Fix discrete feature discretizer once they are rediscretized in the algorithm

Complete proposal with only discretizing numeric features
Update fimdlp version and change tests
2025-08-24 12:44:09 +02:00 · 2025-08-24 01:09:25 +02:00 · 2025-08-22 20:16:15 +02:00 · 2025-08-21 19:20:03 +02:00 · 2025-08-21 19:01:10 +02:00 · 2025-08-21 12:56:41 +02:00
18 changed files with 664 additions and 43 deletions
--- a/.sonarlint/connectedMode.json
+++ b/.sonarlint/connectedMode.json
@@ -1,4 +1,5 @@
 {
    "sonarCloudOrganization": "rmontanana",
-    "projectKey": "rmontanana_BayesNet"
+    "projectKey": "rmontanana_BayesNet",
+    "region": "EU"
 }
--- a/.vscode/launch.json
+++ b/.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"
        },
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,7 +5,24 @@ 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).

-## [Unreleased]
+## [1.2.2] - 2025-08-19
+
+### Fixed
+
+- Fixed an issue with local discretization that was discretizing all features wether they were numeric or categorical.
+- Fix testutils to return states for all features:
+  - An empty vector is now returned for numeric features.
+  - Categorical features now return their unique states.
+
+## [1.2.1] - 2025-07-19
+
+### Internal
+
+- Update Libtorch to version 2.7.1
+- Update libraries versions:
+  - mdlp: 2.1.1
+  - Folding: 1.1.2
+  - ArffFiles: 1.2.1

 ## [1.2.0] - 2025-07-08

--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1,7 +1,7 @@
 cmake_minimum_required(VERSION 3.27)

 project(bayesnet
-  VERSION 1.2.0
+  VERSION 1.2.2
  DESCRIPTION "Bayesian Network and basic classifiers Library."
  HOMEPAGE_URL "https://github.com/rmontanana/bayesnet"
  LANGUAGES CXX
--- a/49
+++ b/49
@@ -21,15 +21,18 @@ 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
+GREEN = \033[0;32m
+YELLOW = \033[1;33m
+RED = \033[0;31m
+NC = \033[0m # No Color

 define ClearTests
 	@for t in $(test_targets); do \
 		if [ -f $(f_debug)/tests/$$t ]; then \
-			echo ">>> Cleaning $$t..." ; \
+			echo ">>> Removing $$t..." ; \
 			rm -f $(f_debug)/tests/$$t ; \
 		fi ; \
 	done
@@ -48,6 +51,20 @@ define setup_target
 	@echo ">>> Done"
 endef

+define status_file_folder
+	@if [ -d $(1) ]; then \
+		st1=" ✅ $(GREEN)"; \
+	else \
+		st1=" ❌ $(RED)"; \
+	fi; \
+	if [ -f $(1)/libbayesnet.a ]; then \
+		st2=" ✅ $(GREEN)"; \
+	else \
+		st2=" ❌ $(RED)"; \
+	fi; \
+	printf "  $(YELLOW)$(2):$(NC) $$st1 Folder $(NC)  $$st2 Library $(NC)\n"
+endef
+
 setup: ## Install dependencies for tests and coverage
 	@if [ "$(shell uname)" = "Darwin" ]; then \
 		brew install gcovr; \
@@ -61,7 +78,7 @@ setup: ## Install dependencies for tests and coverage

 clean: ## Clean the project
 	@echo ">>> Cleaning the project..."
-	@if test -f CMakeCache.txt ; then echo "- Deleting CMakeCache.txt"; rm -f CMakeCache.txt; fimake 
+	@if test -f CMakeCache.txt ; then echo "- Deleting CMakeCache.txt"; rm -f CMakeCache.txt; fi
 	@for folder in $(f_release) $(f_debug) vpcpkg_installed install_test ; do \
 		if test -d "$$folder" ; then \
 			echo "- Deleting $$folder folder" ; \
@@ -80,11 +97,12 @@ debug: ## Setup debug version using Conan
 release: ## Setup release version using Conan
 	@$(call setup_target,"Release","$(f_release)","ENABLE_TESTING=OFF")

