Add notes to Classifier & Changelog

Remove other projects' sources

.clang-tidy

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

.gitignore

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

.gitmodules

@@ -1,12 +1,18 @@
 [submodule "lib/mdlp"]
 	path = lib/mdlp
 	url = https://github.com/rmontanana/mdlp
+	main = main
+	update = merge
 [submodule "lib/catch2"]
 	path = lib/catch2
+        main  = v2.x
+	update = merge
 	url = https://github.com/catchorg/Catch2.git
-[submodule "lib/argparse"]
-	path = lib/argparse
-	url = https://github.com/p-ranav/argparse
 [submodule "lib/json"]
 	path = lib/json
 	url = https://github.com/nlohmann/json.git
+        master = master
+	update = merge
+[submodule "lib/folding"]
+	path = lib/folding
+	url = https://github.com/rmontanana/folding

.vscode/c_cpp_properties.json

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

.vscode/launch.json

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

.vscode/settings.json

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

.vscode/tasks.json

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

CHANGELOG.md

@@ -0,0 +1,23 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.0.1] - 2024-02-12
+
+### Added
+
+- Notes in Classifier class
+- BoostAODE: Add note with used features in initialization with feature selection
+- BoostAODE: Add note with the number of models
+- BoostAODE: Add note with the number of features used to create models if not all features are used
+- Test version number in TestBayesModels
+- Add tests with feature_select and notes on BoostAODE
+
+### Fixed
+
+- Network predict test
+- Network predict_proba test
+- Network score test

CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(BayesNet
-  VERSION 0.1.0
+  VERSION 1.0.1
   DESCRIPTION "Bayesian Network and basic classifiers Library."
   HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
   LANGUAGES CXX
@@ -24,7 +24,7 @@ set(CMAKE_CXX_STANDARD_REQUIRED            ON)
 set(CMAKE_CXX_EXTENSIONS                  OFF)
 set(CMAKE_EXPORT_COMPILE_COMMANDS          ON)
 set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${TORCH_CXX_FLAGS}")
-
+SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -pthread")
 # Options
 # -------
 option(ENABLE_CLANG_TIDY "Enable to add clang tidy."              OFF)
@@ -34,14 +34,13 @@ option(CODE_COVERAGE "Collect coverage from test library"         OFF)
 # CMakes modules
 # --------------
 set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
-
 include(AddGitSubmodule)
+
 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)
 
@@ -53,7 +52,6 @@ endif (ENABLE_CLANG_TIDY)
 # ---------------------------------------------
 # include(FetchContent)
 add_git_submodule("lib/mdlp")
-add_git_submodule("lib/argparse")
 add_git_submodule("lib/json")
 
 # Subdirectories
@@ -61,12 +59,9 @@ add_git_submodule("lib/json")
 add_subdirectory(config)
 add_subdirectory(lib/Files)
 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)
 
 # Testing
 # -------
@@ -74,7 +69,6 @@ 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 buildr buildd test clean debug release
+
+f_release = build_release
+f_debug = build_debug
+app_targets = BayesNet
+test_targets = unit_tests_bayesnet 
+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 \
@@ -12,48 +32,54 @@ setup: ## Install dependencies for tests and coverage
 	fi
 
 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";
 
 debug: ## Build a debug version of the project
 	@echo ">>> Building Debug BayesNet...";
-	@if [ -d ./build ]; then rm -rf ./build; fi
-	@mkdir build; 
-	cmake -S . -B build -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CODE_COVERAGE=ON; \
-	cmake --build build -j 32;
+	@if [ -d ./$(f_debug) ]; then rm -rf ./$(f_debug); fi
+	@mkdir $(f_debug); 
+	@cmake -S . -B $(f_debug) -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CODE_COVERAGE=ON
 	@echo ">>> Done";
 
 release: ## Build a Release version of the project
 	@echo ">>> Building Release BayesNet...";
-	@if [ -d ./build ]; then rm -rf ./build; fi
-	@mkdir build; 
-	cmake -S . -B build -D CMAKE_BUILD_TYPE=Release; \
-	cmake --build build -t main -t BayesNetSample -j 32;
+	@if [ -d ./$(f_release) ]; then rm -rf ./$(f_release); fi
+	@mkdir $(f_release); 
+	@cmake -S . -B $(f_release) -D CMAKE_BUILD_TYPE=Release
 	@echo ">>> Done";	
 
-test: ## Run tests
-	@echo "* Running tests...";
-	find . -name "*.gcda" -print0 | xargs -0 rm
-	@cd build; \
-	cmake --build . --target unit_tests ;
-	@cd build/tests; \
-	./unit_tests;
+opt = ""
+test: ## Run tests (opt="-s") to verbose output the tests, (opt="-c='Test Maximum Spanning Tree'") to run only that section
+	@echo ">>> Running BayesNet & Platform tests...";
+	@$(MAKE) clean
+	@cmake --build $(f_debug) -t $(test_targets) $(n_procs)
+	@for t in $(test_targets); do \
+		if [ -f $(f_debug)/tests/$$t ]; then \
+			cd $(f_debug)/tests ; \
+			./$$t $(opt) ; \
+		fi ; \
+	done
+	@echo ">>> Done";
 
 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
+	@gcovr $(f_debug)/tests
+	@echo ">>> Done";	
+
 
 help: ## Show help message
 	@IFS=$$'\n' ; \

README.md

@@ -1,5 +1,22 @@
 # BayesNet
 
-Bayesian Network Classifier with libtorch from scratch
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+Bayesian Network Classifiers using libtorch from scratch
+
+### Release
+
+```bash
+make release
+make buildr
+```
+
+### Debug & Tests
+
+```bash
+make debug
+make test
+make coverage
+```
 
 ## 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 }

config/config.h.in

@@ -11,3 +11,4 @@ static constexpr std::string_view project_name = " @PROJECT_NAME@ ";
 static constexpr std::string_view project_version = "@PROJECT_VERSION@";
 static constexpr std::string_view project_description = "@PROJECT_DESCRIPTION@";
 static constexpr std::string_view git_sha = "@GIT_SHA@";
+static constexpr std::string_view data_path = "@BayesNet_SOURCE_DIR@/tests/data/";

data/_TAN_cpp_accuracy__.json

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

data/glass.net

@@ -1,25 +0,0 @@
-Type Si
-Type Fe
-Type RI
-Type Na
-Type Ba
-Type Ca
-Type Al
-Type K
-Type Mg
-Fe RI
-Fe Ba
-Fe Ca
-RI Na
-RI Ba
-RI Ca
-RI Al
-RI K
-RI Mg
-Ba Ca
-Ba Al
-Ca Al
-Ca K
-Ca Mg
-Al K
-K Mg

data/mfeat-factors-kdb2.net

@@ -1,645 +0,0 @@
-class att215
-class att25
-class att131
-class att95
-class att122
-class att17
-class att28
-class att5
-class att121
-class att214
-class att197
-class att116
-class att182
-class att60
-class att168
-class att178
-class att206
-class att89
-class att77
-class att209
-class att73
-class att126
-class att16
-class att74
-class att27
-class att61
-class att20
-class att101
-class att85
-class att76
-class att137
-class att211
-class att143
-class att14
-class att40
-class att210
-class att155
-class att170
-class att160
-class att23
-class att162
-class att203
-class att164
-class att107
-class att62
-class att42
-class att71
-class att128
-class att138
-class att83
-class att171
-class att92
-class att163
-class att49
-class att161
-class att158
-class att176
-class att11
-class att145
-class att4
-class att172
-class att196
-class att58
-class att68
-class att169
-class att80
-class att32
-class att175
-class att87
-class att88
-class att159
-class att18
-class att52
-class att98
-class att136
-class att150
-class att156
-class att110
-class att100
-class att63
-class att148
-class att90
-class att167
-class att35
-class att205
-class att51
-class att21
-class att142
-class att46
-class att134
-class att39
-class att102
-class att208
-class att130
-class att149
-class att96
-class att75
-class att118
-class att78
-class att213
-class att112
-class att38
-class att174
-class att189
-class att70
-class att179
-class att59
-class att79
-class att15
-class att47
-class att124
-class att34
-class att54
-class att191
-class att86
-class att56
-class att151
-class att66
-class att173
-class att44
-class att198
-class att139
-class att216
-class att129
-class att152
-class att69
-class att81
-class att50
-class att153
-class att41
-class att204
-class att188
-class att26
-class att13
-class att117
-class att114
-class att10
-class att64
-class att200
-class att9
-class att3
-class att119
-class att45
-class att104
-class att140
-class att30
-class att183
-class att146
-class att141
-class att202
-class att194
-class att24
-class att147
-class att8
-class att212
-class att123
-class att166
-class att187
-class att127
-class att190
-class att105
-class att106
-class att184
-class att82
-class att2
-class att135
-class att154
-class att111
-class att115
-class att99
-class att22
-class att84
-class att207
-class att94
-class att177
-class att103
-class att93
-class att201
-class att43
-class att36
-class att12
-class att125
-class att165
-class att180
-class att195
-class att157
-class att48
-class att6
-class att113
-class att193
-class att91
-class att72
-class att31
-class att132
-class att33
-class att57
-class att144
-class att192
-class att185
-class att37
-class att53
-class att120
-class att186
-class att199
-class att65
-class att108
-class att133
-class att29
-class att19
-class att7
-class att97
-class att67
-class att55
-class att1
-class att109
-class att181
-att215 att25
-att215 att131
-att215 att95
-att25 att131
-att25 att121
-att25 att73
-att25 att61
-att25 att85
-att25 att169
-att25 att13
-att131 att95
-att131 att122
-att131 att17
-att131 att28
-att131 att121
-att131 att214
-att131 att116
-att131 att126
-att131 att143
-att95 att122
-att95 att17
-att95 att28
-att95 att5
-att95 att214
-att95 att116
-att95 att60
-att95 att143
-att95 att155
-att95 att71
-att122 att182
-att122 att170
-att17 att5
-att17 att197
-att17 att89
-att17 att77
-att17 att161
-att28 att206
-att28 att16
-att28 att76
-att28 att172
-att28 att124
-att28 att64
-att5 att197
-att5 att89
-att5 att209
-att121 att73
-att214 att178
-att214 att58
-att214 att142
-att197 att209
-att197 att101
-att116 att182
-att116 att60
-att116 att168
-att116 att178
-att116 att206
-att116 att126
-att116 att16
-att116 att27
-att116 att20
-att116 att211
-att116 att164
-att116 att128
-att182 att27
-att182 att14
-att60 att168
-att60 att156
-att168 att156
-att168 att96
-att178 att20
-att178 att58
-att178 att142
-att178 att130
-att206 att74
-att206 att170
-att206 att158
-att89 att77
-att89 att137
-att89 att149
-att89 att173
-att77 att137
-att77 att161
-att209 att101
-att209 att41
-att73 att61
-att73 att157
-att126 att162
-att126 att138
-att126 att150
-att16 att74
-att16 att76
-att16 att40
-att16 att4
-att74 att14
-att74 att62
-att27 att171
-att61 att85
-att61 att169
-att20 att211
-att20 att210
-att20 att164
-att20 att176
-att101 att41
-att85 att13
-att76 att40
-att76 att160
-att137 att149
-att211 att210
-att211 att162
-att211 att171
-att211 att163
-att211 att175
-att211 att79
-att143 att155
-att143 att23
-att143 att71
-att143 att83
-att143 att11
-att14 att98
-att40 att160
-att40 att4
-att40 att196
-att40 att52
-att210 att42
-att210 att114
-att155 att23
-att155 att203
-att155 att107
-att155 att11
-att170 att158
-att160 att52
-att23 att203
-att162 att138
-att162 att18
-att162 att150
-att162 att90
-att162 att174
-att203 att107
-att203 att49
-att203 att59
-att203 att191
-att203 att119
-att164 att62
-att164 att42
-att164 att128
-att164 att92
-att164 att163
-att164 att176
-att164 att145
-att164 att68
-att164 att80
-att164 att98
-att164 att110
-att164 att205
-att164 att21
-att164 att213
-att164 att112
-att164 att38
-att164 att56
-att164 att44
-att107 att59
-att107 att47
-att107 att191
-att71 att83
-att71 att167
-att71 att35
-att128 att92
-att138 att18
-att83 att167
-att171 att87
-att171 att159
-att171 att63
-att171 att51
-att171 att39
-att171 att75
-att163 att49
-att163 att175
-att163 att87
-att163 att79
-att163 att151
-att163 att139
-att163 att187
-att163 att91
-att161 att173
-att176 att145
-att176 att172
-att176 att68
-att176 att80
-att176 att32
-att176 att110
-att176 att205
-att176 att21
-att176 att134
-att176 att56
-att4 att196
-att4 att88
-att4 att136
-att4 att100
-att4 att148
-att4 att208
-att172 att112
-att172 att184
-att196 att88
-att196 att136
-att196 att100
-att196 att208
-att58 att46
-att68 att32
-att32 att200
-att87 att159
-att87 att63
-att87 att75
-att87 att15
-att87 att99
-att159 att195
-att18 att90
-att18 att102
-att18 att78
-att18 att198
-att52 att124
-att98 att86
-att150 att174
-att150 att66
-att156 att96
-att156 att216
-att156 att204
-att156 att24
-att156 att84
-att100 att148
-att63 att51
-att63 att3
-att63 att183
-att90 att102
-att90 att78
-att167 att35
-att167 att179
-att35 att179
-att51 att39
-att51 att3
-att21 att134
-att21 att213
-att21 att38
-att21 att189
-att21 att129
-att21 att81
-att21 att117
-att21 att9
-att142 att46
-att142 att130
-att142 att118
-att142 att10
-att142 att202
-att142 att190
-att142 att106
-att46 att70
-att46 att34
-att46 att166
-att134 att2
-att102 att54
-att130 att118
-att130 att10
-att130 att202
-att149 att125
-att96 att216
-att96 att24
-att75 att15
-att75 att99
-att118 att70
-att78 att198
-att213 att189
-att38 att50
-att38 att26
-att174 att54
-att174 att66
-att174 att30
-att189 att86
-att189 att129
-att189 att69
-att189 att81
-att189 att153
-att189 att117
-att189 att9
-att189 att45
-att189 att105
-att70 att34
-att59 att47
-att79 att151
-att79 att139
-att79 att187
-att79 att127
-att79 att103
-att79 att43
-att79 att91
-att79 att19
-att124 att64
-att54 att114
-att54 att30
-att191 att119
-att86 att194
-att56 att44
-att56 att152
-att56 att50
-att56 att188
-att56 att26
-att56 att104
-att56 att140
-att56 att146
-att56 att194
-att56 att8
-att56 att2
-att56 att133
-att56 att1
-att173 att125
-att173 att113
-att44 att152
-att44 att188
-att44 att200
-att44 att212
-att44 att1
-att139 att103
-att139 att43
-att139 att31
-att139 att199
-att139 att7
-att216 att204
-att216 att36
-att216 att12
-att216 att180
-att216 att108
-att129 att69
-att152 att140
-att69 att153
-att81 att45
-att153 att141
-att41 att53
-att204 att12
-att13 att157
-att114 att6
-att114 att186
-att10 att190
-att64 att184
-att200 att104
-att9 att146
-att9 att141
-att9 att177
-att9 att37
-att9 att133
-att9 att109
-att9 att181
-att3 att183
-att3 att147
-att3 att123
-att3 att135
-att3 att111
-att45 att105
-att45 att177
-att45 att93
-att45 att201
-att45 att193
-att45 att37
-att45 att97
-att140 att8
-att30 att6
-att183 att147
-att183 att123
-att202 att166
-att202 att106
-att202 att82
-att24 att84
-att24 att36
-att147 att135
-att8 att212
-att166 att82
-att187 att127
-att187 att115
-att127 att115
-att105 att93
-att106 att154
-att82 att154
-att82 att22
-att135 att111
-att135 att207
-att154 att22
-att154 att94
-att111 att207
-att22 att94
-att84 att48
-att177 att165
-att103 att195
-att103 att109
-att93 att201
-att93 att165
-att93 att193
-att93 att33
-att201 att33
-att201 att57
-att36 att180
-att36 att72
-att36 att132
-att36 att144
-att125 att113
-att125 att185
-att125 att65
-att125 att29
-att180 att48
-att180 att72
-att180 att192
-att180 att108
-att6 att186
-att113 att185
-att113 att53
-att193 att97
-att91 att31
-att91 att19
-att72 att132
-att72 att192
-att31 att199
-att31 att67
-att132 att144
-att132 att120
-att33 att57
-att144 att120
-att185 att65
-att199 att7
-att199 att67
-att199 att55
-att65 att29
-att67 att55
-att109 att181

