Add predict_proba to Ld classifiers

CHANGELOG.md

@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Fix the vcpkg configuration in building the library.
 - Fix the sample app to use the vcpkg configuration.
+- Add predict_proba method to all Ld classifiers.
 
 ## [1.1.0] - 2025-04-27
 

README.md

@@ -6,6 +6,7 @@
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/cf3e0ac71d764650b1bf4d8d00d303b1)](https://app.codacy.com/gh/Doctorado-ML/BayesNet/dashboard?utm_source=gh&utm_medium=referral&utm_content=&utm_campaign=Badge_grade)
 [![Security Rating](https://sonarcloud.io/api/project_badges/measure?project=rmontanana_BayesNet&metric=security_rating)](https://sonarcloud.io/summary/new_code?id=rmontanana_BayesNet)
 [![Reliability Rating](https://sonarcloud.io/api/project_badges/measure?project=rmontanana_BayesNet&metric=reliability_rating)](https://sonarcloud.io/summary/new_code?id=rmontanana_BayesNet)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/Doctorado-ML/BayesNet)
 ![Gitea Last Commit](https://img.shields.io/gitea/last-commit/rmontanana/bayesnet?gitea_url=https://gitea.rmontanana.es&logo=gitea)
 [![Coverage Badge](https://img.shields.io/badge/Coverage-99,1%25-green)](https://gitea.rmontanana.es/rmontanana/BayesNet)
 [![DOI](https://zenodo.org/badge/667782806.svg)](https://doi.org/10.5281/zenodo.14210344)

bayesnet/classifiers/KDBLd.cc

@@ -28,6 +28,11 @@ namespace bayesnet {
         auto Xt = prepareX(X);
         return KDB::predict(Xt);
     }
+    torch::Tensor KDBLd::predict_proba(torch::Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return KDB::predict_proba(Xt);
+    }
     std::vector<std::string> KDBLd::graph(const std::string& name) const
     {
         return KDB::graph(name);

bayesnet/classifiers/KDBLd.h

@@ -18,6 +18,7 @@ namespace bayesnet {
         KDBLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) override;
         std::vector<std::string> graph(const std::string& name = "KDB") const override;
         torch::Tensor predict(torch::Tensor& X) override;
+        torch::Tensor predict_proba(torch::Tensor& X) override;
         static inline std::string version() { return "0.0.1"; };
     };
 }

bayesnet/classifiers/SPODELd.cc

@@ -43,6 +43,11 @@ namespace bayesnet {
         auto Xt = prepareX(X);
         return SPODE::predict(Xt);
     }
+    torch::Tensor SPODELd::predict_proba(torch::Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return SPODE::predict_proba(Xt);
+    }
     std::vector<std::string> SPODELd::graph(const std::string& name) const
     {
         return SPODE::graph(name);

bayesnet/classifiers/SPODELd.h

@@ -19,6 +19,7 @@ namespace bayesnet {
         SPODELd& commonFit(const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing);
         std::vector<std::string> graph(const std::string& name = "SPODELd") const override;
         torch::Tensor predict(torch::Tensor& X) override;
+        torch::Tensor predict_proba(torch::Tensor& X) override;
         static inline std::string version() { return "0.0.1"; };
     };
 }

bayesnet/classifiers/TANLd.cc

@@ -29,6 +29,11 @@ namespace bayesnet {
         auto Xt = prepareX(X);
         return TAN::predict(Xt);
     }
+    torch::Tensor TANLd::predict_proba(torch::Tensor& X)
+    {
+        auto Xt = prepareX(X);
+        return TAN::predict_proba(Xt);
+    }
     std::vector<std::string> TANLd::graph(const std::string& name) const
     {
         return TAN::graph(name);

bayesnet/classifiers/TANLd.h

@@ -18,6 +18,7 @@ namespace bayesnet {
         TANLd& fit(torch::Tensor& X, torch::Tensor& y, const std::vector<std::string>& features, const std::string& className, map<std::string, std::vector<int>>& states, const Smoothing_t smoothing) override;
         std::vector<std::string> graph(const std::string& name = "TANLd") const override;
         torch::Tensor predict(torch::Tensor& X) override;
+        torch::Tensor predict_proba(torch::Tensor& X) override;
     };
 }
 #endif // !TANLD_H

