Refactor library structure and add sample

CHANGELOG.md

@@ -11,6 +11,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Change _ascending_ hyperparameter to _order_ with these possible values _{"asc", "desc", "rand"}_, Default is _"desc"_.
 - Add the _predict_single_ hyperparameter to control if only the last model created is used to predict in boost training or the whole ensemble (all the models built so far). Default is true.
+- sample app to show how to use the library (make sample)
+
+### Changed
+
+- Change the library structure adding folders for each group of classes (classifiers, ensembles, etc).
 
 ## [1.0.3]
 

CMakeLists.txt

@@ -65,10 +65,9 @@ add_git_submodule("lib/json")
 # --------------
 add_subdirectory(config)
 add_subdirectory(lib/Files)
+add_subdirectory(sample)
 add_subdirectory(src)
 
-file(GLOB BayesNet_SOURCES CONFIGURE_DEPENDS ${BayesNet_SOURCE_DIR}/src/*.cc)
-
 # Testing
 # -------
 if (ENABLE_TESTING)

Makefile

@@ -1,11 +1,11 @@
 SHELL := /bin/bash
 .DEFAULT_GOAL := help
-.PHONY: coverage setup help buildr buildd test clean debug release
+.PHONY: coverage setup help buildr buildd test clean debug release sample
 
 f_release = build_release
 f_debug = build_debug
 app_targets = BayesNet
-test_targets = unit_tests_bayesnet 
+test_targets = unit_tests_bayesnet
 n_procs = -j 16
 
 define ClearTests
@@ -59,6 +59,12 @@ release: ## Build a Release version of the project
 	@if [ -d ./$(f_release) ]; then rm -rf ./$(f_release); fi
 	@mkdir $(f_release); 
 	@cmake -S . -B $(f_release) -D CMAKE_BUILD_TYPE=Release
+	@echo ">>> Done";
+
+sample: ## Build sample
+	@echo ">>> Building Sample...";
+	cmake --build $(f_release) -t bayesnet_sample $(n_procs)
+	$(f_release)/sample/bayesnet_sample tests/data/iris.arff
 	@echo ">>> Done";	
 
 opt = ""

sample/CMakeLists.txt

@@ -0,0 +1,14 @@
+include_directories(
+    ${BayesNet_SOURCE_DIR}/src
+    ${BayesNet_SOURCE_DIR}/src/classifiers
+    ${BayesNet_SOURCE_DIR}/src/ensembles
+    ${BayesNet_SOURCE_DIR}/src/bayesian_network
+    ${BayesNet_SOURCE_DIR}/src/utils
+    ${BayesNet_SOURCE_DIR}/src/feature_selection
+    ${BayesNet_SOURCE_DIR}/lib/Files
+    ${BayesNet_SOURCE_DIR}/lib/mdlp
+    ${BayesNet_SOURCE_DIR}/lib/json/include
+    ${CMAKE_BINARY_DIR}/configured_files/include
+)
+add_executable(bayesnet_sample sample.cc) 
+target_link_libraries(bayesnet_sample ArffFiles BayesNet)