-buildd: ## Build the debug targets
-	cmake --build $(f_debug) --config Debug -t $(app_targets) --parallel $(JOBS)
+buildd: ## Build the debug && test targets
+	@cmake --build $(f_debug) --config Debug -t $(app_targets) --parallel $(JOBS)
+	@cmake --build $(f_debug) -t $(test_targets) --parallel $(JOBS)

 buildr: ## Build the release targets
-	cmake --build $(f_release) --config Release -t $(app_targets) --parallel $(JOBS)
+	@cmake --build $(f_release) --config Release -t $(app_targets) --parallel $(JOBS)


 # Install targets
@@ -241,9 +259,24 @@ sample: ## Build sample with Conan
 	sample/build/bayesnet_sample $(fname) $(model)
 	@echo ">>> Done";

+info: ## Show project information
+	@version=$$(grep -A1 "project(bayesnet" CMakeLists.txt | grep "VERSION" | sed 's/.*VERSION \([0-9.]*\).*/\1/'); \
+	printf "$(GREEN)BayesNet Library: $(YELLOW)ver. $$version$(NC)\n"
+	@echo ""
+	@printf "$(GREEN)Project folders:$(NC)\n"
+	$(call status_file_folder, $(f_release), "Build\ Release")
+	$(call status_file_folder, $(f_debug), "Build\ Debug\ \ ")
+	@echo ""
+	@printf "$(GREEN)Build commands:$(NC)\n"
+	@printf "   $(YELLOW)make release && make buildr$(NC) - Build library for release\n"
+	@printf "   $(YELLOW)make debug && make buildd$(NC)   - Build library for debug\n"
+	@printf "   $(YELLOW)make test$(NC) - Run tests\n"
+	@printf "   $(YELLOW)Usage:$(NC) make help\n"
+	@echo ""
+	@printf "   $(YELLOW)Parallel Jobs:   $(GREEN)$(JOBS)$(NC)\n"
+
 # Help target
 # ===========
-
 help: ## Show help message
 	@IFS=$$'\n' ; \
 	help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \
--- a/bayesnet/classifiers/KDBLd.cc
+++ b/bayesnet/classifiers/KDBLd.cc
@@ -37,6 +37,7 @@ namespace bayesnet {
        className = className_;
        states = iterativeLocalDiscretization(y, static_cast<KDB*>(this), dataset, features, className, states_, smoothing);
        KDB::fit(dataset, features, className, states, smoothing);
+        fitted = true;
        return *this;
    }
    torch::Tensor KDBLd::predict(torch::Tensor& X)
--- a/bayesnet/classifiers/Proposal.cc
+++ b/bayesnet/classifiers/Proposal.cc
@@ -101,6 +101,9 @@ namespace bayesnet {
            auto xvf_ptr = Xf.index({ index }).data_ptr<float>();
            auto xvf = std::vector<mdlp::precision_t>(xvf_ptr, xvf_ptr + Xf.size(1));
            discretizers[feature]->fit(xvf, yxv);
+            // Enables the discretizer in predict time, because now we have a discretizer fitted for this feature, 
+            // either it was a numeric feature in the beginning or not 
+            wasNumeric[index] = true;
        }
        if (upgrade) {
            // Discretize again X (only the affected indices) with the new fitted discretizers
@@ -118,17 +121,20 @@ namespace bayesnet {
        }
        return states;
    }
-    map<std::string, std::vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y)
+    map<std::string, std::vector<int>> Proposal::fit_local_discretization(const torch::Tensor& y, map<std::string, std::vector<int>> states)
    {
        // Discretize the continuous input data and build pDataset (Classifier::dataset)
+        // We expect to have in states for numeric features an empty vector and for discretized features a vector of states