sample/CMakeLists.txt

@@ -10,7 +10,25 @@ find_package(Torch CONFIG REQUIRED)
 find_package(fimdlp CONFIG REQUIRED)
 find_package(folding CONFIG REQUIRED)
 find_package(arff-files CONFIG REQUIRED)
-find_package(bayesnet CONFIG REQUIRED)
+find_package(nlohmann_json CONFIG REQUIRED)
+
+option(BAYESNET_VCPKG_CONFIG "Use vcpkg config for BayesNet" ON)
+
+if (BAYESNET_VCPKG_CONFIG)
+  message(STATUS "Using BayesNet vcpkg config")
+  find_package(bayesnet CONFIG REQUIRED)
+  set(BayesNet_LIBRARIES bayesnet::bayesnet)
+else(BAYESNET_VCPKG_CONFIG)
+  message(STATUS "Using BayesNet local library config")
+  find_library(bayesnet NAMES libbayesnet bayesnet libbayesnet.a PATHS ${Platform_SOURCE_DIR}/../lib/lib REQUIRED)
+  find_path(Bayesnet_INCLUDE_DIRS REQUIRED NAMES bayesnet PATHS ${Platform_SOURCE_DIR}/../lib/include)
+  add_library(bayesnet::bayesnet UNKNOWN IMPORTED)
+  set_target_properties(bayesnet::bayesnet PROPERTIES
+    IMPORTED_LOCATION ${bayesnet}
+    INTERFACE_INCLUDE_DIRECTORIES ${Bayesnet_INCLUDE_DIRS}
+  )
+endif(BAYESNET_VCPKG_CONFIG)
+message(STATUS "BayesNet: ${bayesnet}")
 
 add_executable(bayesnet_sample sample.cc) 
 target_link_libraries(bayesnet_sample PRIVATE 

sample/sample.cc

@@ -4,9 +4,22 @@
 // SPDX-License-Identifier: MIT
 // ***************************************************************
 
+#include <map>
+#include <string>
 #include <ArffFiles/ArffFiles.hpp>
 #include <fimdlp/CPPFImdlp.h>
-#include <bayesnet/ensembles/XBAODE.h>
+#include <bayesnet/classifiers/TANLd.h>
+#include <bayesnet/classifiers/KDBLd.h>
+#include <bayesnet/ensembles/AODELd.h>
+
+torch::Tensor matrix2tensor(const std::vector<std::vector<float>>& matrix)
+{
+    auto tensor = torch::empty({ static_cast<int>(matrix.size()), static_cast<int>(matrix[0].size()) }, torch::kFloat32);
+    for (int i = 0; i < matrix.size(); ++i) {
+        tensor.index_put_({ i, "..." }, torch::tensor(matrix[i], torch::kFloat32));
+    }
+    return tensor;
+}
 
 std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y)
 {
@@ -19,32 +32,40 @@ std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, m
     }
     return Xd;
 }
-tuple<torch::Tensor, torch::Tensor, std::vector<std::string>, std::string, map<std::string, std::vector<int>>> loadDataset(const std::string& name, bool class_last)
+std::tuple<torch::Tensor, torch::Tensor, std::vector<std::string>, std::string> loadArff(const std::string& name, bool class_last)
 {
     auto handler = ArffFiles();
     handler.load(name, class_last);
     // Get Dataset X, y
-    std::vector<mdlp::samples_t>& X = handler.getX();
+    std::vector<mdlp::samples_t> X = handler.getX();
-    mdlp::labels_t& y = handler.getY();
+    mdlp::labels_t y = handler.getY();
-    // Get className & Features
-    auto className = handler.getClassName();
     std::vector<std::string> features;
     auto attributes = handler.getAttributes();
     transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
-    torch::Tensor Xd;
+    auto Xt = matrix2tensor(X);
-    auto states = map<std::string, std::vector<int>>();
+    auto yt = torch::tensor(y, torch::kInt32);
-    auto Xr = discretizeDataset(X, y);
+    return { Xt, yt, features, handler.getClassName() };
-    Xd = torch::zeros({ static_cast<int>(Xr.size()), static_cast<int>(Xr[0].size()) }, torch::kInt32);
-    for (int i = 0; i < features.size(); ++i) {
-        states[features[i]] = std::vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
-        auto item = states.at(features[i]);
-        iota(begin(item), end(item), 0);
-        Xd.index_put_({ i, "..." }, torch::tensor(Xr[i], torch::kInt32));
-    }
-    states[className] = std::vector<int>(*max_element(y.begin(), y.end()) + 1);
-    iota(begin(states.at(className)), end(states.at(className)), 0);
-    return { Xd, torch::tensor(y, torch::kInt32), features, className, states };
 }
+// tuple<torch::Tensor, torch::Tensor, std::vector<std::string>, std::string, map<std::string, std::vector<int>>> loadDataset(const std::string& name, bool class_last)
+// {
+//     auto [X, y, features, className] = loadArff(name, class_last);
+//     // Discretize the dataset
+//     torch::Tensor Xd;
+//     auto states = map<std::string, std::vector<int>>();
+//     // Fill the class states
+//     states[className] = std::vector<int>(*max_element(y.begin(), y.end()) + 1);
+//     iota(begin(states.at(className)), end(states.at(className)), 0);
+//     auto Xr = discretizeDataset(X, y);
+//     Xd = torch::zeros({ static_cast<int>(Xr.size()), static_cast<int>(Xr[0].size()) }, torch::kInt32);
+//     for (int i = 0; i < features.size(); ++i) {
+//         states[features[i]] = std::vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
+//         auto item = states.at(features[i]);
+//         iota(begin(item), end(item), 0);
+//         Xd.index_put_({ i, "..." }, torch::tensor(Xr[i], torch::kInt32));
+//     }
+//     auto yt = torch::tensor(y, torch::kInt32);
+//     return { Xd, yt, features, className, states };
+// }
 