data/mfeat-factors-kdb3.net

@@ -1,859 +0,0 @@
-class att215
-class att25
-class att131
-class att95
-class att122
-class att17
-class att28
-class att5
-class att121
-class att214
-class att197
-class att116
-class att182
-class att60
-class att168
-class att178
-class att206
-class att89
-class att77
-class att209
-class att73
-class att126
-class att16
-class att74
-class att27
-class att61
-class att20
-class att101
-class att85
-class att76
-class att137
-class att211
-class att143
-class att14
-class att40
-class att210
-class att155
-class att170
-class att160
-class att23
-class att162
-class att203
-class att164
-class att107
-class att62
-class att42
-class att71
-class att128
-class att138
-class att83
-class att171
-class att92
-class att163
-class att49
-class att161
-class att158
-class att176
-class att11
-class att145
-class att4
-class att172
-class att196
-class att58
-class att68
-class att169
-class att80
-class att32
-class att175
-class att87
-class att88
-class att159
-class att18
-class att52
-class att98
-class att136
-class att150
-class att156
-class att110
-class att100
-class att63
-class att148
-class att90
-class att167
-class att35
-class att205
-class att51
-class att21
-class att142
-class att46
-class att134
-class att39
-class att102
-class att208
-class att130
-class att149
-class att96
-class att75
-class att118
-class att78
-class att213
-class att112
-class att38
-class att174
-class att189
-class att70
-class att179
-class att59
-class att79
-class att15
-class att47
-class att124
-class att34
-class att54
-class att191
-class att86
-class att56
-class att151
-class att66
-class att173
-class att44
-class att198
-class att139
-class att216
-class att129
-class att152
-class att69
-class att81
-class att50
-class att153
-class att41
-class att204
-class att188
-class att26
-class att13
-class att117
-class att114
-class att10
-class att64
-class att200
-class att9
-class att3
-class att119
-class att45
-class att104
-class att140
-class att30
-class att183
-class att146
-class att141
-class att202
-class att194
-class att24
-class att147
-class att8
-class att212
-class att123
-class att166
-class att187
-class att127
-class att190
-class att105
-class att106
-class att184
-class att82
-class att2
-class att135
-class att154
-class att111
-class att115
-class att99
-class att22
-class att84
-class att207
-class att94
-class att177
-class att103
-class att93
-class att201
-class att43
-class att36
-class att12
-class att125
-class att165
-class att180
-class att195
-class att157
-class att48
-class att6
-class att113
-class att193
-class att91
-class att72
-class att31
-class att132
-class att33
-class att57
-class att144
-class att192
-class att185
-class att37
-class att53
-class att120
-class att186
-class att199
-class att65
-class att108
-class att133
-class att29
-class att19
-class att7
-class att97
-class att67
-class att55
-class att1
-class att109
-class att181
-att215 att25
-att215 att131
-att215 att95
-att215 att17
-att215 att214
-att215 att143
-att25 att131
-att25 att95
-att25 att122
-att25 att121
-att25 att73
-att25 att61
-att25 att85
-att25 att169
-att25 att13
-att25 att157
-att131 att95
-att131 att122
-att131 att17
-att131 att28
-att131 att5
-att131 att121
-att131 att214
-att131 att116
-att131 att182
-att131 att60
-att131 att126
-att131 att16
-att131 att27
-att131 att20
-att131 att143
-att131 att155
-att95 att122
-att95 att17
-att95 att28
-att95 att5
-att95 att121
-att95 att214
-att95 att197
-att95 att116
-att95 att60
-att95 att168
-att95 att178
-att95 att143
-att95 att155
-att95 att23
-att95 att71
-att95 att167
-att122 att28
-att122 att182
-att122 att170
-att17 att5
-att17 att197
-att17 att89
-att17 att77
-att17 att209
-att17 att137
-att17 att161
-att17 att41
-att28 att206
-att28 att16
-att28 att76
-att28 att40
-att28 att210
-att28 att160
-att28 att172
-att28 att124
-att28 att64
-att5 att197
-att5 att89
-att5 att77
-att5 att209
-att5 att101
-att121 att73
-att121 att61
-att214 att116
-att214 att178
-att214 att206
-att214 att58
-att214 att142
-att214 att46
-att197 att89
-att197 att209
-att197 att101
-att116 att182
-att116 att60
-att116 att168
-att116 att178
-att116 att206
-att116 att73
-att116 att126
-att116 att16
-att116 att74
-att116 att27
-att116 att20
-att116 att211
-att116 att164
-att116 att128
-att116 att92
-att116 att176
-att116 att68
-att182 att27
-att182 att14
-att60 att168
-att60 att156
-att60 att96
-att168 att126
-att168 att156
-att168 att96
-att168 att216
-att178 att20
-att178 att211
-att178 att58
-att178 att142
-att178 att130
-att178 att166
-att206 att74
-att206 att170
-att206 att158
-att89 att77
-att89 att137
-att89 att149
-att89 att173
-att77 att137
-att77 att161
-att77 att149
-att209 att101
-att209 att41
-att73 att61
-att73 att85
-att73 att13
-att73 att157
-att126 att162
-att126 att138
-att126 att18
-att126 att150
-att16 att74
-att16 att76
-att16 att40
-att16 att4
-att16 att196
-att16 att136
-att74 att14
-att74 att62
-att27 att171
-att27 att63
-att61 att85
-att61 att169
-att20 att76
-att20 att211
-att20 att210
-att20 att170
-att20 att164
-att20 att128
-att20 att176
-att20 att80
-att101 att41
-att85 att169
-att85 att13
-att76 att14
-att76 att40
-att76 att160
-att76 att4
-att76 att52
-att137 att161
-att137 att149
-att137 att173
-att137 att125
-att211 att210
-att211 att162
-att211 att164
-att211 att62
-att211 att42
-att211 att171
-att211 att163
-att211 att175
-att211 att79
-att211 att151
-att211 att43
-att143 att155
-att143 att23
-att143 att203
-att143 att71
-att143 att83
-att143 att11
-att14 att98
-att40 att160
-att40 att4
-att40 att196
-att40 att88
-att40 att52
-att210 att162
-att210 att42
-att210 att114
-att155 att23
-att155 att203
-att155 att107
-att155 att11
-att170 att158
-att160 att52
-att160 att124
-att23 att203
-att23 att107
-att23 att71
-att23 att11
-att162 att138
-att162 att18
-att162 att150
-att162 att90
-att162 att102
-att162 att174
-att162 att66
-att203 att107
-att203 att49
-att203 att59
-att203 att47
-att203 att191
-att203 att119
-att164 att62
-att164 att42
-att164 att128
-att164 att171
-att164 att92
-att164 att163
-att164 att158
-att164 att176
-att164 att145
-att164 att172
-att164 att58
-att164 att68
-att164 att80
-att164 att32
-att164 att98
-att164 att156
-att164 att110
-att164 att205
-att164 att21
-att164 att134
-att164 att213
-att164 att112
-att164 att38
-att164 att189
-att164 att56
-att164 att44
-att164 att152
-att164 att8
-att107 att83
-att107 att49
-att107 att59
-att107 att47
-att107 att191
-att42 att138
-att42 att54
-att42 att114
-att71 att83
-att71 att167
-att71 att35
-att71 att179
-att128 att92
-att128 att112
-att138 att18
-att138 att150
-att83 att167
-att83 att35
-att171 att87
-att171 att159
-att171 att63
-att171 att51
-att171 att39
-att171 att75
-att92 att163
-att92 att145
-att92 att56
-att163 att49
-att163 att175
-att163 att87
-att163 att79
-att163 att151
-att163 att139
-att163 att187
-att163 att127
-att163 att103
-att163 att91
-att49 att37
-att161 att173
-att161 att113
-att176 att145
-att176 att172
-att176 att68
-att176 att80
-att176 att32
-att176 att175
-att176 att98
-att176 att110
-att176 att205
-att176 att21
-att176 att134
-att176 att213
-att176 att56
-att4 att196
-att4 att88
-att4 att136
-att4 att100
-att4 att148
-att4 att208
-att172 att112
-att172 att184
-att196 att88
-att196 att136
-att196 att100
-att196 att148
-att196 att208
-att58 att142
-att58 att46
-att58 att34
-att68 att32
-att80 att38
-att32 att110
-att32 att21
-att32 att44
-att32 att200
-att175 att87
-att175 att159
-att175 att79
-att175 att187
-att175 att115
-att87 att159
-att87 att63
-att87 att51
-att87 att75
-att87 att15
-att87 att99
-att159 att75
-att159 att15
-att159 att195
-att18 att90
-att18 att102
-att18 att78
-att18 att198
-att52 att124
-att52 att64
-att98 att86
-att136 att100
-att136 att208
-att150 att90
-att150 att174
-att150 att66
-att156 att205
-att156 att96
-att156 att216
-att156 att204
-att156 att24
-att156 att84
-att156 att36
-att156 att12
-att156 att108
-att100 att148
-att63 att51
-att63 att39
-att63 att3
-att63 att183
-att63 att147
-att90 att102
-att90 att78
-att167 att35
-att167 att179
-att35 att179
-att51 att39
-att51 att3
-att51 att183
-att21 att134
-att21 att213
-att21 att38
-att21 att189
-att21 att129
-att21 att81
-att21 att153
-att21 att117
-att21 att9
-att142 att46
-att142 att130
-att142 att118
-att142 att70
-att142 att10
-att142 att202
-att142 att190
-att142 att106
-att46 att130
-att46 att118
-att46 att70
-att46 att34
-att46 att166
-att46 att82
-att134 att2
-att39 att3
-att102 att78
-att102 att174
-att102 att54
-att102 att198
-att130 att118
-att130 att10
-att130 att202
-att130 att190
-att130 att106
-att149 att125
-att96 att216
-att96 att204
-att96 att24
-att75 att15
-att75 att99
-att118 att70
-att118 att10
-att118 att202
-att78 att198
-att213 att189
-att213 att129
-att213 att69
-att213 att81
-att38 att50
-att38 att26
-att174 att54
-att174 att66
-att174 att30
-att189 att86
-att189 att129
-att189 att69
-att189 att81
-att189 att153
-att189 att117
-att189 att9
-att189 att45
-att189 att141
-att189 att105
-att70 att34
-att70 att154
-att179 att59
-att59 att47
-att59 att191
-att59 att119
-att79 att86
-att79 att151
-att79 att139
-att79 att187
-att79 att127
-att79 att103
-att79 att43
-att79 att193
-att79 att91
-att79 att19
-att124 att64
-att54 att114
-att54 att30
-att54 att6
-att191 att119
-att86 att194
-att56 att44
-att56 att152
-att56 att50
-att56 att188
-att56 att26
-att56 att200
-att56 att104
-att56 att140
-att56 att146
-att56 att194
-att56 att8
-att56 att2
-att56 att133
-att56 att1
-att151 att139
-att66 att30
-att173 att125
-att173 att113
-att173 att185
-att44 att152
-att44 att50
-att44 att188
-att44 att200
-att44 att104
-att44 att140
-att44 att194
-att44 att212
-att44 att1
-att139 att26
-att139 att99
-att139 att103
-att139 att43
-att139 att91
-att139 att31
-att139 att199
-att139 att7
-att216 att204
-att216 att24
-att216 att84
-att216 att36
-att216 att12
-att216 att180
-att216 att108
-att129 att69
-att152 att188
-att152 att140
-att69 att153
-att69 att9
-att69 att177
-att81 att45
-att81 att105
-att153 att117
-att153 att141
-att41 att53
-att204 att12
-att204 att180
-att188 att146
-att188 att212
-att13 att157
-att114 att6
-att114 att186
-att10 att190
-att64 att184
-att200 att104
-att9 att45
-att9 att146
-att9 att141
-att9 att177
-att9 att37
-att9 att133
-att9 att109
-att9 att181
-att3 att183
-att3 att147
-att3 att123
-att3 att135
-att3 att111
-att45 att105
-att45 att177
-att45 att93
-att45 att201
-att45 att165
-att45 att193
-att45 att33
-att45 att37
-att45 att133
-att45 att97
-att140 att8
-att30 att6
-att30 att186
-att183 att147
-att183 att123
-att183 att135
-att146 att2
-att202 att166
-att202 att106
-att202 att82
-att24 att84
-att24 att36
-att24 att132
-att147 att123
-att147 att135
-att147 att111
-att147 att207
-att8 att212
-att166 att82
-att166 att22
-att166 att94
-att187 att127
-att187 att115
-att127 att115
-att105 att184
-att105 att93
-att105 att201
-att106 att154
-att82 att154
-att82 att22
-att135 att111
-att135 att207
-att154 att22
-att154 att94
-att111 att207
-att99 att195
-att22 att94
-att84 att48
-att177 att93
-att177 att165
-att177 att181
-att103 att195
-att103 att97
-att103 att109
-att93 att201
-att93 att165
-att93 att193
-att93 att33
-att93 att57
-att201 att33
-att201 att57
-att43 att31
-att36 att180
-att36 att48
-att36 att72
-att36 att132
-att36 att144
-att125 att113
-att125 att185
-att125 att65
-att125 att29
-att180 att48
-att180 att72
-att180 att192
-att180 att108
-att48 att72
-att6 att186
-att113 att185
-att113 att53
-att113 att65
-att193 att97
-att91 att31
-att91 att199
-att91 att19
-att72 att132
-att72 att144
-att72 att192
-att72 att120
-att31 att199
-att31 att7
-att31 att67
-att31 att55
-att31 att1
-att132 att144
-att132 att120
-att33 att57
-att144 att192
-att144 att120
-att185 att53
-att185 att65
-att185 att29
-att199 att19
-att199 att7
-att199 att67
-att199 att55
-att199 att109
-att65 att29
-att7 att67
-att67 att55
-att109 att181
-

data/mfeat-factors.net

@@ -1,859 +0,0 @@
-class att215
-class att25
-class att131
-class att95
-class att122
-class att17
-class att28
-class att5
-class att121
-class att214
-class att197
-class att116
-class att182
-class att60
-class att168
-class att178
-class att206
-class att89
-class att77
-class att209
-class att73
-class att126
-class att16
-class att74
-class att27
-class att61
-class att20
-class att101
-class att85
-class att76
-class att137
-class att211
-class att143
-class att14
-class att40
-class att210
-class att155
-class att170
-class att160
-class att23
-class att162
-class att203
-class att164
-class att107
-class att62
-class att42
-class att71
-class att128
-class att138
-class att83
-class att171
-class att92
-class att163
-class att49
-class att161
-class att158
-class att176
-class att11
-class att145
-class att4
-class att172
-class att196
-class att58
-class att68
-class att169
-class att80
-class att32
-class att175
-class att87
-class att88
-class att159
-class att18
-class att52
-class att98
-class att136
-class att150
-class att156
-class att110
-class att100
-class att63
-class att148
-class att90
-class att167
-class att35
-class att205
-class att51
-class att21
-class att142
-class att46
-class att134
-class att39
-class att102
-class att208
-class att130
-class att149
-class att96
-class att75
-class att118
-class att78
-class att213
-class att112
-class att38
-class att174
-class att189
-class att70
-class att179
-class att59
-class att79
-class att15
-class att47
-class att124
-class att34
-class att54
-class att191
-class att86
-class att56
-class att151
-class att66
-class att173
-class att44
-class att198
-class att139
-class att216
-class att129
-class att152
-class att69
-class att81
-class att50
-class att153
-class att41
-class att204
-class att188
-class att26
-class att13
-class att117
-class att114
-class att10
-class att64
-class att200
-class att9
-class att3
-class att119
-class att45
-class att104
-class att140
-class att30
-class att183
-class att146
-class att141
-class att202
-class att194
-class att24
-class att147
-class att8
-class att212
-class att123
-class att166
-class att187
-class att127
-class att190
-class att105
-class att106
-class att184
-class att82
-class att2
-class att135
-class att154
-class att111
-class att115
-class att99
-class att22
-class att84
-class att207
-class att94
-class att177
-class att103
-class att93
-class att201
-class att43
-class att36
-class att12
-class att125
-class att165
-class att180
-class att195
-class att157
-class att48
-class att6
-class att113
-class att193
-class att91
-class att72
-class att31
-class att132
-class att33
-class att57
-class att144
-class att192
-class att185
-class att37
-class att53
-class att120
-class att186
-class att199
-class att65
-class att108
-class att133
-class att29
-class att19
-class att7
-class att97
-class att67
-class att55
-class att1
-class att109
-class att181
-att215 att25
-att215 att131
-att215 att95
-att215 att17
-att215 att214
-att215 att143
-att25 att131
-att25 att95
-att25 att122
-att25 att121
-att25 att73
-att25 att61
-att25 att85
-att25 att169
-att25 att13
-att25 att157
-att131 att95
-att131 att122
-att131 att17
-att131 att28
-att131 att5
-att131 att121
-att131 att214
-att131 att116
-att131 att182
-att131 att60
-att131 att126
-att131 att16
-att131 att27
-att131 att20
-att131 att143
-att131 att155
-att95 att122
-att95 att17
-att95 att28
-att95 att5
-att95 att121
-att95 att214
-att95 att197
-att95 att116
-att95 att60
-att95 att168
-att95 att178
-att95 att143
-att95 att155
-att95 att23
-att95 att71
-att95 att167
-att122 att28
-att122 att182
-att122 att170
-att17 att5
-att17 att197
-att17 att89
-att17 att77
-att17 att209
-att17 att137
-att17 att161
-att17 att41
-att28 att206
-att28 att16
-att28 att76
-att28 att40
-att28 att210
-att28 att160
-att28 att172
-att28 att124
-att28 att64
-att5 att197
-att5 att89
-att5 att77
-att5 att209
-att5 att101
-att121 att73
-att121 att61
-att214 att116
-att214 att178
-att214 att206
-att214 att58
-att214 att142
-att214 att46
-att197 att89
-att197 att209
-att197 att101
-att116 att182
-att116 att60
-att116 att168
-att116 att178
-att116 att206
-att116 att73
-att116 att126
-att116 att16
-att116 att74
-att116 att27
-att116 att20
-att116 att211
-att116 att164
-att116 att128
-att116 att92
-att116 att176
-att116 att68
-att182 att27
-att182 att14
-att60 att168
-att60 att156
-att60 att96
-att168 att126
-att168 att156
-att168 att96
-att168 att216
-att178 att20
-att178 att211
-att178 att58
-att178 att142
-att178 att130
-att178 att166
-att206 att74
-att206 att170
-att206 att158
-att89 att77
-att89 att137
-att89 att149
-att89 att173
-att77 att137
-att77 att161
-att77 att149
-att209 att101
-att209 att41
-att73 att61
-att73 att85
-att73 att13
-att73 att157
-att126 att162
-att126 att138
-att126 att18
-att126 att150
-att16 att74
-att16 att76
-att16 att40
-att16 att4
-att16 att196
-att16 att136
-att74 att14
-att74 att62
-att27 att171
-att27 att63
-att61 att85
-att61 att169
-att20 att76
-att20 att211
-att20 att210
-att20 att170
-att20 att164
-att20 att128
-att20 att176
-att20 att80
-att101 att41
-att85 att169
-att85 att13
-att76 att14
-att76 att40
-att76 att160
-att76 att4
-att76 att52
-att137 att161
-att137 att149
-att137 att173
-att137 att125
-att211 att210
-att211 att162
-att211 att164
-att211 att62
-att211 att42
-att211 att171
-att211 att163
-att211 att175
-att211 att79
-att211 att151
-att211 att43
-att143 att155
-att143 att23
-att143 att203
-att143 att71
-att143 att83
-att143 att11
-att14 att98
-att40 att160
-att40 att4
-att40 att196
-att40 att88
-att40 att52
-att210 att162
-att210 att42
-att210 att114
-att155 att23
-att155 att203
-att155 att107
-att155 att11
-att170 att158
-att160 att52
-att160 att124
-att23 att203
-att23 att107
-att23 att71
-att23 att11
-att162 att138
-att162 att18
-att162 att150
-att162 att90
-att162 att102
-att162 att174
-att162 att66
-att203 att107
-att203 att49
-att203 att59
-att203 att47
-att203 att191
-att203 att119
-att164 att62
-att164 att42
-att164 att128
-att164 att171
-att164 att92
-att164 att163
-att164 att158
-att164 att176
-att164 att145
-att164 att172
-att164 att58
-att164 att68
-att164 att80
-att164 att32
-att164 att98
-att164 att156
-att164 att110
-att164 att205
-att164 att21
-att164 att134
-att164 att213
-att164 att112
-att164 att38
-att164 att189
-att164 att56
-att164 att44
-att164 att152
-att164 att8
-att107 att83
-att107 att49
-att107 att59
-att107 att47
-att107 att191
-att42 att138
-att42 att54
-att42 att114
-att71 att83
-att71 att167
-att71 att35
-att71 att179
-att128 att92
-att128 att112
-att138 att18
-att138 att150
-att83 att167
-att83 att35
-att171 att87
-att171 att159
-att171 att63
-att171 att51
-att171 att39
-att171 att75
-att92 att163
-att92 att145
-att92 att56
-att163 att49
-att163 att175
-att163 att87
-att163 att79
-att163 att151
-att163 att139
-att163 att187
-att163 att127
-att163 att103
-att163 att91
-att49 att37
-att161 att173
-att161 att113
-att176 att145
-att176 att172
-att176 att68
-att176 att80
-att176 att32
-att176 att175
-att176 att98
-att176 att110
-att176 att205
-att176 att21
-att176 att134
-att176 att213
-att176 att56
-att4 att196
-att4 att88
-att4 att136
-att4 att100
-att4 att148
-att4 att208
-att172 att112
-att172 att184
-att196 att88
-att196 att136
-att196 att100
-att196 att148
-att196 att208
-att58 att142
-att58 att46
-att58 att34
-att68 att32
-att80 att38
-att32 att110
-att32 att21
-att32 att44
-att32 att200
-att175 att87
-att175 att159
-att175 att79
-att175 att187
-att175 att115
-att87 att159
-att87 att63
-att87 att51
-att87 att75
-att87 att15
-att87 att99
-att159 att75
-att159 att15
-att159 att195
-att18 att90
-att18 att102
-att18 att78
-att18 att198
-att52 att124
-att52 att64
-att98 att86
-att136 att100
-att136 att208
-att150 att90
-att150 att174
-att150 att66
-att156 att205
-att156 att96
-att156 att216
-att156 att204
-att156 att24
-att156 att84
-att156 att36
-att156 att12
-att156 att108
-att100 att148
-att63 att51
-att63 att39
-att63 att3
-att63 att183
-att63 att147
-att90 att102
-att90 att78
-att167 att35
-att167 att179
-att35 att179
-att51 att39
-att51 att3
-att51 att183
-att21 att134
-att21 att213
-att21 att38
-att21 att189
-att21 att129
-att21 att81
-att21 att153
-att21 att117
-att21 att9
-att142 att46
-att142 att130
-att142 att118
-att142 att70
-att142 att10
-att142 att202
-att142 att190
-att142 att106
-att46 att130
-att46 att118
-att46 att70
-att46 att34
-att46 att166
-att46 att82
-att134 att2
-att39 att3
-att102 att78
-att102 att174
-att102 att54
-att102 att198
-att130 att118
-att130 att10
-att130 att202
-att130 att190
-att130 att106
-att149 att125
-att96 att216
-att96 att204
-att96 att24
-att75 att15
-att75 att99
-att118 att70
-att118 att10
-att118 att202
-att78 att198
-att213 att189
-att213 att129
-att213 att69
-att213 att81
-att38 att50
-att38 att26
-att174 att54
-att174 att66
-att174 att30
-att189 att86
-att189 att129
-att189 att69
-att189 att81
-att189 att153
-att189 att117
-att189 att9
-att189 att45
-att189 att141
-att189 att105
-att70 att34
-att70 att154
-att179 att59
-att59 att47
-att59 att191
-att59 att119
-att79 att86
-att79 att151
-att79 att139
-att79 att187
-att79 att127
-att79 att103
-att79 att43
-att79 att193
-att79 att91
-att79 att19
-att124 att64
-att54 att114
-att54 att30
-att54 att6
-att191 att119
-att86 att194
-att56 att44
-att56 att152
-att56 att50
-att56 att188
-att56 att26
-att56 att200
-att56 att104
-att56 att140
-att56 att146
-att56 att194
-att56 att8
-att56 att2
-att56 att133
-att56 att1
-att151 att139
-att66 att30
-att173 att125
-att173 att113
-att173 att185
-att44 att152
-att44 att50
-att44 att188
-att44 att200
-att44 att104
-att44 att140
-att44 att194
-att44 att212
-att44 att1
-att139 att26
-att139 att99
-att139 att103
-att139 att43
-att139 att91
-att139 att31
-att139 att199
-att139 att7
-att216 att204
-att216 att24
-att216 att84
-att216 att36
-att216 att12
-att216 att180
-att216 att108
-att129 att69
-att152 att188
-att152 att140
-att69 att153
-att69 att9
-att69 att177
-att81 att45
-att81 att105
-att153 att117
-att153 att141
-att41 att53
-att204 att12
-att204 att180
-att188 att146
-att188 att212
-att13 att157
-att114 att6
-att114 att186
-att10 att190
-att64 att184
-att200 att104
-att9 att45
-att9 att146
-att9 att141
-att9 att177
-att9 att37
-att9 att133
-att9 att109
-att9 att181
-att3 att183
-att3 att147
-att3 att123
-att3 att135
-att3 att111
-att45 att105
-att45 att177
-att45 att93
-att45 att201
-att45 att165
-att45 att193
-att45 att33
-att45 att37
-att45 att133
-att45 att97
-att140 att8
-att30 att6
-att30 att186
-att183 att147
-att183 att123
-att183 att135
-att146 att2
-att202 att166
-att202 att106
-att202 att82
-att24 att84
-att24 att36
-att24 att132
-att147 att123
-att147 att135
-att147 att111
-att147 att207
-att8 att212
-att166 att82
-att166 att22
-att166 att94
-att187 att127
-att187 att115
-att127 att115
-att105 att184
-att105 att93
-att105 att201
-att106 att154
-att82 att154
-att82 att22
-att135 att111
-att135 att207
-att154 att22
-att154 att94
-att111 att207
-att99 att195
-att22 att94
-att84 att48
-att177 att93
-att177 att165
-att177 att181
-att103 att195
-att103 att97
-att103 att109
-att93 att201
-att93 att165
-att93 att193
-att93 att33
-att93 att57
-att201 att33
-att201 att57
-att43 att31
-att36 att180
-att36 att48
-att36 att72
-att36 att132
-att36 att144
-att125 att113
-att125 att185
-att125 att65
-att125 att29
-att180 att48
-att180 att72
-att180 att192
-att180 att108
-att48 att72
-att6 att186
-att113 att185
-att113 att53
-att113 att65
-att193 att97
-att91 att31
-att91 att199
-att91 att19
-att72 att132
-att72 att144
-att72 att192
-att72 att120
-att31 att199
-att31 att7
-att31 att67
-att31 att55
-att31 att1
-att132 att144
-att132 att120
-att33 att57
-att144 att192
-att144 att120
-att185 att53
-att185 att65
-att185 att29
-att199 att19
-att199 att7
-att199 att67
-att199 att55
-att199 att109
-att65 att29
-att7 att67
-att67 att55
-att109 att181
-

gcovr.cfg

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

lib/Files/ArffFiles.cc

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

lib/Files/ArffFiles.h

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

lib/Files/CMakeLists.txt

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

sample/CMakeLists.txt

@@ -1,7 +0,0 @@
-include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
-include_directories(${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)
-add_executable(BayesNetSample sample.cc ${BayesNet_SOURCE_DIR}/src/Platform/Folding.cc ${BayesNet_SOURCE_DIR}/src/Platform/Models.cc) 
-target_link_libraries(BayesNetSample BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

