Continue conan integration

Reviewed-on: #1
This parameters enables/disables the output in std::err the Warning messages that produces trying to create a fold that lacks any values of the class

.gitignore

@@ -37,4 +37,28 @@ build_*/**
 cmake-build*/**
 .idea
 puml/**
-.vscode/settings.json
+.vscode/settings.json
+
+# CMake generated files
+CMakeFiles/
+CMakeCache.txt
+cmake_install.cmake
+compile_commands.json
+Makefile
+CTestTestfile.cmake
+DartConfiguration.tcl
+Testing/
+CMakePresets.json
+
+# Conan generated files
+conan_toolchain.cmake
+conan*.sh
+deactivate_*.sh
+cmakedeps*.cmake
+conandeps*.cmake
+*-Target-*.cmake
+*-debug-*.cmake
+*Config*.cmake
+*Targets.cmake
+Find*.cmake
+module-*.cmake

.gitmodules

@@ -1,6 +0,0 @@
-[submodule "tests/lib/Catch2"]
-	path = tests/lib/Catch2
-	url = https://github.com/catchorg/Catch2.git
-[submodule "tests/lib/mdlp"]
-	path = tests/lib/mdlp
-	url = https://github.com/rmontanana/mdlp

CHANGELOG.md

@@ -5,6 +5,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.1.1] 2024-12-13
+
+- Added a new parameter `quiet` to enable/disable the warning messages in the Stratified K-Fold partitioning. Default value `true`.
+
 ## [1.1.0] 2024-05-11
 
 ### Fixed

CMakeLists.txt

@@ -1,13 +1,13 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(Folding
-  VERSION 1.1.0
   DESCRIPTION "Folding utility for BayesNet library"
   HOMEPAGE_URL "https://github.com/rmontanana/folding"
   LANGUAGES CXX
 )
 
 find_package(Torch REQUIRED)
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D_GLIBCXX_USE_CXX11_ABI=0")
 
 if (POLICY CMP0135)
   cmake_policy(SET CMP0135 NEW)
@@ -33,15 +33,14 @@ include(AddGitSubmodule)
 
 # Subdirectories
 # --------------
-add_subdirectory(config)
 
 # Testing
 # -------
 if (ENABLE_TESTING)
   MESSAGE("Testing enabled")
-  add_git_submodule("tests/lib/Catch2")  
+  find_package(Catch2 REQUIRED)
-  add_git_submodule("tests/lib/Files")  
+  find_package(arff-files REQUIRED)
-  add_git_submodule("tests/lib/mdlp")  
+  find_package(fimdlp REQUIRED)
   include(CTest)
   add_subdirectory(tests)
 endif (ENABLE_TESTING)

CMakeUserPresets.json

@@ -0,0 +1,9 @@
+{
+    "version": 4,
+    "vendor": {
+        "conan": {}
+    },
+    "include": [
+        "build_Debug/CMakePresets.json"
+    ]
+}

Makefile

@@ -28,7 +28,8 @@ build: ## Build a debug version of the project
 	@echo ">>> Building Debug Folding...";
 	@if [ -d ./$(f_debug) ]; then rm -rf ./$(f_debug); fi
 	@mkdir $(f_debug); 
-	@cmake -S . -B $(f_debug) -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON
+	@conan install . --output-folder=$(f_debug) --build=missing --profile:build=default --profile:host=default
+	@cmake -S . -B $(f_debug) -D CMAKE_BUILD_TYPE=Debug -D ENABLE_TESTING=ON -D CMAKE_TOOLCHAIN_FILE=$(f_debug)/conan_toolchain.cmake
 	@echo ">>> Done";
 
 opt = ""