 int main(int argc, char* argv[])
 {
@@ -53,29 +74,42 @@ int main(int argc, char* argv[])
         return 1;
     }
     std::string file_name = argv[1];
-    torch::Tensor X, y;
+    std::string model_name = argv[2];
-    std::vector<std::string> features;
+    std::map<std::string, bayesnet::Classifier*> models{ {"TANLd", new bayesnet::TANLd()}, {"KDBLd", new bayesnet::KDBLd(2)}, {"AODELd", new bayesnet::AODELd() }
-    std::string className;
+    };
-    map<std::string, std::vector<int>> states;
+    if (models.find(model_name) == models.end()) {
-    auto clf = bayesnet::XBAODE(); // false for not using voting in predict
+        std::cerr << "Model not found: " << model_name << std::endl;
-    std::cout << "Library version: " << clf.getVersion() << std::endl;
+        return 1;
-    tie(X, y, features, className, states) = loadDataset(file_name, true);
-    torch::Tensor weights = torch::full({ X.size(1) }, 15, torch::kDouble);
-    torch::Tensor dataset;
-    try {
-        auto yresized = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
-        dataset = torch::cat({ X, yresized }, 0);
     }
-    catch (const std::exception& e) {
+    auto clf = models[model_name];
-        std::stringstream oss;
+    std::cout << "Library version: " << clf->getVersion() << std::endl;
-        oss << "* Error in X and y dimensions *\n";
+    // auto [X, y, features, className, states] = loadDataset(file_name, true);
-        oss << "X dimensions: " << dataset.sizes() << "\n";
+    auto [Xt, yt, features, className] = loadArff(file_name, true);
-        oss << "y dimensions: " << y.sizes();
+    std::map<std::string, std::vector<int>> states;
-        throw std::runtime_error(oss.str());
+    // int m = Xt.size(1);
+    // auto weights = torch::full({ m }, 1 / m, torch::kDouble);
+    // auto dataset = buildDataset(Xv, yv);
+    // try {
+    //     auto yresized = torch::transpose(y.view({ y.size(0), 1 }), 0, 1);
+    //     dataset = torch::cat({ X, yresized }, 0);
+    // }
+    // catch (const std::exception& e) {
+    //     std::stringstream oss;
+    //     oss << "* Error in X and y dimensions *\n";
+    //     oss << "X dimensions: " << dataset.sizes() << "\n";
+    //     oss << "y dimensions: " << y.sizes();
+    //     throw std::runtime_error(oss.str());
+    // }
+    clf->fit(Xt, yt, features, className, states, bayesnet::Smoothing_t::ORIGINAL);
+    auto total = yt.size(0);
+    auto y_proba = clf->predict_proba(Xt);
+    auto y_pred = y_proba.argmax(1);
+    auto accuracy_value = (y_pred == yt).sum().item<float>() / total;
+    auto score = clf->score(Xt, yt);
+    std::cout << "File: " << file_name << " Model: " << model_name << " score: " << score << " Computed accuracy: " << accuracy_value << std::endl;
+    for (const auto clf : models) {
+        delete clf.second;
     }
-    clf.fit(dataset, features, className, states, weights, bayesnet::Smoothing_t::LAPLACE);
-    auto score = clf.score(X, y);
-    std::cout << "File: " << file_name << " Model: BoostAODE score: " << score << std::endl;
     return 0;
 }
 

sample/vcpkg.json

@@ -6,7 +6,7 @@
         "fimdlp",
         "libtorch-bin",
         "folding",
-        "bayesnet"
+        "nlohmann-json"
     ],
     "overrides": [
         {