friedmanQ);
+        double criticalValue = quantile(chiSquared, 1 - significance);
+        oss << "Friedman statistic: " << friedmanQ << endl;
+        oss << "Critical χ2 Value for df=" << fixed << (int)degreesOfFreedom
+            << " and alpha=" << setprecision(2) << fixed << significance << ": " << setprecision(7) << scientific << criticalValue << std::endl;
+        oss << "p-value: " << scientific << p_value << " is " << (p_value < significance ? "less" : "greater") << " than " << setprecision(2) << fixed << significance << endl;
+        bool result;
+        if (p_value < significance) {
+            oss << Colors::GREEN() << "The null hypothesis H0 is rejected." << endl;
+            result = true;
+        } else {
+            oss << Colors::YELLOW() << "The null hypothesis H0 is accepted. Computed p-values will not be significant." << endl;
+            result = false;
+        }
+        oss << Colors::BLUE() << "***************************************************************************************************************" << Colors::RESET() << endl;
+        if (output) {
+            cout << oss.str();
+        }
+        friedmanResult = { friedmanQ, criticalValue, p_value, result };
+        return result;
+    }
+    FriedmanResult& Statistics::getFriedmanResult()
+    {
+        return friedmanResult;
+    }
+    HolmResult& Statistics::getHolmResult()
+    {
+        return holmResult;
+    }
+    map<string, map<string, float>>& Statistics::getRanks()
+    {
+        return ranksModels;
+    }
+} // namespace platform

src/Platform/Statistics.h

@@ -0,0 +1,64 @@
+#ifndef STATISTICS_H
+#define STATISTICS_H
+#include <iostream>
+#include <vector>
+#include <map>
+#include <nlohmann/json.hpp>
+
+using namespace std;
+using json = nlohmann::json;
+
+namespace platform {
+    struct WTL {
+        int win;
+        int tie;
+        int loss;
+    };
+    struct FriedmanResult {
+        double statistic;
+        double criticalValue;
+        long double pvalue;
+        bool reject;
+    };
+    struct HolmLine {
+        string model;
+        long double pvalue;
+        double rank;
+        WTL wtl;
+        bool reject;
+    };
+    struct HolmResult {
+        string model;
+        vector<HolmLine> holmLines;
+    };
+    class Statistics {
+    public:
+        Statistics(const vector<string>& models, const vector<string>& datasets, const json& data, double significance = 0.05, bool output = true);
+        bool friedmanTest();
+        void postHocHolmTest(bool friedmanResult);
+        FriedmanResult& getFriedmanResult();
+        HolmResult& getHolmResult();
+        map<string, map<string, float>>& getRanks();
+    private:
+        void fit();
+        void computeRanks();
+        void computeWTL();
+        const vector<string>& models;
+        const vector<string>& datasets;
+        const json& data;
+        double significance;
+        bool output;
+        bool fitted = false;
+        int nModels = 0;
+        int nDatasets = 0;
+        int controlIdx = 0;
+        map<int, WTL> wtl;
+        map<string, float> ranks;
+        int maxModelName = 0;
+        int maxDatasetName = 0;
+        FriedmanResult friedmanResult;
+        HolmResult holmResult;
+        map<string, map<string, float>> ranksModels;
+    };
+}
+#endif // !STATISTICS_H

src/Platform/Symbols.h

@@ -0,0 +1,18 @@
+#ifndef SYMBOLS_H
+#define SYMBOLS_H
+#include <string>
+using namespace std;
+namespace platform {
+    class Symbols {
+    public:
+        inline static const string check_mark{ "\u2714" };
+        inline static const string exclamation{ "\u2757" };
+        inline static const string black_star{ "\u2605" };
+        inline static const string cross{ "\u2717" };
+        inline static const string upward_arrow{ "\u27B6" };
+        inline static const string down_arrow{ "\u27B4" };
+        inline static const string equal_best{ check_mark };
+        inline static const string better_best{ black_star };
+    };
+}
+#endif // !SYMBOLS_H