sample/sample.cc

@@ -1,236 +0,0 @@
-#include <iostream>
-#include <torch/torch.h>
-#include <string>
-#include <map>
-#include <argparse/argparse.hpp>
-#include "ArffFiles.h"
-#include "BayesMetrics.h"
-#include "CPPFImdlp.h"
-#include "Folding.h"
-#include "Models.h"
-#include "modelRegister.h"
-
-
-using namespace std;
-
-const string PATH = "../../data/";
-
-pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features)
-{
-    vector<mdlp::labels_t>Xd;
-    map<string, int> maxes;
-
-    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]);
-        maxes[features[i]] = *max_element(xd.begin(), xd.end()) + 1;
-        Xd.push_back(xd);
-    }
-    return { Xd, maxes };
-}
-
-bool file_exists(const std::string& name)
-{
-    if (FILE* file = fopen(name.c_str(), "r")) {
-        fclose(file);
-        return true;
-    } else {
-        return false;
-    }
-}
-pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vector<vector<int>> X, vector<int> y)
-{
-    vector<vector<int>> Xr; // nxm
-    vector<int> yr;
-    for (int col = 0; col < X.size(); ++col) {
-        Xr.push_back(vector<int>());
-    }
-    for (auto index : indices) {
-        for (int col = 0; col < X.size(); ++col) {
-            Xr[col].push_back(X[col][index]);
-        }
-        yr.push_back(y[index]);
-    }
-    return { Xr, yr };
-}
-
-int main(int argc, char** argv)
-{
-    map<string, bool> datasets = {
-            {"diabetes",           true},
-            {"ecoli",              true},
-            {"glass",              true},
-            {"iris",               true},
-            {"kdd_JapaneseVowels", false},
-            {"letter",             true},
-            {"liver-disorders",    true},
-            {"mfeat-factors",      true},
-    };
-    auto valid_datasets = vector<string>();
-    transform(datasets.begin(), datasets.end(), back_inserter(valid_datasets),
-        [](const pair<string, bool>& pair) { return pair.first; });
-    argparse::ArgumentParser program("BayesNetSample");
-    program.add_argument("-d", "--dataset")
-        .help("Dataset file name")
-        .action([valid_datasets](const std::string& value) {
-        if (find(valid_datasets.begin(), valid_datasets.end(), value) != valid_datasets.end()) {
-            return value;
-        }
-        throw runtime_error("file must be one of {diabetes, ecoli, glass, iris, kdd_JapaneseVowels, letter, liver-disorders, mfeat-factors}");
-            }
-    );
-    program.add_argument("-p", "--path")
-        .help(" folder where the data files are located, default")
-        .default_value(string{ PATH }
-    );
-    program.add_argument("-m", "--model")
-        .help("Model to use " + platform::Models::instance()->toString())
-        .action([](const std::string& value) {
-        static const vector<string> choices = platform::Models::instance()->getNames();
-        if (find(choices.begin(), choices.end(), value) != choices.end()) {
-            return value;
-        }
-        throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
-            }
-    );
-    program.add_argument("--discretize").help("Discretize input dataset").default_value(false).implicit_value(true);
-    program.add_argument("--dumpcpt").help("Dump CPT Tables").default_value(false).implicit_value(true);
-    program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value(false).implicit_value(true);
-    program.add_argument("--tensors").help("Use tensors to store samples").default_value(false).implicit_value(true);
-    program.add_argument("-f", "--folds").help("Number of folds").default_value(5).scan<'i', int>().action([](const string& value) {
-        try {
-            auto k = stoi(value);
-            if (k < 2) {
-                throw runtime_error("Number of folds must be greater than 1");
-            }
-            return k;
-        }
-        catch (const runtime_error& err) {
-            throw runtime_error(err.what());
-        }
-        catch (...) {
-            throw runtime_error("Number of folds must be an integer");
-        }});
-    program.add_argument("-s", "--seed").help("Random seed").default_value(-1).scan<'i', int>();
-    bool class_last, stratified, tensors, dump_cpt;
-    string model_name, file_name, path, complete_file_name;
-    int nFolds, seed;
-    try {
-        program.parse_args(argc, argv);
-        file_name = program.get<string>("dataset");
-        path = program.get<string>("path");
-        model_name = program.get<string>("model");
-        complete_file_name = path + file_name + ".arff";
-        stratified = program.get<bool>("stratified");
-        tensors = program.get<bool>("tensors");
-        nFolds = program.get<int>("folds");
-        seed = program.get<int>("seed");
-        dump_cpt = program.get<bool>("dumpcpt");
-        class_last = datasets[file_name];
-        if (!file_exists(complete_file_name)) {
-            throw runtime_error("Data File " + path + file_name + ".arff" + " does not exist");
-        }
-    }
-    catch (const exception& err) {
-        cerr << err.what() << endl;
-        cerr << program;
-        exit(1);
-    }
-
-    /*
-    * Begin Processing
-    */
-    auto handler = ArffFiles();
-    handler.load(complete_file_name, class_last);
-    // Get Dataset X, y
-    vector<mdlp::samples_t>& X = handler.getX();
-    mdlp::labels_t& y = handler.getY();
-    // Get className & Features
-    auto className = handler.getClassName();
-    vector<string> features;
-    auto attributes = handler.getAttributes();
-    transform(attributes.begin(), attributes.end(), back_inserter(features),
-        [](const pair<string, string>& item) { return item.first; });
-    // Discretize Dataset
-    auto [Xd, maxes] = discretize(X, y, features);
-    maxes[className] = *max_element(y.begin(), y.end()) + 1;
-    map<string, vector<int>> states;
-    for (auto feature : features) {
-        states[feature] = vector<int>(maxes[feature]);
-    }
-    states[className] = vector<int>(maxes[className]);
-    auto clf = platform::Models::instance()->create(model_name);
-    clf->fit(Xd, y, features, className, states);
-    if (dump_cpt) {
-        cout << "--- CPT Tables ---" << endl;
-        clf->dump_cpt();
-    }
-    auto lines = clf->show();
-    for (auto line : lines) {
-        cout << line << endl;
-    }
-    cout << "--- Topological Order ---" << endl;
-    auto order = clf->topological_order();
-    for (auto name : order) {
-        cout << name << ", ";
-    }
-    cout << "end." << endl;
-    auto score = clf->score(Xd, y);
-    cout << "Score: " << score << endl;
-    // auto graph = clf->graph();
-    // auto dot_file = model_name + "_" + file_name;
-    // ofstream file(dot_file + ".dot");
-    // file << graph;
-    // 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;
-}

src/BayesNet/AODE.cc

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

src/BayesNet/AODE.h

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

src/BayesNet/AODELd.cc

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

src/BayesNet/AODELd.h

@@ -5,16 +5,16 @@
 #include "SPODELd.h"
 
 namespace bayesnet {
-    using namespace std;
     class AODELd : public Ensemble, public Proposal {
+    protected:
+        void trainModel(const torch::Tensor& weights) override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         AODELd();
+        AODELd& fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_) override;
         virtual ~AODELd() = default;
-        AODELd& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        vector<string> graph(const string& name = "AODE") override;
-        Tensor predict(Tensor& X) override;
-        void train() override;
-        static inline string version() { return "0.0.1"; };
+        std::vector<std::string> graph(const std::string& name = "AODELd") const override;
+        static inline std::string version() { return "0.0.1"; };
     };
 }
 #endif // !AODELD_H

src/BayesNet/BaseClassifier.h

@@ -1,28 +1,38 @@
 #ifndef BASE_H
 #define BASE_H
 #include <torch/torch.h>
+#include <nlohmann/json.hpp>
 #include <vector>
 namespace bayesnet {
-    using namespace std;
+    enum status_t { NORMAL, WARNING, ERROR };
     class BaseClassifier {
     public:
-        // X is nxm vector, y is nx1 vector
-        virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        // X is nxm std::vector, y is nx1 std::vector
+        virtual BaseClassifier& fit(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) = 0;
         // X is nxm tensor, y is nx1 tensor
-        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights) = 0;
         virtual ~BaseClassifier() = default;
         torch::Tensor virtual predict(torch::Tensor& X) = 0;
-        vector<int> virtual predict(vector<vector<int>>& X) = 0;
-        float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
+        std::vector<int> virtual predict(std::vector<std::vector<int >>& X) = 0;
+        status_t virtual getStatus() const = 0;
+        float virtual score(std::vector<std::vector<int>>& X, std::vector<int>& y) = 0;
         float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
-        int virtual getNumberOfNodes() = 0;
-        int virtual getNumberOfEdges() = 0;
-        int virtual getNumberOfStates() = 0;
-        vector<string> virtual show() = 0;
-        vector<string> virtual graph(const string& title = "") = 0;
-        const string inline getVersion() const { return "0.1.0"; };
-        vector<string> virtual topological_order() = 0;
-        void virtual dump_cpt() = 0;
+        int virtual getNumberOfNodes()const = 0;
+        int virtual getNumberOfEdges()const = 0;
+        int virtual getNumberOfStates() const = 0;
+        std::vector<std::string> virtual show() const = 0;
+        std::vector<std::string> virtual graph(const std::string& title = "") const = 0;
+        virtual std::string getVersion() = 0;
+        std::vector<std::string> virtual topological_order() = 0;
+        std::vector<std::string> virtual getNotes() const = 0;
+        void virtual dump_cpt()const = 0;
+        virtual void setHyperparameters(const nlohmann::json& hyperparameters) = 0;
+        std::vector<std::string>& getValidHyperparameters() { return validHyperparameters; }
+    protected:
+        virtual void trainModel(const torch::Tensor& weights) = 0;
+        std::vector<std::string> validHyperparameters;
     };
 }
 #endif

src/BayesNet/BayesMetrics.cc

@@ -1,16 +1,16 @@
 #include "BayesMetrics.h"
 #include "Mst.h"
 namespace bayesnet {
-    //samples is nxm tensor used to fit the model
-    Metrics::Metrics(torch::Tensor& samples, vector<string>& features, string& className, int classNumStates)
+    //samples is n+1xm tensor used to fit the model
+    Metrics::Metrics(const torch::Tensor& samples, const std::vector<std::string>& features, const std::string& className, const int classNumStates)
         : samples(samples)
         , features(features)
         , className(className)
         , classNumStates(classNumStates)
     {
     }
-    //samples is nxm vector used to fit the model
-    Metrics::Metrics(const vector<vector<int>>& vsamples, const vector<int>& labels, const vector<string>& features, const string& className, const int classNumStates)
+    //samples is nxm std::vector used to fit the model
+    Metrics::Metrics(const std::vector<std::vector<int>>& vsamples, const std::vector<int>& labels, const std::vector<std::string>& features, const std::string& className, const int classNumStates)
         : features(features)
         , className(className)
         , classNumStates(classNumStates)
@@ -21,28 +21,57 @@ namespace bayesnet {
         }
         samples.index_put_({ -1, "..." }, torch::tensor(labels, torch::kInt32));
     }
-    vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
+    std::vector<int> Metrics::SelectKBestWeighted(const torch::Tensor& weights, bool ascending, unsigned k)
     {
-        vector<pair<string, string>> result;
-        for (int i = 0; i < source.size(); ++i) {
-            string temp = source[i];
-            for (int j = i + 1; j < source.size(); ++j) {
-                result.push_back({ temp, source[j] });
+        // Return the K Best features 
+        auto n = samples.size(0) - 1;
+        if (k == 0) {
+            k = n;
+        }
+        // compute scores
+        scoresKBest.clear();
+        featuresKBest.clear();
+        auto label = samples.index({ -1, "..." });
+        for (int i = 0; i < n; ++i) {
+            scoresKBest.push_back(mutualInformation(label, samples.index({ i, "..." }), weights));
+            featuresKBest.push_back(i);
+        }
+        // sort & reduce scores and features
+        if (ascending) {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] < scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::less<double>());
+            if (k < n) {
+                for (int i = 0; i < n - k; ++i) {
+                    featuresKBest.erase(featuresKBest.begin());
+                    scoresKBest.erase(scoresKBest.begin());
                 }
             }
-        return result;
+        } else {
+            sort(featuresKBest.begin(), featuresKBest.end(), [&](int i, int j)
+                { return scoresKBest[i] > scoresKBest[j]; });
+            sort(scoresKBest.begin(), scoresKBest.end(), std::greater<double>());
+            featuresKBest.resize(k);
+            scoresKBest.resize(k);
         }
-    torch::Tensor Metrics::conditionalEdge()
+        return featuresKBest;
+    }
+    std::vector<double> Metrics::getScoresKBest() const
     {
-        auto result = vector<double>();
-        auto source = vector<string>(features);
+        return scoresKBest;
+    }
+
+    torch::Tensor Metrics::conditionalEdge(const torch::Tensor& weights)
+    {
+        auto result = std::vector<double>();
+        auto source = std::vector<std::string>(features);
         source.push_back(className);
         auto combinations = doCombinations(source);
         // Compute class prior
-        auto margin = torch::zeros({ classNumStates });
+        auto margin = torch::zeros({ classNumStates }, torch::kFloat);
         for (int value = 0; value < classNumStates; ++value) {
             auto mask = samples.index({ -1,  "..." }) == value;
-            margin[value] = mask.sum().item<float>() / samples.size(1);
+            margin[value] = mask.sum().item<double>() / samples.size(1);
         }
         for (auto [first, second] : combinations) {
             int index_first = find(features.begin(), features.end(), first) - features.begin();
@@ -52,8 +81,9 @@ namespace bayesnet {
                 auto mask = samples.index({ -1, "..." }) == value;
                 auto first_dataset = samples.index({ index_first, mask });
                 auto second_dataset = samples.index({ index_second, mask });
-                auto mi = mutualInformation(first_dataset, second_dataset);
-                auto pb = margin[value].item<float>();
+                auto weights_dataset = weights.index({ mask });
+                auto mi = mutualInformation(first_dataset, second_dataset, weights_dataset);
+                auto pb = margin[value].item<double>();
                 accumulated += pb * mi;
             }
             result.push_back(accumulated);
@@ -70,31 +100,32 @@ namespace bayesnet {
         return matrix;
     }
     // To use in Python
-    vector<float> Metrics::conditionalEdgeWeights()
+    std::vector<float> Metrics::conditionalEdgeWeights(std::vector<float>& weights_)
     {
-        auto matrix = conditionalEdge();
+        const torch::Tensor weights = torch::tensor(weights_);
+        auto matrix = conditionalEdge(weights);
         std::vector<float> v(matrix.data_ptr<float>(), matrix.data_ptr<float>() + matrix.numel());
         return v;
     }
-    double Metrics::entropy(torch::Tensor& feature)
+    double Metrics::entropy(const torch::Tensor& feature, const torch::Tensor& weights)
     {
-        torch::Tensor counts = feature.bincount();
-        int totalWeight = counts.sum().item<int>();
+        torch::Tensor counts = feature.bincount(weights);
+        double totalWeight = counts.sum().item<double>();
         torch::Tensor probs = counts.to(torch::kFloat) / totalWeight;
         torch::Tensor logProbs = torch::log(probs);
         torch::Tensor entropy = -probs * logProbs;
         return entropy.nansum().item<double>();
     }
     // H(Y|X) = sum_{x in X} p(x) H(Y|X=x)
-    double Metrics::conditionalEntropy(torch::Tensor& firstFeature, torch::Tensor& secondFeature)
+    double Metrics::conditionalEntropy(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
     {
         int numSamples = firstFeature.sizes()[0];
-        torch::Tensor featureCounts = secondFeature.bincount();
-        unordered_map<int, unordered_map<int, double>> jointCounts;
+        torch::Tensor featureCounts = secondFeature.bincount(weights);
+        std::unordered_map<int, std::unordered_map<int, double>> jointCounts;
         double totalWeight = 0;
         for (auto i = 0; i < numSamples; i++) {
-            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += 1;
-            totalWeight += 1;
+            jointCounts[secondFeature[i].item<int>()][firstFeature[i].item<int>()] += weights[i].item<double>();
+            totalWeight += weights[i].item<float>();
         }
         if (totalWeight == 0)
             return 0;
@@ -115,16 +146,16 @@ namespace bayesnet {
         return entropyValue;
     }
     // I(X;Y) = H(Y) - H(Y|X)
-    double Metrics::mutualInformation(torch::Tensor& firstFeature, torch::Tensor& secondFeature)
+    double Metrics::mutualInformation(const torch::Tensor& firstFeature, const torch::Tensor& secondFeature, const torch::Tensor& weights)
     {
-        return entropy(firstFeature) - conditionalEntropy(firstFeature, secondFeature);
+        return entropy(firstFeature, weights) - conditionalEntropy(firstFeature, secondFeature, weights);
     }
     /*
     Compute the maximum spanning tree considering the weights as distances
     and the indices of the weights as nodes of this square matrix using
     Kruskal algorithm
     */
-    vector<pair<int, int>> Metrics::maximumSpanningTree(vector<string> features, Tensor& weights, int root)
+    std::vector<std::pair<int, int>> Metrics::maximumSpanningTree(const std::vector<std::string>& features, const torch::Tensor& weights, const int root)
     {
         auto mst = MST(features, weights, root);
         return mst.maximumSpanningTree();

src/BayesNet/BayesMetrics.h

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

src/BayesNet/BoostAODE.cc

@@ -0,0 +1,210 @@
+#include <set>
+#include <functional>
+#include <limits.h>
+#include "BoostAODE.h"
+#include "CFS.h"
+#include "FCBF.h"
+#include "IWSS.h"
+#include "folding.hpp"
+
+namespace bayesnet {
+    BoostAODE::BoostAODE() : Ensemble()
+    {
+        validHyperparameters = { "repeatSparent", "maxModels", "ascending", "convergence", "threshold", "select_features", "tolerance" };
+
+    }
+    void BoostAODE::buildModel(const torch::Tensor& weights)
+    {
+        // Models shall be built in trainModel
+        models.clear();
+        n_models = 0;
+        // Prepare the validation dataset
+        auto y_ = dataset.index({ -1, "..." });
+        if (convergence) {
+            // Prepare train & validation sets from train data
+            auto fold = folding::StratifiedKFold(5, y_, 271);
+            dataset_ = torch::clone(dataset);
+            // save input dataset
+            auto [train, test] = fold.getFold(0);
+            auto train_t = torch::tensor(train);
+            auto test_t = torch::tensor(test);
+            // Get train and validation sets
+            X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), train_t });
+            y_train = dataset.index({ -1, train_t });
+            X_test = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), test_t });
+            y_test = dataset.index({ -1, test_t });
+            dataset = X_train;
+            m = X_train.size(1);
+            auto n_classes = states.at(className).size();
+            metrics = Metrics(dataset, features, className, n_classes);
+            // Build dataset with train data
+            buildDataset(y_train);
+        } else {
+            // Use all data to train
+            X_train = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." });
+            y_train = y_;
+        }
+    }
+    void BoostAODE::setHyperparameters(const nlohmann::json& hyperparameters_)
+    {
+        auto hyperparameters = hyperparameters_;
+        if (hyperparameters.contains("repeatSparent")) {
+            repeatSparent = hyperparameters["repeatSparent"];
+            hyperparameters.erase("repeatSparent");
+        }
+        if (hyperparameters.contains("maxModels")) {
+            maxModels = hyperparameters["maxModels"];
+            hyperparameters.erase("maxModels");
+        }
+        if (hyperparameters.contains("ascending")) {
+            ascending = hyperparameters["ascending"];
+            hyperparameters.erase("ascending");
+        }
+        if (hyperparameters.contains("convergence")) {
+            convergence = hyperparameters["convergence"];
+            hyperparameters.erase("convergence");
+        }
+        if (hyperparameters.contains("threshold")) {
+            threshold = hyperparameters["threshold"];
+            hyperparameters.erase("threshold");
+        }
+        if (hyperparameters.contains("tolerance")) {
+            tolerance = hyperparameters["tolerance"];
+            hyperparameters.erase("tolerance");
+        }
+        if (hyperparameters.contains("select_features")) {
+            auto selectedAlgorithm = hyperparameters["select_features"];
+            std::vector<std::string> algos = { "IWSS", "FCBF", "CFS" };
+            selectFeatures = true;
+            algorithm = selectedAlgorithm;
+            if (std::find(algos.begin(), algos.end(), selectedAlgorithm) == algos.end()) {
+                throw std::invalid_argument("Invalid selectFeatures value [IWSS, FCBF, CFS]");
+            }
+            hyperparameters.erase("select_features");
+        }
+        if (!hyperparameters.empty()) {
+            throw std::invalid_argument("Invalid hyperparameters" + hyperparameters.dump());
+        }
+    }
+    std::unordered_set<int> BoostAODE::initializeModels()
+    {
+        std::unordered_set<int> featuresUsed;
+        torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
+        int maxFeatures = 0;
+        if (algorithm == "CFS") {
+            featureSelector = new CFS(dataset, features, className, maxFeatures, states.at(className).size(), weights_);
+        } else if (algorithm == "IWSS") {
+            if (threshold < 0 || threshold >0.5) {
+                throw std::invalid_argument("Invalid threshold value for IWSS [0, 0.5]");
+            }
+            featureSelector = new IWSS(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
+        } else if (algorithm == "FCBF") {
+            if (threshold < 1e-7 || threshold > 1) {
+                throw std::invalid_argument("Invalid threshold value [1e-7, 1]");
+            }
+            featureSelector = new FCBF(dataset, features, className, maxFeatures, states.at(className).size(), weights_, threshold);
+        }
+        featureSelector->fit();
+        auto cfsFeatures = featureSelector->getFeatures();
+        for (const int& feature : cfsFeatures) {
+            // std::cout << "Feature: [" << feature << "] " << feature << " " << features.at(feature) << std::endl;
+            featuresUsed.insert(feature);
+            std::unique_ptr<Classifier> model = std::make_unique<SPODE>(feature);
+            model->fit(dataset, features, className, states, weights_);
+            models.push_back(std::move(model));
+            significanceModels.push_back(1.0);
+            n_models++;
+        }
+        notes.push_back("Used features in initialization: " + std::to_string(featuresUsed.size()) + " of " + std::to_string(features.size()) + " with " + algorithm);
+        delete featureSelector;
+        return featuresUsed;
+    }
+    void BoostAODE::trainModel(const torch::Tensor& weights)
+    {
+        std::unordered_set<int> featuresUsed;
+        if (selectFeatures) {
+            featuresUsed = initializeModels();
+        }
+        if (maxModels == 0)
+            maxModels = .1 * n > 10 ? .1 * n : n;
+        torch::Tensor weights_ = torch::full({ m }, 1.0 / m, torch::kFloat64);
+        bool exitCondition = false;
+        // Variables to control the accuracy finish condition
+        double priorAccuracy = 0.0;
+        double delta = 1.0;
+        double threshold = 1e-4;
+        int count = 0; // number of times the accuracy is lower than the threshold
+        fitted = true; // to enable predict
+        // Step 0: Set the finish condition
+        // if not repeatSparent a finish condition is run out of features
+        // n_models == maxModels
+        // epsilon sub t > 0.5 => inverse the weights policy
+        // validation error is not decreasing
+        while (!exitCondition) {
+            // Step 1: Build ranking with mutual information
+            auto featureSelection = metrics.SelectKBestWeighted(weights_, ascending, n); // Get all the features sorted
+            std::unique_ptr<Classifier> model;
+            auto feature = featureSelection[0];
+            if (!repeatSparent || featuresUsed.size() < featureSelection.size()) {
+                bool used = true;
+                for (const auto& feat : featureSelection) {
+                    if (std::find(featuresUsed.begin(), featuresUsed.end(), feat) != featuresUsed.end()) {
+                        continue;
+                    }
+                    used = false;
+                    feature = feat;
+                    break;
+                }
+                if (used) {
+                    exitCondition = true;
+                    continue;
+                }
+            }
+            featuresUsed.insert(feature);
+            model = std::make_unique<SPODE>(feature);
+            model->fit(dataset, features, className, states, weights_);
+            auto ypred = model->predict(X_train);
+            // Step 3.1: Compute the classifier amout of say
+            auto mask_wrong = ypred != y_train;
+            auto mask_right = ypred == y_train;
+            auto masked_weights = weights_ * mask_wrong.to(weights_.dtype());
+            double epsilon_t = masked_weights.sum().item<double>();
+            double wt = (1 - epsilon_t) / epsilon_t;
+            double alpha_t = epsilon_t == 0 ? 1 : 0.5 * log(wt);
+            // Step 3.2: Update weights for next classifier
+            // Step 3.2.1: Update weights of wrong samples
+            weights_ += mask_wrong.to(weights_.dtype()) * exp(alpha_t) * weights_;
+            // Step 3.2.2: Update weights of right samples
+            weights_ += mask_right.to(weights_.dtype()) * exp(-alpha_t) * weights_;
+            // Step 3.3: Normalise the weights
+            double totalWeights = torch::sum(weights_).item<double>();
+            weights_ = weights_ / totalWeights;
+            // Step 3.4: Store classifier and its accuracy to weigh its future vote
+            models.push_back(std::move(model));
+            significanceModels.push_back(alpha_t);
+            n_models++;
+            if (convergence) {
+                auto y_val_predict = predict(X_test);
+                double accuracy = (y_val_predict == y_test).sum().item<double>() / (double)y_test.size(0);
+                if (priorAccuracy == 0) {
+                    priorAccuracy = accuracy;
+                } else {
+                    delta = accuracy - priorAccuracy;
+                }
+                if (delta < threshold) {
+                    count++;
+                }
+            }
+            exitCondition = n_models >= maxModels && repeatSparent || epsilon_t > 0.5 || count > tolerance;
+        }
+        if (featuresUsed.size() != features.size()) {
+            notes.push_back("Used features in train: " + std::to_string(featuresUsed.size()) + " of " + std::to_string(features.size()));
+            status = WARNING;
+        }
+        notes.push_back("Number of models: " + std::to_string(n_models));
+    }
+    std::vector<std::string> BoostAODE::graph(const std::string& title) const
+    {
+        return Ensemble::graph(title);
+    }
+}