        int m = Xf.size(1);
        int n = Xf.size(0);
-        map<std::string, std::vector<int>> states;
        pDataset = torch::zeros({ n + 1, m }, torch::kInt32);
        auto yv = std::vector<int>(y.data_ptr<int>(), y.data_ptr<int>() + y.size(0));
        // discretize input data by feature(row)
        std::unique_ptr<mdlp::Discretizer> discretizer;
+        wasNumeric.resize(pFeatures.size());
        for (auto i = 0; i < pFeatures.size(); ++i) {
+            auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
+            auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
            if (discretizationType == discretization_t::BINQ) {
                discretizer = std::make_unique<mdlp::BinDisc>(ld_params.proposed_cuts, mdlp::strategy_t::QUANTILE);
            } else if (discretizationType == discretization_t::BINU) {
@@ -136,13 +142,19 @@ namespace bayesnet {
            } else { // Default is MDLP
                discretizer = std::make_unique<mdlp::CPPFImdlp>(ld_params.min_length, ld_params.max_depth, ld_params.proposed_cuts);
            }
-            auto Xt_ptr = Xf.index({ i }).data_ptr<float>();
-            auto Xt = std::vector<float>(Xt_ptr, Xt_ptr + Xf.size(1));
-            discretizer->fit(Xt, yv);
-            pDataset.index_put_({ i, "..." }, torch::tensor(discretizer->transform(Xt)));
-            auto xStates = std::vector<int>(discretizer->getCutPoints().size() + 1);
+            if (states[pFeatures[i]].empty()) {
+                // If the feature is numeric, we discretize it
+                pDataset.index_put_({ i, "..." }, torch::tensor(discretizer->fit_transform(Xt, yv)));
+                int n_states = discretizer->getCutPoints().size() + 1;
+                auto xStates = std::vector<int>(n_states);
                iota(xStates.begin(), xStates.end(), 0);
                states[pFeatures[i]] = xStates;
+                wasNumeric[i] = true;
+            } else {
+                wasNumeric[i] = false;
+                // If the feature is categorical, we just copy it
+                pDataset.index_put_({ i, "..." }, Xf[i].to(torch::kInt32));
+            }
            discretizers[pFeatures[i]] = std::move(discretizer);
        }
        int n_classes = torch::max(y).item<int>() + 1;
@@ -157,8 +169,13 @@ namespace bayesnet {
        auto Xtd = torch::zeros_like(X, torch::kInt32);
        for (int i = 0; i < X.size(0); ++i) {
            auto Xt = std::vector<float>(X[i].data_ptr<float>(), X[i].data_ptr<float>() + X.size(1));
+            std::vector<int> Xd;
+            if (wasNumeric[i]) {
                auto Xd = discretizers[pFeatures[i]]->transform(Xt);
                Xtd.index_put_({ i }, torch::tensor(Xd, torch::kInt32));
+            } else {
+                Xtd.index_put_({ i }, Xf[i].to(torch::kInt32));
+            }
        }
        return Xtd;
    }
@@ -190,7 +207,7 @@ namespace bayesnet {
    )
    {
        // Phase 1: Initial discretization (same as original)
-        auto currentStates = fit_local_discretization(y);
+        auto currentStates = fit_local_discretization(y, initialStates);
        auto previousModel = Network();