sample/sample.cc

@@ -0,0 +1,62 @@
+#include "ArffFiles.h"
+#include "CPPFImdlp.h"
+#include "BoostAODE.h"
+
+std::vector<mdlp::labels_t> discretizeDataset(std::vector<mdlp::samples_t>& X, mdlp::labels_t& y)
+{
+    std::vector<mdlp::labels_t> Xd;
+    auto fimdlp = mdlp::CPPFImdlp();
+    for (int i = 0; i < X.size(); i++) {
+        fimdlp.fit(X[i], y);
+        mdlp::labels_t& xd = fimdlp.transform(X[i]);
+        Xd.push_back(xd);
+    }
+    return Xd;
+}
+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 handler = ArffFiles();
+    handler.load(name, class_last);
+    // Get Dataset X, y
+    std::vector<mdlp::samples_t>& X = handler.getX();
+    mdlp::labels_t& y = handler.getY();
+    // Get className & Features
+    auto className = handler.getClassName();
+    std::vector<std::string> features;
+    auto attributes = handler.getAttributes();
+    transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
+    torch::Tensor Xd;
+    auto states = map<std::string, std::vector<int>>();
+    auto Xr = discretizeDataset(X, y);
+    Xd = torch::zeros({ static_cast<int>(Xr.size()), static_cast<int>(Xr[0].size()) }, torch::kInt32);
+    for (int i = 0; i < features.size(); ++i) {
+        states[features[i]] = std::vector<int>(*max_element(Xr[i].begin(), Xr[i].end()) + 1);
+        auto item = states.at(features[i]);
+        iota(begin(item), end(item), 0);
+        Xd.index_put_({ i, "..." }, torch::tensor(Xr[i], torch::kInt32));
+    }
+    states[className] = std::vector<int>(*max_element(y.begin(), y.end()) + 1);
+    iota(begin(states.at(className)), end(states.at(className)), 0);
+    return { Xd, torch::tensor(y, torch::kInt32), features, className, states };
+}
+
+int main(int argc, char* argv[])
+{
+    if (argc < 2) {
+        std::cerr << "Usage: " << argv[0] << " <file_name>" << std::endl;
+        return 1;
+    }
+    std::string file_name = argv[1];
+    torch::Tensor X, y;
+    std::vector<std::string> features;
+    std::string className;
+    map<std::string, std::vector<int>> states;
+    auto clf = bayesnet::BoostAODE(false); // false for not using voting in predict
+    std::cout << "Library version: " << clf.getVersion() << std::endl;
+    tie(X, y, features, className, states) = loadDataset(file_name, true);
+    clf.fit(X, y, features, className, states);
+    auto score = clf.score(X, y);
+    std::cout << "File: " << file_name << " score: " << score << std::endl;
+    return 0;
+}
+

src/CMakeLists.txt

@@ -4,10 +4,15 @@ include_directories(
     ${BayesNet_SOURCE_DIR}/lib/folding
     ${BayesNet_SOURCE_DIR}/lib/json/include
     ${BayesNet_SOURCE_DIR}/src
+    ${BayesNet_SOURCE_DIR}/src/feature_selection
+    ${BayesNet_SOURCE_DIR}/src/bayesian_network
+    ${BayesNet_SOURCE_DIR}/src/classifiers
+    ${BayesNet_SOURCE_DIR}/src/ensembles
+    ${BayesNet_SOURCE_DIR}/src/utils
     ${CMAKE_BINARY_DIR}/configured_files/include
 )
 
-add_library(BayesNet bayesnetUtils.cc Network.cc Node.cc BayesMetrics.cc Classifier.cc 
-    KDB.cc TAN.cc SPODE.cc Ensemble.cc AODE.cc TANLd.cc KDBLd.cc SPODELd.cc AODELd.cc BoostAODE.cc 
-    Mst.cc Proposal.cc CFS.cc FCBF.cc IWSS.cc FeatureSelect.cc )
+file(GLOB_RECURSE Sources "*.cc")
+
+add_library(BayesNet ${Sources})
 target_link_libraries(BayesNet mdlp "${TORCH_LIBRARIES}")

tests/CMakeLists.txt

@@ -2,13 +2,18 @@ if(ENABLE_TESTING)
     set(TEST_BAYESNET "unit_tests_bayesnet")
     include_directories(
         ${BayesNet_SOURCE_DIR}/src
-        ${BayesNet_SOURCE_DIR}/src/Platform
+        ${BayesNet_SOURCE_DIR}/src/feature_selection
+        ${BayesNet_SOURCE_DIR}/src/bayesian_network
+        ${BayesNet_SOURCE_DIR}/src/classifiers
+        ${BayesNet_SOURCE_DIR}/src/utils
+        ${BayesNet_SOURCE_DIR}/src/ensembles
         ${BayesNet_SOURCE_DIR}/lib/Files
         ${BayesNet_SOURCE_DIR}/lib/mdlp
         ${BayesNet_SOURCE_DIR}/lib/folding
         ${BayesNet_SOURCE_DIR}/lib/json/include
         ${CMAKE_BINARY_DIR}/configured_files/include
     )
+    file(GLOB_RECURSE BayesNet_SOURCES "${BayesNet_SOURCE_DIR}/src/*.cc")
     set(TEST_SOURCES_BAYESNET TestBayesModels.cc TestBayesNetwork.cc TestBayesMetrics.cc TestUtils.cc ${BayesNet_SOURCES})
     add_executable(${TEST_BAYESNET} ${TEST_SOURCES_BAYESNET})
     target_link_libraries(${TEST_BAYESNET} PUBLIC "${TORCH_LIBRARIES}" ArffFiles mdlp Catch2::Catch2WithMain )