src/BayesNet/BoostAODE.h

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

src/BayesNet/CFS.cc

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

src/BayesNet/CFS.h

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

src/BayesNet/CMakeLists.txt

@@ -1,5 +1,13 @@
-include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
-include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
+include_directories(
+    ${BayesNet_SOURCE_DIR}/lib/mdlp
+    ${BayesNet_SOURCE_DIR}/lib/Files
+    ${BayesNet_SOURCE_DIR}/lib/folding
+    ${BayesNet_SOURCE_DIR}/lib/json/include
+    ${BayesNet_SOURCE_DIR}/src/BayesNet
+    ${CMAKE_BINARY_DIR}/configured_files/include
+)
+
 add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 
-    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc Mst.cc Proposal.cc)
-target_link_libraries(BayesNet mdlp ArffFiles "${TORCH_LIBRARIES}")
+    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc BoostAODE.cc 
+    Mst.cc Proposal.cc CFS.cc FCBF.cc IWSS.cc FeatureSelect.cc )
+target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")

src/BayesNet/Classifier.cc

@@ -2,113 +2,125 @@
 #include "bayesnetUtils.h"
 
 namespace bayesnet {
-    using namespace torch;
-
     Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
-    Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
     {
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
         this->features = features;
         this->className = className;
         this->states = states;
+        m = dataset.size(1);
+        n = dataset.size(0) - 1;
         checkFitParameters();
-        auto n_classes = states[className].size();
-        metrics = Metrics(samples, features, className, n_classes);
+        auto n_classes = states.at(className).size();
+        metrics = Metrics(dataset, features, className, n_classes);
         model.initialize();
-        train();
-        if (Xv.empty()) {
-            // fit with tensors
-            model.fit(X, y, features, className);
-        } else {
-            // fit with vectors
-            model.fit(Xv, yv, features, className);
-        }
+        buildModel(weights);
+        trainModel(weights);
         fitted = true;
         return *this;
     }
-    // X is nxm where n is the number of features and m the number of samples
-    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    void Classifier::buildDataset(torch::Tensor& ytmp)
     {
-        this->X = X;
-        this->y = y;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        return build(features, className, states);
+        try {
+            auto yresized = torch::transpose(ytmp.view({ ytmp.size(0), 1 }), 0, 1);
+            dataset = torch::cat({ dataset, yresized }, 0);
         }
-    void Classifier::generateTensorXFromVector()
+        catch (const std::exception& e) {
+            std::cerr << e.what() << '\n';
+            std::cout << "X dimensions: " << dataset.sizes() << "\n";
+            std::cout << "y dimensions: " << ytmp.sizes() << "\n";
+            exit(1);
+        }
+    }
+    void Classifier::trainModel(const torch::Tensor& weights)
     {
-        X = torch::zeros({ static_cast<int>(Xv.size()), static_cast<int>(Xv[0].size()) }, kInt32);
-        for (int i = 0; i < Xv.size(); ++i) {
-            X.index_put_({ i, "..." }, torch::tensor(Xv[i], kInt32));
-        }
+        model.fit(dataset, weights, features, className, states);
     }
     // X is nxm where n is the number of features and m the number of samples
-    Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier& Classifier::fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
     {
-        Xv = X;
-        generateTensorXFromVector();
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, states);
+        dataset = X;
+        buildDataset(y);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    // X is nxm where n is the number of features and m the number of samples
+    Classifier& Classifier::fit(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
+    {
+        dataset = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, torch::kInt32);
+        for (int i = 0; i < X.size(); ++i) {
+            dataset.index_put_({ i, "..." }, torch::tensor(X[i], torch::kInt32));
+        }
+        auto ytmp = torch::tensor(y, torch::kInt32);
+        buildDataset(ytmp);
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    Classifier& Classifier::fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states)
+    {
+        this->dataset = dataset;
+        const torch::Tensor weights = torch::full({ dataset.size(1) }, 1.0 / dataset.size(1), torch::kDouble);
+        return build(features, className, states, weights);
+    }
+    Classifier& Classifier::fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights)
+    {
+        this->dataset = dataset;
+        return build(features, className, states, weights);
     }
     void Classifier::checkFitParameters()
     {
-        auto sizes = X.sizes();
-        m = sizes[1];
-        n = sizes[0];
-        if (m != y.size(0)) {
-            throw invalid_argument("X and y must have the same number of samples");
+        if (torch::is_floating_point(dataset)) {
+            throw std::invalid_argument("dataset (X, y) must be of type Integer");
         }
         if (n != features.size()) {
-            throw invalid_argument("X and features must have the same number of features");
+            throw std::invalid_argument("Classifier: X " + std::to_string(n) + " and features " + std::to_string(features.size()) + " must have the same number of features");
         }
         if (states.find(className) == states.end()) {
-            throw invalid_argument("className not found in states");
+            throw std::invalid_argument("className not found in states");
         }
         for (auto feature : features) {
             if (states.find(feature) == states.end()) {
-                throw invalid_argument("feature [" + feature + "] not found in states");
+                throw std::invalid_argument("feature [" + feature + "] not found in states");
             }
         }
     }
-    Tensor Classifier::predict(Tensor& X)
+    torch::Tensor Classifier::predict(torch::Tensor& X)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::logic_error("Classifier has not been fitted");
         }
         return model.predict(X);
     }
-    vector<int> Classifier::predict(vector<vector<int>>& X)
+    std::vector<int> Classifier::predict(std::vector<std::vector<int>>& X)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::logic_error("Classifier has not been fitted");
         }
         auto m_ = X[0].size();
         auto n_ = X.size();
-        vector<vector<int>> Xd(n_, vector<int>(m_, 0));
+        std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
         for (auto i = 0; i < n_; i++) {
-            Xd[i] = vector<int>(X[i].begin(), X[i].end());
+            Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
         }
         auto yp = model.predict(Xd);
         return yp;
     }
-    float Classifier::score(Tensor& X, Tensor& y)
+    float Classifier::score(torch::Tensor& X, torch::Tensor& y)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::logic_error("Classifier has not been fitted");
         }
-        Tensor y_pred = predict(X);
+        torch::Tensor y_pred = predict(X);
         return (y_pred == y).sum().item<float>() / y.size(0);
     }
-    float Classifier::score(vector<vector<int>>& X, vector<int>& y)
+    float Classifier::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
     {
         if (!fitted) {
-            throw logic_error("Classifier has not been fitted");
+            throw std::logic_error("Classifier has not been fitted");
         }
         return model.score(X, y);
     }
-    vector<string> Classifier::show()
+    std::vector<std::string> Classifier::show() const
     {
         return model.show();
     }
@@ -120,26 +132,29 @@ namespace bayesnet {
         }
         model.addNode(className);
     }
-    int Classifier::getNumberOfNodes()
+    int Classifier::getNumberOfNodes() const
     {
         // Features does not include class
-        return fitted ? model.getFeatures().size() + 1 : 0;
+        return fitted ? model.getFeatures().size() : 0;
     }
-    int Classifier::getNumberOfEdges()
+    int Classifier::getNumberOfEdges() const
     {
-        return fitted ? model.getEdges().size() : 0;
+        return fitted ? model.getNumEdges() : 0;
     }
-    int Classifier::getNumberOfStates()
+    int Classifier::getNumberOfStates() const
     {
         return fitted ? model.getStates() : 0;
     }
-    vector<string> Classifier::topological_order()
+    std::vector<std::string> Classifier::topological_order()
     {
         return model.topological_sort();
     }
-    void Classifier::dump_cpt()
+    void Classifier::dump_cpt() const
     {
         model.dump_cpt();
     }
-
+    void Classifier::setHyperparameters(const nlohmann::json& hyperparameters)
+    {
+        //For classifiers that don't have hyperparameters
+    }
 }

src/BayesNet/Classifier.h

@@ -4,45 +4,48 @@
 #include "BaseClassifier.h"
 #include "Network.h"
 #include "BayesMetrics.h"
-using namespace std;
-using namespace torch;
 
 namespace bayesnet {
     class Classifier : public BaseClassifier {
     private:
-        bool fitted;
-        Classifier& build(vector<string>& features, string className, map<string, vector<int>>& states);
+        Classifier& build(const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
     protected:
-        Network model;
+        bool fitted;
         int m, n; // m: number of samples, n: number of features
-        Tensor X; // nxm tensor
-        vector<vector<int>> Xv; // nxm vector
-        Tensor y;
-        vector<int> yv;
-        Tensor samples; // (n+1)xm tensor
+        Network model;
         Metrics metrics;
-        vector<string> features;
-        string className;
-        map<string, vector<int>> states;
+        std::vector<std::string> features;
+        std::string className;
+        std::map<std::string, std::vector<int>> states;
+        torch::Tensor dataset; // (n+1)xm tensor
+        status_t status = NORMAL;
+        std::vector<std::string> notes; // Used to store messages occurred during the fit process
         void checkFitParameters();
-        void generateTensorXFromVector();
-        virtual void train() = 0;
+        virtual void buildModel(const torch::Tensor& weights) = 0;
+        void trainModel(const torch::Tensor& weights) override;
+        void buildDataset(torch::Tensor& y);
     public:
         Classifier(Network model);
         virtual ~Classifier() = default;
-        Classifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
-        Classifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) override;
+        Classifier& fit(std::vector<std::vector<int>>& X, std::vector<int>& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states) override;
+        Classifier& fit(torch::Tensor& dataset, const std::vector<std::string>& features, const std::string& className, std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights) override;
         void addNodes();
-        int getNumberOfNodes() override;
-        int getNumberOfEdges() override;
-        int getNumberOfStates() override;
-        Tensor predict(Tensor& X) override;
-        vector<int> predict(vector<vector<int>>& X) override;
-        float score(Tensor& X, Tensor& y) override;
-        float score(vector<vector<int>>& X, vector<int>& y) override;
-        vector<string> show() override;
-        vector<string> topological_order() override;
-        void dump_cpt() override;
+        int getNumberOfNodes() const override;
+        int getNumberOfEdges() const override;
+        int getNumberOfStates() const override;
+        torch::Tensor predict(torch::Tensor& X) override;
+        status_t getStatus() const override { return status; }
+        std::string getVersion() override { return { project_version.begin(), project_version.end() }; };
+        std::vector<int> predict(std::vector<std::vector<int>>& X) override;
+        float score(torch::Tensor& X, torch::Tensor& y) override;
+        float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
+        std::vector<std::string> show() const override;
+        std::vector<std::string> topological_order()  override;
+        std::vector<std::string> getNotes() const override { return notes; }
+        void dump_cpt() const override;
+        void setHyperparameters(const nlohmann::json& hyperparameters) override; //For classifiers that don't have hyperparameters
     };
 }
 #endif

src/BayesNet/Ensemble.cc

@@ -1,65 +1,29 @@
 #include "Ensemble.h"
 
 namespace bayesnet {
-    using namespace torch;
 
-    Ensemble::Ensemble() : n_models(0), metrics(Metrics()), fitted(false) {}
-    Ensemble& Ensemble::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Ensemble::Ensemble() : Classifier(Network()), n_models(0) {}
+
+    void Ensemble::trainModel(const torch::Tensor& weights)
     {
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        this->features = features;
-        this->className = className;
-        this->states = states;
-        auto n_classes = states[className].size();
-        metrics = Metrics(samples, features, className, n_classes);
-        // Build models
-        train();
-        // Train models
         n_models = models.size();
         for (auto i = 0; i < n_models; ++i) {
-            if (Xv.empty()) {
-                // fit with tensors
-                models[i]->fit(X, y, features, className, states);
-            } else {
-                // fit with vectors
-                models[i]->fit(Xv, yv, features, className, states);
+            // fit with std::vectors
+            models[i]->fit(dataset, features, className, states);
         }
     }
-        fitted = true;
-        return *this;
-    }
-    void Ensemble::generateTensorXFromVector()
-    {
-        X = torch::zeros({ static_cast<int>(Xv.size()), static_cast<int>(Xv[0].size()) }, kInt32);
-        for (int i = 0; i < Xv.size(); ++i) {
-            X.index_put_({ i, "..." }, torch::tensor(Xv[i], kInt32));
-        }
-    }
-    Ensemble& Ensemble::fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states)
-    {
-        this->X = X;
-        this->y = y;
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
-        return build(features, className, states);
-    }
-    Ensemble& Ensemble::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
-    {
-        Xv = X;
-        generateTensorXFromVector();
-        this->y = torch::tensor(y, kInt32);
-        yv = y;
-        return build(features, className, states);
-    }
-    vector<int> Ensemble::voting(Tensor& y_pred)
+    std::vector<int> Ensemble::voting(torch::Tensor& y_pred)
     {
         auto y_pred_ = y_pred.accessor<int, 2>();
-        vector<int> y_pred_final;
+        std::vector<int> y_pred_final;
+        int numClasses = states.at(className).size();
+        // y_pred is m x n_models with the prediction of every model for each sample
         for (int i = 0; i < y_pred.size(0); ++i) {
-            vector<float> votes(y_pred.size(1), 0);
-            for (int j = 0; j < y_pred.size(1); ++j) {
-                votes[y_pred_[i][j]] += 1;
+            // votes store in each index (value of class) the significance added by each model
+            // i.e. votes[0] contains how much value has the value 0 of class. That value is generated by the models predictions
+            std::vector<double> votes(numClasses, 0.0);
+            for (int j = 0; j < n_models; ++j) {
+                votes[y_pred_[i][j]] += significanceModels.at(j);
             }
             // argsort in descending order
             auto indices = argsort(votes);
@@ -67,19 +31,18 @@ namespace bayesnet {
         }
         return y_pred_final;
     }
-    Tensor Ensemble::predict(Tensor& X)
+    torch::Tensor Ensemble::predict(torch::Tensor& X)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
-        Tensor y_pred = torch::zeros({ X.size(1), n_models }, kInt32);
-        //Create a threadpool
-        auto threads{ vector<thread>() };
-        mutex mtx;
+        torch::Tensor y_pred = torch::zeros({ X.size(1), n_models }, torch::kInt32);
+        auto threads{ std::vector<std::thread>() };
+        std::mutex mtx;
         for (auto i = 0; i < n_models; ++i) {
-            threads.push_back(thread([&, i]() {
+            threads.push_back(std::thread([&, i]() {
                 auto ypredict = models[i]->predict(X);
-                lock_guard<mutex> lock(mtx);
+                std::lock_guard<std::mutex> lock(mtx);
                 y_pred.index_put_({ "...", i }, ypredict);
                 }));
         }
@@ -88,27 +51,27 @@ namespace bayesnet {
         }
         return torch::tensor(voting(y_pred));
     }
-    vector<int> Ensemble::predict(vector<vector<int>>& X)
+    std::vector<int> Ensemble::predict(std::vector<std::vector<int>>& X)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
         long m_ = X[0].size();
         long n_ = X.size();
-        vector<vector<int>> Xd(n_, vector<int>(m_, 0));
+        std::vector<std::vector<int>> Xd(n_, std::vector<int>(m_, 0));
         for (auto i = 0; i < n_; i++) {
-            Xd[i] = vector<int>(X[i].begin(), X[i].end());
+            Xd[i] = std::vector<int>(X[i].begin(), X[i].end());
         }
-        Tensor y_pred = torch::zeros({ m_, n_models }, kInt32);
+        torch::Tensor y_pred = torch::zeros({ m_, n_models }, torch::kInt32);
         for (auto i = 0; i < n_models; ++i) {
-            y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), kInt32));
+            y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), torch::kInt32));
         }
         return voting(y_pred);
     }
-    float Ensemble::score(Tensor& X, Tensor& y)
+    float Ensemble::score(torch::Tensor& X, torch::Tensor& y)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
         auto y_pred = predict(X);
         int correct = 0;
@@ -119,10 +82,10 @@ namespace bayesnet {
         }
         return (double)correct / y_pred.size(0);
     }
-    float Ensemble::score(vector<vector<int>>& X, vector<int>& y)
+    float Ensemble::score(std::vector<std::vector<int>>& X, std::vector<int>& y)
     {
         if (!fitted) {
-            throw logic_error("Ensemble has not been fitted");
+            throw std::logic_error("Ensemble has not been fitted");
         }
         auto y_pred = predict(X);
         int correct = 0;
@@ -132,27 +95,26 @@ namespace bayesnet {
             }
         }
         return (double)correct / y_pred.size();
-
     }
-    vector<string> Ensemble::show()
+    std::vector<std::string> Ensemble::show() const
     {
-        auto result = vector<string>();
+        auto result = std::vector<std::string>();
         for (auto i = 0; i < n_models; ++i) {
             auto res = models[i]->show();
             result.insert(result.end(), res.begin(), res.end());
         }
         return result;
     }
-    vector<string> Ensemble::graph(const string& title)
+    std::vector<std::string> Ensemble::graph(const std::string& title) const
     {
-        auto result = vector<string>();
+        auto result = std::vector<std::string>();
         for (auto i = 0; i < n_models; ++i) {
-            auto res = models[i]->graph(title + "_" + to_string(i));
+            auto res = models[i]->graph(title + "_" + std::to_string(i));
             result.insert(result.end(), res.begin(), res.end());
         }
         return result;
     }
-    int Ensemble::getNumberOfNodes()
+    int Ensemble::getNumberOfNodes() const
     {
         int nodes = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -160,7 +122,7 @@ namespace bayesnet {
         }
         return nodes;
     }
-    int Ensemble::getNumberOfEdges()
+    int Ensemble::getNumberOfEdges() const
     {
         int edges = 0;
         for (auto i = 0; i < n_models; ++i) {
@@ -168,7 +130,7 @@ namespace bayesnet {
         }
         return edges;
     }
-    int Ensemble::getNumberOfStates()
+    int Ensemble::getNumberOfStates() const
     {
         int nstates = 0;
         for (auto i = 0; i < n_models; ++i) {

src/BayesNet/Ensemble.h

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

src/BayesNet/FCBF.cc

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

src/BayesNet/FCBF.h

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

src/BayesNet/FeatureSelect.cc

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

src/BayesNet/FeatureSelect.h

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

src/BayesNet/IWSS.cc

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

src/BayesNet/IWSS.h

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

src/BayesNet/KDB.cc

@@ -1,10 +1,21 @@
 #include "KDB.h"
 
 namespace bayesnet {
-    using namespace torch;
+    KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta)
+    {
+        validHyperparameters = { "k", "theta" };
 
-    KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
-    void KDB::train()
+    }
+    void KDB::setHyperparameters(const nlohmann::json& hyperparameters)
+    {
+        if (hyperparameters.contains("k")) {
+            k = hyperparameters["k"];
+        }
+        if (hyperparameters.contains("theta")) {
+            theta = hyperparameters["theta"];
+        }
+    }
+    void KDB::buildModel(const torch::Tensor& weights)
     {
         /*
         1. For each feature Xi, compute mutual information, I(X;C),
@@ -28,15 +39,16 @@ namespace bayesnet {
         // 1. For each feature Xi, compute mutual information, I(X;C),
         // where C is the class.
         addNodes();
-        vector <float> mi;
+        const torch::Tensor& y = dataset.index({ -1, "..." });
+        std::vector<double> mi;
         for (auto i = 0; i < features.size(); i++) {
-            Tensor firstFeature = X.index({ i, "..." });
-            mi.push_back(metrics.mutualInformation(firstFeature, y));
+            torch::Tensor firstFeature = dataset.index({ i, "..." });
+            mi.push_back(metrics.mutualInformation(firstFeature, y, weights));
         }
         // 2. Compute class conditional mutual information I(Xi;XjIC), f or each
-        auto conditionalEdgeWeights = metrics.conditionalEdge();
+        auto conditionalEdgeWeights = metrics.conditionalEdge(weights);
         // 3. Let the used variable list, S, be empty.
-        vector<int> S;
+        std::vector<int> S;
         // 4. Let the DAG network being constructed, BN, begin with a single
         // class node, C.
         // 5. Repeat until S includes all domain features
@@ -54,9 +66,9 @@ namespace bayesnet {
             S.push_back(idx);
         }
     }
-    void KDB::add_m_edges(int idx, vector<int>& S, Tensor& weights)
+    void KDB::add_m_edges(int idx, std::vector<int>& S, torch::Tensor& weights)
     {
-        auto n_edges = min(k, static_cast<int>(S.size()));
+        auto n_edges = std::min(k, static_cast<int>(S.size()));
         auto cond_w = clone(weights);
         bool exit_cond = k == 0;
         int num = 0;
@@ -68,7 +80,7 @@ namespace bayesnet {
                     model.addEdge(features[max_minfo], features[idx]);
                     num++;
                 }
-                catch (const invalid_argument& e) {
+                catch (const std::invalid_argument& e) {
                     // Loops are not allowed
                 }
             }
@@ -78,11 +90,11 @@ namespace bayesnet {
             exit_cond = num == n_edges || candidates.size(0) == 0;
         }
     }
-    vector<string> KDB::graph(const string& title)
+    std::vector<std::string> KDB::graph(const std::string& title) const
     {
-        string header{ title };
+        std::string header{ title };
         if (title == "KDB") {
-            header += " (k=" + to_string(k) + ", theta=" + to_string(theta) + ")";
+            header += " (k=" + std::to_string(k) + ", theta=" + std::to_string(theta) + ")";
         }
         return model.graph(header);
     }

src/BayesNet/KDB.h

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

src/BayesNet/KDBLd.cc

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

src/BayesNet/KDBLd.h

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

src/BayesNet/Mst.cc

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

src/BayesNet/Mst.h

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

src/BayesNet/Network.cc

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

src/BayesNet/Network.h

@@ -3,62 +3,61 @@
 #include "Node.h"
 #include <map>
 #include <vector>
+#include "config.h"
 