        if (convergence_params.verbose) {
--- a/bayesnet/classifiers/Proposal.h
+++ b/bayesnet/classifiers/Proposal.h
@@ -23,9 +23,8 @@ namespace bayesnet {
    protected:
        void checkInput(const torch::Tensor& X, const torch::Tensor& y);
        torch::Tensor prepareX(torch::Tensor& X);
-        map<std::string, std::vector<int>> localDiscretizationProposal(const map<std::string, std::vector<int>>& states, Network& model);
-        map<std::string, std::vector<int>> fit_local_discretization(const torch::Tensor& y);
-
+        // fit_local_discretization is only called by aodeld
+        map<std::string, std::vector<int>> fit_local_discretization(const torch::Tensor& y, map<std::string, std::vector<int>> states);
        // Iterative discretization method
        template<typename Classifier>
        map<std::string, std::vector<int>> iterativeLocalDiscretization(
@@ -37,18 +36,15 @@ namespace bayesnet {
            const map<std::string, std::vector<int>>& initialStates,
            const Smoothing_t smoothing
        );
-
        torch::Tensor Xf; // X continuous nxm tensor
        torch::Tensor y; // y discrete nx1 tensor
        map<std::string, std::unique_ptr<mdlp::Discretizer>> discretizers;
-
        // MDLP parameters
        struct {
            size_t min_length = 3; // Minimum length of the interval to consider it in mdlp
            float proposed_cuts = 0.0; // Proposed cuts for the Discretization algorithm
            int max_depth = std::numeric_limits<int>::max(); // Maximum depth of the MDLP tree
        } ld_params;
-
        // Convergence parameters
        struct {
            int maxIterations = 10;
@@ -60,10 +56,12 @@ namespace bayesnet {
            "max_iterations", "verbose_convergence"
        };
    private:
+        map<std::string, std::vector<int>> localDiscretizationProposal(const map<std::string, std::vector<int>>& states, Network& model);
        std::vector<int> factorize(const std::vector<std::string>& labels_t);
        std::vector<std::string>& notes; // Notes during fit from BaseClassifier
        torch::Tensor& pDataset; // (n+1)xm tensor
        std::vector<std::string>& pFeatures;
+        std::vector<bool> wasNumeric;
        std::string& pClassName;
        enum class discretization_t {
            MDLP,
--- a/bayesnet/classifiers/SPODELd.cc
+++ b/bayesnet/classifiers/SPODELd.cc
@@ -36,6 +36,7 @@ namespace bayesnet {
        className = className_;
        states = iterativeLocalDiscretization(y, static_cast<SPODE*>(this), dataset, features, className, states_, smoothing);
        SPODE::fit(dataset, features, className, states, smoothing);
+        fitted = true;
        return *this;
    }
    torch::Tensor SPODELd::predict(torch::Tensor& X)
--- a/bayesnet/classifiers/TANLd.cc
+++ b/bayesnet/classifiers/TANLd.cc
@@ -35,6 +35,7 @@ namespace bayesnet {
        className = className_;
        states = iterativeLocalDiscretization(y, static_cast<TAN*>(this), dataset, features, className, states_, smoothing);
        TAN::fit(dataset, features, className, states, smoothing);
+        fitted = true;
        return *this;
    }
    torch::Tensor TANLd::predict(torch::Tensor& X)
--- a/bayesnet/ensembles/AODELd.cc
+++ b/bayesnet/ensembles/AODELd.cc
@@ -19,11 +19,12 @@ namespace bayesnet {
        Xf = X_;
        y = y_;
        // Fills std::vectors Xv & yv with the data from tensors X_ (discretized) & y
-        states = fit_local_discretization(y);
+        states = fit_local_discretization(y, states_);
        // We have discretized the input data
        // 1st we need to fit the model to build the normal AODE structure, Ensemble::fit  
        // calls buildModel to initialize the base models
        Ensemble::fit(dataset, features, className, states, smoothing);
+        fitted = true;
        return *this;

    }
--- a/conanfile.py
+++ b/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]")
--- a/tests/TestBayesModels.cc
+++ b/tests/TestBayesModels.cc
@@ -20,7 +20,7 @@
 #include "bayesnet/ensembles/AODELd.h"
 #include "bayesnet/ensembles/BoostAODE.h"

-const std::string ACTUAL_VERSION = "1.2.0";
+const std::string ACTUAL_VERSION = "1.2.2";