README.md

@@ -1,9 +1,10 @@
 # <img src="logo.png" alt="logo" width="50"/>  Folding
 
+
 ![C++](https://img.shields.io/badge/c++-%2300599C.svg?style=flat&logo=c%2B%2B&logoColor=white)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](<https://opensource.org/licenses/MIT>)
-![Gitea Release](https://img.shields.io/gitea/v/release/rmontanana/folding?gitea_url=https://gitea.rmontanana.es:3000)
+![Gitea Release](https://img.shields.io/gitea/v/release/rmontanana/folding?gitea_url=https://gitea.rmontanana.es)
-![Gitea Last Commit](https://img.shields.io/gitea/last-commit/rmontanana/folding?gitea_url=https://gitea.rmontanana.es:3000&logo=gitea)
+![Gitea Last Commit](https://img.shields.io/gitea/last-commit/rmontanana/folding?gitea_url=https://gitea.rmontanana.es&logo=gitea)
 
 K-Fold and stratified K-Fold header-only library for BayesNet classifiers & platform
 

conanfile.py

@@ -0,0 +1,49 @@
+import re
+from conan import ConanFile
+from conan.tools.files import copy
+from conan.tools.cmake import CMakeToolchain
+
+
+class FoldingConan(ConanFile):
+    name = "folding"
+    version = "X.X.X"
+    description = "K-Fold and stratified K-Fold header-only library"
+    url = "https://github.com/rmontanana/folding"
+    license = "MIT"
+    homepage = "https://github.com/rmontanana/ArffFiles"
+    topics = ("kfold", "stratified folding")
+    no_copy_source = True
+    exports_sources = "folding.hpp"
+    package_type = "header-library"
+    # build_type = "Debug"
+
+    def requirements(self):
+        # Build dependency
+        self.requires("libtorch/2.7.0")
+
+    def build_requirements(self):
+        # Test dependencies
+        self.test_requires("catch2/3.8.1")
+        self.test_requires("arff-files/1.2.0")
+        self.test_requires("fimdlp/2.0.1")
+
+    def generate(self):
+        tc = CMakeToolchain(self)
+        tc.generate()
+
+    def init(self):
+        # Read the CMakeLists.txt file to get the version
+        with open("folding.hpp", "r") as f:
+            content = f.read()
+            match = re.search(
+                r'const std::string FOLDING_VERSION = "([^"]+)";', content
+            )
+            if match:
+                self.version = match.group(1)
+
+    def package(self):
+        copy(self, "*.hpp", self.source_folder, self.package_folder)
+
+    def package_info(self):
+        self.cpp_info.bindirs = []
+        self.cpp_info.libdirs = []

config/CMakeLists.txt

@@ -1,4 +0,0 @@
-configure_file(
-  "config.h.in"
-  "${CMAKE_BINARY_DIR}/configured_files/include/folding_config.h" ESCAPE_QUOTES
-)

config/config.h.in

@@ -1,14 +0,0 @@
-#pragma once
-
-#include <string>
-#include <string_view>
-
-#define PROJECT_VERSION_MAJOR @PROJECT_VERSION_MAJOR @
-#define PROJECT_VERSION_MINOR @PROJECT_VERSION_MINOR @
-#define PROJECT_VERSION_PATCH @PROJECT_VERSION_PATCH @
-
-static constexpr std::string_view folding_project_name = "@PROJECT_NAME@";
-static constexpr std::string_view folding_project_version = "@PROJECT_VERSION@";
-static constexpr std::string_view folding_project_description = "@PROJECT_DESCRIPTION@";
-static constexpr std::string_view folding_data_path = "@Folding_SOURCE_DIR@/tests/data/";
-static constexpr std::string_view folding_csv_path = "@Folding_SOURCE_DIR@/tests/csv/";

