Complete fixing the linter warnings

Add Registrar of models

.clang-tidy

@@ -0,0 +1,17 @@
+---
+Checks: '-*,
+         clang-*,
+         bugprone-*,
+         cppcoreguidelines-*,
+         modernize-*,
+         performance-*,
+         -cppcoreguidelines-pro-type-vararg,
+         -modernize-use-trailing-return-type,
+         -bugprone-exception-escape'
+
+HeaderFilterRegex: 'src/*'
+AnalyzeTemporaryDtors: false
+WarningsAsErrors: ''
+FormatStyle: file
+FormatStyleOptions: ''
+...

.gitmodules

@@ -0,0 +1,12 @@
+[submodule "lib/mdlp"]
+	path = lib/mdlp
+	url = https://github.com/rmontanana/mdlp
+[submodule "lib/catch2"]
+	path = lib/catch2
+	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

.vscode/launch.json

@@ -4,22 +4,37 @@
         {
             "type": "lldb",
             "request": "launch",
-            "name": "bayesnet",
-            "program": "${workspaceFolder}/build/sample/main",
+            "name": "sample",
+            "program": "${workspaceFolder}/build/sample/BayesNetSample",
             "args": [
-                "-f",
-                "iris"
+                "-d",
+                "iris",
+                "-m",
+                "TAN",
+                "-p",
+                "../../data/",
+                "--tensors"
             ],
-            "cwd": "${workspaceFolder}",
-            "preLaunchTask": "CMake: build"
+            "cwd": "${workspaceFolder}/build/sample/",
         },
         {
             "type": "lldb",
             "request": "launch",
-            "name": "aout",
-            "program": "${workspaceFolder}/a.out",
-            "args": [],
-            "cwd": "${workspaceFolder}"
+            "name": "experiment",
+            "program": "${workspaceFolder}/build/src/Platform/main",
+            "args": [
+                "-m",
+                "TAN",
+                "-p",
+                "/Users/rmontanana/Code/discretizbench/datasets",
+                "--discretize",
+                "--stratified",
+                "--title",
+                "Debug test",
+                "-d",
+                "ionosphere"
+            ],
+            "cwd": "${workspaceFolder}/build/src/Platform",
         },
         {
             "name": "Build & debug active file",

.vscode/settings.json

@@ -97,7 +97,12 @@
         "future": "cpp",
         "queue": "cpp",
         "typeindex": "cpp",
-        "shared_mutex": "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"

CMakeLists.txt

@@ -33,12 +33,24 @@ set(CMAKE_BUILD_TYPE "Debug")
 # --------------
 set(CMAKE_MODULE_PATH ${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules ${CMAKE_MODULE_PATH})
 
+include(AddGitSubmodule)
+include(StaticAnalyzers) # clang-tidy
+include(CodeCoverage)
+
+# External libraries - dependencies of BayesNet
+# ---------------------------------------------
+# include(FetchContent)
+add_git_submodule("lib/mdlp")
+add_git_submodule("lib/catch2")
+add_git_submodule("lib/argparse")
+add_git_submodule("lib/json")
 
 # Subdirectories
 # --------------
 add_subdirectory(config)
-add_subdirectory(${BayesNet_SOURCE_DIR}/src/BayesNet)
-add_subdirectory(${BayesNet_SOURCE_DIR}/src/Platform)
+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)
@@ -51,14 +63,14 @@ if (ENABLE_TESTING)
   MESSAGE("Testing enabled")
   enable_testing()
   if (CODE_COVERAGE)
-    include(CodeCoverage)
+    #include(CodeCoverage)
     MESSAGE("Code coverage enabled")
     set(CMAKE_C_FLAGS " ${CMAKE_C_FLAGS} -fprofile-arcs -ftest-coverage")
     set(CMAKE_CXX_FLAGS " ${CMAKE_CXX_FLAGS} -fprofile-arcs -ftest-coverage")
     SET(GCC_COVERAGE_LINK_FLAGS " ${GCC_COVERAGE_LINK_FLAGS} -lgcov --coverage")
   endif (CODE_COVERAGE)
-  find_package(Catch2 3 REQUIRED)
+  #find_package(Catch2 3 REQUIRED)
   include(CTest)
-  include(Catch)
+  #include(Catch)
   add_subdirectory(tests)
 endif (ENABLE_TESTING)

cmake/modules/AddGitSubmodule.cmake

@@ -0,0 +1,12 @@
+
+function(add_git_submodule dir)
+  find_package(Git REQUIRED) 
+
+  if(NOT EXISTS ${dir}/CMakeLists.txt)
+    message(STATUS "🚨 Adding git submodule => ${dir}")
+    execute_process(COMMAND ${GIT_EXECUTABLE}
+      submodule update --init --recursive -- ${dir}
+      WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}) 
+  endif()
+  add_subdirectory(${dir})
+endfunction(add_git_submodule)

cmake/modules/StaticAnalyzers.cmake

@@ -0,0 +1,22 @@
+if(ENABLE_CLANG_TIDY)
+    find_program(CLANG_TIDY_COMMAND NAMES clang-tidy)
+
+    if(NOT CLANG_TIDY_COMMAND)
+        message(WARNING "🔴 CMake_RUN_CLANG_TIDY is ON but clang-tidy is not found!")
+        set(CMAKE_CXX_CLANG_TIDY "" CACHE STRING "" FORCE)
+    else()
+    
+        message(STATUS "🟢 CMake_RUN_CLANG_TIDY is ON")
+        set(CLANGTIDY_EXTRA_ARGS
+            "-extra-arg=-Wno-unknown-warning-option"
+        )
+        set(CMAKE_CXX_CLANG_TIDY "${CLANG_TIDY_COMMAND};-p=${CMAKE_BINARY_DIR};${CLANGTIDY_EXTRA_ARGS}" CACHE STRING "" FORCE)
+
+        add_custom_target(clang-tidy
+            COMMAND ${CMAKE_COMMAND} --build ${CMAKE_BINARY_DIR} --target ${CMAKE_PROJECT_NAME}
+            COMMAND ${CMAKE_COMMAND} --build ${CMAKE_BINARY_DIR} --target clang-tidy
+            COMMENT "Running clang-tidy..."
+        )
+       set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
+    endif()
+endif(ENABLE_CLANG_TIDY)

data/_TAN_cpp_accuracy__.json

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

lib/Files/ArffFiles.cc

@@ -2,6 +2,7 @@
 #include <fstream>
 #include <sstream>
 #include <map>
+#include <iostream>
 
 using namespace std;
 
@@ -42,7 +43,7 @@ vector<int>& ArffFiles::getY()
     return y;
 }
 
-void ArffFiles::load(const string& fileName, bool classLast)
+void ArffFiles::loadCommon(string fileName)
 {
     ifstream file(fileName);
     if (!file.is_open()) {
@@ -74,24 +75,51 @@ void ArffFiles::load(const string& fileName, bool classLast)
     file.close();
     if (attributes.empty())
         throw invalid_argument("No attributes found");
+}
+
+void ArffFiles::load(const string& fileName, bool classLast)
+{
+    int labelIndex;
+    loadCommon(fileName);
     if (classLast) {
         className = get<0>(attributes.back());
         classType = get<1>(attributes.back());
         attributes.pop_back();
+        labelIndex = static_cast<int>(attributes.size());
     } else {
         className = get<0>(attributes.front());
         classType = get<1>(attributes.front());
         attributes.erase(attributes.begin());
+        labelIndex = 0;
     }
-    generateDataset(classLast);
-
+    generateDataset(labelIndex);
+}
+void ArffFiles::load(const string& fileName, const 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]);
+            attributes.erase(attributes.begin() + i);
+            labelIndex = i;
+            found = true;
+            break;
+        }
+    }
+    if (!found) {
+        throw invalid_argument("Class name not found");
+    }
+    generateDataset(labelIndex);
 }
 
-void ArffFiles::generateDataset(bool classLast)
+void ArffFiles::generateDataset(int labelIndex)
 {
     X = vector<vector<float>>(attributes.size(), vector<float>(lines.size()));
     auto yy = vector<string>(lines.size(), "");
-    int labelIndex = classLast ? static_cast<int>(attributes.size()) : 0;
+    auto removeLines = vector<int>(); // Lines with missing values
     for (size_t i = 0; i < lines.size(); i++) {
         stringstream ss(lines[i]);
         string value;
@@ -101,10 +129,20 @@ void ArffFiles::generateDataset(bool classLast)
             if (pos++ == labelIndex) {
                 yy[i] = value;
             } else {
-                X[xIndex++][i] = stof(value);
+                if (value == "?") {
+                    X[xIndex++][i] = -1;
+                    removeLines.push_back(i);
+                } else
+                    X[xIndex++][i] = stof(value);
             }
         }
     }
+    for (auto i : removeLines) {
+        yy.erase(yy.begin() + i);
+        for (auto& x : X) {
+            x.erase(x.begin() + i);
+        }
+    }
     y = factorize(yy);
 }
 

lib/Files/ArffFiles.h

@@ -14,12 +14,12 @@ private:
     string classType;
     vector<vector<float>> X;
     vector<int> y;
-
-    void generateDataset(bool);
-
+    void generateDataset(int);
+    void loadCommon(string);
 public:
     ArffFiles();
     void load(const string&, bool = true);
+    void load(const string&, const string&);
     vector<string> getLines() const;
     unsigned long int getSize() const;
     string getClassName() const;

lib/Files/CMakeLists.txt

@@ -0,0 +1,2 @@
+add_library(ArffFiles ArffFiles.cc)
+#target_link_libraries(BayesNet "${TORCH_LIBRARIES}")

sample/CMakeLists.txt

@@ -1,4 +1,7 @@
 include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
 include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
-add_executable(sample sample.cc ${BayesNet_SOURCE_DIR}/src/Platform/ArffFiles.cc ${BayesNet_SOURCE_DIR}/src/Platform/CPPFImdlp.cpp ${BayesNet_SOURCE_DIR}/src/Platform/Metrics.cpp ${BayesNet_SOURCE_DIR}/src/Platform/typesFImdlp.h ${BayesNet_HEADERS})
-target_link_libraries(sample BayesNet "${TORCH_LIBRARIES}")
+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