src/Platform/Utils.h

@@ -0,0 +1,19 @@
+#ifndef UTILS_H
+#define UTILS_H
+#include <sstream>
+#include <string>
+#include <vector>
+namespace platform {
+    //static vector<string> split(const string& text, char delimiter);
+    static std::vector<std::string> split(const std::string& text, char delimiter)
+    {
+        std::vector<std::string> result;
+        std::stringstream ss(text);
+        std::string token;
+        while (std::getline(ss, token, delimiter)) {
+            result.push_back(token);
+        }
+        return result;
+    }
+}
+#endif

src/Platform/best.cc

@@ -0,0 +1,95 @@
+#include <iostream>
+#include <argparse/argparse.hpp>
+#include "Paths.h"
+#include "BestResults.h"
+#include "Colors.h"
+
+using namespace std;
+
+argparse::ArgumentParser manageArguments(int argc, char** argv)
+{
+    argparse::ArgumentParser program("best");
+    program.add_argument("-m", "--model").default_value("").help("Filter results of the selected model) (any for all models)");
+    program.add_argument("-s", "--score").default_value("").help("Filter results of the score name supplied");
+    program.add_argument("--build").help("build best score results file").default_value(false).implicit_value(true);
+    program.add_argument("--report").help("report of best score results file").default_value(false).implicit_value(true);
+    program.add_argument("--friedman").help("Friedman test").default_value(false).implicit_value(true);
+    program.add_argument("--excel").help("Output to excel").default_value(false).implicit_value(true);
+    program.add_argument("--level").help("significance level").default_value(0.05).scan<'g', double>().action([](const string& value) {
+        try {
+            auto k = stod(value);
+            if (k < 0.01 || k > 0.15) {
+                throw runtime_error("Significance level hast to be a number in [0.01, 0.15]");
+            }
+            return k;
+        }
+        catch (const runtime_error& err) {
+            throw runtime_error(err.what());
+        }
+        catch (...) {
+            throw runtime_error("Number of folds must be an decimal number");
+        }});
+    try {
+        program.parse_args(argc, argv);
+        auto model = program.get<string>("model");
+        auto score = program.get<string>("score");
+        auto build = program.get<bool>("build");
+        auto report = program.get<bool>("report");
+        auto friedman = program.get<bool>("friedman");
+        auto excel = program.get<bool>("excel");
+        auto level = program.get<double>("level");
+        if (model == "" || score == "") {
+            throw runtime_error("Model and score name must be supplied");
+        }
+        if (friedman && model != "any") {
+            cerr << "Friedman test can only be used with all models" << endl;
+            cerr << program;
+            exit(1);
+        }
+        if (excel && model != "any") {
+            cerr << "Excel ourput can only be used with all models" << endl;
+            cerr << program;
+            exit(1);
+        }
+        if (!report && !build) {
+            cerr << "Either build, report or both, have to be selected to do anything!" << endl;
+            cerr << program;
+            exit(1);
+        }
+    }
+    catch (const exception& err) {
+        cerr << err.what() << endl;
+        cerr << program;
+        exit(1);
+    }
+    return program;
+}
+
+int main(int argc, char** argv)
+{
+    auto program = manageArguments(argc, argv);
+    auto model = program.get<string>("model");
+    auto score = program.get<string>("score");
+    auto build = program.get<bool>("build");
+    auto report = program.get<bool>("report");
+    auto friedman = program.get<bool>("friedman");
+    auto excel = program.get<bool>("excel");
+    auto level = program.get<double>("level");
+    auto results = platform::BestResults(platform::Paths::results(), score, model, friedman, level);
+    if (build) {
+        if (model == "any") {
+            results.buildAll();
+        } else {
+            string fileName = results.build();
+            cout << Colors::GREEN() << fileName << " created!" << Colors::RESET() << endl;
+        }
+    }
+    if (report) {
+        if (model == "any") {
+            results.reportAll(excel);
+        } else {
+            results.reportSingle();
+        }
+    }
+    return 0;
+}