 namespace bayesnet {
     class Network {
     private:
-        map<string, unique_ptr<Node>> nodes;
-        map<string, vector<int>> dataset;
+        std::map<std::string, std::unique_ptr<Node>> nodes;
         bool fitted;
         float maxThreads = 0.95;
         int classNumStates;
-        vector<string> features; // Including class
-        string className;
-        int laplaceSmoothing = 1;
+        std::vector<std::string> features; // Including classname
+        std::string className;
+        double laplaceSmoothing;
         torch::Tensor samples; // nxm tensor used to fit the model
         bool isCyclic(const std::string&, std::unordered_set<std::string>&, std::unordered_set<std::string>&);
-        vector<double> predict_sample(const vector<int>&);
-        vector<double> predict_sample(const torch::Tensor&);
-        vector<double> exactInference(map<string, int>&);
-        double computeFactor(map<string, int>&);
-        double mutual_info(torch::Tensor&, torch::Tensor&);
-        double entropy(torch::Tensor&);
-        double conditionalEntropy(torch::Tensor&, torch::Tensor&);
-        double mutualInformation(torch::Tensor&, torch::Tensor&);
-        void completeFit();
-        void checkFitData(int n_features, int n_samples, int n_samples_y, const vector<string>& featureNames, const string& className);
-        void setStates();
+        std::vector<double> predict_sample(const std::vector<int>&);
+        std::vector<double> predict_sample(const torch::Tensor&);
+        std::vector<double> exactInference(std::map<std::string, int>&);
+        double computeFactor(std::map<std::string, int>&);
+        void completeFit(const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
+        void checkFitData(int n_features, int n_samples, int n_samples_y, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states, const torch::Tensor& weights);
+        void setStates(const std::map<std::string, std::vector<int>>&);
     public:
         Network();
-        explicit Network(float, int);
         explicit Network(float);
         explicit Network(Network&);
+        ~Network() = default;
         torch::Tensor& getSamples();
         float getmaxThreads();
-        void addNode(const string&);
-        void addEdge(const string&, const string&);
-        map<string, std::unique_ptr<Node>>& getNodes();
-        vector<string> getFeatures();
-        int getStates();
-        vector<pair<string, string>> getEdges();
-        int getClassNumStates();
-        string getClassName();
-        void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
-        void fit(torch::Tensor&, torch::Tensor&, const vector<string>&, const string&);
-        vector<int> predict(const vector<vector<int>>&); // Return mx1 vector of predictions
+        void addNode(const std::string&);
+        void addEdge(const std::string&, const std::string&);
+        std::map<std::string, std::unique_ptr<Node>>& getNodes();
+        std::vector<std::string> getFeatures() const;
+        int getStates() const;
+        std::vector<std::pair<std::string, std::string>> getEdges() const;
+        int getNumEdges() const;
+        int getClassNumStates() const;
+        std::string getClassName() const;
+        /*
+        Notice: Nodes have to be inserted in the same order as they are in the dataset, i.e., first node is first column and so on.
+        */
+        void fit(const std::vector<std::vector<int>>& input_data, const std::vector<int>& labels, const std::vector<double>& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
+        void fit(const torch::Tensor& X, const torch::Tensor& y, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
+        void fit(const torch::Tensor& samples, const torch::Tensor& weights, const std::vector<std::string>& featureNames, const std::string& className, const std::map<std::string, std::vector<int>>& states);
+        std::vector<int> predict(const std::vector<std::vector<int>>&); // Return mx1 std::vector of predictions
         torch::Tensor predict(const torch::Tensor&); // Return mx1 tensor of predictions
-        //Computes the conditional edge weight of variable index u and v conditioned on class_node
-        torch::Tensor conditionalEdgeWeight();
         torch::Tensor predict_tensor(const torch::Tensor& samples, const bool proba);
-        vector<vector<double>> predict_proba(const vector<vector<int>>&); // Return mxn vector of probabilities
+        std::vector<std::vector<double>> predict_proba(const std::vector<std::vector<int>>&); // Return mxn std::vector of probabilities
         torch::Tensor predict_proba(const torch::Tensor&); // Return mxn tensor of probabilities
-        double score(const vector<vector<int>>&, const vector<int>&);
-        vector<string> topological_sort();
-        vector<string> show();
-        vector<string> graph(const string& title); // Returns a vector of strings representing the graph in graphviz format
+        double score(const std::vector<std::vector<int>>&, const std::vector<int>&);
+        std::vector<std::string> topological_sort();
+        std::vector<std::string> show() const;
+        std::vector<std::string> graph(const std::string& title) const; // Returns a std::vector of std::strings representing the graph in graphviz format
         void initialize();
-        void dump_cpt();
-        inline string version() { return "0.1.0"; }
+        void dump_cpt() const;
+        inline std::string version() { return  { project_version.begin(), project_version.end() }; }
     };
 }
 #endif

src/BayesNet/Node.cc

@@ -3,7 +3,7 @@
 namespace bayesnet {
 
     Node::Node(const std::string& name)
-        : name(name), numStates(0), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
+        : name(name), numStates(0), cpTable(torch::Tensor()), parents(std::vector<Node*>()), children(std::vector<Node*>())
     {
     }
     void Node::clear()
@@ -14,7 +14,7 @@ namespace bayesnet {
         dimensions.clear();
         numStates = 0;
     }
-    string Node::getName() const
+    std::string Node::getName() const
     {
         return name;
     }
@@ -34,11 +34,11 @@ namespace bayesnet {
     {
         children.push_back(child);
     }
-    vector<Node*>& Node::getParents()
+    std::vector<Node*>& Node::getParents()
     {
         return parents;
     }
-    vector<Node*>& Node::getChildren()
+    std::vector<Node*>& Node::getChildren()
     {
         return children;
     }
@@ -63,28 +63,28 @@ namespace bayesnet {
     */
     unsigned Node::minFill()
     {
-        unordered_set<string> neighbors;
+        std::unordered_set<std::string> neighbors;
         for (auto child : children) {
             neighbors.emplace(child->getName());
         }
         for (auto parent : parents) {
             neighbors.emplace(parent->getName());
         }
-        auto source = vector<string>(neighbors.begin(), neighbors.end());
+        auto source = std::vector<std::string>(neighbors.begin(), neighbors.end());
         return combinations(source).size();
     }
-    vector<pair<string, string>> Node::combinations(const vector<string>& source)
+    std::vector<std::pair<std::string, std::string>> Node::combinations(const std::vector<std::string>& source)
     {
-        vector<pair<string, string>> result;
+        std::vector<std::pair<std::string, std::string>> result;
         for (int i = 0; i < source.size(); ++i) {
-            string temp = source[i];
+            std::string temp = source[i];
             for (int j = i + 1; j < source.size(); ++j) {
                 result.push_back({ temp, source[j] });
             }
         }
         return result;
     }
-    void Node::computeCPT(map<string, vector<int>>& dataset, const int laplaceSmoothing)
+    void Node::computeCPT(const torch::Tensor& dataset, const std::vector<std::string>& features, const double laplaceSmoothing, const torch::Tensor& weights)
     {
         dimensions.clear();
         // Get dimensions of the CPT
@@ -94,27 +94,39 @@ namespace bayesnet {
         // Create a tensor of zeros with the dimensions of the CPT
         cpTable = torch::zeros(dimensions, torch::kFloat) + laplaceSmoothing;
         // Fill table with counts
-        for (int n_sample = 0; n_sample < dataset[name].size(); ++n_sample) {
-            torch::List<c10::optional<torch::Tensor>> coordinates;
-            coordinates.push_back(torch::tensor(dataset[name][n_sample]));
-            transform(parents.begin(), parents.end(), back_inserter(coordinates), [&dataset, &n_sample](const auto& parent) { return torch::tensor(dataset[parent->getName()][n_sample]); });
+        auto pos = find(features.begin(), features.end(), name);
+        if (pos == features.end()) {
+            throw std::logic_error("Feature " + name + " not found in dataset");
+        }
+        int name_index = pos - features.begin();
+        for (int n_sample = 0; n_sample < dataset.size(1); ++n_sample) {
+            c10::List<c10::optional<at::Tensor>> coordinates;
+            coordinates.push_back(dataset.index({ name_index, n_sample }));
+            for (auto parent : parents) {
+                pos = find(features.begin(), features.end(), parent->getName());
+                if (pos == features.end()) {
+                    throw std::logic_error("Feature parent " + parent->getName() + " not found in dataset");
+                }
+                int parent_index = pos - features.begin();
+                coordinates.push_back(dataset.index({ parent_index, n_sample }));
+            }
             // Increment the count of the corresponding coordinate
-            cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + 1);
+            cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + weights.index({ n_sample }).item<double>());
         }
         // Normalize the counts
         cpTable = cpTable / cpTable.sum(0);
     }
-    float Node::getFactorValue(map<string, int>& evidence)
+    float Node::getFactorValue(std::map<std::string, int>& evidence)
     {
-        torch::List<c10::optional<torch::Tensor>> coordinates;
+        c10::List<c10::optional<at::Tensor>> coordinates;
         // following predetermined order of indices in the cpTable (see Node.h)
-        coordinates.push_back(torch::tensor(evidence[name]));
-        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return torch::tensor(evidence[parent->getName()]); });
+        coordinates.push_back(at::tensor(evidence[name]));
+        transform(parents.begin(), parents.end(), std::back_inserter(coordinates), [&evidence](const auto& parent) { return at::tensor(evidence[parent->getName()]); });
         return cpTable.index({ coordinates }).item<float>();
     }
-    vector<string> Node::graph(const string& className)
+    std::vector<std::string> Node::graph(const std::string& className)
     {
-        auto output = vector<string>();
+        auto output = std::vector<std::string>();
         auto suffix = name == className ? ", fontcolor=red, fillcolor=lightblue, style=filled " : "";
         output.push_back(name + " [shape=circle" + suffix + "] \n");
         transform(children.begin(), children.end(), back_inserter(output), [this](const auto& child) { return name + " -> " + child->getName(); });

src/BayesNet/Node.h

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

src/BayesNet/Proposal.cc

@@ -2,21 +2,30 @@
 #include "ArffFiles.h"
 
 namespace bayesnet {
-    Proposal::Proposal(vector<vector<int>>& Xv_, vector<int>& yv_, vector<string>& features_, string& className_) : Xv(Xv_), yv(yv_), pFeatures(features_), pClassName(className_) {}
+    Proposal::Proposal(torch::Tensor& dataset_, std::vector<std::string>& features_, std::string& className_) : pDataset(dataset_), pFeatures(features_), pClassName(className_) {}
     Proposal::~Proposal()
     {
         for (auto& [key, value] : discretizers) {
             delete value;
         }
     }
-    void Proposal::localDiscretizationProposal(map<string, vector<int>>& states, Network& model)
+    void Proposal::checkInput(const torch::Tensor& X, const torch::Tensor& y)
+    {
+        if (!torch::is_floating_point(X)) {
+            throw std::invalid_argument("X must be a floating point tensor");
+        }
+        if (torch::is_floating_point(y)) {
+            throw std::invalid_argument("y must be an integer tensor");
+        }
+    }
+    map<std::string, std::vector<int>> Proposal::localDiscretizationProposal(const map<std::string, std::vector<int>>& oldStates, Network& model)
     {
         // order of local discretization is important. no good 0, 1, 2...
         // although we rediscretize features after the local discretization of every feature
         auto order = model.topological_sort();
         auto& nodes = model.getNodes();
-        vector<int> indicesToReDiscretize;
-        auto n_samples = Xf.size(1);
+        map<std::string, std::vector<int>> states = oldStates;
+        std::vector<int> indicesToReDiscretize;
         bool upgrade = false; // Flag to check if we need to upgrade the model
         for (auto feature : order) {
             auto nodeParents = nodes[feature]->getParents();
@@ -24,76 +33,75 @@ namespace bayesnet {
             upgrade = true;
             int index = find(pFeatures.begin(), pFeatures.end(), feature) - pFeatures.begin();
             indicesToReDiscretize.push_back(index); // We need to re-discretize this feature
-            vector<string> parents;
+            std::vector<std::string> parents;
             transform(nodeParents.begin(), nodeParents.end(), back_inserter(parents), [](const auto& p) { return p->getName(); });
             // Remove class as parent as it will be added later
             parents.erase(remove(parents.begin(), parents.end(), pClassName), parents.end());
             // Get the indices of the parents
-            vector<int> indices;
+            std::vector<int> indices;
+            indices.push_back(-1); // Add class index
             transform(parents.begin(), parents.end(), back_inserter(indices), [&](const auto& p) {return find(pFeatures.begin(), pFeatures.end(), p) - pFeatures.begin(); });
             // Now we fit the discretizer of the feature, conditioned on its parents and the class i.e. discretizer.fit(X[index], X[indices] + y)
-            vector<string> yJoinParents;
-            transform(yv.begin(), yv.end(), back_inserter(yJoinParents), [&](const auto& p) {return to_string(p); });
+            std::vector<std::string> yJoinParents(Xf.size(1));
             for (auto idx : indices) {
-                for (int i = 0; i < n_samples; ++i) {
-                    yJoinParents[i] += to_string(Xv[idx][i]);
+                for (int i = 0; i < Xf.size(1); ++i) {
+                    yJoinParents[i] += to_string(pDataset.index({ idx, i }).item<int>());
                 }
             }
             auto arff = ArffFiles();
             auto yxv = arff.factorize(yJoinParents);
             auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
-            auto xvf = vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
+            auto xvf = std::vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
             discretizers[feature]->fit(xvf, yxv);
-            //
-            //
-            //
-            // auto tmp = discretizers[feature]->transform(xvf);
-            // Xv[index] = tmp;
-            // auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
-            // iota(xStates.begin(), xStates.end(), 0);
-            // //Update new states of the feature/node
-            // states[feature] = xStates;
         }
         if (upgrade) {
             // Discretize again X (only the affected indices) with the new fitted discretizers
             for (auto index : indicesToReDiscretize) {
                 auto Xt_ptr = Xf.index({ index }).data_ptr<float>();
-                auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
-                Xv[index] = discretizers[pFeatures[index]]->transform(Xt);
-                auto xStates = vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
+                auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+                pDataset.index_put_({ index, "..." }, torch::tensor(discretizers[pFeatures[index]]->transform(Xt)));
+                auto xStates = std::vector<int>(discretizers[pFeatures[index]]->getCutPoints().size() + 1);
                 iota(xStates.begin(), xStates.end(), 0);
                 //Update new states of the feature/node
                 states[pFeatures[index]] = xStates;
             }
+            const torch::Tensor weights = torch::full({ pDataset.size(1) }, 1.0 / pDataset.size(1), torch::kDouble);
+            model.fit(pDataset, weights, pFeatures, pClassName, states);
         }
+        return states;
     }
-    void Proposal::fit_local_discretization(map<string, vector<int>>& states, torch::Tensor& y)
+    map<std::string, std::vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
     {
-        // Sharing Xv and yv with Classifier
-        Xv = vector<vector<int>>();
-        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        // Discretize the continuous input data and build pDataset (Classifier::dataset)
+        int m = Xf.size(1);
+        int n = Xf.size(0);
+        map<std::string, std::vector<int>> states;
+        pDataset = torch::zeros({ n + 1, m }, torch::kInt32);
+        auto yv = std::vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
         // discretize input data by feature(row)
-        for (int i = 0; i < pFeatures.size(); ++i) {
+        for (auto i = 0; i < pFeatures.size(); ++i) {
             auto* discretizer = new mdlp::CPPFImdlp();
             auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
-            auto Xt = vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
+            auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
             discretizer->fit(Xt, yv);
-            Xv.push_back(discretizer->transform(Xt));
-            auto xStates = vector<int>(discretizer->getCutPoints().size() + 1);
+            pDataset.index_put_({ i, "..." }, torch::tensor(discretizer->transform(Xt)));
+            auto xStates = std::vector<int>(discretizer->getCutPoints().size() + 1);
             iota(xStates.begin(), xStates.end(), 0);
             states[pFeatures[i]] = xStates;
             discretizers[pFeatures[i]] = discretizer;
         }
         int n_classes = torch::max(y).item<int>() + 1;
-        auto yStates = vector<int>(n_classes);
+        auto yStates = std::vector<int>(n_classes);
         iota(yStates.begin(), yStates.end(), 0);
         states[pClassName] = yStates;
+        pDataset.index_put_({ n, "..." }, y);
+        return states;
     }
     torch::Tensor Proposal::prepareX(torch::Tensor& X)
     {
         auto Xtd = torch::zeros_like(X, torch::kInt32);
         for (int i = 0; i < X.size(0); ++i) {
-            auto Xt = vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
+            auto Xt = std::vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
             auto Xd = discretizers[pFeatures[i]]->transform(Xt);
             Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
         }

src/BayesNet/Proposal.h

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

src/BayesNet/SPODE.cc

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

src/BayesNet/SPODE.h

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

src/BayesNet/SPODELd.cc

@@ -1,34 +1,46 @@
 #include "SPODELd.h"
 
 namespace bayesnet {
-    using namespace std;
-    SPODELd::SPODELd(int root) : SPODE(root), Proposal(SPODE::Xv, SPODE::yv, features, className) {}
-    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, vector<string>& features_, string className_, map<string, vector<int>>& states_)
+    SPODELd::SPODELd(int root) : SPODE(root), Proposal(dataset, features, className) {}
+    SPODELd& SPODELd::fit(torch::Tensor& X_, torch::Tensor& y_, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
     {
-        // This first part should go in a Classifier method called fit_local_discretization o fit_float...
+        checkInput(X_, y_);
         features = features_;
         className = className_;
         Xf = X_;
         y = y_;
-        // Fills vectors Xv & yv with the data from tensors X_ (discretized) & y
-        fit_local_discretization(states, y);
-        generateTensorXFromVector();
+        // Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
         // We have discretized the input data
         // 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
-        SPODE::fit(SPODE::Xv, SPODE::yv, features, className, states);
-        localDiscretizationProposal(states, model);
-        generateTensorXFromVector();
-        Tensor ytmp = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        samples = torch::cat({ X, ytmp }, 0);
-        model.fit(SPODE::Xv, SPODE::yv, features, className);
+        SPODE::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
         return *this;
     }
-    Tensor SPODELd::predict(Tensor& X)
+    SPODELd& SPODELd::fit(torch::Tensor& dataset, const std::vector<std::string>& features_, const std::string& className_, map<std::string, std::vector<int>>& states_)
+    {
+        if (!torch::is_floating_point(dataset)) {
+            throw std::runtime_error("Dataset must be a floating point tensor");
+        }
+        Xf = dataset.index({ torch::indexing::Slice(0, dataset.size(0) - 1), "..." }).clone();
+        y = dataset.index({ -1, "..." }).clone();
+        features = features_;
+        className = className_;
+        // Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
+        states = fit_local_discretization(y);
+        // We have discretized the input data
+        // 1st we need to fit the model to build the normal SPODE structure, SPODE::fit initializes the base Bayesian network
+        SPODE::fit(dataset, features, className, states);
+        states = localDiscretizationProposal(states, model);
+        return *this;
+    }
+
+    torch::Tensor SPODELd::predict(torch::Tensor& X)
     {
         auto Xt = prepareX(X);
         return SPODE::predict(Xt);
     }
-    vector<string> SPODELd::graph(const string& name)
+    std::vector<std::string> SPODELd::graph(const std::string& name) const
     {
         return SPODE::graph(name);
     }

src/BayesNet/SPODELd.h

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

src/BayesNet/TAN.cc

@@ -1,29 +1,27 @@
 #include "TAN.h"
 
 namespace bayesnet {
-    using namespace torch;
-
     TAN::TAN() : Classifier(Network()) {}
 
-    void TAN::train()
+    void TAN::buildModel(const torch::Tensor& weights)
     {
         // 0. Add all nodes to the model
         addNodes();
         // 1. Compute mutual information between each feature and the class and set the root node
         // as the highest mutual information with the class
-        auto mi = vector <pair<int, float >>();
-        Tensor class_dataset = samples.index({ -1, "..." });
+        auto mi = std::vector <std::pair<int, float >>();
+        torch::Tensor class_dataset = dataset.index({ -1, "..." });
         for (int i = 0; i < static_cast<int>(features.size()); ++i) {
-            Tensor feature_dataset = samples.index({ i, "..." });
-            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
+            torch::Tensor feature_dataset = dataset.index({ i, "..." });
+            auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset, weights);
             mi.push_back({ i, mi_value });
         }
         sort(mi.begin(), mi.end(), [](const auto& left, const auto& right) {return left.second < right.second;});
         auto root = mi[mi.size() - 1].first;
         // 2. Compute mutual information between each feature and the class
-        auto weights = metrics.conditionalEdge();
+        auto weights_matrix = metrics.conditionalEdge(weights);
         // 3. Compute the maximum spanning tree
-        auto mst = metrics.maximumSpanningTree(features, weights, root);
+        auto mst = metrics.maximumSpanningTree(features, weights_matrix, root);
         // 4. Add edges from the maximum spanning tree to the model
         for (auto i = 0; i < mst.size(); ++i) {
             auto [from, to] = mst[i];
@@ -34,7 +32,7 @@ namespace bayesnet {
             model.addEdge(className, feature);
         }
     }
-    vector<string> TAN::graph(const string& title)
+    std::vector<std::string> TAN::graph(const std::string& title) const
     {
         return model.graph(title);
     }

src/BayesNet/TAN.h

@@ -2,16 +2,14 @@
 #define TAN_H
 #include "Classifier.h"
 namespace bayesnet {
-    using namespace std;
-    using namespace torch;
     class TAN : public Classifier {
     private:
     protected:
-        void train() override;
+        void buildModel(const torch::Tensor& weights) override;
     public:
         TAN();
-        virtual ~TAN() {};
-        vector<string> graph(const string& name = "TAN") override;
+        virtual ~TAN() = default;
+        std::vector<std::string> graph(const std::string& name = "TAN") const override;
     };
 }
 #endif

src/BayesNet/TANLd.cc

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

src/BayesNet/TANLd.h

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

src/BayesNet/bayesnetUtils.cc

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

src/BayesNet/bayesnetUtils.h

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

src/Platform/CMakeLists.txt

@@ -1,8 +0,0 @@
-include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
-include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
-include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
-include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
-include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
-include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
-add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc Report.cc)
-target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/Datasets.cc

@@ -1,231 +0,0 @@
-#include "Datasets.h"
-#include "platformUtils.h"
-#include "ArffFiles.h"
-namespace platform {
-    void Datasets::load()
-    {
-        ifstream catalog(path + "/all.txt");
-        if (catalog.is_open()) {
-            string line;
-            while (getline(catalog, line)) {
-                vector<string> tokens = split(line, ',');
-                string name = tokens[0];
-                string 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" + "]");
-        }
-    }
-    vector<string> Datasets::getNames()
-    {
-        vector<string> result;
-        transform(datasets.begin(), datasets.end(), back_inserter(result), [](const auto& d) { return d.first; });
-        return result;
-    }
-    vector<string> Datasets::getFeatures(string name)
-    {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getFeatures();
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    map<string, vector<int>> Datasets::getStates(string name)
-    {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getStates();
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    string Datasets::getClassName(string name)
-    {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getClassName();
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    int Datasets::getNSamples(string name)
-    {
-        if (datasets[name]->isLoaded()) {
-            return datasets[name]->getNSamples();
-        } else {
-            throw invalid_argument("Dataset not loaded.");
-        }
-    }
-    pair<vector<vector<float>>&, vector<int>&> Datasets::getVectors(string name)
-    {
-        if (!datasets[name]->isLoaded()) {
-            datasets[name]->load();
-        }
-        return datasets[name]->getVectors();
-    }
-    pair<vector<vector<int>>&, vector<int>&> Datasets::getVectorsDiscretized(string name)
-    {
-        if (!datasets[name]->isLoaded()) {
-            datasets[name]->load();
-        }
-        return datasets[name]->getVectorsDiscretized();
-    }
-    pair<torch::Tensor&, torch::Tensor&> Datasets::getTensors(string name)
-    {
-        if (!datasets[name]->isLoaded()) {
-            datasets[name]->load();
-        }
-        return datasets[name]->getTensors();
-    }
-    bool Datasets::isDataset(const string& name)
-    {
-        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