@@ -1,96 +1,20 @@
 #include <iostream>
-#include <string>
 #include <torch/torch.h>
+#include <string>
 #include <thread>
-#include <getopt.h>
+#include <map>
+#include <argparse/argparse.hpp>
 #include "ArffFiles.h"
-#include "Network.h"
-#include "Metrics.hpp"
+#include "BayesMetrics.h"
 #include "CPPFImdlp.h"
-#include "KDB.h"
-#include "SPODE.h"
-#include "AODE.h"
-#include "TAN.h"
+#include "Folding.h"
+#include "Models.h"
+#include "modelRegister.h"
 
 
 using namespace std;
 
-const string PATH = "data/";
-
-/* print a description of all supported options */
-void usage(const char* path)
-{
-    /* take only the last portion of the path */
-    const char* basename = strrchr(path, '/');
-    basename = basename ? basename + 1 : path;
-
-    cout << "usage: " << basename << "[OPTION]" << endl;
-    cout << "  -h, --help\t\t Print this help and exit." << endl;
-    cout
-        << "  -f, --file[=FILENAME]\t {diabetes, glass, iris, kdd_JapaneseVowels, letter, liver-disorders, mfeat-factors}."
-        << endl;
-    cout << "  -p, --path[=FILENAME]\t folder where the data files are located, default " << PATH << endl;
-    cout << "  -m, --model={AODE, KDB, SPODE, TAN}\t " << endl;
-}
-
-tuple<string, string, string> parse_arguments(int argc, char** argv)
-{
-    string file_name;
-    string model_name;
-    string path = PATH;
-    const vector<struct option> long_options = {
-            {"help",          no_argument,       nullptr, 'h'},
-            {"file",          required_argument, nullptr, 'f'},
-            {"path",          required_argument, nullptr, 'p'},
-            {"model",         required_argument, nullptr, 'm'},
-            {nullptr,         no_argument,       nullptr, 0}
-    };
-    while (true) {
-        const auto c = getopt_long(argc, argv, "hf:p:m:", long_options.data(), nullptr);
-        if (c == -1)
-            break;
-        switch (c) {
-            case 'h':
-                usage(argv[0]);
-                exit(0);
-            case 'f':
-                file_name = string(optarg);
-                break;
-            case 'm':
-                model_name = string(optarg);
-                break;
-            case 'p':
-                path = optarg;
-                if (path.back() != '/')
-                    path += '/';
-                break;
-            case '?':
-                usage(argv[0]);
-                exit(1);
-            default:
-                abort();
-        }
-    }
-    if (file_name.empty()) {
-        usage(argv[0]);
-        exit(1);
-    }
-    return make_tuple(file_name, path, model_name);
-}
-
-inline constexpr auto hash_conv(const std::string_view sv)
-{
-    unsigned long hash{ 5381 };
-    for (unsigned char c : sv) {
-        hash = ((hash << 5) + hash) ^ c;
-    }
-    return hash;
-}
-
-inline constexpr auto operator"" _sh(const char* str, size_t len)
-{
-    return hash_conv(std::string_view{ str, len });
-}
+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)
 {
@@ -116,8 +40,23 @@ bool file_exists(const std::string& name)
         return false;
     }
 }
+pair<vector<vector<int>>, vector<int>> extract_indices(vector<int> indices, vector<vector<int>> X, vector<int> y)
+{
+    vector<vector<int>> Xr;
+    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 };
+}
 
-tuple<string, string, string> get_options(int argc, char** argv)
+int main(int argc, char** argv)
 {
     map<string, bool> datasets = {
             {"diabetes",           true},
@@ -129,88 +68,102 @@ tuple<string, string, string> get_options(int argc, char** argv)
             {"liver-disorders",    true},
             {"mfeat-factors",      true},
     };
-    vector <string> models = { "AODE", "KDB", "SPODE", "TAN" };
-    string file_name;
-    string path;
-    string model_name;
-    tie(file_name, path, model_name) = parse_arguments(argc, argv);
-    if (datasets.find(file_name) == datasets.end()) {
-        cout << "Invalid file name: " << file_name << endl;
-        usage(argv[0]);
+    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("--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;
+    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");
+        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);
     }
-    if (!file_exists(path + file_name + ".arff")) {
-        cout << "Data File " << path + file_name + ".arff" << " does not exist" << endl;
-        usage(argv[0]);
-        exit(1);
-    }
-    if (find(models.begin(), models.end(), model_name) == models.end()) {
-        cout << "Invalid model name: " << model_name << endl;
-        usage(argv[0]);
-        exit(1);
-    }
-    return { file_name, path, model_name };
-}
 
-int main(int argc, char** argv)
-{
-    string file_name, path, model_name;
-    tie(file_name, path, model_name) = get_options(argc, argv);
+    /*
+    * Begin Processing
+    */
     auto handler = ArffFiles();
-    handler.load(path + file_name + ".arff");
+    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;
-    for (auto feature : handler.getAttributes()) {
-        features.push_back(feature.first);
-    }
+    auto attributes = handler.getAttributes();
+    transform(attributes.begin(), attributes.end(), back_inserter(features),
+        [](const pair<string, string>& item) { return item.first; });
     // Discretize Dataset
-    vector<mdlp::labels_t> Xd;
-    map<string, int> maxes;
-    tie(Xd, maxes) = discretize(X, y, features);
+    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]);
-    double score;
-    vector<string> lines;
-    vector<string> graph;
-    auto kdb = bayesnet::KDB(2);
-    auto aode = bayesnet::AODE();
-    auto spode = bayesnet::SPODE(2);
-    auto tan = bayesnet::TAN();
-    switch (hash_conv(model_name)) {
-        case "AODE"_sh:
-            aode.fit(Xd, y, features, className, states);
-            lines = aode.show();
-            score = aode.score(Xd, y);
-            graph = aode.graph();
-            break;
-        case "KDB"_sh:
-            kdb.fit(Xd, y, features, className, states);
-            lines = kdb.show();
-            score = kdb.score(Xd, y);
-            graph = kdb.graph();
-            break;
-        case "SPODE"_sh:
-            spode.fit(Xd, y, features, className, states);
-            lines = spode.show();
-            score = spode.score(Xd, y);
-            graph = spode.graph();
-            break;
-        case "TAN"_sh:
-            tan.fit(Xd, y, features, className, states);
-            lines = tan.show();
-            score = tan.score(Xd, y);
-            graph = tan.graph();
-            break;
-    }
+    states[className] = vector<int>(maxes[className]);
+    auto clf = platform::Models::instance()->create(model_name);
+    clf->fit(Xd, y, features, className, states);
+    auto score = clf->score(Xd, y);
+    auto lines = clf->show();
+    auto graph = clf->graph();
     for (auto line : lines) {
         cout << line << endl;
     }
@@ -221,5 +174,48 @@ int main(int argc, char** argv)
     file.close();
     cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
     cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
+    string stratified_string = stratified ? " Stratified" : "";
+    cout << nFolds << " Folds" << stratified_string << " Cross validation" << endl;
+    cout << "==========================================" << endl;
+    torch::Tensor Xt = torch::zeros({ static_cast<int>(Xd.size()), static_cast<int>(Xd[0].size()) }, torch::kInt32);
+    torch::Tensor yt = torch::tensor(y, torch::kInt32);
+    for (int i = 0; i < features.size(); ++i) {
+        Xt.index_put_({ i, "..." }, torch::tensor(Xd[i], torch::kInt32));
+    }
+    float total_score = 0, total_score_train = 0, score_train, score_test;
+    Fold* fold;
+    if (stratified)
+        fold = new StratifiedKFold(nFolds, y, seed);
+    else
+        fold = new KFold(nFolds, y.size(), seed);
+    for (auto i = 0; i < nFolds; ++i) {
+        auto [train, test] = fold->getFold(i);
+        cout << "Fold: " << i + 1 << endl;
+        if (tensors) {
+            auto ttrain = torch::tensor(train, torch::kInt64);
+            auto ttest = torch::tensor(test, torch::kInt64);
+            torch::Tensor Xtraint = torch::index_select(Xt, 1, ttrain);
+            torch::Tensor ytraint = yt.index({ ttrain });
+            torch::Tensor Xtestt = torch::index_select(Xt, 1, ttest);
+            torch::Tensor ytestt = yt.index({ ttest });
+            clf->fit(Xtraint, ytraint, features, className, states);
+            score_train = clf->score(Xtraint, ytraint);
+            score_test = clf->score(Xtestt, ytestt);
+        } else {
+            auto [Xtrain, ytrain] = extract_indices(train, Xd, y);
+            auto [Xtest, ytest] = extract_indices(test, Xd, y);
+            clf->fit(Xtrain, ytrain, features, className, states);
+            score_train = clf->score(Xtrain, ytrain);
+            score_test = clf->score(Xtest, ytest);
+        }
+        total_score_train += score_train;
+        total_score += score_test;
+        cout << "Score Train: " << score_train << endl;
+        cout << "Score Test : " << score_test << endl;
+        cout << "-------------------------------------------------------------------------------" << endl;
+    }
+    cout << "**********************************************************************************" << endl;
+    cout << "Average Score Train: " << total_score_train / nFolds << endl;
+    cout << "Average Score Test : " << total_score / nFolds << endl;
     return 0;
 }

src/BayesNet/AODE.h

@@ -8,7 +8,8 @@ namespace bayesnet {
         void train() override;
     public:
         AODE();
-        vector<string> graph(string title = "AODE");
+        virtual ~AODE() {};
+        vector<string> graph(string title = "AODE") override;
     };
 }
 #endif