 TEST_CASE("Test Bayesian Classifiers score & version", "[Models]")
 {
@@ -496,3 +496,59 @@ TEST_CASE("Local discretization hyperparameters", "[Models]")
    REQUIRE_NOTHROW(clft.fit(raw.Xt, raw.yt, raw.features, raw.className, raw.states, raw.smoothing));
    REQUIRE(clft.getStatus() == bayesnet::NORMAL);
 }
+TEST_CASE("Test Dataset Loading", "[Datasets]")
+{
+    int max_sample = 4;
+    // Test loading a dataset
+    RawDatasets dataset("iris", true);
+    REQUIRE(dataset.Xt.size(0) == 4);
+    REQUIRE(dataset.Xt.size(1) == 150);
+    REQUIRE(dataset.yt.size(0) == 150);
+    std::cout << "Dataset iris discretized " << std::endl;
+    for (int sample = 0; sample < max_sample; sample++) {
+        for (int feature = 0; feature < 4; feature++) {
+            std::cout << dataset.Xt[feature][sample].item<int>() << " ";
+        }
+        std::cout << "| " << dataset.yt[sample].item<int>() << std::endl;
+    }
+    dataset = RawDatasets("iris", false);
+    std::cout << "Dataset iris raw " << std::endl;
+    for (int sample = 0; sample < max_sample; sample++) {
+        for (int feature = 0; feature < 4; feature++) {
+            std::cout << dataset.Xt[feature][sample].item<float>() << " ";
+        }
+        std::cout << "| " << dataset.yt[sample].item<int>() << std::endl;
+    }
+    // Test loading a dataset
+    dataset = RawDatasets("heart-statlog", true);
+    REQUIRE(dataset.Xt.size(0) == 13);
+    REQUIRE(dataset.Xt.size(1) == 270);
+    REQUIRE(dataset.yt.size(0) == 270);
+    std::cout << "Dataset heart-statlog discretized " << std::endl;
+    for (int sample = 0; sample < max_sample; sample++) {
+        for (int feature = 0; feature < 13; feature++) {
+            std::cout << dataset.Xt[feature][sample].item<int>() << " ";
+        }
+        std::cout << "| " << dataset.yt[sample].item<int>() << std::endl;
+    }
+    auto features = dataset.features;
+    std::cout << "States:" << std::endl;
+    for (int i = 0; i < 13; i++) {
+        std::cout << i << " has " << dataset.states.at(features[i]).size() << " states." << std::endl;
+    }
+    dataset = RawDatasets("heart-statlog", false);
+    std::cout << "Dataset heart-statlog raw " << std::endl;
+    for (int sample = 0; sample < max_sample; sample++) {
+        for (int feature = 0; feature < 13; feature++) {
+            std::cout << dataset.Xt[feature][sample].item<float>() << " ";
+        }
+        std::cout << "| " << dataset.yt[sample].item<int>() << std::endl;
+    }
+    std::cout << "States:" << std::endl;
+    for (int i = 0; i < 13; i++) {
+        std::cout << i << " has " << dataset.states.at(features[i]).size() << " states." << std::endl;
+    }
+    auto clf = bayesnet::TANLd();
+    clf.fit(dataset.Xt, dataset.yt, dataset.features, dataset.className, dataset.states, dataset.smoothing);
+    std::cout << "Score: " << clf.score(dataset.Xt, dataset.yt) << std::endl;
+}
--- a/tests/TestModulesVersions.cc
+++ b/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" }
--- a/tests/TestUtils.cc
+++ b/tests/TestUtils.cc
@@ -5,6 +5,7 @@
 // ***************************************************************

 #include <random>
+#include <nlohmann/json.hpp>
 #include "TestUtils.h"
 #include "bayesnet/config.h"

@@ -51,6 +52,7 @@ private:

 RawDatasets::RawDatasets(const std::string& file_name, bool discretize_, int num_samples_, bool shuffle_, bool class_last, bool debug)
 {
+    catalog = loadCatalog();
    num_samples = num_samples_;
    shuffle = shuffle_;
    discretize = discretize_;
@@ -62,7 +64,7 @@ RawDatasets::RawDatasets(const std::string& file_name, bool discretize_, int num
    nSamples = dataset.size(1);
    weights = torch::full({ nSamples }, 1.0 / nSamples, torch::kDouble);
    weightsv = std::vector<double>(nSamples, 1.0 / nSamples);
-    classNumStates = discretize ? states.at(className).size() : 0;
+    classNumStates = states.at(className).size();
    auto fold = folding::StratifiedKFold(5, yt, 271);
    auto [train, test] = fold.getFold(0);
    auto train_t = torch::tensor(train);
@@ -78,18 +80,90 @@ RawDatasets::RawDatasets(const std::string& file_name, bool discretize_, int num

 map<std::string, int> RawDatasets::discretizeDataset(std::vector<mdlp::samples_t>& X)
 {
-
    map<std::string, int> maxes;
    auto fimdlp = mdlp::CPPFImdlp();
    for (int i = 0; i < X.size(); i++) {
+        mdlp::labels_t xd;
+        if (is_numeric.at(i)) {
            fimdlp.fit(X[i], yv);
-        mdlp::labels_t& xd = fimdlp.transform(X[i]);
+            xd = fimdlp.transform(X[i]);
+        } else {
+            std::transform(X[i].begin(), X[i].end(), back_inserter(xd), [](const auto& val) {
+                return static_cast<int>(val);
+                });
+        }
        maxes[features[i]] = *max_element(xd.begin(), xd.end()) + 1;
        Xv.push_back(xd);
    }
    return maxes;
 }

+map<std::string, std::vector<int>> RawDatasets::loadCatalog()
+{
+    map<std::string, std::vector<int>> catalogNames;
+    ifstream catalog(Paths::datasets() + "all.txt");
+    std::vector<int> numericFeaturesIdx;
+    if (!catalog.is_open()) {
+        throw std::invalid_argument("Unable to open catalog file. [" + Paths::datasets() + +"all.txt" + "]");
+    }
+    std::string line;
+    std::vector<std::string> sorted_lines;
+    while (getline(catalog, line)) {
+        if (line.empty() || line[0] == '#') {
+            continue;
+        }
+        sorted_lines.push_back(line);
+    }
+    sort(sorted_lines.begin(), sorted_lines.end(), [](const auto& lhs, const auto& rhs) {
+        const auto result = mismatch(lhs.cbegin(), lhs.cend(), rhs.cbegin(), rhs.cend(), [](const auto& lhs, const auto& rhs) {return tolower(lhs) == tolower(rhs);});
+
+        return result.second != rhs.cend() && (result.first == lhs.cend() || tolower(*result.first) < tolower(*result.second));
+        });
+
+    for (const auto& line : sorted_lines) {
+        std::vector<std::string> tokens = split(line, ';');
+        std::string name = tokens[0];
+        std::string className;
+        numericFeaturesIdx.clear();
+        int size = tokens.size();
+        switch (size) {
+            case 1:
+                className = "-1";
+                numericFeaturesIdx.push_back(-1);
+                break;
+            case 2:
+                className = tokens[1];
+                numericFeaturesIdx.push_back(-1);
+                break;