@@ -1,65 +0,0 @@
-#ifndef DATASETS_H
-#define DATASETS_H
-#include <torch/torch.h>
-#include <map>
-#include <vector>
-#include <string>
-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;
-        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(); };
-        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);
-    };
-};
-
-#endif

src/Platform/DotEnv.h

@@ -1,62 +0,0 @@
-#ifndef DOTENV_H
-#define DOTENV_H
-#include <string>
-#include <map>
-#include <fstream>
-#include <sstream>
-#include "platformUtils.h"
-namespace platform {
-    class DotEnv {
-    private:
-        std::map<std::string, std::string> env;
-        std::string trim(const std::string& str)
-        {
-            std::string result = str;
-            result.erase(result.begin(), std::find_if(result.begin(), result.end(), [](int ch) {
-                return !std::isspace(ch);
-                }));
-            result.erase(std::find_if(result.rbegin(), result.rend(), [](int ch) {
-                return !std::isspace(ch);
-                }).base(), result.end());
-            return result;
-        }
-    public:
-        DotEnv()
-        {
-            std::ifstream file(".env");
-            if (!file.is_open()) {
-                std::cerr << "File .env not found" << std::endl;
-                exit(1);
-            }
-            std::string line;
-            while (std::getline(file, line)) {
-                line = trim(line);
-                if (line.empty() || line[0] == '#') {
-                    continue;
-                }
-                std::istringstream iss(line);
-                std::string key, value;
-                if (std::getline(iss, key, '=') && std::getline(iss, value)) {
-                    env[key] = value;
-                }
-            }
-        }
-        std::string get(const std::string& key)
-        {
-            return env[key];
-        }
-        std::vector<int> getSeeds()
-        {
-            auto seeds = std::vector<int>();
-            auto seeds_str = env["seeds"];
-            seeds_str = trim(seeds_str);
-            seeds_str = seeds_str.substr(1, seeds_str.size() - 2);
-            auto seeds_str_split = split(seeds_str, ',');
-            transform(seeds_str_split.begin(), seeds_str_split.end(), back_inserter(seeds), [](const std::string& str) {
-                return stoi(str);
-                });
-            return seeds;
-        }
-    };
-}
-#endif

src/Platform/Experiment.cc

@@ -1,184 +0,0 @@
-#include "Experiment.h"
-#include "Datasets.h"
-#include "Models.h"
-#include "Report.h"
-
-namespace platform {
-    using json = nlohmann::json;
-    string get_date()
-    {
-        time_t rawtime;
-        tm* timeinfo;
-        time(&rawtime);
-        timeinfo = std::localtime(&rawtime);
-        std::ostringstream oss;
-        oss << std::put_time(timeinfo, "%Y-%m-%d");
-        return oss.str();
-    }
-    string get_time()
-    {
-        time_t rawtime;
-        tm* timeinfo;
-        time(&rawtime);
-        timeinfo = std::localtime(&rawtime);
-        std::ostringstream oss;
-        oss << std::put_time(timeinfo, "%H:%M:%S");
-        return oss.str();
-    }
-    string Experiment::get_file_name()
-    {
-        string result = "results_" + score_name + "_" + model + "_" + platform + "_" + get_date() + "_" + get_time() + "_" + (stratified ? "1" : "0") + ".json";
-        return result;
-    }
-
-    json Experiment::build_json()
-    {
-        json result;
-        result["title"] = title;
-        result["date"] = get_date();
-        result["time"] = get_time();
-        result["model"] = model;
-        result["version"] = model_version;
-        result["platform"] = platform;
-        result["score_name"] = score_name;
-        result["language"] = language;
-        result["language_version"] = language_version;
-        result["discretized"] = discretized;
-        result["stratified"] = stratified;
-        result["folds"] = nfolds;
-        result["seeds"] = randomSeeds;
-        result["duration"] = duration;
-        result["results"] = json::array();
-        for (const auto& r : results) {
-            json j;
-            j["dataset"] = r.getDataset();
-            j["hyperparameters"] = r.getHyperparameters();
-            j["samples"] = r.getSamples();
-            j["features"] = r.getFeatures();
-            j["classes"] = r.getClasses();
-            j["score_train"] = r.getScoreTrain();
-            j["score_test"] = r.getScoreTest();
-            j["score"] = r.getScoreTest();
-            j["score_std"] = r.getScoreTestStd();
-            j["score_train_std"] = r.getScoreTrainStd();
-            j["score_test_std"] = r.getScoreTestStd();
-            j["train_time"] = r.getTrainTime();
-            j["train_time_std"] = r.getTrainTimeStd();
-            j["test_time"] = r.getTestTime();
-            j["test_time_std"] = r.getTestTimeStd();
-            j["time"] = r.getTestTime() + r.getTrainTime();
-            j["time_std"] = r.getTestTimeStd() + r.getTrainTimeStd();
-            j["scores_train"] = r.getScoresTrain();
-            j["scores_test"] = r.getScoresTest();
-            j["times_train"] = r.getTimesTrain();
-            j["times_test"] = r.getTimesTest();
-            j["nodes"] = r.getNodes();
-            j["leaves"] = r.getLeaves();
-            j["depth"] = r.getDepth();
-            result["results"].push_back(j);
-        }
-        return result;
-    }
-    void Experiment::save(const string& path)
-    {
-        json data = build_json();
-        ofstream file(path + "/" + get_file_name());
-        file << data;
-        file.close();
-    }
-
-    void Experiment::report()
-    {
-        json data = build_json();
-        Report report(data);
-        report.show();
-    }
-
-    void Experiment::show()
-    {
-        json data = build_json();
-        cout << data.dump(4) << endl;
-    }
-
-    void Experiment::go(vector<string> filesToProcess, const string& path)
-    {
-        cout << "*** Starting experiment: " << title << " ***" << endl;
-        for (auto fileName : filesToProcess) {
-            cout << "- " << setw(20) << left << fileName << " " << right << flush;
-            cross_validation(path, fileName);
-            cout << endl;
-        }
-    }
-
-    void Experiment::cross_validation(const string& path, const string& fileName)
-    {
-        auto datasets = platform::Datasets(path, discretized, platform::ARFF);
-        // Get dataset
-        auto [X, y] = datasets.getTensors(fileName);
-        auto states = datasets.getStates(fileName);
-        auto features = datasets.getFeatures(fileName);
-        auto samples = datasets.getNSamples(fileName);
-        auto className = datasets.getClassName(fileName);
-        cout << " (" << setw(5) << samples << "," << setw(3) << features.size() << ") " << flush;
-        // Prepare Result
-        auto result = Result();
-        auto [values, counts] = at::_unique(y);
-        result.setSamples(X.size(1)).setFeatures(X.size(0)).setClasses(values.size(0));
-        int nResults = nfolds * static_cast<int>(randomSeeds.size());
-        auto accuracy_test = torch::zeros({ nResults }, torch::kFloat64);
-        auto accuracy_train = torch::zeros({ nResults }, torch::kFloat64);
-        auto train_time = torch::zeros({ nResults }, torch::kFloat64);
-        auto test_time = torch::zeros({ nResults }, torch::kFloat64);
-        auto nodes = torch::zeros({ nResults }, torch::kFloat64);
-        auto edges = torch::zeros({ nResults }, torch::kFloat64);
-        auto num_states = torch::zeros({ nResults }, torch::kFloat64);
-        Timer train_timer, test_timer;
-        int item = 0;
-        for (auto seed : randomSeeds) {
-            cout << "(" << seed << ") doing Fold: " << flush;
-            Fold* fold;
-            if (stratified)
-                fold = new StratifiedKFold(nfolds, y, seed);
-            else
-                fold = new KFold(nfolds, y.size(0), seed);
-            for (int nfold = 0; nfold < nfolds; nfold++) {
-                auto clf = Models::instance()->create(model);
-                setModelVersion(clf->getVersion());
-                train_timer.start();
-                auto [train, test] = fold->getFold(nfold);
-                auto train_t = torch::tensor(train);
-                auto test_t = torch::tensor(test);
-                auto X_train = X.index({ "...", train_t });
-                auto y_train = y.index({ train_t });
-                auto X_test = X.index({ "...", test_t });
-                auto y_test = y.index({ test_t });
-                cout << nfold + 1 << ", " << flush;
-                clf->fit(X_train, y_train, features, className, states);
-                nodes[item] = clf->getNumberOfNodes();
-                edges[item] = clf->getNumberOfEdges();
-                num_states[item] = clf->getNumberOfStates();
-                train_time[item] = train_timer.getDuration();
-                auto accuracy_train_value = clf->score(X_train, y_train);
-                test_timer.start();
-                auto accuracy_test_value = clf->score(X_test, y_test);
-                test_time[item] = test_timer.getDuration();
-                accuracy_train[item] = accuracy_train_value;
-                accuracy_test[item] = accuracy_test_value;
-                // Store results and times in vector
-                result.addScoreTrain(accuracy_train_value);
-                result.addScoreTest(accuracy_test_value);
-                result.addTimeTrain(train_time[item].item<double>());
-                result.addTimeTest(test_time[item].item<double>());
-                item++;
-            }
-            cout << "end. " << flush;
-            delete fold;
-        }
-        result.setScoreTest(torch::mean(accuracy_test).item<double>()).setScoreTrain(torch::mean(accuracy_train).item<double>());
-        result.setScoreTestStd(torch::std(accuracy_test).item<double>()).setScoreTrainStd(torch::std(accuracy_train).item<double>());
-        result.setTrainTime(torch::mean(train_time).item<double>()).setTestTime(torch::mean(test_time).item<double>());
-        result.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

@@ -1,114 +0,0 @@
-#ifndef EXPERIMENT_H
-#define EXPERIMENT_H
-#include <torch/torch.h>
-#include <nlohmann/json.hpp>
-#include <string>
-#include <chrono>
-#include "Folding.h"
-#include "BaseClassifier.h"
-#include "TAN.h"
-#include "KDB.h"
-#include "AODE.h"
-
-using namespace std;
-namespace platform {
-    using json = nlohmann::json;
-    class Timer {
-    private:
-        chrono::high_resolution_clock::time_point begin;
-    public:
-        Timer() = default;
-        ~Timer() = default;
-        void start() { begin = chrono::high_resolution_clock::now(); }
-        double getDuration()
-        {
-            chrono::high_resolution_clock::time_point end = chrono::high_resolution_clock::now();
-            chrono::duration<double> time_span = chrono::duration_cast<chrono::duration<double>>(end - begin);
-            return time_span.count();
-        }
-    };
-    class Result {
-    private:
-        string dataset, hyperparameters, model_version;
-        int samples{ 0 }, features{ 0 }, classes{ 0 };
-        double score_train{ 0 }, score_test{ 0 }, score_train_std{ 0 }, score_test_std{ 0 }, train_time{ 0 }, train_time_std{ 0 }, test_time{ 0 }, test_time_std{ 0 };
-        float nodes{ 0 }, leaves{ 0 }, depth{ 0 };
-        vector<double> scores_train, scores_test, times_train, times_test;
-    public:
-        Result() = default;
-        Result& setDataset(const string& dataset) { this->dataset = dataset; return *this; }
-        Result& setHyperparameters(const string& 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; }
-        Result& setScoreTrain(double score) { this->score_train = score; return *this; }
-        Result& setScoreTest(double score) { this->score_test = score; return *this; }
-        Result& setScoreTrainStd(double score_std) { this->score_train_std = score_std; return *this; }
-        Result& setScoreTestStd(double score_std) { this->score_test_std = score_std; return *this; }
-        Result& setTrainTime(double train_time) { this->train_time = train_time; return *this; }
-        Result& setTrainTimeStd(double train_time_std) { this->train_time_std = train_time_std; return *this; }
-        Result& setTestTime(double test_time) { this->test_time = test_time; return *this; }
-        Result& setTestTimeStd(double test_time_std) { this->test_time_std = test_time_std; return *this; }
-        Result& setNodes(float nodes) { this->nodes = nodes; return *this; }
-        Result& setLeaves(float leaves) { this->leaves = leaves; return *this; }
-        Result& setDepth(float depth) { this->depth = depth; return *this; }
-        Result& addScoreTrain(double score) { scores_train.push_back(score); return *this; }
-        Result& addScoreTest(double score) { scores_test.push_back(score); return *this; }
-        Result& addTimeTrain(double time) { times_train.push_back(time); return *this; }
-        Result& addTimeTest(double time) { times_test.push_back(time); return *this; }
-        const float get_score_train() const { return score_train; }
-        float get_score_test() { return score_test; }
-        const string& getDataset() const { return dataset; }
-        const string& getHyperparameters() const { return hyperparameters; }
-        const int getSamples() const { return samples; }
-        const int getFeatures() const { return features; }
-        const int getClasses() const { return classes; }
-        const double getScoreTrain() const { return score_train; }
-        const double getScoreTest() const { return score_test; }
-        const double getScoreTrainStd() const { return score_train_std; }
-        const double getScoreTestStd() const { return score_test_std; }
-        const double getTrainTime() const { return train_time; }
-        const double getTrainTimeStd() const { return train_time_std; }
-        const double getTestTime() const { return test_time; }
-        const double getTestTimeStd() const { return test_time_std; }
-        const float getNodes() const { return nodes; }
-        const float getLeaves() const { return leaves; }
-        const float getDepth() const { return depth; }
-        const vector<double>& getScoresTrain() const { return scores_train; }
-        const vector<double>& getScoresTest() const { return scores_test; }
-        const vector<double>& getTimesTrain() const { return times_train; }
-        const vector<double>& getTimesTest() const { return times_test; }
-    };
-    class Experiment {
-    private:
-        string title, model, platform, score_name, model_version, language_version, language;
-        bool discretized{ false }, stratified{ false };
-        vector<Result> results;
-        vector<int> randomSeeds;
-        int nfolds{ 0 };
-        float duration{ 0 };
-        json build_json();
-    public:
-        Experiment() = default;
-        Experiment& setTitle(const string& title) { this->title = title; return *this; }
-        Experiment& setModel(const string& model) { this->model = model; return *this; }
-        Experiment& setPlatform(const string& platform) { this->platform = platform; return *this; }
-        Experiment& setScoreName(const string& score_name) { this->score_name = score_name; return *this; }
-        Experiment& setModelVersion(const string& model_version) { this->model_version = model_version; return *this; }
-        Experiment& setLanguage(const string& language) { this->language = language; return *this; }
-        Experiment& setLanguageVersion(const string& language_version) { this->language_version = language_version; return *this; }
-        Experiment& setDiscretized(bool discretized) { this->discretized = discretized; return *this; }
-        Experiment& setStratified(bool stratified) { this->stratified = stratified; return *this; }
-        Experiment& setNFolds(int nfolds) { this->nfolds = nfolds; return *this; }
-        Experiment& addResult(Result result) { results.push_back(result); return *this; }
-        Experiment& addRandomSeed(int randomSeed) { randomSeeds.push_back(randomSeed); return *this; }
-        Experiment& setDuration(float duration) { this->duration = duration; return *this; }
-        string get_file_name();
-        void save(const string& path);
-        void cross_validation(const string& path, const string& fileName);
-        void go(vector<string> filesToProcess, const string& path);
-        void show();
-        void report();
-    };
-}
-#endif

src/Platform/Folding.cc

@@ -1,95 +0,0 @@
-#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) + ")");
-    }
-    int nTest = n / k;
-    auto train = vector<int>();
-    auto test = vector<int>();
-    for (int i = 0; i < n; i++) {
-        if (i >= nTest * nFold && i < nTest * (nFold + 1)) {
-            test.push_back(indices[i]);
-        } else {
-            train.push_back(indices[i]);
-        }
-    }
-    return { train, test };
-}
-StratifiedKFold::StratifiedKFold(int k, torch::Tensor& y, int seed) : Fold(k, y.numel(), seed)
-{
-    n = y.numel();
-    this->y = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
-    build();
-}
-StratifiedKFold::StratifiedKFold(int k, const vector<int>& y, int seed)
-    : Fold(k, y.size(), seed)
-{
-    this->y = y;
-    n = y.size();
-    build();
-}
-void StratifiedKFold::build()
-{
-    stratified_indices = vector<vector<int>>(k);
-    int fold_size = n / k;
-    // Compute class counts and indices
-    auto class_indices = map<int, vector<int>>();
-    vector<int> class_counts(*max_element(y.begin(), y.end()) + 1, 0);
-    for (auto i = 0; i < n; ++i) {
-        class_counts[y[i]]++;
-        class_indices[y[i]].push_back(i);
-    }
-    // Shuffle class indices
-    for (auto& [cls, indices] : class_indices) {
-        shuffle(indices.begin(), indices.end(), random_seed);
-    }
-    // Assign indices to folds
-    for (auto label = 0; label < class_counts.size(); ++label) {
-        auto num_samples_to_take = class_counts[label] / k;
-        if (num_samples_to_take == 0)
-            continue;
-        auto remainder_samples_to_take = class_counts[label] % k;
-        for (auto fold = 0; fold < k; ++fold) {
-            auto it = next(class_indices[label].begin(), num_samples_to_take);
-            move(class_indices[label].begin(), it, back_inserter(stratified_indices[fold]));  // ##
-            class_indices[label].erase(class_indices[label].begin(), it);
-        }
-        while (remainder_samples_to_take > 0) {
-            int fold = (rand() % static_cast<int>(k));
-            if (stratified_indices[fold].size() == fold_size + 1) {
-                continue;
-            }
-            auto it = next(class_indices[label].begin(), 1);
-            stratified_indices[fold].push_back(*class_indices[label].begin());
-            class_indices[label].erase(class_indices[label].begin(), it);
-            remainder_samples_to_take--;
-        }
-    }
-}
-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 };
-}

src/Platform/Folding.h

@@ -1,37 +0,0 @@
-#ifndef FOLDING_H
-#define FOLDING_H
-#include <torch/torch.h>
-#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;
-};
-#endif

src/Platform/Models.cc

@@ -1,54 +0,0 @@
-#include "Models.h"
-namespace platform {
-    using namespace std;
-    // Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
-    Models* Models::factory = nullptr;;
-    Models* Models::instance()
-    {
-        //manages singleton
-        if (factory == nullptr)
-            factory = new Models();
-        return factory;
-    }
-    void Models::registerFactoryFunction(const string& name,
-        function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
-    {
-        // register the class factory function
-        functionRegistry[name] = classFactoryFunction;
-    }
-    shared_ptr<bayesnet::BaseClassifier> Models::create(const string& name)
-    {
-        bayesnet::BaseClassifier* instance = nullptr;
-
-        // find name in the registry and call factory method.
-        auto it = functionRegistry.find(name);
-        if (it != functionRegistry.end())
-            instance = it->second();
-        // wrap instance in a shared ptr and return
-        if (instance != nullptr)
-            return shared_ptr<bayesnet::BaseClassifier>(instance);
-        else
-            return nullptr;
-    }
-    vector<string> Models::getNames()
-    {
-        vector<string> names;
-        transform(functionRegistry.begin(), functionRegistry.end(), back_inserter(names),
-            [](const pair<string, function<bayesnet::BaseClassifier* (void)>>& pair) { return pair.first; });
-        return names;
-    }
-    string Models::toString()
-    {
-        string result = "";
-        for (const auto& pair : functionRegistry) {
-            result += pair.first + ", ";
-        }
-        return "{" + result.substr(0, result.size() - 2) + "}";
-    }
-
-    Registrar::Registrar(const string& name, function<bayesnet::BaseClassifier* (void)> classFactoryFunction)
-    {
-        // register the class factory function 
-        Models::instance()->registerFactoryFunction(name, classFactoryFunction);
-    }
-}

src/Platform/Models.h

@@ -1,36 +0,0 @@
-#ifndef MODELS_H
-#define MODELS_H
-#include <map>
-#include "BaseClassifier.h"
-#include "AODE.h"
-#include "TAN.h"
-#include "KDB.h"
-#include "SPODE.h"
-#include "TANLd.h"
-#include "KDBLd.h"
-#include "SPODELd.h"
-#include "AODELd.h"
-namespace platform {
-    class Models {
-    private:
-        map<string, function<bayesnet::BaseClassifier* (void)>> functionRegistry;
-        static Models* factory; //singleton
-        Models() {};
-    public:
-        Models(Models&) = delete;
-        void operator=(const Models&) = delete;
-        // Idea from: https://www.codeproject.com/Articles/567242/AplusC-2b-2bplusObjectplusFactory
-        static Models* instance();
-        shared_ptr<bayesnet::BaseClassifier> create(const string& name);
-        void registerFactoryFunction(const string& name,
-            function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
-        vector<string> getNames();
-        string toString();
-
-    };
-    class Registrar {
-    public:
-        Registrar(const string& className, function<bayesnet::BaseClassifier* (void)> classFactoryFunction);
-    };
-}
-#endif

src/Platform/Report.cc

@@ -1,66 +0,0 @@
-#include "Report.h"
-
-namespace platform {
-    string headerLine(const string& text)
-    {
-        int n = MAXL - text.length() - 3;
-        return "* " + text + string(n, ' ') + "*\n";
-    }
-    string Report::fromVector(const string& key)
-    {
-        string result = "";
-
-        for (auto& item : data[key]) {
-            result += to_string(item) + ", ";
-        }
-        return "[" + result.substr(0, result.length() - 2) + "]";
-    }
-    string fVector(const json& data)
-    {
-        string result = "";
-        for (const auto& item : data) {
-            result += to_string(item) + ", ";
-        }
-        return "[" + result.substr(0, result.length() - 2) + "]";
-    }
-    void Report::show()
-    {
-        header();
-        body();
-    }
-    void Report::header()
-    {
-        cout << string(MAXL, '*') << endl;
-        cout << headerLine("Report " + data["model"].get<string>() + " ver. " + data["version"].get<string>() + " with " + to_string(data["folds"].get<int>()) + " Folds cross validation and " + to_string(data["seeds"].size()) + " random seeds. " + data["date"].get<string>() + " " + data["time"].get<string>());
-        cout << headerLine(data["title"].get<string>());
-        cout << headerLine("Random seeds: " + fromVector("seeds") + " Stratified: " + (data["stratified"].get<bool>() ? "True" : "False"));
-        cout << headerLine("Execution took  " + to_string(data["duration"].get<float>()) + " seconds,   " + to_string(data["duration"].get<float>() / 3600) + " hours, on " + data["platform"].get<string>());
-        cout << headerLine("Score is " + data["score_name"].get<string>());
-        cout << string(MAXL, '*') << endl;
-        cout << endl;
-    }
-    void Report::body()
-    {
-        cout << "Dataset                        Sampl. Feat. Cls Nodes   Edges   States  Score           Time              Hyperparameters" << endl;
-        cout << "============================== ====== ===== === ======= ======= ======= =============== ================= ===============" << endl;
-        for (const auto& r : data["results"]) {
-            cout << setw(30) << left << r["dataset"].get<string>() << " ";
-            cout << setw(6) << right << r["samples"].get<int>() << " ";
-            cout << setw(5) << right << r["features"].get<int>() << " ";
-            cout << setw(3) << right << r["classes"].get<int>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["nodes"].get<float>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["leaves"].get<float>() << " ";
-            cout << setw(7) << setprecision(2) << fixed << r["depth"].get<float>() << " ";
-            cout << setw(8) << right << setprecision(6) << fixed << r["score_test"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["score_test_std"].get<double>() << " ";
-            cout << setw(10) << right << setprecision(6) << fixed << r["test_time"].get<double>() << "±" << setw(6) << setprecision(4) << fixed << r["test_time_std"].get<double>() << " ";
-            cout << " " << r["hyperparameters"].get<string>();
-            cout << endl;
-            cout << string(MAXL, '*') << endl;
-            cout << headerLine("Train scores: " + fVector(r["scores_train"]));
-            cout << headerLine("Test  scores: " + fVector(r["scores_test"]));
-            cout << headerLine("Train  times: " + fVector(r["times_train"]));
-            cout << headerLine("Test   times: " + fVector(r["times_test"]));
-            cout << string(MAXL, '*') << endl;
-        }
-    }
-}