src/BayesNet/BaseClassifier.h

@@ -1,48 +1,23 @@
-#ifndef CLASSIFIERS_H
-#define CLASSIFIERS_H
+#ifndef BASE_H
+#define BASE_H
 #include <torch/torch.h>
-#include "Network.h"
-#include "Metrics.hpp"
-using namespace std;
-using namespace torch;
-
+#include <vector>
 namespace bayesnet {
+    using namespace std;
     class BaseClassifier {
-    private:
-        bool fitted;
-        BaseClassifier& build(vector<string>& features, string className, map<string, vector<int>>& states);
-    protected:
-        Network model;
-        int m, n; // m: number of samples, n: number of features
-        Tensor X;
-        vector<vector<int>> Xv;
-        Tensor y;
-        vector<int> yv;
-        Tensor dataset;
-        Metrics metrics;
-        vector<string> features;
-        string className;
-        map<string, vector<int>> states;
-        void checkFitParameters();
-        virtual void train() = 0;
     public:
-        BaseClassifier(Network model);
+        virtual BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        virtual BaseClassifier& fit(torch::Tensor& X, torch::Tensor& y, vector<string>& features, string className, map<string, vector<int>>& states) = 0;
+        vector<int> virtual predict(vector<vector<int>>& X) = 0;
+        float virtual score(vector<vector<int>>& X, vector<int>& y) = 0;
+        float virtual score(torch::Tensor& X, torch::Tensor& y) = 0;
+        int virtual getNumberOfNodes() = 0;
+        int virtual getNumberOfEdges() = 0;
+        int virtual getNumberOfStates() = 0;
+        vector<string> virtual show() = 0;
+        vector<string> virtual graph(string title = "") = 0;
         virtual ~BaseClassifier() = default;
-        BaseClassifier& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states);
-        void addNodes();
-        int getNumberOfNodes();
-        int getNumberOfEdges();
-        Tensor predict(Tensor& X);
-        vector<int> predict(vector<vector<int>>& X);
-        float score(Tensor& X, Tensor& y);
-        float score(vector<vector<int>>& X, vector<int>& y);
-        vector<string> show();
-        virtual vector<string> graph(string title) = 0;
+        const string inline getVersion() const { return "0.1.0"; };
     };
 }
 #endif
-
-
-
-
-

src/BayesNet/BayesMetrics.cc

@@ -1,6 +1,5 @@
-#include "Metrics.hpp"
+#include "BayesMetrics.h"
 #include "Mst.h"
-using namespace std;
 namespace bayesnet {
     Metrics::Metrics(torch::Tensor& samples, vector<string>& features, string& className, int classNumStates)
         : samples(samples)
@@ -13,12 +12,12 @@ namespace bayesnet {
         : features(features)
         , className(className)
         , classNumStates(classNumStates)
+        , samples(torch::zeros({ static_cast<int>(vsamples[0].size()), static_cast<int>(vsamples.size() + 1) }, torch::kInt32))
     {
-        samples = torch::zeros({ static_cast<int64_t>(vsamples[0].size()), static_cast<int64_t>(vsamples.size() + 1) }, torch::kInt64);
         for (int i = 0; i < vsamples.size(); ++i) {
-            samples.index_put_({ "...", i }, torch::tensor(vsamples[i], torch::kInt64));
+            samples.index_put_({ "...", i }, torch::tensor(vsamples[i], torch::kInt32));
         }
-        samples.index_put_({ "...", -1 }, torch::tensor(labels, torch::kInt64));
+        samples.index_put_({ "...", -1 }, torch::tensor(labels, torch::kInt32));
     }
     vector<pair<string, string>> Metrics::doCombinations(const vector<string>& source)
     {
@@ -44,8 +43,8 @@ namespace bayesnet {
             margin[value] = mask.sum().item<float>() / samples.sizes()[0];
         }
         for (auto [first, second] : combinations) {
-            int64_t index_first = find(features.begin(), features.end(), first) - features.begin();
-            int64_t index_second = find(features.begin(), features.end(), second) - features.begin();
+            int index_first = find(features.begin(), features.end(), first) - features.begin();
+            int index_second = find(features.begin(), features.end(), second) - features.begin();
             double accumulated = 0;
             for (int value = 0; value < classNumStates; ++value) {
                 auto mask = samples.index({ "...", -1 }) == value;
@@ -95,7 +94,7 @@ namespace bayesnet {
             totalWeight += 1;
         }
         if (totalWeight == 0)
-            throw invalid_argument("Total weight should not be zero");
+            return 0;
         double entropyValue = 0;
         for (int value = 0; value < featureCounts.sizes()[0]; ++value) {
             double p_f = featureCounts[value].item<double>() / totalWeight;
@@ -124,7 +123,6 @@ namespace bayesnet {
     */
     vector<pair<int, int>> Metrics::maximumSpanningTree(vector<string> features, Tensor& weights, int root)
     {
-        auto result = vector<pair<int, int>>();
         auto mst = MST(features, weights, root);
         return mst.maximumSpanningTree();
     }

src/BayesNet/BayesMetrics.h

@@ -11,7 +11,7 @@ namespace bayesnet {
         Tensor samples;
         vector<string> features;
         string className;
-        int classNumStates;
+        int classNumStates = 0;
     public:
         Metrics() = default;
         Metrics(Tensor&, vector<string>&, string&, int);

src/BayesNet/CMakeLists.txt

@@ -1,2 +1,2 @@
-add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc Metrics.cc BaseClassifier.cc KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc Mst.cc)
+add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc Mst.cc)
 target_link_libraries(BayesNet "${TORCH_LIBRARIES}")

src/BayesNet/Classifier.cc

@@ -1,12 +1,11 @@
-#include "BaseClassifier.h"
+#include "Classifier.h"
 #include "bayesnetUtils.h"
 
 namespace bayesnet {
-    using namespace std;
     using namespace torch;
 
-    BaseClassifier::BaseClassifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
-    BaseClassifier& BaseClassifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
+    Classifier::Classifier(Network model) : model(model), m(0), n(0), metrics(Metrics()), fitted(false) {}
+    Classifier& Classifier::build(vector<string>& features, string className, map<string, vector<int>>& states)
     {
         dataset = torch::cat({ X, y.view({y.size(0), 1}) }, 1);
         this->features = features;
@@ -16,22 +15,37 @@ namespace bayesnet {
         auto n_classes = states[className].size();
         metrics = Metrics(dataset, features, className, n_classes);
         train();
-        model.fit(Xv, yv, features, className);
+        if (Xv == vector<vector<int>>()) {
+            // fit with tensors
+            model.fit(X, y, features, className);
+        } else {
+            // fit with vectors
+            model.fit(Xv, yv, features, className);
+        }
         fitted = true;
         return *this;
     }
-    BaseClassifier& BaseClassifier::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, vector<string>& features, string className, map<string, vector<int>>& states)
     {
-        this->X = torch::zeros({ static_cast<int64_t>(X[0].size()), static_cast<int64_t>(X.size()) }, kInt64);
+        this->X = torch::transpose(X, 0, 1);
+        this->y = y;
+        Xv = vector<vector<int>>();
+        yv = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        return build(features, className, states);
+    }
+
+    Classifier& Classifier::fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states)
+    {
+        this->X = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, kInt32);
         Xv = X;
         for (int i = 0; i < X.size(); ++i) {
-            this->X.index_put_({ "...", i }, torch::tensor(X[i], kInt64));
+            this->X.index_put_({ "...", i }, torch::tensor(X[i], kInt32));
         }
-        this->y = torch::tensor(y, kInt64);
+        this->y = torch::tensor(y, kInt32);
         yv = y;
         return build(features, className, states);
     }
-    void BaseClassifier::checkFitParameters()
+    void Classifier::checkFitParameters()
     {
         auto sizes = X.sizes();
         m = sizes[0];
@@ -52,23 +66,24 @@ namespace bayesnet {
         }
     }
 
-    Tensor BaseClassifier::predict(Tensor& X)
+    Tensor Classifier::predict(Tensor& X)
     {
         if (!fitted) {
             throw logic_error("Classifier has not been fitted");
         }
         auto m_ = X.size(0);
         auto n_ = X.size(1);
+        //auto Xt = torch::transpose(X, 0, 1);
         vector<vector<int>> Xd(n_, vector<int>(m_, 0));
         for (auto i = 0; i < n_; i++) {
             auto temp = X.index({ "...", i });
-            Xd[i] = vector<int>(temp.data_ptr<int>(), temp.data_ptr<int>() + m_);
+            Xd[i] = vector<int>(temp.data_ptr<int>(), temp.data_ptr<int>() + temp.numel());
         }
         auto yp = model.predict(Xd);
-        auto ypred = torch::tensor(yp, torch::kInt64);
+        auto ypred = torch::tensor(yp, torch::kInt32);
         return ypred;
     }
-    vector<int> BaseClassifier::predict(vector<vector<int>>& X)
+    vector<int> Classifier::predict(vector<vector<int>>& X)
     {
         if (!fitted) {
             throw logic_error("Classifier has not been fitted");
@@ -82,15 +97,16 @@ namespace bayesnet {
         auto yp = model.predict(Xd);
         return yp;
     }
-    float BaseClassifier::score(Tensor& X, Tensor& y)
+    float Classifier::score(Tensor& X, Tensor& y)
     {
         if (!fitted) {
             throw logic_error("Classifier has not been fitted");
         }
-        Tensor y_pred = predict(X);
+        auto Xt = torch::transpose(X, 0, 1);
+        Tensor y_pred = predict(Xt);
         return (y_pred == y).sum().item<float>() / y.size(0);
     }
-    float BaseClassifier::score(vector<vector<int>>& X, vector<int>& y)
+    float Classifier::score(vector<vector<int>>& X, vector<int>& y)
     {
         if (!fitted) {
             throw logic_error("Classifier has not been fitted");
@@ -103,11 +119,11 @@ namespace bayesnet {
         }
         return model.score(Xd, y);
     }
-    vector<string> BaseClassifier::show()
+    vector<string> Classifier::show()
     {
         return model.show();
     }
-    void BaseClassifier::addNodes()
+    void Classifier::addNodes()
     {
         // Add all nodes to the network
         for (auto feature : features) {
@@ -115,13 +131,17 @@ namespace bayesnet {
         }
         model.addNode(className, states[className].size());
     }
-    int BaseClassifier::getNumberOfNodes()
+    int Classifier::getNumberOfNodes()
     {
         // Features does not include class
         return fitted ? model.getFeatures().size() + 1 : 0;
     }
-    int BaseClassifier::getNumberOfEdges()
+    int Classifier::getNumberOfEdges()
     {
         return fitted ? model.getEdges().size() : 0;
     }
+    int Classifier::getNumberOfStates()
+    {
+        return fitted ? model.getStates() : 0;
+    }
 }

