Add notes to Classifier & Changelog

Remove other projects' sources

.gitmodules

@@ -8,11 +8,6 @@
         main  = v2.x
 	update = merge
 	url = https://github.com/catchorg/Catch2.git
-[submodule "lib/argparse"]
-	path = lib/argparse
-	url = https://github.com/p-ranav/argparse
-	master = master
-	update = merge
 [submodule "lib/json"]
 	path = lib/json
 	url = https://github.com/nlohmann/json.git

CHANGELOG.md

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

CMakeLists.txt

@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.20)
 
 project(BayesNet
-  VERSION 1.0.0
+  VERSION 1.0.1
   DESCRIPTION "Bayesian Network and basic classifiers Library."
   HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
   LANGUAGES CXX
@@ -52,7 +52,6 @@ endif (ENABLE_CLANG_TIDY)
 # ---------------------------------------------
 # include(FetchContent)
 add_git_submodule("lib/mdlp")
-add_git_submodule("lib/argparse")
 add_git_submodule("lib/json")
 
 # Subdirectories

src/BayesNet/BaseClassifier.h

@@ -26,6 +26,7 @@ namespace bayesnet {
         std::vector<std::string> virtual graph(const std::string& title = "") const = 0;
         virtual std::string getVersion() = 0;
         std::vector<std::string> virtual topological_order() = 0;
+        std::vector<std::string> virtual getNotes() const = 0;
         void virtual dump_cpt()const = 0;
         virtual void setHyperparameters(const nlohmann::json& hyperparameters) = 0;
         std::vector<std::string>& getValidHyperparameters() { return validHyperparameters; }

src/BayesNet/BoostAODE.cc

@@ -115,6 +115,7 @@ namespace bayesnet {
             significanceModels.push_back(1.0);
             n_models++;
         }
+        notes.push_back("Used features in initialization: " + std::to_string(featuresUsed.size()) + " of " + std::to_string(features.size()) + " with " + algorithm);
         delete featureSelector;
         return featuresUsed;
     }
@@ -197,8 +198,10 @@ namespace bayesnet {
             exitCondition = n_models >= maxModels && repeatSparent || epsilon_t > 0.5 || count > tolerance;
         }
         if (featuresUsed.size() != features.size()) {
+            notes.push_back("Used features in train: " + std::to_string(featuresUsed.size()) + " of " + std::to_string(features.size()));
             status = WARNING;
         }
+        notes.push_back("Number of models: " + std::to_string(n_models));
     }
     std::vector<std::string> BoostAODE::graph(const std::string& title) const
     {

src/BayesNet/Classifier.h

@@ -19,6 +19,7 @@ namespace bayesnet {
         std::map<std::string, std::vector<int>> states;
         torch::Tensor dataset; // (n+1)xm tensor
         status_t status = NORMAL;
+        std::vector<std::string> notes; // Used to store messages occurred during the fit process
         void checkFitParameters();
         virtual void buildModel(const torch::Tensor& weights) = 0;
         void trainModel(const torch::Tensor& weights) override;
@@ -36,12 +37,13 @@ namespace bayesnet {
         int getNumberOfStates() const override;
         torch::Tensor predict(torch::Tensor& X) override;
         status_t getStatus() const override { return status; }
-        std::string getVersion() override { return "0.2.0"; };
+        std::string getVersion() override { return { project_version.begin(), project_version.end() }; };
         std::vector<int> predict(std::vector<std::vector<int>>& X) override;
         float score(torch::Tensor& X, torch::Tensor& y) override;
         float score(std::vector<std::vector<int>>& X, std::vector<int>& y) override;
         std::vector<std::string> show() const override;
         std::vector<std::string> topological_order()  override;
+        std::vector<std::string> getNotes() const override { return notes; }
         void dump_cpt() const override;
         void setHyperparameters(const nlohmann::json& hyperparameters) override; //For classifiers that don't have hyperparameters
     };

tests/CMakeLists.txt

@@ -7,7 +7,6 @@ if(ENABLE_TESTING)
         ${BayesNet_SOURCE_DIR}/lib/mdlp
         ${BayesNet_SOURCE_DIR}/lib/folding
         ${BayesNet_SOURCE_DIR}/lib/json/include
-        ${BayesNet_SOURCE_DIR}/lib/argparse/include
         ${CMAKE_BINARY_DIR}/configured_files/include
     )
     set(TEST_SOURCES_BAYESNET TestBayesModels.cc TestBayesNetwork.cc TestBayesMetrics.cc TestUtils.cc ${BayesNet_SOURCES})

tests/TestBayesModels.cc

@@ -16,6 +16,11 @@
 #include "AODELd.h"
 #include "TestUtils.h"
 