src/Platform/Report.h

@@ -1,23 +0,0 @@
-#ifndef REPORT_H
-#define REPORT_H
-#include <string>
-#include <iostream>
-#include <nlohmann/json.hpp>
-
-using json = nlohmann::json;
-const int MAXL = 121;
-namespace platform {
-    using namespace std;
-    class Report {
-    public:
-        explicit Report(json data_) { data = data_; };
-        virtual ~Report() = default;
-        void show();
-    private:
-        void header();
-        void body();
-        string fromVector(const string& key);
-        json data;
-    };
-};
-#endif

src/Platform/main.cc

@@ -1,123 +0,0 @@
-#include <iostream>
-#include <argparse/argparse.hpp>
-#include "platformUtils.h"
-#include "Experiment.h"
-#include "Datasets.h"
-#include "DotEnv.h"
-#include "Models.h"
-#include "modelRegister.h"
-
-using namespace std;
-const string PATH_RESULTS = "results";
-const string PATH_DATASETS = "datasets";
-
-argparse::ArgumentParser manageArguments(int argc, char** argv)
-{
-    auto env = platform::DotEnv();
-    argparse::ArgumentParser program("BayesNetSample");
-    program.add_argument("-d", "--dataset").default_value("").help("Dataset file name");
-    program.add_argument("-p", "--path")
-        .help("folder where the data files are located, default")
-        .default_value(string{ PATH_DATASETS }
-    );
-    program.add_argument("-m", "--model")
-        .help("Model to use " + platform::Models::instance()->toString())
-        .action([](const std::string& value) {
-        static const vector<string> choices = platform::Models::instance()->getNames();
-        if (find(choices.begin(), choices.end(), value) != choices.end()) {
-            return value;
-        }
-        throw runtime_error("Model must be one of " + platform::Models::instance()->toString());
-            }
-    );
-    program.add_argument("--title").default_value("").help("Experiment title");
-    program.add_argument("--discretize").help("Discretize input dataset").default_value((bool)stoi(env.get("discretize"))).implicit_value(true);
-    program.add_argument("--stratified").help("If Stratified KFold is to be done").default_value((bool)stoi(env.get("stratified"))).implicit_value(true);
-    program.add_argument("-f", "--folds").help("Number of folds").default_value(stoi(env.get("n_folds"))).scan<'i', int>().action([](const string& value) {
-        try {
-            auto k = stoi(value);
-            if (k < 2) {
-                throw runtime_error("Number of folds must be greater than 1");
-            }
-            return k;
-        }
-        catch (const runtime_error& err) {
-            throw runtime_error(err.what());
-        }
-        catch (...) {
-            throw runtime_error("Number of folds must be an integer");
-        }});
-    auto seed_values = env.getSeeds();
-    program.add_argument("-s", "--seeds").nargs(1, 10).help("Random seeds. Set to -1 to have pseudo random").scan<'i', int>().default_value(seed_values);
-    try {
-        program.parse_args(argc, argv);
-        auto file_name = program.get<string>("dataset");
-        auto path = program.get<string>("path");
-        auto model_name = program.get<string>("model");
-        auto discretize_dataset = program.get<bool>("discretize");
-        auto stratified = program.get<bool>("stratified");
-        auto n_folds = program.get<int>("folds");
-        auto seeds = program.get<vector<int>>("seeds");
-        auto complete_file_name = path + file_name + ".arff";
-        auto title = program.get<string>("title");
-        if (title == "" && file_name == "") {
-            throw runtime_error("title is mandatory if dataset is not provided");
-        }
-    }
-    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);
-    bool saveResults = false;
-    auto file_name = program.get<string>("dataset");
-    auto path = program.get<string>("path");
-    auto model_name = program.get<string>("model");
-    auto discretize_dataset = program.get<bool>("discretize");
-    auto stratified = program.get<bool>("stratified");
-    auto n_folds = program.get<int>("folds");
-    auto seeds = program.get<vector<int>>("seeds");
-    vector<string> filesToTest;
-    auto datasets = platform::Datasets(path, true, platform::ARFF);
-    auto title = program.get<string>("title");
-    if (file_name != "") {
-        if (!datasets.isDataset(file_name)) {
-            cerr << "Dataset " << file_name << " not found" << endl;
-            exit(1);
-        }
-        if (title == "") {
-            title = "Test " + file_name + " " + model_name + " " + to_string(n_folds) + " folds";
-        }
-        filesToTest.push_back(file_name);
-    } else {
-        filesToTest = platform::Datasets(path, true, platform::ARFF).getNames();
-        saveResults = true;
-    }
-    /*
-    * Begin Processing
-    */
-    auto env = platform::DotEnv();
-    auto experiment = platform::Experiment();
-    experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("1.0.0");
-    experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform(env.get("platform"));
-    experiment.setStratified(stratified).setNFolds(n_folds).setScoreName("accuracy");
-    for (auto seed : seeds) {
-        experiment.addRandomSeed(seed);
-    }
-    platform::Timer timer;
-    timer.start();
-    experiment.go(filesToTest, path);
-    experiment.setDuration(timer.getDuration());
-    if (saveResults)
-        experiment.save(PATH_RESULTS);
-    else
-        experiment.report();
-    cout << "Done!" << endl;
-    return 0;
-}

src/Platform/modelRegister.h

@@ -1,19 +0,0 @@
-#ifndef MODEL_REGISTER_H
-#define MODEL_REGISTER_H
-static platform::Registrar registrarT("TAN",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TAN();});
-static platform::Registrar registrarTLD("TANLd",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TANLd();});
-static platform::Registrar registrarS("SPODE",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODE(2);});
-static platform::Registrar registrarSLD("SPODELd",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODELd(2);});
-static platform::Registrar registrarK("KDB",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDB(2);});
-static platform::Registrar registrarKLD("KDBLd",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDBLd(2);});
-static platform::Registrar registrarA("AODE",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
-static platform::Registrar registrarALD("AODELd",
-    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODELd();});
-#endif

src/Platform/platformUtils.cc

@@ -1,108 +0,0 @@
-#include "platformUtils.h"
-
-using namespace torch;
-
-vector<string> split(const string& text, char delimiter)
-{
-    vector<string> result;
-    stringstream ss(text);
-    string token;
-    while (getline(ss, token, delimiter)) {
-        result.push_back(token);
-    }
-    return result;
-}
-
-pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features)
-{
-    vector<mdlp::labels_t> Xd;
-    map<string, int> maxes;
-    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]);
-        maxes[features[i]] = *max_element(xd.begin(), xd.end()) + 1;
-        Xd.push_back(xd);
-    }
-    return { Xd, maxes };
-}
-
-vector<mdlp::labels_t> 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;
-}
-
-bool file_exists(const string& name)
-{
-    if (FILE* file = fopen(name.c_str(), "r")) {
-        fclose(file);
-        return true;
-    } else {
-        return false;
-    }
-}
-
-tuple<Tensor, Tensor, vector<string>, string, map<string, vector<int>>> loadDataset(const string& path, const string& name, bool class_last, bool discretize_dataset)
-{
-    auto handler = ArffFiles();
-    handler.load(path + static_cast<string>(name) + ".arff", class_last);
-    // Get Dataset X, y
-    vector<mdlp::samples_t>& X = handler.getX();
-    mdlp::labels_t& y = handler.getY();
-    // Get className & Features
-    auto className = handler.getClassName();
-    vector<string> features;
-    auto attributes = handler.getAttributes();
-    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
-    Tensor Xd;
-    auto states = map<string, vector<int>>();
-    if (discretize_dataset) {
-        auto Xr = discretizeDataset(X, y);
-        Xd = torch::zeros({ static_cast<int>(Xr[0].size()), static_cast<int>(Xr.size()) }, torch::kInt32);
-        for (int i = 0; i < features.size(); ++i) {
-            states[features[i]] = vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
-            iota(begin(states[features[i]]), end(states[features[i]]), 0);
-            Xd.index_put_({ "...", i }, torch::tensor(Xr[i], torch::kInt32));
-        }
-        states[className] = vector<int>(*max_element(y.begin(), y.end()) + 1);
-        iota(begin(states[className]), end(states[className]), 0);
-    } else {
-        Xd = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, torch::kFloat32);
-        for (int i = 0; i < features.size(); ++i) {
-            Xd.index_put_({ "...", i }, torch::tensor(X[i]));
-        }
-    }
-    return { Xd, torch::tensor(y, torch::kInt32), features, className, states };
-}
-
-tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(const string& name)
-{
-    auto handler = ArffFiles();
-    handler.load(PATH + static_cast<string>(name) + ".arff");
-    // Get Dataset X, y
-    vector<mdlp::samples_t>& X = handler.getX();
-    mdlp::labels_t& y = handler.getY();
-    // Get className & Features
-    auto className = handler.getClassName();
-    vector<string> features;
-    auto attributes = handler.getAttributes();
-    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
-    // Discretize Dataset
-    vector<mdlp::labels_t> Xd;
-    map<string, int> maxes;
-    tie(Xd, maxes) = discretize(X, y, features);
-    maxes[className] = *max_element(y.begin(), y.end()) + 1;
-    map<string, vector<int>> states;
-    for (auto feature : features) {
-        states[feature] = vector<int>(maxes[feature]);
-    }
-    states[className] = vector<int>(maxes[className]);
-    return { Xd, y, features, className, states };
-}

src/Platform/platformUtils.h

@@ -1,21 +0,0 @@
-#ifndef PLATFORM_UTILS_H
-#define PLATFORM_UTILS_H
-#include <torch/torch.h>
-#include <string>
-#include <vector>
-#include <map>
-#include <tuple>
-#include "ArffFiles.h"
-#include "CPPFImdlp.h"
-using namespace std;
-const string PATH = "../../data/";
-
-bool file_exists(const std::string& name);
-vector<string> split(const string& text, char delimiter);
-pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t>& X, mdlp::labels_t& y, vector<string> features);
-vector<mdlp::labels_t> discretizeDataset(vector<mdlp::samples_t>& X, mdlp::labels_t& y);
-pair<torch::Tensor, map<string, vector<int>>> discretizeTorch(torch::Tensor& X, torch::Tensor& y, vector<string>& features, const string& className);
-tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(const string& name);
-tuple<torch::Tensor, torch::Tensor, vector<string>, string, map<string, vector<int>>> loadDataset(const string& path, const string& name, bool class_last, bool discretize_dataset);
-map<string, vector<int>> get_states(vector<string>& features, string className, map<string, int>& maxes);
-#endif //PLATFORM_UTILS_H

tests/BayesModels.cc

@@ -1,88 +0,0 @@
-#define CATCH_CONFIG_MAIN  // This tells Catch to provide a main() - only do
-#include <catch2/catch_test_macros.hpp>
-#include <catch2/catch_approx.hpp>
-#include <catch2/generators/catch_generators.hpp>
-#include <vector>
-#include <map>
-#include <string>
-#include "KDB.h"
-#include "TAN.h"
-#include "SPODE.h"
-#include "AODE.h"
-#include "platformUtils.h"
-
-TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
-{
-    map <pair<string, string>, float> scores = {
-        {{"diabetes", "AODE"}, 0.811198}, {{"diabetes", "KDB"}, 0.852865}, {{"diabetes", "SPODE"}, 0.802083}, {{"diabetes", "TAN"}, 0.821615},
-        {{"ecoli", "AODE"}, 0.889881}, {{"ecoli", "KDB"}, 0.889881}, {{"ecoli", "SPODE"}, 0.880952}, {{"ecoli", "TAN"}, 0.892857},
-        {{"glass", "AODE"}, 0.78972}, {{"glass", "KDB"}, 0.827103}, {{"glass", "SPODE"}, 0.775701}, {{"glass", "TAN"}, 0.827103},
-        {{"iris", "AODE"}, 0.973333}, {{"iris", "KDB"}, 0.973333}, {{"iris", "SPODE"}, 0.973333}, {{"iris", "TAN"}, 0.973333}
-    };
-
-    string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
-    auto [Xd, y, features, className, states] = loadFile(file_name);
-
-    SECTION("Test TAN classifier (" + file_name + ")")
-    {
-        auto clf = bayesnet::TAN();
-        clf.fit(Xd, y, features, className, states);
-        auto score = clf.score(Xd, y);
-        //scores[{file_name, "TAN"}] = score;
-        REQUIRE(score == Catch::Approx(scores[{file_name, "TAN"}]).epsilon(1e-6));
-    }
-    SECTION("Test KDB classifier (" + file_name + ")")
-    {
-        auto clf = bayesnet::KDB(2);
-        clf.fit(Xd, y, features, className, states);
-        auto score = clf.score(Xd, y);
-        //scores[{file_name, "KDB"}] = score;
-        REQUIRE(score == Catch::Approx(scores[{file_name, "KDB"
-        }]).epsilon(1e-6));
-    }
-    SECTION("Test SPODE classifier (" + file_name + ")")
-    {
-        auto clf = bayesnet::SPODE(1);
-        clf.fit(Xd, y, features, className, states);
-        auto score = clf.score(Xd, y);
-        // scores[{file_name, "SPODE"}] = score;
-        REQUIRE(score == Catch::Approx(scores[{file_name, "SPODE"}]).epsilon(1e-6));
-    }
-    SECTION("Test AODE classifier (" + file_name + ")")
-    {
-        auto clf = bayesnet::AODE();
-        clf.fit(Xd, y, features, className, states);
-        auto score = clf.score(Xd, y);
-        // scores[{file_name, "AODE"}] = score;
-        REQUIRE(score == Catch::Approx(scores[{file_name, "AODE"}]).epsilon(1e-6));
-    }
-    // for (auto scores : scores) {
-    //     cout << "{{\"" << scores.first.first << "\", \"" << scores.first.second << "\"}, " << scores.second << "}, ";
-    // }
-}
-TEST_CASE("Models features")
-{
-    auto graph = vector<string>({ "digraph BayesNet {\nlabel=<BayesNet Test>\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n",
-        "class [shape=circle, fontcolor=red, fillcolor=lightblue, style=filled ] \n",
-        "class -> sepallength", "class -> sepalwidth", "class -> petallength", "class -> petalwidth", "petallength [shape=circle] \n",
-        "petallength -> sepallength", "petalwidth [shape=circle] \n", "sepallength [shape=circle] \n",
-        "sepallength -> sepalwidth", "sepalwidth [shape=circle] \n", "sepalwidth -> petalwidth", "}\n"
-        }
-    );
-
-    auto clf = bayesnet::TAN();
-    auto [Xd, y, features, className, states] = loadFile("iris");
-    clf.fit(Xd, y, features, className, states);
-    REQUIRE(clf.getNumberOfNodes() == 5);
-    REQUIRE(clf.getNumberOfEdges() == 7);
-    REQUIRE(clf.show() == vector<string>{"class -> sepallength, sepalwidth, petallength, petalwidth, ", "petallength -> sepallength, ", "petalwidth -> ", "sepallength -> sepalwidth, ", "sepalwidth -> petalwidth, "});
-    REQUIRE(clf.graph("Test") == graph);
-}
-TEST_CASE("Get num features & num edges")
-{
-    auto [Xd, y, features, className, states] = loadFile("iris");
-    auto clf = bayesnet::KDB(2);
-    clf.fit(Xd, y, features, className, states);
-    REQUIRE(clf.getNumberOfNodes() == 5);
-    REQUIRE(clf.getNumberOfEdges() == 8);
-}

tests/BayesNetwork.cc

@@ -1,33 +0,0 @@
-#include <catch2/catch_test_macros.hpp>
-#include <catch2/catch_approx.hpp>
-#include <catch2/generators/catch_generators.hpp>
-#include <string>
-#include "KDB.h"
-#include "platformUtils.h"
-
-TEST_CASE("Test Bayesian Network")
-{
-    auto [Xd, y, features, className, states] = loadFile("iris");
-
-    SECTION("Test get features")
-    {
-        auto net = bayesnet::Network();
-        net.addNode("A");
-        net.addNode("B");
-        REQUIRE(net.getFeatures() == vector<string>{"A", "B"});
-        net.addNode("C");
-        REQUIRE(net.getFeatures() == vector<string>{"A", "B", "C"});
-    }
-    SECTION("Test get edges")
-    {
-        auto net = bayesnet::Network();
-        net.addNode("A");
-        net.addNode("B");
-        net.addNode("C");
-        net.addEdge("A", "B");
-        net.addEdge("B", "C");
-        REQUIRE(net.getEdges() == vector<pair<string, string>>{ {"A", "B"}, { "B", "C" } });
-        net.addEdge("A", "C");
-        REQUIRE(net.getEdges() == vector<pair<string, string>>{ {"A", "B"}, { "A", "C" }, { "B", "C" } });
-    }
-}

tests/CMakeLists.txt

@@ -1,11 +1,16 @@
 if(ENABLE_TESTING)
-    set(TEST_MAIN "unit_tests")
-    include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
-    include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
-    include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
-    include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
-    set(TEST_SOURCES BayesModels.cc BayesNetwork.cc ${BayesNet_SOURCE_DIR}/src/Platform/platformUtils.cc ${BayesNet_SOURCES})
-    add_executable(${TEST_MAIN} ${TEST_SOURCES})
-    target_link_libraries(${TEST_MAIN} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain)
-    add_test(NAME ${TEST_MAIN} COMMAND ${TEST_MAIN})
+    set(TEST_BAYESNET "unit_tests_bayesnet")
+    include_directories(
+        ${BayesNet_SOURCE_DIR}/src/BayesNet
+        ${BayesNet_SOURCE_DIR}/src/Platform
+        ${BayesNet_SOURCE_DIR}/lib/Files
+        ${BayesNet_SOURCE_DIR}/lib/mdlp
+        ${BayesNet_SOURCE_DIR}/lib/folding
+        ${BayesNet_SOURCE_DIR}/lib/json/include
+        ${CMAKE_BINARY_DIR}/configured_files/include
+    )
+    set(TEST_SOURCES_BAYESNET TestBayesModels.cc TestBayesNetwork.cc TestBayesMetrics.cc TestUtils.cc ${BayesNet_SOURCES})
+    add_executable(${TEST_BAYESNET} ${TEST_SOURCES_BAYESNET})
+    target_link_libraries(${TEST_BAYESNET} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain)
+    add_test(NAME ${TEST_BAYESNET} COMMAND ${TEST_BAYESNET})
 endif(ENABLE_TESTING)

tests/TestBayesMetrics.cc

@@ -0,0 +1,62 @@
+#include <catch2/catch_test_macros.hpp>
+#include <catch2/catch_approx.hpp>
+#include <catch2/generators/catch_generators.hpp>
+#include "BayesMetrics.h"
+#include "TestUtils.h"
+
+
+TEST_CASE("Metrics Test", "[BayesNet]")
+{
+    std::string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
+    map<std::string, pair<int, std::vector<int>>> resultsKBest = {
+        {"glass", {7, { 0, 1, 7, 6, 3, 5, 2 }}},
+        {"iris", {3, { 0, 3, 2 }} },
+        {"ecoli", {6, { 2, 4, 1, 0, 6, 5 }}},
+        {"diabetes", {2, { 7, 1 }}}
+    };
+    map<std::string, double> resultsMI = {
+        {"glass", 0.12805398},
+        {"iris", 0.3158139948},
+        {"ecoli", 0.0089431099},
+        {"diabetes", 0.0345470614}
+    };
+    map<pair<std::string, int>, std::vector<pair<int, int>>> resultsMST = {
+        { {"glass", 0}, { {0, 6}, {0, 5}, {0, 3}, {5, 1}, {5, 8}, {5, 4}, {6, 2}, {6, 7} } },
+        { {"glass", 1}, { {1, 5}, {5, 0}, {5, 8}, {5, 4}, {0, 6}, {0, 3}, {6, 2}, {6, 7} } },
+        { {"iris", 0}, { {0, 1}, {0, 2}, {1, 3} } },
+        { {"iris", 1}, { {1, 0}, {1, 3}, {0, 2} } },
+        { {"ecoli", 0}, { {0, 1}, {0, 2}, {1, 5}, {1, 3}, {5, 6}, {5, 4} } },
+        { {"ecoli", 1}, { {1, 0}, {1, 5}, {1, 3}, {5, 6}, {5, 4}, {0, 2} } },
+        { {"diabetes", 0}, { {0, 7}, {0, 2}, {0, 6}, {2, 3}, {3, 4}, {3, 5}, {4, 1} } },
+        { {"diabetes", 1}, { {1, 4}, {4, 3}, {3, 2}, {3, 5}, {2, 0}, {0, 7}, {0, 6} } }
+    };
+    auto raw = RawDatasets(file_name, true);
+    bayesnet::Metrics metrics(raw.dataset, raw.featurest, raw.classNamet, raw.classNumStates);
+
+    SECTION("Test Constructor")
+    {
+        REQUIRE(metrics.getScoresKBest().size() == 0);
+    }
+
+    SECTION("Test SelectKBestWeighted")
+    {
+        std::vector<int> kBest = metrics.SelectKBestWeighted(raw.weights, true, resultsKBest.at(file_name).first);
+        REQUIRE(kBest.size() == resultsKBest.at(file_name).first);
+        REQUIRE(kBest == resultsKBest.at(file_name).second);
+    }
+
+    SECTION("Test Mutual Information")
+    {
+        auto result = metrics.mutualInformation(raw.dataset.index({ 1, "..." }), raw.dataset.index({ 2, "..." }), raw.weights);
+        REQUIRE(result == Catch::Approx(resultsMI.at(file_name)).epsilon(raw.epsilon));
+    }
+
+    SECTION("Test Maximum Spanning Tree")
+    {
+        auto weights_matrix = metrics.conditionalEdge(raw.weights);
+        for (int i = 0; i < 2; ++i) {
+            auto result = metrics.maximumSpanningTree(raw.featurest, weights_matrix, i);
+            REQUIRE(result == resultsMST.at({ file_name, i }));
+        }
+    }
+}