src/BayesNet/Classifier.h

@@ -0,0 +1,50 @@
+#ifndef CLASSIFIER_H
+#define CLASSIFIER_H
+#include <torch/torch.h>
+#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);
+    protected:
+        Network model;
+        int m, n; // m: number of samples, n: number of features
+        Tensor X;
+        vector<vector<int>> Xv;
+        Tensor y;
+        vector<int> yv;
+        Tensor dataset;
+        Metrics metrics;
+        vector<string> features;
+        string className;
+        map<string, vector<int>> states;
+        void checkFitParameters();
+        virtual void train() = 0;
+    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;
+        void addNodes();
+        int getNumberOfNodes() override;
+        int getNumberOfEdges() override;
+        int getNumberOfStates() override;
+        Tensor predict(Tensor& X);
+        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;
+    };
+}
+#endif
+
+
+
+
+

src/BayesNet/Ensemble.cc

@@ -1,7 +1,6 @@
 #include "Ensemble.h"
 
 namespace bayesnet {
-    using namespace std;
     using namespace torch;
 
     Ensemble::Ensemble() : m(0), n(0), n_models(0), metrics(Metrics()), fitted(false) {}
@@ -23,14 +22,22 @@ namespace bayesnet {
         fitted = true;
         return *this;
     }
+    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)
     {
-        this->X = torch::zeros({ static_cast<int64_t>(X[0].size()), static_cast<int64_t>(X.size()) }, kInt64);
+        this->X = torch::zeros({ static_cast<int>(X[0].size()), static_cast<int>(X.size()) }, kInt32);
         Xv = X;
         for (int i = 0; i < X.size(); ++i) {
-            this->X.index_put_({ "...", i }, torch::tensor(X[i], kInt64));
+            this->X.index_put_({ "...", i }, torch::tensor(X[i], kInt32));
         }
-        this->y = torch::tensor(y, kInt64);
+        this->y = torch::tensor(y, kInt32);
         yv = y;
         return build(features, className, states);
     }
@@ -39,7 +46,7 @@ namespace bayesnet {
         if (!fitted) {
             throw logic_error("Ensemble has not been fitted");
         }
-        Tensor y_pred = torch::zeros({ X.size(0), n_models }, kInt64);
+        Tensor y_pred = torch::zeros({ X.size(0), n_models }, kInt32);
         for (auto i = 0; i < n_models; ++i) {
             y_pred.index_put_({ "...", i }, models[i]->predict(X));
         }
@@ -47,7 +54,7 @@ namespace bayesnet {
     }
     vector<int> Ensemble::voting(Tensor& y_pred)
     {
-        auto y_pred_ = y_pred.accessor<int64_t, 2>();
+        auto y_pred_ = y_pred.accessor<int, 2>();
         vector<int> y_pred_final;
         for (int i = 0; i < y_pred.size(0); ++i) {
             vector<float> votes(states[className].size(), 0);
@@ -70,12 +77,26 @@ namespace bayesnet {
         for (auto i = 0; i < n_; i++) {
             Xd[i] = vector<int>(X[i].begin(), X[i].end());
         }
-        Tensor y_pred = torch::zeros({ m_, n_models }, kInt64);
+        Tensor y_pred = torch::zeros({ m_, n_models }, kInt32);
         for (auto i = 0; i < n_models; ++i) {
-            y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), kInt64));
+            y_pred.index_put_({ "...", i }, torch::tensor(models[i]->predict(Xd), kInt32));
         }
         return voting(y_pred);
     }
+    float Ensemble::score(Tensor& X, Tensor& y)
+    {
+        if (!fitted) {
+            throw logic_error("Ensemble has not been fitted");
+        }
+        auto y_pred = predict(X);
+        int correct = 0;
+        for (int i = 0; i < y_pred.size(0); ++i) {
+            if (y_pred[i].item<int>() == y[i].item<int>()) {
+                correct++;
+            }
+        }
+        return (double)correct / y_pred.size(0);
+    }
     float Ensemble::score(vector<vector<int>>& X, vector<int>& y)
     {
         if (!fitted) {
@@ -109,4 +130,28 @@ namespace bayesnet {
         }
         return result;
     }
+    int Ensemble::getNumberOfNodes()
+    {
+        int nodes = 0;
+        for (auto i = 0; i < n_models; ++i) {
+            nodes += models[i]->getNumberOfNodes();
+        }
+        return nodes;
+    }
+    int Ensemble::getNumberOfEdges()
+    {
+        int edges = 0;
+        for (auto i = 0; i < n_models; ++i) {
+            edges += models[i]->getNumberOfEdges();
+        }
+        return edges;
+    }
+    int Ensemble::getNumberOfStates()
+    {
+        int nstates = 0;
+        for (auto i = 0; i < n_models; ++i) {
+            nstates += models[i]->getNumberOfStates();
+        }
+        return nstates;
+    }
 }

src/BayesNet/Ensemble.h

@@ -1,20 +1,20 @@
 #ifndef ENSEMBLE_H
 #define ENSEMBLE_H
 #include <torch/torch.h>
-#include "BaseClassifier.h"
-#include "Metrics.hpp"
+#include "Classifier.h"
+#include "BayesMetrics.h"
 #include "bayesnetUtils.h"
 using namespace std;
 using namespace torch;
 
 namespace bayesnet {
-    class Ensemble {
+    class Ensemble : public BaseClassifier {
     private:
         bool fitted;
         long n_models;
         Ensemble& build(vector<string>& features, string className, map<string, vector<int>>& states);
     protected:
-        vector<unique_ptr<BaseClassifier>> models;
+        vector<unique_ptr<Classifier>> models;
         int m, n; // m: number of samples, n: number of features
         Tensor X;
         vector<vector<int>> Xv;
@@ -30,13 +30,17 @@ namespace bayesnet {
     public:
         Ensemble();
         virtual ~Ensemble() = default;
-        Ensemble& fit(vector<vector<int>>& X, vector<int>& y, vector<string>& features, string className, map<string, vector<int>>& states);
+        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);
-        vector<int> predict(vector<vector<int>>& X);
-        float score(Tensor& X, Tensor& y);
-        float score(vector<vector<int>>& X, vector<int>& y);
-        vector<string> show();
-        vector<string> graph(string title);
+        vector<int> predict(vector<vector<int>>& X) override;
+        float score(Tensor& X, Tensor& y) override;
+        float score(vector<vector<int>>& X, vector<int>& y) override;
+        int getNumberOfNodes() override;
+        int getNumberOfEdges() override;
+        int getNumberOfStates() override;
+        vector<string> show() override;
+        vector<string> graph(string title) override;
     };
 }
 #endif

src/BayesNet/KDB.cc

@@ -1,10 +1,9 @@
 #include "KDB.h"
 
 namespace bayesnet {
-    using namespace std;
     using namespace torch;
 
-    KDB::KDB(int k, float theta) : BaseClassifier(Network()), k(k), theta(theta) {}
+    KDB::KDB(int k, float theta) : Classifier(Network()), k(k), theta(theta) {}
     void KDB::train()
     {
         /*

src/BayesNet/KDB.h

@@ -1,11 +1,11 @@
 #ifndef KDB_H
 #define KDB_H
-#include "BaseClassifier.h"
+#include "Classifier.h"
 #include "bayesnetUtils.h"
 namespace bayesnet {
     using namespace std;
     using namespace torch;
-    class KDB : public BaseClassifier {
+    class KDB : public Classifier {
     private:
         int k;
         float theta;
@@ -13,7 +13,8 @@ namespace bayesnet {
     protected:
         void train() override;
     public:
-        KDB(int k, float theta = 0.03);
+        explicit KDB(int k, float theta = 0.03);
+        virtual ~KDB() {};
         vector<string> graph(string name = "KDB") override;
     };
 }

src/BayesNet/Mst.cc

@@ -7,9 +7,8 @@
 
 namespace bayesnet {
     using namespace std;
-    Graph::Graph(int V)
+    Graph::Graph(int V) : V(V), parent(vector<int>(V))
     {
-        parent = vector<int>(V);
         for (int i = 0; i < V; i++)
             parent[i] = i;
         G.clear();
@@ -34,10 +33,10 @@ namespace bayesnet {
     }
     void Graph::kruskal_algorithm()
     {
-        int i, uSt, vEd;
         // sort the edges ordered on decreasing weight
-        sort(G.begin(), G.end(), [](auto& left, auto& right) {return left.first > right.first;});
-        for (i = 0; i < G.size(); i++) {
+        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) {
@@ -103,7 +102,7 @@ namespace bayesnet {
 