folding.hpp

@@ -11,7 +11,7 @@
 #include <random> 
 #include <vector>
 namespace folding {
-    const std::string FOLDING_VERSION = "1.1.0";
+    const std::string FOLDING_VERSION = "1.1.1";
     class Fold {
     public:
         inline Fold(int k, int n, int seed = -1) : k(k), n(n), seed(seed)
@@ -59,16 +59,18 @@ namespace folding {
     };
     class StratifiedKFold : public Fold {
     public:
-        inline StratifiedKFold(int k, const std::vector<int>& y, int seed = -1) : Fold(k, y.size(), seed)
+        inline StratifiedKFold(int k, const std::vector<int>& y, int seed = -1, bool quiet = true) : Fold(k, y.size(), seed)
         {
             this->y = y;
             n = y.size();
+            this->quiet = quiet;
             build();
         }
-        inline StratifiedKFold(int k, torch::Tensor& y, int seed = -1) : Fold(k, y.numel(), seed)
+        inline StratifiedKFold(int k, torch::Tensor& y, int seed = -1, bool quiet = true) : Fold(k, y.numel(), seed)
         {
             n = y.numel();
             this->y = std::vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + n);
+            this->quiet = quiet;
             build();
         }
 
@@ -90,6 +92,7 @@ namespace folding {
         std::vector<int> y;
         std::vector<std::vector<int>> stratified_indices;
         bool faulty = false; // Only true if the number of samples of any class is less than the number of folds.
+        bool quiet = true; // Enable or disable warning messages
         void build()
         {
             stratified_indices = std::vector<std::vector<int>>(k);
@@ -105,7 +108,8 @@ namespace folding {
                 int num_samples_to_take = num_samples / k;
                 int remainder_samples_to_take = num_samples % k;
                 if (num_samples_to_take == 0) {
-                    std::cerr << "Warning! The number of samples in class " << label << " (" << num_samples
+                    if (!quiet)
+                        std::cerr << "Warning! The number of samples in class " << label << " (" << num_samples
                         << ") is less than the number of folds (" << k << ")." << std::endl;
                     faulty = true;
                 }

tests/CMakeLists.txt

@@ -1,12 +1,15 @@
 if(ENABLE_TESTING)
     include_directories(
         ${Folding_SOURCE_DIR}
-        lib/Files
-        lib/mdlp
         ${CMAKE_BINARY_DIR}/configured_files/include
     )
     set(TEST_FOLDING "unit_tests_folding")
     add_executable(${TEST_FOLDING} TestFolding.cc TestUtils.cc)
-    target_link_libraries(${TEST_FOLDING} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain)
+    target_link_libraries(${TEST_FOLDING} PUBLIC 
+        ${TORCH_LIBRARIES}
+        arff-files::arff-files 
+        fimdlp::fimdlp 
+        Catch2::Catch2WithMain
+    )
     add_test(NAME ${TEST_FOLDING} COMMAND ${TEST_FOLDING})
 endif(ENABLE_TESTING)

tests/TestFolding.cc

@@ -12,7 +12,7 @@
 
 TEST_CASE("Version Test", "[Folding]")
 {
-    std::string actual_version = { folding_project_version.begin(), folding_project_version.end() };
+    std::string actual_version = "1.1.1";
     auto data = std::vector<int>(100);
     folding::StratifiedKFold stratified_kfold(5, data, 17);
     REQUIRE(stratified_kfold.version() == actual_version);
@@ -186,4 +186,38 @@ TEST_CASE("StratifiedKFold Test", "[Folding]")
             }
         }
     }
+}
+TEST_CASE("Stratified KFold quiet parameter", "[Folding]")
+{
+    auto raw = RawDatasets("glass", true);
+    std::string expected = "Warning! The number of samples in class 2 (9) is less than the number of folds (10).\n";
+
+    SECTION("With vectors")
+    {
+        // Redirect cerr to a stringstream
+        std::streambuf* originalCerrBuffer = std::cerr.rdbuf();
+        std::stringstream capturedOutput;
+        std::cerr.rdbuf(capturedOutput.rdbuf());
+        // StratifiedKFold with quiet parameter set to false
+        folding::StratifiedKFold stratified_kfold(10, raw.yv, 17, false);
+        // Restore the original cerr buffer
+        std::cerr.rdbuf(originalCerrBuffer);
+        // Check the captured output
+        REQUIRE(capturedOutput.str() == expected);
+        REQUIRE(stratified_kfold.isFaulty());
+    }
+    SECTION("With tensors")
+    {
+        // Redirect cerr to a stringstream
+        std::streambuf* originalCerrBuffer = std::cerr.rdbuf();
+        std::stringstream capturedOutput;
+        std::cerr.rdbuf(capturedOutput.rdbuf());
+        // StratifiedKFold with quiet parameter set to false
+        folding::StratifiedKFold stratified_kfold(10, raw.yt, 17, false);
+        // Restore the original cerr buffer
+        std::cerr.rdbuf(originalCerrBuffer);
+        // Check the captured output
+        REQUIRE(capturedOutput.str() == expected);
+        REQUIRE(stratified_kfold.isFaulty());
+    }
 }