+TEST_CASE("Library check version", "[BayesNet]")
+{
+    auto clf = bayesnet::KDB(2);
+    REQUIRE(clf.getVersion() == "1.0.1");
+}
 TEST_CASE("Test Bayesian Classifiers score", "[BayesNet]")
 {
     map <pair<std::string, std::string>, float> scores = {
@@ -139,3 +144,33 @@ TEST_CASE("Get num features & num edges", "[BayesNet]")
     REQUIRE(clf.getNumberOfNodes() == 5);
     REQUIRE(clf.getNumberOfEdges() == 8);
 }
+TEST_CASE("BoostAODE feature_select CFS", "[BayesNet]")
+{
+    auto raw = RawDatasets("glass", true);
+    auto clf = bayesnet::BoostAODE();
+    clf.setHyperparameters({ {"select_features", "CFS"} });
+    clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+    REQUIRE(clf.getNumberOfNodes() == 90);
+    REQUIRE(clf.getNumberOfEdges() == 153);
+    REQUIRE(clf.getNotes().size() == 2);
+    REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 9 with CFS");
+    REQUIRE(clf.getNotes()[1] == "Number of models: 9");
+}
+TEST_CASE("BoostAODE test used features in train note", "[BayesNet]")
+{
+    auto raw = RawDatasets("diabetes", true);
+    auto clf = bayesnet::BoostAODE();
+    clf.setHyperparameters({
+        {"ascending",true},
+        {"convergence", true},
+        {"repeatSparent",true},
+        {"select_features","CFS"}
+        });
+    clf.fit(raw.Xv, raw.yv, raw.featuresv, raw.classNamev, raw.statesv);
+    REQUIRE(clf.getNumberOfNodes() == 72);
+    REQUIRE(clf.getNumberOfEdges() == 120);
+    REQUIRE(clf.getNotes().size() == 3);
+    REQUIRE(clf.getNotes()[0] == "Used features in initialization: 6 of 8 with CFS");
+    REQUIRE(clf.getNotes()[1] == "Used features in train: 7 of 8");
+    REQUIRE(clf.getNotes()[2] == "Number of models: 8");
+}

tests/TestBayesNetwork.cc

@@ -25,6 +25,7 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
 
     auto raw = RawDatasets("iris", true);
     auto net = bayesnet::Network();
+    double threshold = 1e-4;
 