         // Make a complete graph
         for (int i = 0; i < num_features - 1; ++i) {
-            for (int j = i; j < num_features; ++j) {
+            for (int j = i + 1; j < num_features; ++j) {
                 g.addEdge(i, j, weights[i][j].item<float>());
             }
         }

src/BayesNet/Mst.h

@@ -10,7 +10,7 @@ namespace bayesnet {
     private:
         Tensor weights;
         vector<string> features;
-        int root;
+        int root = 0;
     public:
         MST() = default;
         MST(vector<string>& features, Tensor& weights, int root);
@@ -23,7 +23,7 @@ namespace bayesnet {
         vector <pair<float, pair<int, int>>> T; // vector for mst
         vector<int> parent;
     public:
-        Graph(int V);
+        explicit Graph(int V);
         void addEdge(int u, int v, float wt);
         int find_set(int i);
         void union_set(int u, int v);

src/BayesNet/Network.cc

@@ -1,14 +1,15 @@
 #include <thread>
 #include <mutex>
 #include "Network.h"
+#include "bayesnetUtils.h"
 namespace bayesnet {
     Network::Network() : laplaceSmoothing(1), features(vector<string>()), className(""), classNumStates(0), maxThreads(0.8), fitted(false) {}
     Network::Network(float maxT) : laplaceSmoothing(1), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
     Network::Network(float maxT, int smoothing) : laplaceSmoothing(smoothing), features(vector<string>()), className(""), classNumStates(0), maxThreads(maxT), fitted(false) {}
     Network::Network(Network& other) : laplaceSmoothing(other.laplaceSmoothing), features(other.features), className(other.className), classNumStates(other.getClassNumStates()), maxThreads(other.getmaxThreads()), fitted(other.fitted)
     {
-        for (auto& pair : other.nodes) {
-            nodes[pair.first] = make_unique<Node>(*pair.second);
+        for (const auto& pair : other.nodes) {
+            nodes[pair.first] = std::make_unique<Node>(*pair.second);
         }
     }
     float Network::getmaxThreads()
@@ -19,17 +20,18 @@ namespace bayesnet {
     {
         return samples;
     }
-    void Network::addNode(string name, int numStates)
+    void Network::addNode(const string& name, int numStates)
     {
         if (find(features.begin(), features.end(), name) == features.end()) {
             features.push_back(name);
         }
         if (nodes.find(name) != nodes.end()) {
-            // if node exists update its number of states
+            // if node exists update its number of states and remove parents, children and CPT
+            nodes[name]->clear();
             nodes[name]->setNumStates(numStates);
             return;
         }
-        nodes[name] = make_unique<Node>(name, numStates);
+        nodes[name] = std::make_unique<Node>(name, numStates);
     }
     vector<string> Network::getFeatures()
     {
@@ -67,7 +69,7 @@ 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 string& parent, const string& child)
     {
         if (nodes.find(parent) == nodes.end()) {
             throw invalid_argument("Parent node " + parent + " does not exist");
@@ -87,27 +89,50 @@ namespace bayesnet {
             nodes[child]->removeParent(nodes[parent].get());
             throw invalid_argument("Adding this edge forms a cycle in the graph.");
         }
-
     }
     map<string, std::unique_ptr<Node>>& Network::getNodes()
     {
         return nodes;
     }
+    void Network::fit(torch::Tensor& X, torch::Tensor& y, const vector<string>& featureNames, const string& className)
+    {
+        features = featureNames;
+        this->className = className;
+        dataset.clear();
+        // Specific part
+        classNumStates = torch::max(y).item<int>() + 1;
+        samples = torch::cat({ X, y.view({ y.size(0), 1 }) }, 1);
+        for (int i = 0; i < featureNames.size(); ++i) {
+            auto column = torch::flatten(X.index({ "...", i }));
+            auto k = vector<int>();
+            for (auto z = 0; z < X.size(0); ++z) {
+                k.push_back(column[z].item<int>());
+            }
+            dataset[featureNames[i]] = k;
+        }
+        dataset[className] = vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
+        completeFit();
+    }
     void Network::fit(const vector<vector<int>>& input_data, const vector<int>& labels, const vector<string>& featureNames, const string& className)
     {
         features = featureNames;
         this->className = className;
         dataset.clear();
-
+        // Specific part
+        classNumStates = *max_element(labels.begin(), labels.end()) + 1;
         // Build dataset & tensor of samples
-        samples = torch::zeros({ static_cast<int64_t>(input_data[0].size()), static_cast<int64_t>(input_data.size() + 1) }, torch::kInt64);
+        samples = torch::zeros({ static_cast<int>(input_data[0].size()), static_cast<int>(input_data.size() + 1) }, 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::kInt64));
+            samples.index_put_({ "...", i }, torch::tensor(input_data[i], torch::kInt32));
         }
         dataset[className] = labels;
-        samples.index_put_({ "...", -1 }, torch::tensor(labels, torch::kInt64));
-        classNumStates = *max_element(labels.begin(), labels.end()) + 1;
+        samples.index_put_({ "...", -1 }, torch::tensor(labels, torch::kInt32));
+        completeFit();
+    }
+    void Network::completeFit()
+    {
+
         int maxThreadsRunning = static_cast<int>(std::thread::hardware_concurrency() * maxThreads);
         if (maxThreadsRunning < 1) {
             maxThreadsRunning = 1;
@@ -117,15 +142,9 @@ namespace bayesnet {
         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; });
-
-            if (nextNodeIndex >= nodes.size()) {
-                break;  // No more work remaining
-            }
-
             threads.emplace_back([this, &nextNodeIndex, &mtx, &cv, &activeThreads]() {
                 while (true) {
                     unique_lock<mutex> lock(mtx);
@@ -135,7 +154,6 @@ namespace bayesnet {
                     auto& pair = *std::next(nodes.begin(), nextNodeIndex);
                     ++nextNodeIndex;
                     lock.unlock();
-
                     pair.second->computeCPT(dataset, laplaceSmoothing);
                     lock.lock();
                     nodes[pair.first] = std::move(pair.second);
@@ -145,7 +163,6 @@ namespace bayesnet {
                 --activeThreads;
                 cv.notify_one();
                 });
-
             ++activeThreads;
         }
         for (auto& thread : threads) {
@@ -213,7 +230,6 @@ namespace bayesnet {
             evidence[features[i]] = sample[i];
         }
         return exactInference(evidence);
-
     }
     double Network::computeFactor(map<string, int>& completeEvidence)
     {
@@ -243,9 +259,7 @@ namespace bayesnet {
 
         // Normalize result
         double sum = accumulate(result.begin(), result.end(), 0.0);
-        for (double& value : result) {
-            value /= sum;
-        }
+        transform(result.begin(), result.end(), result.begin(), [sum](double& value) { return value / sum; });
         return result;
     }
     vector<string> Network::show()
@@ -261,7 +275,7 @@ namespace bayesnet {
         }
         return result;
     }
-    vector<string> Network::graph(string title)
+    vector<string> Network::graph(const string& title)
     {
         auto output = vector<string>();
         auto prefix = "digraph BayesNet {\nlabel=<BayesNet ";
@@ -287,5 +301,4 @@ namespace bayesnet {
         }
         return edges;
     }
-
 }

src/BayesNet/Network.h

@@ -7,7 +7,7 @@
 namespace bayesnet {
     class Network {
     private:
-        map<string, std::unique_ptr<Node>> nodes;
+        map<string, unique_ptr<Node>> nodes;
         map<string, vector<int>> dataset;
         bool fitted;
         float maxThreads;
@@ -24,15 +24,16 @@ namespace bayesnet {
         double entropy(torch::Tensor&);
         double conditionalEntropy(torch::Tensor&, torch::Tensor&);
         double mutualInformation(torch::Tensor&, torch::Tensor&);
+        void completeFit();
     public:
         Network();
-        Network(float, int);
-        Network(float);
-        Network(Network&);
+        explicit Network(float, int);
+        explicit Network(float);
+        explicit Network(Network&);
         torch::Tensor& getSamples();
         float getmaxThreads();
-        void addNode(string, int);
-        void addEdge(const string, const string);
+        void addNode(const string&, int);
+        void addEdge(const string&, const string&);
         map<string, std::unique_ptr<Node>>& getNodes();
         vector<string> getFeatures();
         int getStates();
@@ -40,13 +41,14 @@ namespace bayesnet {
         int getClassNumStates();
         string getClassName();
         void fit(const vector<vector<int>>&, const vector<int>&, const vector<string>&, const string&);
+        void fit(torch::Tensor&, torch::Tensor&, const vector<string>&, const string&);
         vector<int> predict(const vector<vector<int>>&);
         //Computes the conditional edge weight of variable index u and v conditioned on class_node
         torch::Tensor conditionalEdgeWeight();
         vector<vector<double>> predict_proba(const vector<vector<int>>&);
         double score(const vector<vector<int>>&, const vector<int>&);
         vector<string> show();
-        vector<string> graph(string title); // Returns a vector of strings representing the graph in graphviz format
+        vector<string> graph(const string& title); // Returns a vector of strings representing the graph in graphviz format
         inline string version() { return "0.1.0"; }
     };
 }

src/BayesNet/Node.cc

@@ -6,6 +6,14 @@ namespace bayesnet {
         : name(name), numStates(numStates), cpTable(torch::Tensor()), parents(vector<Node*>()), children(vector<Node*>())
     {
     }
+    void Node::clear()
+    {
+        parents.clear();
+        children.clear();
+        cpTable = torch::Tensor();
+        dimensions.clear();
+        numStates = 0;
+    }
     string Node::getName() const
     {
         return name;
@@ -80,19 +88,15 @@ namespace bayesnet {
     {
         // Get dimensions of the CPT
         dimensions.push_back(numStates);
-        for (auto father : getParents()) {
-            dimensions.push_back(father->getNumStates());
-        }
-        auto length = dimensions.size();
+        transform(parents.begin(), parents.end(), back_inserter(dimensions), [](const auto& parent) { return parent->getNumStates(); });
+
         // 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]));
-            for (auto father : getParents()) {
-                coordinates.push_back(torch::tensor(dataset[father->getName()][n_sample]));
-            }
+            transform(parents.begin(), parents.end(), back_inserter(coordinates), [&dataset, &n_sample](const auto& parent) { return torch::tensor(dataset[parent->getName()][n_sample]); });
             // Increment the count of the corresponding coordinate
             cpTable.index_put_({ coordinates }, cpTable.index({ coordinates }) + 1);
         }
@@ -104,19 +108,15 @@ namespace bayesnet {
         torch::List<c10::optional<torch::Tensor>> coordinates;
         // following predetermined order of indices in the cpTable (see Node.h)
         coordinates.push_back(torch::tensor(evidence[name]));
-        for (auto parent : getParents()) {
-            coordinates.push_back(torch::tensor(evidence[parent->getName()]));
-        }
+        transform(parents.begin(), parents.end(), back_inserter(coordinates), [&evidence](const auto& parent) { return torch::tensor(evidence[parent->getName()]); });
         return cpTable.index({ coordinates }).item<float>();
     }
-    vector<string> Node::graph(string className)
+    vector<string> Node::graph(const string& className)
     {
         auto output = vector<string>();
         auto suffix = name == className ? ", fontcolor=red, fillcolor=lightblue, style=filled " : "";
         output.push_back(name + " [shape=circle" + suffix + "] \n");
-        for (auto& child : children) {
-            output.push_back(name + " -> " + child->getName());
-        }
+        transform(children.begin(), children.end(), back_inserter(output), [this](const auto& child) { return name + " -> " + child->getName(); });
         return output;
     }
 }