tests/TestUtils.h

@@ -8,7 +8,6 @@
 #include <tuple>
 #include "ArffFiles.h"
 #include "CPPFImdlp.h"
-#include "folding_config.h"
 
 bool file_exists(const std::string& name);
 std::pair<vector<mdlp::labels_t>, map<std::string, int>> discretize(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y, std::vector<string> features);
@@ -45,11 +44,11 @@ class Paths {
 public:
     static std::string datasets()
     {
-        return { folding_data_path.begin(), folding_data_path.end() };
+        return "../../tests/data/";
     }
     static std::string csv()
     {
-        return { folding_csv_path.begin(), folding_csv_path.end() };
+        return "../../tests/csv/";
     }
 };
 class CSVFiles {

tests/lib/Files/ArffFiles.cc

@@ -1,174 +0,0 @@
-// ***************************************************************
-// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
-// SPDX-FileType: SOURCE
-// SPDX-License-Identifier: MIT
-// ***************************************************************
-
-#include "ArffFiles.h"
-#include <fstream>
-#include <sstream>
-#include <map>
-#include <iostream>
-
-ArffFiles::ArffFiles() = default;
-
-std::vector<std::string> ArffFiles::getLines() const
-{
-    return lines;
-}
-
-unsigned long int ArffFiles::getSize() const
-{
-    return lines.size();
-}
-
-std::vector<std::pair<std::string, std::string>> ArffFiles::getAttributes() const
-{
-    return attributes;
-}
-
-std::string ArffFiles::getClassName() const
-{
-    return className;
-}
-
-std::string ArffFiles::getClassType() const
-{
-    return classType;
-}
-
-std::vector<std::vector<float>>& ArffFiles::getX()
-{
-    return X;
-}
-
-std::vector<int>& ArffFiles::getY()
-{
-    return y;
-}
-
-void ArffFiles::loadCommon(std::string fileName)
-{
-    std::ifstream file(fileName);
-    if (!file.is_open()) {
-        throw std::invalid_argument("Unable to open file");
-    }
-    std::string line;
-    std::string keyword;
-    std::string attribute;
-    std::string type;
-    std::string type_w;
-    while (getline(file, line)) {
-        if (line.empty() || line[0] == '%' || line == "\r" || line == " ") {
-            continue;
-        }
-        if (line.find("@attribute") != std::string::npos || line.find("@ATTRIBUTE") != std::string::npos) {
-            std::stringstream ss(line);
-            ss >> keyword >> attribute;
-            type = "";
-            while (ss >> type_w)
-                type += type_w + " ";
-            attributes.emplace_back(trim(attribute), trim(type));
-            continue;
-        }
-        if (line[0] == '@') {
-            continue;
-        }
-        lines.push_back(line);
-    }
-    file.close();
-    if (attributes.empty())
-        throw std::invalid_argument("No attributes found");
-}
-
-void ArffFiles::load(const std::string& fileName, bool classLast)
-{
-    int labelIndex;
-    loadCommon(fileName);
-    if (classLast) {
-        className = std::get<0>(attributes.back());
-        classType = std::get<1>(attributes.back());
-        attributes.pop_back();
-        labelIndex = static_cast<int>(attributes.size());
-    } else {
-        className = std::get<0>(attributes.front());
-        classType = std::get<1>(attributes.front());
-        attributes.erase(attributes.begin());
-        labelIndex = 0;
-    }
-    generateDataset(labelIndex);