+            case 3:
+                {
+                    className = tokens[1];
+                    auto numericFeatures = tokens[2];
+                    if (numericFeatures == "all") {
+                        numericFeaturesIdx.push_back(-1);
+                    } else {
+                        if (numericFeatures != "none") {
+                            auto features = nlohmann::json::parse(numericFeatures);
+                            for (auto& f : features) {
+                                numericFeaturesIdx.push_back(f);
+                            }
+                        }
+                    }
+                }
+                break;
+            default:
+                throw std::invalid_argument("Invalid catalog file format.");
+
+        }
+        catalogNames[name] = numericFeaturesIdx;
+    }
+    catalog.close();
+    if (catalogNames.empty()) {
+        throw std::invalid_argument("Catalog is empty. Please check the catalog file.");
+    }
+    return catalogNames;
+}
+
 void RawDatasets::loadDataset(const std::string& name, bool class_last)
 {
    auto handler = ShuffleArffFiles(num_samples, shuffle);
@@ -101,6 +175,26 @@ 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);
+    if (numericFeaturesIdx.empty()) {
+        // no numeric features
+        is_numeric.assign(features.size(), false);
+    } else {
+        if (numericFeaturesIdx[0] == -1) {
+            // all features are numeric
+            is_numeric.assign(features.size(), true);
+        } else {
+            // some features are numeric
+            is_numeric.assign(features.size(), false);
+            for (const auto& idx : numericFeaturesIdx) {
+                if (idx >= 0 && idx < features.size()) {
+                    is_numeric[idx] = true;
+                }
+            }
+        }
+    }
    // Discretize Dataset
    auto maxValues = discretizeDataset(X);
    maxValues[className] = *max_element(yv.begin(), yv.end()) + 1;
@@ -113,13 +207,23 @@ void RawDatasets::loadDataset(const std::string& name, bool class_last)
            Xt.index_put_({ i, "..." }, torch::tensor(Xv[i], torch::kInt32));
        }
        states[className] = std::vector<int>(maxValues[className]);
-        iota(begin(states.at(className)), end(states.at(className)), 0);
    } else {
        Xt = torch::zeros({ static_cast<int>(X.size()), static_cast<int>(X[0].size()) }, torch::kFloat32);
        for (int i = 0; i < features.size(); ++i) {
            Xt.index_put_({ i, "..." }, torch::tensor(X[i]));
+            if (!is_numeric.at(i)) {
+                states[features[i]] = std::vector<int>(maxValues[features[i]]);
+                iota(begin(states.at(features[i])), end(states.at(features[i])), 0);
+            } else {
+                states[features[i]] = std::vector<int>();
            }
        }
        yt = torch::tensor(yv, torch::kInt32);
+        int maxy = *max_element(yv.begin(), yv.end()) + 1;
+        states[className] = std::vector<int>(maxy);
+    }
+    iota(begin(states.at(className)), end(states.at(className)), 0);
+    yt = torch::tensor(yv, torch::kInt32);
+
 }