src/BayesNet/Node.h

@@ -16,7 +16,8 @@ namespace bayesnet {
         vector<int64_t> dimensions; // dimensions of the cpTable
     public:
         vector<pair<string, string>> combinations(const vector<string>&);
-        Node(const std::string&, int);
+        Node(const string&, int);
+        void clear();
         void addParent(Node*);
         void addChild(Node*);
         void removeParent(Node*);
@@ -29,7 +30,7 @@ namespace bayesnet {
         int getNumStates() const;
         void setNumStates(int);
         unsigned minFill();
-        vector<string> graph(string clasName); // Returns a vector of strings representing the graph in graphviz format
+        vector<string> graph(const string& clasName); // Returns a vector of strings representing the graph in graphviz format
         float getFactorValue(map<string, int>&);
     };
 }

src/BayesNet/SPODE.cc

@@ -2,7 +2,7 @@
 
 namespace bayesnet {
 
-    SPODE::SPODE(int root) : BaseClassifier(Network()), root(root) {}
+    SPODE::SPODE(int root) : Classifier(Network()), root(root) {}
 
     void SPODE::train()
     {

src/BayesNet/SPODE.h

@@ -1,14 +1,16 @@
 #ifndef SPODE_H
 #define SPODE_H
-#include "BaseClassifier.h"
+#include "Classifier.h"
+
 namespace bayesnet {
-    class SPODE : public BaseClassifier {
+    class SPODE : public Classifier {
     private:
         int root;
     protected:
         void train() override;
     public:
-        SPODE(int root);
+        explicit SPODE(int root);
+        virtual ~SPODE() {};
         vector<string> graph(string name = "SPODE") override;
     };
 }

src/BayesNet/TAN.cc

@@ -1,10 +1,9 @@
 #include "TAN.h"
 
 namespace bayesnet {
-    using namespace std;
     using namespace torch;
 
-    TAN::TAN() : BaseClassifier(Network()) {}
+    TAN::TAN() : Classifier(Network()) {}
 
     void TAN::train()
     {
@@ -19,7 +18,7 @@ namespace bayesnet {
             auto mi_value = metrics.mutualInformation(class_dataset, feature_dataset);
             mi.push_back({ i, mi_value });
         }
-        sort(mi.begin(), mi.end(), [](auto& left, auto& right) {return left.second < right.second;});
+        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();

src/BayesNet/TAN.h

@@ -1,15 +1,16 @@
 #ifndef TAN_H
 #define TAN_H
-#include "BaseClassifier.h"
+#include "Classifier.h"
 namespace bayesnet {
     using namespace std;
     using namespace torch;
-    class TAN : public BaseClassifier {
+    class TAN : public Classifier {
     private:
     protected:
         void train() override;
     public:
         TAN();
+        virtual ~TAN() {};
         vector<string> graph(string name = "TAN") override;
     };
 }

src/BayesNet/bayesnetUtils.cc

@@ -11,21 +11,16 @@ namespace bayesnet {
         sort(indices.begin(), indices.end(), [&nums](int i, int j) {return nums[i] > nums[j];});
         return indices;
     }
-    vector<vector<int>> tensorToVector(const Tensor& tensor)
+    vector<vector<int>> tensorToVector(Tensor& tensor)
     {
         // convert mxn tensor to nxm vector
         vector<vector<int>> result;
-        auto tensor_accessor = tensor.accessor<int, 2>();
-
-        // Iterate over columns and rows of the tensor
-        for (int j = 0; j < tensor.size(1); ++j) {
-            vector<int> column;
-            for (int i = 0; i < tensor.size(0); ++i) {
-                column.push_back(tensor_accessor[i][j]);
-            }
-            result.push_back(column);
+        // 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));
+            result.push_back(col);
         }
-
         return result;
     }
 }

src/BayesNet/bayesnetUtils.h

@@ -6,6 +6,6 @@ namespace bayesnet {
     using namespace std;
     using namespace torch;
     vector<int> argsort(vector<float>& nums);
-    vector<vector<int>> tensorToVector(const Tensor& tensor);
+    vector<vector<int>> tensorToVector(Tensor& tensor);
 }
 #endif //BAYESNET_UTILS_H

src/Platform/CMakeLists.txt

@@ -1,4 +1,8 @@
 include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
 include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
-add_executable(main Experiment.cc ArffFiles.cc CPPFImdlp.cpp Metrics.cpp platformUtils.cc)
-target_link_libraries(main BayesNet "${TORCH_LIBRARIES}")
+include_directories(${BayesNet_SOURCE_DIR}/lib/Files)
+include_directories(${BayesNet_SOURCE_DIR}/lib/mdlp)
+include_directories(${BayesNet_SOURCE_DIR}/lib/argparse/include)
+include_directories(${BayesNet_SOURCE_DIR}/lib/json/include)
+add_executable(main main.cc Folding.cc platformUtils.cc Experiment.cc Datasets.cc Models.cc)
+target_link_libraries(main BayesNet ArffFiles mdlp "${TORCH_LIBRARIES}")