     SECTION("Test get features")
     {
@@ -167,97 +168,44 @@ TEST_CASE("Test Bayesian Network", "[BayesNet]")
         REQUIRE(str[5] == "C [shape=circle] \n");
         REQUIRE(str[6] == "}\n");
     }
-
+    SECTION("Test predict")
-
+    {
-    // SECTION("Test predict")
+        auto net = bayesnet::Network();
-    // {
+        buildModel(net, raw.featuresv, raw.classNamev);
-    //     auto net = bayesnet::Network();
+        net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
-    //     net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
+        std::vector<std::vector<int>> test = { {1, 2, 0, 1, 1}, {0, 1, 2, 0, 1}, {0, 0, 0, 0, 1}, {2, 2, 2, 2, 1} };
-    //     std::vector<std::vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
+        std::vector<int> y_test = { 2, 2, 0, 2, 1 };
-    //     std::vector<int> y_test = { 0, 1, 1, 0, 2 };
+        auto y_pred = net.predict(test);
-    //     auto y_pred = net.predict(test);
+        REQUIRE(y_pred == y_test);
-    //     REQUIRE(y_pred == y_test);
+    }
-    // }
+    SECTION("Test predict_proba")
-
+    {
-    //     SECTION("Test predict_proba")
+        auto net = bayesnet::Network();
-    //     {
+        buildModel(net, raw.featuresv, raw.classNamev);
-    //         auto net = bayesnet::Network();
+        net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
-    //         net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
+        std::vector<std::vector<int>> test = { {1, 2, 0, 1, 1}, {0, 1, 2, 0, 1}, {0, 0, 0, 0, 1}, {2, 2, 2, 2, 1} };
-    //         std::vector<std::vector<int>> test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
+        std::vector<std::vector<double>> y_test = {
-    //         auto y_test = { 0, 1, 1, 0, 2 };
+            {0.450237, 0.0866621, 0.463101},
-    //         auto y_pred = net.predict(test);
+            {0.244443, 0.0925922, 0.662964},
-    //         REQUIRE(y_pred == y_test);
+            {0.913441, 0.0125857, 0.0739732},
-    //     }
+            {0.450237, 0.0866621, 0.463101},
+            {0.0135226, 0.971726, 0.0147519}
+        };
+        auto y_pred = net.predict_proba(test);
+        REQUIRE(y_pred.size() == 5);
+        REQUIRE(y_pred[0].size() == 3);
+        for (int i = 0; i < y_pred.size(); ++i) {
+            for (int j = 0; j < y_pred[i].size(); ++j) {
+                REQUIRE(y_pred[i][j] == Catch::Approx(y_test[i][j]).margin(threshold));
+            }
+        }
+    }
+    SECTION("Test score")
+    {
+        auto net = bayesnet::Network();
+        buildModel(net, raw.featuresv, raw.classNamev);
+        net.fit(raw.Xv, raw.yv, raw.weightsv, raw.featuresv, raw.classNamev, raw.statesv);
+        auto score = net.score(raw.Xv, raw.yv);
+        REQUIRE(score == Catch::Approx(0.97333333).margin(threshold));
+    }
 }
-
-// SECTION("Test score")
-// {
-//     auto net = bayesnet::Network();
-//     net.fit(Xd, y, weights, features, className, states);
-//     auto test = { {1, 2, 0, 1}, {0, 1, 2, 0}, {1, 1, 1, 1}, {0, 0, 0, 0}, {2, 2, 2, 2} };
-//     auto score = net.score(X, y);
-//     REQUIRE(score == Catch::Approx();
-// }
-
-// 
-// 
-
-// SECTION("Test graph")
-// {
-//     auto net = bayesnet::Network();
-//     net.addNode("A");
-//     net.addNode("B");
-//     net.addNode("C");
-//     net.addEdge("A", "B");
-//     net.addEdge("A", "C");
-//     auto str = net.graph("Test Graph");
-//     REQUIRE(str.size() == 6);
-//     REQUIRE(str[0] == "digraph \"Test Graph\" {");
-//     REQUIRE(str[1] == "  A -> B;");
-//     REQUIRE(str[2] == "  A -> C;");
-//     REQUIRE(str[3] == "  B [shape=ellipse];");
-//     REQUIRE(str[4] == "  C [shape=ellipse];");
-//     REQUIRE(str[5] == "}");
-// }
-
-// SECTION("Test initialize")
-// {
-//     auto net = bayesnet::Network();
-//     net.addNode("A");
-//     net.addNode("B");
-//     net.addNode("C");
-//     net.addEdge("A", "B");
-//     net.addEdge("A", "C");
-//     net.initialize();
-//     REQUIRE(net.getNodes().size() == 0);
-//     REQUIRE(net.getEdges().size() == 0);
-//     REQUIRE(net.getFeatures().size() == 0);
-//     REQUIRE(net.getClassNumStates() == 0);
-//     REQUIRE(net.getClassName().empty());
-//     REQUIRE(net.getStates() == 0);
-//     REQUIRE(net.getSamples().numel() == 0);
-// }
-
-// SECTION("Test dump_cpt")
-// {
-//     auto net = bayesnet::Network();
-//     net.addNode("A");
-//     net.addNode("B");
-//     net.addNode("C");
-//     net.addEdge("A", "B");
-//     net.addEdge("A", "C");
-//     net.setClassName("C");
-//     net.setStates({ {"A", {0, 1}}, {"B", {0, 1}}, {"C", {0, 1, 2}} });
-//     net.fit({ {0, 0}, {0, 1}, {1, 0}, {1, 1} }, { 0, 1, 1, 2 }, {}, { "A", "B" }, "C", { {"A", {0, 1}}, {"B", {0, 1}}, {"C", {0, 1, 2}} });
-//     net.dump_cpt();
-//     // TODO: Check that the file was created and contains the expected data
-// }
-
-// SECTION("Test version")
-// {
-//     auto net = bayesnet::Network();
-//     REQUIRE(net.version() == "0.2.0");
-// }
-// }
-
-// }