Update fimdlp version and change tests

.vscode/launch.json

@@ -16,7 +16,7 @@
             "name": "test",
             "program": "${workspaceFolder}/build_Debug/tests/TestBayesNet",
             "args": [
-                "[XBAODE]"
+                "Test Dataset Loading"
             ],
             "cwd": "${workspaceFolder}/build_Debug/tests"
         },

Makefile

@@ -21,8 +21,6 @@ sed_command_diagram = 's/Diagram"/Diagram" width="100%" height="100%" /g'
 CPUS := $(shell getconf _NPROCESSORS_ONLN 2>/dev/null \
                  || nproc --all 2>/dev/null \
                  || sysctl -n hw.ncpu)
-
-# --- Your desired job count: CPUs – 7, but never less than 1 --------------
 JOBS := $(shell n=$(CPUS); [ $${n} -gt 7 ] && echo $$((n-7)) || echo 1)
 
 # Colors for output

conanfile.py

@@ -60,7 +60,7 @@ class BayesNetConan(ConanFile):
         self.requires("libtorch/2.7.1")
         self.requires("nlohmann_json/3.11.3")
         self.requires("folding/1.1.2")  # Custom package
-        self.requires("fimdlp/2.1.1")  # Custom package
+        self.requires("fimdlp/2.1.2")  # Custom package
 
     def build_requirements(self):
         self.build_requires("cmake/[>=3.27]")

tests/TestModulesVersions.cc

@@ -16,7 +16,7 @@
 #include "TestUtils.h"
 
 std::map<std::string, std::string> modules = {
-    { "mdlp", "2.1.1" },
+    { "mdlp", "2.1.2" },
     { "Folding", "1.1.2" },
     { "json", "3.11" },
     { "ArffFiles", "1.2.1" }

tests/TestUtils.cc

@@ -78,7 +78,7 @@ RawDatasets::RawDatasets(const std::string& file_name, bool discretize_, int num
         std::cout << to_string();
 }
 
-map<std::string, int> RawDatasets::discretizeDataset(std::vector<mdlp::samples_t>& X, const std::vector<bool>& is_numeric)
+map<std::string, int> RawDatasets::discretizeDataset(std::vector<mdlp::samples_t>& X)
 {
     map<std::string, int> maxes;
     auto fimdlp = mdlp::CPPFImdlp();
@@ -175,8 +175,9 @@ void RawDatasets::loadDataset(const std::string& name, bool class_last)
     className = handler.getClassName();
     auto attributes = handler.getAttributes();
     transform(attributes.begin(), attributes.end(), back_inserter(features), [](const auto& pair) { return pair.first; });
+    is_numeric.clear();
+    is_numeric.reserve(features.size());
     auto numericFeaturesIdx = catalog.at(name);
-    std::vector<bool> is_numeric;
     if (numericFeaturesIdx.empty()) {
         // no numeric features
         is_numeric.assign(features.size(), false);
@@ -195,7 +196,7 @@ void RawDatasets::loadDataset(const std::string& name, bool class_last)
         }
     }
     // Discretize Dataset
-    auto maxValues = discretizeDataset(X, is_numeric);
+    auto maxValues = discretizeDataset(X);
     maxValues[className] = *max_element(yv.begin(), yv.end()) + 1;
     if (discretize) {
         // discretize the tensor as well

tests/TestUtils.h

@@ -27,6 +27,7 @@ public:
     std::vector<double> weightsv;
     std::vector<string> features;
     std::string className;
+    std::vector<bool> is_numeric; // indicates whether each feature is numeric
     map<std::string, std::vector<int>> states;
     //catalog holds the mapping between dataset names and their corresponding indices of numeric features (-1) means all are numeric 
     //and an empty vector means none are numeric
@@ -89,7 +90,7 @@ private:
         }
         return result;
     }
-    map<std::string, int> discretizeDataset(std::vector<mdlp::samples_t>& X, const std::vector<bool>& is_numeric);
+    map<std::string, int> discretizeDataset(std::vector<mdlp::samples_t>& X);
     void loadDataset(const std::string& name, bool class_last);
     map<std::string, std::vector<int>> loadCatalog();
 };