src/Platform/CPPFImdlp.cpp

@@ -1,221 +0,0 @@
-#include <numeric>
-#include <algorithm>
-#include <set>
-#include <cmath>
-#include "CPPFImdlp.h"
-#include "Metrics.h"
-
-namespace mdlp {
-
-    CPPFImdlp::CPPFImdlp(size_t min_length_, int max_depth_, float proposed) : min_length(min_length_),
-        max_depth(max_depth_),
-        proposed_cuts(proposed)
-    {
-    }
-
-    CPPFImdlp::CPPFImdlp() = default;
-
-    CPPFImdlp::~CPPFImdlp() = default;
-
-    size_t CPPFImdlp::compute_max_num_cut_points() const
-    {
-        // Set the actual maximum number of cut points as a number or as a percentage of the number of samples
-        if (proposed_cuts == 0) {
-            return numeric_limits<size_t>::max();
-        }
-        if (proposed_cuts < 0 || proposed_cuts > static_cast<float>(X.size())) {
-            throw invalid_argument("wrong proposed num_cuts value");
-        }
-        if (proposed_cuts < 1)
-            return static_cast<size_t>(round(static_cast<float>(X.size()) * proposed_cuts));
-        return static_cast<size_t>(proposed_cuts);
-    }
-
-    void CPPFImdlp::fit(samples_t& X_, labels_t& y_)
-    {
-        X = X_;
-        y = y_;
-        num_cut_points = compute_max_num_cut_points();
-        depth = 0;
-        discretizedData.clear();
-        cutPoints.clear();
-        if (X.size() != y.size()) {
-            throw invalid_argument("X and y must have the same size");
-        }
-        if (X.empty() || y.empty()) {
-            throw invalid_argument("X and y must have at least one element");
-        }
-        if (min_length < 3) {
-            throw invalid_argument("min_length must be greater than 2");
-        }
-        if (max_depth < 1) {
-            throw invalid_argument("max_depth must be greater than 0");
-        }
-        indices = sortIndices(X_, y_);
-        metrics.setData(y, indices);
-        computeCutPoints(0, X.size(), 1);
-        sort(cutPoints.begin(), cutPoints.end());
-        if (num_cut_points > 0) {
-            // Select the best (with lower entropy) cut points
-            while (cutPoints.size() > num_cut_points) {
-                resizeCutPoints();
-            }
-        }
-    }
-
-    pair<precision_t, size_t> CPPFImdlp::valueCutPoint(size_t start, size_t cut, size_t end)
-    {
-        size_t n;
-        size_t m;
-        size_t idxPrev = cut - 1 >= start ? cut - 1 : cut;
-        size_t idxNext = cut + 1 < end ? cut + 1 : cut;
-        bool backWall; // true if duplicates reach beginning of the interval
-        precision_t previous;
-        precision_t actual;
-        precision_t next;
-        previous = X[indices[idxPrev]];
-        actual = X[indices[cut]];
-        next = X[indices[idxNext]];
-        // definition 2 of the paper => X[t-1] < X[t]
-        // get the first equal value of X in the interval
-        while (idxPrev > start && actual == previous) {
-            previous = X[indices[--idxPrev]];
-        }
-        backWall = idxPrev == start && actual == previous;
-        // get the last equal value of X in the interval
-        while (idxNext < end - 1 && actual == next) {
-            next = X[indices[++idxNext]];
-        }
-        // # of duplicates before cutpoint
-        n = cut - 1 - idxPrev;
-        // # of duplicates after cutpoint
-        m = idxNext - cut - 1;
-        // Decide which values to use
-        cut = cut + (backWall ? m + 1 : -n);
-        actual = X[indices[cut]];
-        return { (actual + previous) / 2, cut };
-    }
-
-    void CPPFImdlp::computeCutPoints(size_t start, size_t end, int depth_)
-    {
-        size_t cut;
-        pair<precision_t, size_t> result;
-        // Check if the interval length and the depth are Ok
-        if (end - start < min_length || depth_ > max_depth)
-            return;
-        depth = depth_ > depth ? depth_ : depth;
-        cut = getCandidate(start, end);
-        if (cut == numeric_limits<size_t>::max())
-            return;
-        if (mdlp(start, cut, end)) {
-            result = valueCutPoint(start, cut, end);
-            cut = result.second;
-            cutPoints.push_back(result.first);
-            computeCutPoints(start, cut, depth_ + 1);
-            computeCutPoints(cut, end, depth_ + 1);
-        }
-    }
-
-    size_t CPPFImdlp::getCandidate(size_t start, size_t end)
-    {
-        /* Definition 1: A binary discretization for A is determined by selecting the cut point TA for which
-        E(A, TA; S) is minimal amongst all the candidate cut points. */
-        size_t candidate = numeric_limits<size_t>::max();
-        size_t elements = end - start;
-        bool sameValues = true;
-        precision_t entropy_left;
-        precision_t entropy_right;
-        precision_t minEntropy;
-        // Check if all the values of the variable in the interval are the same
-        for (size_t idx = start + 1; idx < end; idx++) {
-            if (X[indices[idx]] != X[indices[start]]) {
-                sameValues = false;
-                break;
-            }
-        }
-        if (sameValues)
-            return candidate;
-        minEntropy = metrics.entropy(start, end);
-        for (size_t idx = start + 1; idx < end; idx++) {
-            // Cutpoints are always on boundaries (definition 2)
-            if (y[indices[idx]] == y[indices[idx - 1]])
-                continue;
-            entropy_left = precision_t(idx - start) / static_cast<precision_t>(elements) * metrics.entropy(start, idx);
-            entropy_right = precision_t(end - idx) / static_cast<precision_t>(elements) * metrics.entropy(idx, end);
-            if (entropy_left + entropy_right < minEntropy) {
-                minEntropy = entropy_left + entropy_right;
-                candidate = idx;
-            }
-        }
-        return candidate;
-    }
-
-    bool CPPFImdlp::mdlp(size_t start, size_t cut, size_t end)
-    {
-        int k;
-        int k1;
-        int k2;
-        precision_t ig;
-        precision_t delta;
-        precision_t ent;
-        precision_t ent1;
-        precision_t ent2;
-        auto N = precision_t(end - start);
-        k = metrics.computeNumClasses(start, end);
-        k1 = metrics.computeNumClasses(start, cut);
-        k2 = metrics.computeNumClasses(cut, end);
-        ent = metrics.entropy(start, end);
-        ent1 = metrics.entropy(start, cut);
-        ent2 = metrics.entropy(cut, end);
-        ig = metrics.informationGain(start, cut, end);
-        delta = static_cast<precision_t>(log2(pow(3, precision_t(k)) - 2) -
-            (precision_t(k) * ent - precision_t(k1) * ent1 - precision_t(k2) * ent2));
-        precision_t term = 1 / N * (log2(N - 1) + delta);
-        return ig > term;
-    }
-
-    // Argsort from https://stackoverflow.com/questions/1577475/c-sorting-and-keeping-track-of-indexes
-    indices_t CPPFImdlp::sortIndices(samples_t& X_, labels_t& y_)
-    {
-        indices_t idx(X_.size());
-        iota(idx.begin(), idx.end(), 0);
-        stable_sort(idx.begin(), idx.end(), [&X_, &y_](size_t i1, size_t i2) {
-            if (X_[i1] == X_[i2])
-                return y_[i1] < y_[i2];
-            else
-                return X_[i1] < X_[i2];
-            });
-        return idx;
-    }
-
-    void CPPFImdlp::resizeCutPoints()
-    {
-        //Compute entropy of each of the whole cutpoint set and discards the biggest value
-        precision_t maxEntropy = 0;
-        precision_t entropy;
-        size_t maxEntropyIdx = 0;
-        size_t begin = 0;
-        size_t end;
-        for (size_t idx = 0; idx < cutPoints.size(); idx++) {
-            end = begin;
-            while (X[indices[end]] < cutPoints[idx] && end < X.size())
-                end++;
-            entropy = metrics.entropy(begin, end);
-            if (entropy > maxEntropy) {
-                maxEntropy = entropy;
-                maxEntropyIdx = idx;
-            }
-            begin = end;
-        }
-        cutPoints.erase(cutPoints.begin() + static_cast<long>(maxEntropyIdx));
-    }
-    labels_t& CPPFImdlp::transform(const samples_t& data)
-    {
-        discretizedData.reserve(data.size());
-        for (const precision_t& item : data) {
-            auto upper = upper_bound(cutPoints.begin(), cutPoints.end(), item);
-            discretizedData.push_back(upper - cutPoints.begin());
-        }
-        return discretizedData;
-    }
-}

src/Platform/CPPFImdlp.h

@@ -1,45 +0,0 @@
-#ifndef CPPFIMDLP_H
-#define CPPFIMDLP_H
-
-#include "typesFImdlp.h"
-#include "Metrics.h"
-#include <limits>
-#include <utility>
-#include <string>
-
-namespace mdlp {
-    class CPPFImdlp {
-    protected:
-        size_t min_length = 3;
-        int depth = 0;
-        int max_depth = numeric_limits<int>::max();
-        float proposed_cuts = 0;
-        indices_t indices = indices_t();
-        samples_t X = samples_t();
-        labels_t y = labels_t();
-        Metrics metrics = Metrics(y, indices);
-        cutPoints_t cutPoints;
-        size_t num_cut_points = numeric_limits<size_t>::max();
-        labels_t discretizedData = labels_t();
-
-        static indices_t sortIndices(samples_t&, labels_t&);
-
-        void computeCutPoints(size_t, size_t, int);
-        void resizeCutPoints();
-        bool mdlp(size_t, size_t, size_t);
-        size_t getCandidate(size_t, size_t);
-        size_t compute_max_num_cut_points() const;
-        pair<precision_t, size_t> valueCutPoint(size_t, size_t, size_t);
-
-    public:
-        CPPFImdlp();
-        CPPFImdlp(size_t, int, float);
-        ~CPPFImdlp();
-        void fit(samples_t&, labels_t&);
-        inline cutPoints_t getCutPoints() const { return cutPoints; };
-        labels_t& transform(const samples_t&);
-        inline int get_depth() const { return depth; };
-        static inline string version() { return "1.1.2"; };
-    };
-}
-#endif

src/Platform/Datasets.cc

@@ -0,0 +1,231 @@
+#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 = Xd[0].size();
+            n_features = Xd.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

@@ -0,0 +1,65 @@
+#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

@@ -0,0 +1,62 @@
+#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

@@ -1,201 +1,176 @@
-#include <iostream>
-#include <string>
-#include <torch/torch.h>
-#include <thread>
-#include <getopt.h>
-#include "ArffFiles.h"
-#include "Network.h"
-#include "Metrics.hpp"
-#include "CPPFImdlp.h"
-#include "KDB.h"
-#include "SPODE.h"
-#include "AODE.h"
-#include "TAN.h"
-#include "platformUtils.h"
+#include "Experiment.h"
+#include "Datasets.h"
+#include "Models.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;
+    }
 
-using namespace std;
+    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();
+    }
 
-/* print a description of all supported options */
-void usage(const char* path)
-{
-    /* take only the last portion of the path */
-    const char* basename = strrchr(path, '/');
-    basename = basename ? basename + 1 : path;
+    void Experiment::show()
+    {
+        json data = build_json();
+        cout << data.dump(4) << endl;
+    }
 