tests/TestBayesModels.cc

@@ -0,0 +1,176 @@
+#define CATCH_CONFIG_MAIN  // This tells Catch to provide a main() - only do
+#include <catch2/catch_test_macros.hpp>
+#include <catch2/catch_approx.hpp>
+#include <catch2/generators/catch_generators.hpp>
+#include <vector>
+#include <map>
+#include <string>
+#include "KDB.h"
+#include "TAN.h"
+#include "SPODE.h"
+#include "AODE.h"
+#include "BoostAODE.h"
+#include "TANLd.h"
+#include "KDBLd.h"
+#include "SPODELd.h"
+#include "AODELd.h"
+#include "TestUtils.h"
+
+TEST_CASE("Library check version", "[BayesNet]")
+{
+    auto clf = bayesnet::KDB(2);
+    REQUIRE(clf.getVersion() == "1.0.1");
+}
+TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
+{
+    map <pair<std::string, std::string>, float> scores = {
+        // Diabetes
+        {{"diabetes", "AODE"}, 0.811198}, {{"diabetes", "KDB"}, 0.852865}, {{"diabetes", "SPODE"}, 0.802083}, {{"diabetes", "TAN"}, 0.821615},
+        {{"diabetes", "AODELd"}, 0.8138f}, {{"diabetes", "KDBLd"}, 0.80208f}, {{"diabetes", "SPODELd"}, 0.78646f}, {{"diabetes", "TANLd"}, 0.8099f},  {{"diabetes", "BoostAODE"}, 0.83984f},
+        // Ecoli
+        {{"ecoli", "AODE"}, 0.889881}, {{"ecoli", "KDB"}, 0.889881}, {{"ecoli", "SPODE"}, 0.880952}, {{"ecoli", "TAN"}, 0.892857},
+        {{"ecoli", "AODELd"}, 0.8869f}, {{"ecoli", "KDBLd"}, 0.875f}, {{"ecoli", "SPODELd"}, 0.84226f}, {{"ecoli", "TANLd"}, 0.86905f}, {{"ecoli", "BoostAODE"}, 0.89583f},
+        // Glass
+        {{"glass", "AODE"}, 0.78972}, {{"glass", "KDB"}, 0.827103}, {{"glass", "SPODE"}, 0.775701}, {{"glass", "TAN"}, 0.827103},
+        {{"glass", "AODELd"}, 0.79439f}, {{"glass", "KDBLd"}, 0.85047f}, {{"glass", "SPODELd"}, 0.79439f}, {{"glass", "TANLd"}, 0.86449f}, {{"glass", "BoostAODE"}, 0.84579f},
+        // Iris
+        {{"iris", "AODE"}, 0.973333}, {{"iris", "KDB"}, 0.973333}, {{"iris", "SPODE"}, 0.973333}, {{"iris", "TAN"}, 0.973333},
+        {{"iris", "AODELd"}, 0.973333}, {{"iris", "KDBLd"}, 0.973333}, {{"iris", "SPODELd"}, 0.96f}, {{"iris", "TANLd"}, 0.97333f}, {{"iris", "BoostAODE"}, 0.98f}
+    };
+
+    std::string file_name = GENERATE("glass", "iris", "ecoli", "diabetes");
+    auto raw = RawDatasets(file_name, false);
+
+    SECTION("Test TAN classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::TAN();
+        clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+        auto score = clf.score(raw.Xv, raw.yv);
+        //scores[{file_name, "TAN"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "TAN"}]).epsilon(raw.epsilon));
+    }
+    SECTION("Test TANLd classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::TANLd();
+        clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
+        auto score = clf.score(raw.Xt, raw.yt);
+        //scores[{file_name, "TANLd"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "TANLd"}]).epsilon(raw.epsilon));
+    }
+    SECTION("Test KDB classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::KDB(2);
+        clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+        auto score = clf.score(raw.Xv, raw.yv);
+        //scores[{file_name, "KDB"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "KDB"
+        }]).epsilon(raw.epsilon));
+    }
+    SECTION("Test KDBLd classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::KDBLd(2);
+        clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
+        auto score = clf.score(raw.Xt, raw.yt);
+        //scores[{file_name, "KDBLd"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "KDBLd"
+        }]).epsilon(raw.epsilon));
+    }
+    SECTION("Test SPODE classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::SPODE(1);
+        clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+        auto score = clf.score(raw.Xv, raw.yv);
+        // scores[{file_name, "SPODE"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "SPODE"}]).epsilon(raw.epsilon));
+    }
+    SECTION("Test SPODELd classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::SPODELd(1);
+        clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
+        auto score = clf.score(raw.Xt, raw.yt);
+        // scores[{file_name, "SPODELd"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "SPODELd"}]).epsilon(raw.epsilon));
+    }
+    SECTION("Test AODE classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::AODE();
+        clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+        auto score = clf.score(raw.Xv, raw.yv);
+        // scores[{file_name, "AODE"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "AODE"}]).epsilon(raw.epsilon));
+    }
+    SECTION("Test AODELd classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::AODELd();
+        clf.fit(raw.Xt, raw.yt, raw.featurest, raw.classNamet, raw.statest);
+        auto score = clf.score(raw.Xt, raw.yt);
+        // scores[{file_name, "AODELd"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "AODELd"}]).epsilon(raw.epsilon));
+    }
+    SECTION("Test BoostAODE classifier (" + file_name + ")")
+    {
+        auto clf = bayesnet::BoostAODE();
+        clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+        auto score = clf.score(raw.Xv, raw.yv);
+        // scores[{file_name, "BoostAODE"}] = score;
+        REQUIRE(score == Catch::Approx(scores[{file_name, "BoostAODE"}]).epsilon(raw.epsilon));
+    }
+    // for (auto scores : scores) {
+    //     std::cout << "{{\"" << scores.first.first << "\", \"" << scores.first.second << "\"}, " << scores.second << "}, ";
+    // }
+}
+TEST_CASE("Models features", "[BayesNet]")
+{
+    auto graph = std::vector<std::string>({ "digraph BayesNet {\nlabel=<BayesNet Test>\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n",
+        "class [shape=circle, fontcolor=red, fillcolor=lightblue, style=filled ] \n",
+        "class -> sepallength", "class -> sepalwidth", "class -> petallength", "class -> petalwidth", "petallength [shape=circle] \n",
+        "petallength -> sepallength", "petalwidth [shape=circle] \n", "sepallength [shape=circle] \n",
+        "sepallength -> sepalwidth", "sepalwidth [shape=circle] \n", "sepalwidth -> petalwidth", "}\n"
+        }
+    );
+    auto raw = RawDatasets("iris", true);
+    auto clf = bayesnet::TAN();
+    clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+    REQUIRE(clf.getNumberOfNodes() == 5);
+    REQUIRE(clf.getNumberOfEdges() == 7);
+    REQUIRE(clf.show() == std::vector<std::string>{"class -> sepallength, sepalwidth, petallength, petalwidth, ", "petallength -> sepallength, ", "petalwidth -> ", "sepallength -> sepalwidth, ", "sepalwidth -> petalwidth, "});
+    REQUIRE(clf.graph("Test") == graph);
+}
+TEST_CASE("Get num features & num edges", "[BayesNet]")
+{
+    auto raw = RawDatasets("iris", true);
+    auto clf = bayesnet::KDB(2);
+    clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+    REQUIRE(clf.getNumberOfNodes() == 5);
+    REQUIRE(clf.getNumberOfEdges() == 8);
+}
+TEST_CASE("BoostAODE feature_select CFS", "[BayesNet]")
+{
+    auto raw = RawDatasets("glass", true);
+    auto clf = bayesnet::BoostAODE();
+    clf.setHyperparameters({ {"select_features", "CFS"} });
+    clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+    REQUIRE(clf.getNumberOfNodes() == 90);
+    REQUIRE(clf.getNumberOfEdges() == 153);
+    REQUIRE(clf.getNotes().size() == 2);
+    REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 9 with CFS");
+    REQUIRE(clf.getNotes()[1] == "Number of models: 9");
+}
+TEST_CASE("BoostAODE test used features in train note", "[BayesNet]")
+{
+    auto raw = RawDatasets("diabetes", true);
+    auto clf = bayesnet::BoostAODE();
+    clf.setHyperparameters({
+        {"ascending",true},
+        {"convergence", true},
+        {"repeatSparent",true},
+        {"select_features","CFS"}
+        });
+    clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+    REQUIRE(clf.getNumberOfNodes() == 72);
+    REQUIRE(clf.getNumberOfEdges() == 120);
+    REQUIRE(clf.getNotes().size() == 3);
+    REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 8 with CFS");
+    REQUIRE(clf.getNotes()[1] == "Used features in train: 7 of 8");
+    REQUIRE(clf.getNotes()[2] == "Number of models: 8");
+}

tests/TestBayesNetwork.cc

@@ -0,0 +1,211 @@
+#include <catch2/catch_test_macros.hpp>
+#include <catch2/catch_approx.hpp>
+#include <catch2/generators/catch_generators.hpp>
+#include <string>
+#include "TestUtils.h"
+#include "Network.h"
+
+void buildModel(bayesnet::Network& net, const std::vector<std::string>& features, const std::string& className)
+{
+    std::vector<pair<int, int>> network = { {0, 1}, {0, 2}, {1, 3} };
+    for (const auto& feature : features) {
+        net.addNode(feature);
+    }
+    net.addNode(className);
+    for (const auto& edge : network) {
+        net.addEdge(features.at(edge.first), features.at(edge.second));
+    }
+    for (const auto& feature : features) {
+        net.addEdge(className, feature);
+    }
+}
+
+TEST_CASE("Test Bayesian Network", "[BayesNet]")
+{
+
+    auto raw = RawDatasets("iris", true);
+    auto net = bayesnet::Network();
+    double threshold = 1e-4;
+
+    SECTION("Test get features")
+    {
+        net.addNode("A");
+        net.addNode("B");
+        REQUIRE(net.getFeatures() == std::vector<std::string>{"A", "B"});
+        net.addNode("C");
+        REQUIRE(net.getFeatures() == std::vector<std::string>{"A", "B", "C"});
+    }
+    SECTION("Test get edges")
+    {
+        net.addNode("A");
+        net.addNode("B");
+        net.addNode("C");
+        net.addEdge("A", "B");
+        net.addEdge("B", "C");
+        REQUIRE(net.getEdges() == std::vector<pair<std::string, std::string>>{ {"A", "B"}, { "B", "C" } });
+        REQUIRE(net.getNumEdges() == 2);
+        net.addEdge("A", "C");
+        REQUIRE(net.getEdges() == std::vector<pair<std::string, std::string>>{ {"A", "B"}, { "A", "C" }, { "B", "C" } });
+        REQUIRE(net.getNumEdges() == 3);
+    }
+    SECTION("Test getNodes")
+    {
+        net.addNode("A");
+        net.addNode("B");
+        auto& nodes = net.getNodes();
+        REQUIRE(nodes.count("A") == 1);
+        REQUIRE(nodes.count("B") == 1);
+    }
+
+    SECTION("Test fit Network")
+    {
+        auto net2 = bayesnet::Network();
+        auto net3 = bayesnet::Network();
+        net3.initialize();
+        net2.initialize();
+        net.initialize();
+        buildModel(net, raw.featuresv, raw.classNamev);
+        buildModel(net2, raw.featurest, raw.classNamet);
+        buildModel(net3, raw.featurest, raw.classNamet);
+        std::vector<pair<std::string, std::string>> edges = {
+            {"class", "sepallength"}, {"class", "sepalwidth"}, {"class", "petallength"},
+            {"class", "petalwidth" }, {"sepallength", "sepalwidth"}, {"sepallength", "petallength"},
+            {"sepalwidth", "petalwidth"}
+        };
+        REQUIRE(net.getEdges() == edges);
+        REQUIRE(net2.getEdges() == edges);
+        REQUIRE(net3.getEdges() == edges);
+        std::vector<std::string> features = { "sepallength", "sepalwidth", "petallength", "petalwidth", "class" };
+        REQUIRE(net.getFeatures() == features);
+        REQUIRE(net2.getFeatures() == features);
+        REQUIRE(net3.getFeatures() == features);
+        auto& nodes = net.getNodes();
+        auto& nodes2 = net2.getNodes();
+        auto& nodes3 = net3.getNodes();
+        // Check Nodes parents & children
+        for (const auto& feature : features) {
+            // Parents
+            std::vector<std::string> parents, parents2, parents3, children, children2, children3;
+            auto nodeParents = nodes[feature]->getParents();
+            auto nodeParents2 = nodes2[feature]->getParents();
+            auto nodeParents3 = nodes3[feature]->getParents();
+            transform(nodeParents.begin(), nodeParents.end(), back_inserter(parents), [](const auto& p) { return p->getName(); });
+            transform(nodeParents2.begin(), nodeParents2.end(), back_inserter(parents2), [](const auto& p) { return p->getName(); });
+            transform(nodeParents3.begin(), nodeParents3.end(), back_inserter(parents3), [](const auto& p) { return p->getName(); });
+            REQUIRE(parents == parents2);
+            REQUIRE(parents == parents3);
+            // Children
+            auto nodeChildren = nodes[feature]->getChildren();
+            auto nodeChildren2 = nodes2[feature]->getChildren();
+            auto nodeChildren3 = nodes2[feature]->getChildren();
+            transform(nodeChildren.begin(), nodeChildren.end(), back_inserter(children), [](const auto& p) { return p->getName(); });
+            transform(nodeChildren2.begin(), nodeChildren2.end(), back_inserter(children2), [](const auto& p) { return p->getName(); });
+            transform(nodeChildren3.begin(), nodeChildren3.end(), back_inserter(children3), [](const auto& p) { return p->getName(); });
+            REQUIRE(children == children2);
+            REQUIRE(children == children3);
+        }
+        // Fit networks
+        net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
+        net2.fit(raw.dataset, raw.weights, raw.featurest, raw.classNamet, raw.statest);
+        net3.fit(raw.Xt, raw.yt, raw.weights, raw.featurest, raw.classNamet, raw.statest);
+        REQUIRE(net.getStates() == net2.getStates());
+        REQUIRE(net.getStates() == net3.getStates());
+        // Check Conditional Probabilities tables
+        for (int i = 0; i < features.size(); ++i) {
+            auto feature = features.at(i);
+            for (const auto& feature : features) {
+                auto cpt = nodes[feature]->getCPT();
+                auto cpt2 = nodes2[feature]->getCPT();
+                auto cpt3 = nodes3[feature]->getCPT();
+                REQUIRE(cpt.equal(cpt2));
+                REQUIRE(cpt.equal(cpt3));
+            }
+        }
+    }
+    SECTION("Test show")
+    {
+        auto net = bayesnet::Network();
+        net.addNode("A");
+        net.addNode("B");
+        net.addNode("C");
+        net.addEdge("A", "B");
+        net.addEdge("A", "C");
+        auto str = net.show();
+        REQUIRE(str.size() == 3);
+        REQUIRE(str[0] == "A -> B, C, ");
+        REQUIRE(str[1] == "B -> ");
+        REQUIRE(str[2] == "C -> ");
+    }
+    SECTION("Test topological_sort")
+    {
+        auto net = bayesnet::Network();
+        net.addNode("A");
+        net.addNode("B");
+        net.addNode("C");
+        net.addEdge("A", "B");
+        net.addEdge("A", "C");
+        auto sorted = net.topological_sort();
+        REQUIRE(sorted.size() == 3);
+        REQUIRE(sorted[0] == "A");
+        bool result = sorted[1] == "B" && sorted[2] == "C";
+        REQUIRE(result);
+    }
+    SECTION("Test graph")
+    {
+        auto net = bayesnet::Network();
+        net.addNode("A");
+        net.addNode("B");
+        net.addNode("C");
+        net.addEdge("A", "B");
+        net.addEdge("A", "C");
+        auto str = net.graph("Test Graph");
+        REQUIRE(str.size() == 7);
+        REQUIRE(str[0] == "digraph BayesNet {\nlabel=<BayesNet Test Graph>\nfontsize=30\nfontcolor=blue\nlabelloc=t\nlayout=circo\n");
+        REQUIRE(str[1] == "A [shape=circle] \n");
+        REQUIRE(str[2] == "A -> B");
+        REQUIRE(str[3] == "A -> C");
+        REQUIRE(str[4] == "B [shape=circle] \n");
+        REQUIRE(str[5] == "C [shape=circle] \n");
+        REQUIRE(str[6] == "}\n");
+    }
+    SECTION("Test predict")
+    {
+        auto net = bayesnet::Network();
+        buildModel(net, raw.featuresv, raw.classNamev);
+        net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
+        std::vector<std::vector<int>> test = { {1, 2, 0, 1, 1}, {0, 1, 2, 0, 1}, {0, 0, 0, 0, 1}, {2, 2, 2, 2, 1} };
+        std::vector<int> y_test = { 2, 2, 0, 2, 1 };
+        auto y_pred = net.predict(test);
+        REQUIRE(y_pred == y_test);
+    }
+    SECTION("Test predict_proba")
+    {
+        auto net = bayesnet::Network();
+        buildModel(net, raw.featuresv, raw.classNamev);
+        net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
+        std::vector<std::vector<int>> test = { {1, 2, 0, 1, 1}, {0, 1, 2, 0, 1}, {0, 0, 0, 0, 1}, {2, 2, 2, 2, 1} };
+        std::vector<std::vector<double>> y_test = {
+            {0.450237, 0.0866621, 0.463101},
+            {0.244443, 0.0925922, 0.662964},
+            {0.913441, 0.0125857, 0.0739732},
+            {0.450237, 0.0866621, 0.463101},
+            {0.0135226, 0.971726, 0.0147519}
+        };
+        auto y_pred = net.predict_proba(test);
+        REQUIRE(y_pred.size() == 5);
+        REQUIRE(y_pred[0].size() == 3);
+        for (int i = 0; i < y_pred.size(); ++i) {
+            for (int j = 0; j < y_pred[i].size(); ++j) {
+                REQUIRE(y_pred[i][j] == Catch::Approx(y_test[i][j]).margin(threshold));
+            }
+        }
+    }
+    SECTION("Test score")
+    {
+        auto net = bayesnet::Network();
+        buildModel(net, raw.featuresv, raw.classNamev);
+        net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
+        auto score = net.score(raw.Xv, raw.yv);
+        REQUIRE(score == Catch::Approx(0.97333333).margin(threshold));
+    }
+}

tests/TestUtils.cc

@@ -0,0 +1,105 @@
+#include "TestUtils.h"
+#include "config.h"
+
+class Paths {
+public:
+    static std::string datasets()
+    {
+        return { data_path.begin(), data_path.end() };
+    }
+};
+
+pair<std::vector<mdlp::labels_t>, map<std::string, int>> discretize(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y, std::vector<std::string> features)
+{
+    std::vector<mdlp::labels_t> Xd;
+    map<std::string, int> maxes;
+    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]);
+        maxes[features[i]] = *max_element(xd.begin(), xd.end()) + 1;
+        Xd.push_back(xd);
+    }
+    return { Xd, maxes };
+}
+
+std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y)
+{
+    std::vector<mdlp::labels_t> Xd;
+    auto fimdlp = mdlp::CPPFImdlp();
+    for (int i = 0; i < X.size(); i++) {
+        fimdlp.fit(X[i], y);
+        mdlp::labels_t& xd = fimdlp.transform(X[i]);
+        Xd.push_back(xd);
+    }
+    return Xd;
+}
+
+bool file_exists(const std::string& name)
+{
+    if (FILE* file = fopen(name.c_str(), "r")) {
+        fclose(file);
+        return true;
+    } else {
+        return false;
+    }
+}
+
+tuple<torch::Tensor, torch::Tensor, std::vector<std::string>, std::string, map<std::string, std::vector<int>>> loadDataset(const std::string& name, bool class_last, bool discretize_dataset)
+{
+    auto handler = ArffFiles();
+    handler.load(Paths::datasets() + static_cast<std::string>(name) + ".arff", class_last);
+    // Get Dataset X, y
+    std::vector<mdlp::samples_t>& X = handler.getX();
+    mdlp::labels_t& y = handler.getY();
+    // Get className & Features
+    auto className = handler.getClassName();
+    std::vector<std::string> features;
+    auto attributes = handler.getAttributes();
+    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
+    torch::Tensor Xd;
+    auto states = map<std::string, std::vector<int>>();
+    if (discretize_dataset) {
+        auto Xr = discretizeDataset(X, y);
+        Xd = torch::zeros({ static_cast<int>(Xr.size()), static_cast<int>(Xr[0].size()) }, torch::kInt32);
+        for (int i = 0; i < features.size(); ++i) {
+            states[features[i]] = std::vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
+            auto item = states.at(features[i]);
+            iota(begin(item), end(item), 0);
+            Xd.index_put_({ i, "..." }, torch::tensor(Xr[i], torch::kInt32));
+        }
+        states[className] = std::vector<int>(*max_element(y.begin(), y.end()) + 1);
+        iota(begin(states.at(className)), end(states.at(className)), 0);
+    } else {
+        Xd = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, torch::kFloat32);
+        for (int i = 0; i < features.size(); ++i) {
+            Xd.index_put_({ i, "..." }, torch::tensor(X[i]));
+        }
+    }
+    return { Xd, torch::tensor(y, torch::kInt32), features, className, states };
+}
+
+tuple<std::vector<std::vector<int>>, std::vector<int>, std::vector<std::string>, std::string, map<std::string, std::vector<int>>> loadFile(const std::string& name)
+{
+    auto handler = ArffFiles();
+    handler.load(Paths::datasets() + static_cast<std::string>(name) + ".arff");
+    // Get Dataset X, y
+    std::vector<mdlp::samples_t>& X = handler.getX();
+    mdlp::labels_t& y = handler.getY();
+    // Get className & Features
+    auto className = handler.getClassName();
+    std::vector<std::string> features;
+    auto attributes = handler.getAttributes();
+    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
+    // Discretize Dataset
+    std::vector<mdlp::labels_t> Xd;
+    map<std::string, int> maxes;
+    tie(Xd, maxes) = discretize(X, y, features);
+    maxes[className] = *max_element(y.begin(), y.end()) + 1;
+    map<std::string, std::vector<int>> states;
+    for (auto feature : features) {
+        states[feature] = std::vector<int>(maxes[feature]);
+    }
+    states[className] = std::vector<int>(maxes[className]);
+    return { Xd, y, features, className, states };
+}

tests/TestUtils.h

@@ -0,0 +1,43 @@
+#ifndef TEST_UTILS_H
+#define TEST_UTILS_H
+#include <torch/torch.h>
+#include <string>
+#include <vector>
+#include <map>
+#include <tuple>
+#include "ArffFiles.h"
+#include "CPPFImdlp.h"
+
+bool file_exists(const std::string& name);
+std::pair<vector<mdlp::labels_t>, map<std::string, int>> discretize(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y, std::vector<string> features);
+std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y);
+std::tuple<vector<vector<int>>, std::vector<int>, std::vector<string>, std::string, map<std::string, std::vector<int>>> loadFile(const std::string& name);
+std::tuple<torch::Tensor, torch::Tensor, std::vector<string>, std::string, map<std::string, std::vector<int>>> loadDataset(const std::string& name, bool class_last, bool discretize_dataset);
+
+class RawDatasets {
+public:
+    RawDatasets(const std::string& file_name, bool discretize)
+    {
+        // Xt can be either discretized or not
+        tie(Xt, yt, featurest, classNamet, statest) = loadDataset(file_name, true, discretize);
+        // Xv is always discretized
+        tie(Xv, yv, featuresv, classNamev, statesv) = loadFile(file_name);
+        auto yresized = torch::transpose(yt.view({ yt.size(0), 1 }), 0, 1);
+        dataset = torch::cat({ Xt, yresized }, 0);
+        nSamples = dataset.size(1);
+        weights = torch::full({ nSamples }, 1.0 / nSamples, torch::kDouble);
+        weightsv = std::vector<double>(nSamples, 1.0 / nSamples);
+        classNumStates = discretize ? statest.at(classNamet).size() : 0;
+    }
+    torch::Tensor Xt, yt, dataset, weights;
+    std::vector<vector<int>> Xv;
+    std::vector<double> weightsv;
+    std::vector<int> yv;
+    std::vector<string> featurest, featuresv;
+    map<std::string, std::vector<int>> statest, statesv;
+    std::string classNamet, classNamev;
+    int nSamples, classNumStates;
+    double epsilon = 1e-5;
+};
+
+#endif //TEST_UTILS_H