-}
-void ArffFiles::load(const std::string& fileName, const std::string& name)
-{
-    int labelIndex;
-    loadCommon(fileName);
-    bool found = false;
-    for (int i = 0; i < attributes.size(); ++i) {
-        if (attributes[i].first == name) {
-            className = std::get<0>(attributes[i]);
-            classType = std::get<1>(attributes[i]);
-            attributes.erase(attributes.begin() + i);
-            labelIndex = i;
-            found = true;
-            break;
-        }
-    }
-    if (!found) {
-        throw std::invalid_argument("Class name not found");
-    }
-    generateDataset(labelIndex);
-}
-
-void ArffFiles::generateDataset(int labelIndex)
-{
-    X = std::vector<std::vector<float>>(attributes.size(), std::vector<float>(lines.size()));
-    auto yy = std::vector<std::string>(lines.size(), "");
-    auto removeLines = std::vector<int>(); // Lines with missing values
-    for (size_t i = 0; i < lines.size(); i++) {
-        std::stringstream ss(lines[i]);
-        std::string value;
-        int pos = 0;
-        int xIndex = 0;
-        while (getline(ss, value, ',')) {
-            if (pos++ == labelIndex) {
-                yy[i] = value;
-            } else {
-                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);
-}
-
-std::string ArffFiles::trim(const std::string& source)
-{
-    std::string s(source);
-    s.erase(0, s.find_first_not_of(" '\n\r\t"));
-    s.erase(s.find_last_not_of(" '\n\r\t") + 1);
-    return s;
-}
-
-std::vector<int> ArffFiles::factorize(const std::vector<std::string>& labels_t)
-{
-    std::vector<int> yy;
-    yy.reserve(labels_t.size());
-    std::map<std::string, int> labelMap;
-    int i = 0;
-    for (const std::string& label : labels_t) {
-        if (labelMap.find(label) == labelMap.end()) {
-            labelMap[label] = i++;
-        }
-        yy.push_back(labelMap[label]);
-    }
-    return yy;
-}

tests/lib/Files/ArffFiles.h

@@ -1,38 +0,0 @@
-// ***************************************************************
-// SPDX-FileCopyrightText: Copyright 2024 Ricardo Montañana Gómez
-// SPDX-FileType: SOURCE
-// SPDX-License-Identifier: MIT
-// ***************************************************************
-
-#ifndef ARFFFILES_H
-#define ARFFFILES_H
-
-#include <string>
-#include <vector>
-
-class ArffFiles {
-public:
-    ArffFiles();
-    void load(const std::string&, bool = true);
-    void load(const std::string&, const std::string&);
-    std::vector<std::string> getLines() const;
-    unsigned long int getSize() const;
-    std::string getClassName() const;
-    std::string getClassType() const;
-    static std::string trim(const std::string&);
-    std::vector<std::vector<float>>& getX();
-    std::vector<int>& getY();
-    std::vector<std::pair<std::string, std::string>> getAttributes() const;
-    static std::vector<int> factorize(const std::vector<std::string>& labels_t);
-private:
-    std::vector<std::string> lines;
-    std::vector<std::pair<std::string, std::string>> attributes;
-    std::string className;
-    std::string classType;
-    std::vector<std::vector<float>> X;
-    std::vector<int> y;
-    void generateDataset(int);
-    void loadCommon(std::string);
-};
-
-#endif

tests/lib/Files/CMakeLists.txt

@@ -1 +0,0 @@
-add_library(ArffFiles ArffFiles.cc)