-    cout << "usage: " << basename << "[OPTION]" << endl;
-    cout << "  -h, --help\t\t Print this help and exit." << endl;
-    cout
-        << "  -f, --file[=FILENAME]\t {diabetes, glass, iris, kdd_JapaneseVowels, letter, liver-disorders, mfeat-factors}."
-        << endl;
-    cout << "  -p, --path[=FILENAME]\t folder where the data files are located, default " << PATH << endl;
-    cout << "  -m, --model={AODE, KDB, SPODE, TAN}\t " << endl;
-}
-
-tuple<string, string, string> parse_arguments(int argc, char** argv)
-{
-    string file_name;
-    string model_name;
-    string path = PATH;
-    const vector<struct option> long_options = {
-            {"help",          no_argument,       nullptr, 'h'},
-            {"file",          required_argument, nullptr, 'f'},
-            {"path",          required_argument, nullptr, 'p'},
-            {"model",         required_argument, nullptr, 'm'},
-            {nullptr,         no_argument,       nullptr, 0}
-    };
-    while (true) {
-        const auto c = getopt_long(argc, argv, "hf:p:m:", long_options.data(), nullptr);
-        if (c == -1)
-            break;
-        switch (c) {
-            case 'h':
-                usage(argv[0]);
-                exit(0);
-            case 'f':
-                file_name = string(optarg);
-                break;
-            case 'm':
-                model_name = string(optarg);
-                break;
-            case 'p':
-                path = optarg;
-                if (path.back() != '/')
-                    path += '/';
-                break;
-            case '?':
-                usage(argv[0]);
-                exit(1);
-            default:
-                abort();
+    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;
         }
     }
-    if (file_name.empty()) {
-        usage(argv[0]);
-        exit(1);
+
+    void Experiment::cross_validation(const string& path, const string& fileName)
+    {
+        auto datasets = platform::Datasets(path, true, 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);
     }
-    return make_tuple(file_name, path, model_name);
-}
-
-inline constexpr auto hash_conv(const std::string_view sv)
-{
-    unsigned long hash{ 5381 };
-    for (unsigned char c : sv) {
-        hash = ((hash << 5) + hash) ^ c;
-    }
-    return hash;
-}
-
-inline constexpr auto operator"" _sh(const char* str, size_t len)
-{
-    return hash_conv(std::string_view{ str, len });
-}
-
-
-
-tuple<string, string, string> get_options(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},
-    };
-    vector <string> models = { "AODE", "KDB", "SPODE", "TAN" };
-    string file_name;
-    string path;
-    string model_name;
-    tie(file_name, path, model_name) = parse_arguments(argc, argv);
-    if (datasets.find(file_name) == datasets.end()) {
-        cout << "Invalid file name: " << file_name << endl;
-        usage(argv[0]);
-        exit(1);
-    }
-    if (!file_exists(path + file_name + ".arff")) {
-        cout << "Data File " << path + file_name + ".arff" << " does not exist" << endl;
-        usage(argv[0]);
-        exit(1);
-    }
-    if (find(models.begin(), models.end(), model_name) == models.end()) {
-        cout << "Invalid model name: " << model_name << endl;
-        usage(argv[0]);
-        exit(1);
-    }
-    return { file_name, path, model_name };
-}
-
-int main(int argc, char** argv)
-{
-    string file_name, path, model_name;
-    tie(file_name, path, model_name) = get_options(argc, argv);
-    auto handler = ArffFiles();
-    handler.load(path + file_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;
-    for (auto feature : handler.getAttributes()) {
-        features.push_back(feature.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]);
-    double score;
-    vector<string> lines;
-    vector<string> graph;
-    auto kdb = bayesnet::KDB(2);
-    auto aode = bayesnet::AODE();
-    auto spode = bayesnet::SPODE(2);
-    auto tan = bayesnet::TAN();
-    switch (hash_conv(model_name)) {
-        case "AODE"_sh:
-            aode.fit(Xd, y, features, className, states);
-            lines = aode.show();
-            score = aode.score(Xd, y);
-            graph = aode.graph();
-            break;
-        case "KDB"_sh:
-            kdb.fit(Xd, y, features, className, states);
-            lines = kdb.show();
-            score = kdb.score(Xd, y);
-            graph = kdb.graph();
-            break;
-        case "SPODE"_sh:
-            spode.fit(Xd, y, features, className, states);
-            lines = spode.show();
-            score = spode.score(Xd, y);
-            graph = spode.graph();
-            break;
-        case "TAN"_sh:
-            tan.fit(Xd, y, features, className, states);
-            lines = tan.show();
-            score = tan.score(Xd, y);
-            graph = tan.graph();
-            break;
-    }
-    for (auto line : lines) {
-        cout << line << endl;
-    }
-    cout << "Score: " << score << endl;
-    auto dot_file = model_name + "_" + file_name;
-    ofstream file(dot_file + ".dot");
-    file << graph;
-    file.close();
-    cout << "Graph saved in " << model_name << "_" << file_name << ".dot" << endl;
-    cout << "dot -Tpng -o " + dot_file + ".png " + dot_file + ".dot " << endl;
-    return 0;
 }

src/Platform/Experiment.h

@@ -0,0 +1,113 @@
+#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();
+    };
+}
+#endif

src/Platform/Folding.cc

@@ -0,0 +1,95 @@
+#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

@@ -0,0 +1,37 @@
+#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/Metrics.cpp

@@ -1,78 +0,0 @@
-#include "Metrics.h"
-#include <set>
-#include <cmath>
-
-using namespace std;
-namespace mdlp {
-    Metrics::Metrics(labels_t& y_, indices_t& indices_): y(y_), indices(indices_),
-        numClasses(computeNumClasses(0, indices.size()))
-    {
-    }
-
-    int Metrics::computeNumClasses(size_t start, size_t end)
-    {
-        set<int> nClasses;
-        for (auto i = start; i < end; ++i) {
-            nClasses.insert(y[indices[i]]);
-        }
-        return static_cast<int>(nClasses.size());
-    }
-
-    void Metrics::setData(const labels_t& y_, const indices_t& indices_)
-    {
-        indices = indices_;
-        y = y_;
-        numClasses = computeNumClasses(0, indices.size());
-        entropyCache.clear();
-        igCache.clear();
-    }
-
-    precision_t Metrics::entropy(size_t start, size_t end)
-    {
-        precision_t p;
-        precision_t ventropy = 0;
-        int nElements = 0;
-        labels_t counts(numClasses + 1, 0);
-        if (end - start < 2)
-            return 0;
-        if (entropyCache.find({ start, end }) != entropyCache.end()) {
-            return entropyCache[{start, end}];
-        }
-        for (auto i = &indices[start]; i != &indices[end]; ++i) {
-            counts[y[*i]]++;
-            nElements++;
-        }
-        for (auto count : counts) {
-            if (count > 0) {
-                p = static_cast<precision_t>(count) / static_cast<precision_t>(nElements);
-                ventropy -= p * log2(p);
-            }
-        }
-        entropyCache[{start, end}] = ventropy;
-        return ventropy;
-    }
-
-    precision_t Metrics::informationGain(size_t start, size_t cut, size_t end)
-    {
-        precision_t iGain;
-        precision_t entropyInterval;
-        precision_t entropyLeft;
-        precision_t entropyRight;
-        size_t nElementsLeft = cut - start;
-        size_t nElementsRight = end - cut;
-        size_t nElements = end - start;
-        if (igCache.find(make_tuple(start, cut, end)) != igCache.end()) {
-            return igCache[make_tuple(start, cut, end)];
-        }
-        entropyInterval = entropy(start, end);
-        entropyLeft = entropy(start, cut);
-        entropyRight = entropy(cut, end);
-        iGain = entropyInterval -
-            (static_cast<precision_t>(nElementsLeft) * entropyLeft +
-                static_cast<precision_t>(nElementsRight) * entropyRight) /
-            static_cast<precision_t>(nElements);
-        igCache[make_tuple(start, cut, end)] = iGain;
-        return iGain;
-    }
-
-}

src/Platform/Metrics.h

@@ -1,22 +0,0 @@
-#ifndef CCMETRICS_H
-#define CCMETRICS_H
-
-#include "typesFImdlp.h"
-
-namespace mdlp {
-    class Metrics {
-    protected:
-        labels_t& y;
-        indices_t& indices;
-        int numClasses;
-        cacheEnt_t entropyCache = cacheEnt_t();
-        cacheIg_t igCache = cacheIg_t();
-    public:
-        Metrics(labels_t&, indices_t&);
-        void setData(const labels_t&, const indices_t&);
-        int computeNumClasses(size_t, size_t);
-        precision_t entropy(size_t, size_t);
-        precision_t informationGain(size_t, size_t, size_t);
-    };
-}
-#endif

src/Platform/Models.cc

@@ -0,0 +1,54 @@
+#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

@@ -0,0 +1,32 @@
+#ifndef MODELS_H
+#define MODELS_H
+#include <map>
+#include "BaseClassifier.h"
+#include "AODE.h"
+#include "TAN.h"
+#include "KDB.h"
+#include "SPODE.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/main.cc

@@ -0,0 +1,123 @@
+#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 experiment = platform::Experiment();
+    experiment.setTitle(title).setLanguage("cpp").setLanguageVersion("1.0.0");
+    experiment.setDiscretized(discretize_dataset).setModel(model_name).setPlatform("BayesNet");
+    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.show();
+    cout << "Done!" << endl;
+    return 0;
+}

src/Platform/modelRegister.h

@@ -0,0 +1,11 @@
+#ifndef MODEL_REGISTER_H
+#define MODEL_REGISTER_H
+static platform::Registrar registrarT("TAN",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::TAN();});
+static platform::Registrar registrarS("SPODE",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::SPODE(2);});
+static platform::Registrar registrarK("KDB",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::KDB(2);});
+static platform::Registrar registrarA("AODE",
+    [](void) -> bayesnet::BaseClassifier* { return new bayesnet::AODE();});
+#endif

src/Platform/platformUtils.cc

@@ -1,5 +1,18 @@
 #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;
@@ -14,7 +27,19 @@ pair<vector<mdlp::labels_t>, map<string, int>> discretize(vector<mdlp::samples_t
     return { Xd, maxes };
 }
 
-bool file_exists(const std::string& name)
+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);
@@ -24,7 +49,40 @@ bool file_exists(const std::string& name)
     }
 }
 
-tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(string name)
+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");
@@ -34,9 +92,8 @@ tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vect
     // Get className & Features
     auto className = handler.getClassName();
     vector<string> features;
-    for (auto feature : handler.getAttributes()) {
-        features.push_back(feature.first);
-    }
+    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;

src/Platform/platformUtils.h

@@ -1,5 +1,6 @@
 #ifndef PLATFORM_UTILS_H
 #define PLATFORM_UTILS_H
+#include <torch/torch.h>
 #include <string>
 #include <vector>
 #include <map>
@@ -10,6 +11,11 @@ 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);
-tuple<vector<vector<int>>, vector<int>, vector<string>, string, map<string, vector<int>>> loadFile(string name);
+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

src/Platform/typesFImdlp.h

@@ -1,18 +0,0 @@
-#ifndef TYPES_H
-#define TYPES_H
-
-#include <vector>
-#include <map>
-#include <stdexcept>
-
-using namespace std;
-namespace mdlp {
-    typedef float precision_t;
-    typedef vector<precision_t> samples_t;
-    typedef vector<int> labels_t;
-    typedef vector<size_t> indices_t;
-    typedef vector<precision_t> cutPoints_t;
-    typedef map<pair<int, int>, precision_t> cacheEnt_t;
-    typedef map<tuple<int, int, int>, precision_t> cacheIg_t;
-}
-#endif

tests/CMakeLists.txt

@@ -2,8 +2,10 @@ if(ENABLE_TESTING)
     set(TEST_MAIN "unit_tests")
     include_directories(${BayesNet_SOURCE_DIR}/src/BayesNet)
     include_directories(${BayesNet_SOURCE_DIR}/src/Platform)
-    set(TEST_SOURCES BayesModels.cc BayesNetwork.cc ${BayesNet_SOURCES} ${Platform_SOURCES})
+    include_directories(${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 "${TORCH_LIBRARIES}"  Catch2::Catch2WithMain)
+    target_link_libraries(${TEST_MAIN} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain)
     add_test(NAME ${TEST_MAIN} COMMAND ${TEST_MAIN})
 endif(ENABLE_TESTING)