--- a/tests/TestUtils.h
+++ b/tests/TestUtils.h
@@ -27,7 +27,11 @@ 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
+    map<std::string, std::vector<int>> catalog;
    int nSamples, classNumStates;
    double epsilon = 1e-5;
    bool discretize;
@@ -65,8 +69,30 @@ private:
            + "classNumStates: " + std::to_string(classNumStates) + "\n"
            + "states: " + states_ + "\n";
    }
+    std::string trim(const std::string& str)
+    {
+        std::string result = str;
+        result.erase(result.begin(), std::find_if(result.begin(), result.end(), [](int ch) {
+            return !std::isspace(ch);
+            }));
+        result.erase(std::find_if(result.rbegin(), result.rend(), [](int ch) {
+            return !std::isspace(ch);
+            }).base(), result.end());
+        return result;
+    }
+    std::vector<std::string> split(const std::string& text, char delimiter)
+    {
+        std::vector<std::string> result;
+        std::stringstream ss(text);
+        std::string token;
+        while (std::getline(ss, token, delimiter)) {
+            result.push_back(trim(token));
+        }
+        return result;
+    }
    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();
 };

 #endif //TEST_UTILS_H
--- a/tests/data/all.txt
+++ b/tests/data/all.txt
@@ -0,0 +1,27 @@
+adult;class;[0,2,4,10,11,12]
+balance-scale;class; all
+breast-w;Class; all
+diabetes;class; all
+ecoli;class; all
+glass;Type; all
+hayes-roth;class; none
+heart-statlog;class; [0,3,4,7,9,11]
+ionosphere;class; all
+iris;class; all
+kdd_JapaneseVowels;speaker; all
+letter;class; all
+liver-disorders;selector; all
+mfeat-factors;class; all
+mfeat-fourier;class; all
+mfeat-karhunen;class; all
+mfeat-morphological;class; all
+mfeat-zernike;class; all
+optdigits;class; all
+page-blocks;class; all
+pendigits;class; all
+segment;class; all
+sonar;Class; all
+spambase;class; all
+vehicle;Class; all
+waveform-5000;class; all
+wine;class; all
--- a/tests/data/heart-statlog.arff
+++ b/tests/data/heart-statlog.arff
@@ -0,0 +1,338 @@
+% This database contains 13 attributes (which have been extracted from
+% a larger set of 75)       
+%   
+% 
+% 
+% Attribute Information:
+% ------------------------
+%      0 -- 1. age       
+%      1 -- 2. sex       
+%      2 -- 3. chest pain type  (4 values)       
+%      3 -- 4. resting blood pressure  
+%      4 -- 5. serum cholestoral in mg/dl      
+%      5 -- 6. fasting blood sugar > 120 mg/dl       
+%      6 -- 7. resting electrocardiographic results  (values 0,1,2) 
+%      7 -- 8. maximum heart rate achieved  
+%      8 -- 9. exercise induced angina    
+%      9 -- 10. oldpeak = ST depression induced by exercise relative to rest   
+%     10 -- 11. the slope of the peak exercise ST segment     
+%     11 -- 12. number of major vessels (0-3) colored by flourosopy        
+%     12 -- 13.  thal: 3 = normal; 6 = fixed defect; 7 = reversable defect     
+% 
+% Attributes types
+% -----------------
+% 
+% Real: 1,4,5,8,10,12
+% Ordered:11,
+% Binary: 2,6,9
+% Nominal:7,3,13
+% 
+% Variable to be predicted
+% ------------------------
+% Absence (1) or presence (2) of heart disease
+% 
+% Cost Matrix
+% 
+%          abse  pres
+% absence   0     1
+% presence  5     0
+% 
+% where the rows represent the true values and the columns the predicted.
+% 
+% No missing values.
+% 
+% 270 observations
+%
+%
+%
+%
+% Relabeled values in attribute class
+%    From: 1                       To: absent              
+%    From: 2                       To: present             
+%
+@relation heart-statlog
+@attribute age real
+@attribute sex real
+@attribute chest real
+@attribute resting_blood_pressure real
+@attribute serum_cholestoral real
+@attribute fasting_blood_sugar real
+@attribute resting_electrocardiographic_results real
+@attribute maximum_heart_rate_achieved real
+@attribute exercise_induced_angina real
+@attribute oldpeak real
+@attribute slope real
+@attribute number_of_major_vessels real
+@attribute thal real
+@attribute class { absent, present}
+@data
+70,1,4,130,322,0,2,109,0,2.4,2,3,3,present
+67,0,3,115,564,0,2,160,0,1.6,2,0,7,absent
+57,1,2,124,261,0,0,141,0,0.3,1,0,7,present
+64,1,4,128,263,0,0,105,1,0.2,2,1,7,absent
+74,0,2,120,269,0,2,121,1,0.2,1,1,3,absent
+65,1,4,120,177,0,0,140,0,0.4,1,0,7,absent
+56,1,3,130,256,1,2,142,1,0.6,2,1,6,present
+59,1,4,110,239,0,2,142,1,1.2,2,1,7,present
+60,1,4,140,293,0,2,170,0,1.2,2,2,7,present
+63,0,4,150,407,0,2,154,0,4,2,3,7,present
+59,1,4,135,234,0,0,161,0,0.5,2,0,7,absent
+53,1,4,142,226,0,2,111,1,0,1,0,7,absent
+44,1,3,140,235,0,2,180,0,0,1,0,3,absent
+61,1,1,134,234,0,0,145,0,2.6,2,2,3,present
+57,0,4,128,303,0,2,159,0,0,1,1,3,absent
+71,0,4,112,149,0,0,125,0,1.6,2,0,3,absent
+46,1,4,140,311,0,0,120,1,1.8,2,2,7,present
+53,1,4,140,203,1,2,155,1,3.1,3,0,7,present
+64,1,1,110,211,0,2,144,1,1.8,2,0,3,absent
+40,1,1,140,199,0,0,178,1,1.4,1,0,7,absent
+67,1,4,120,229,0,2,129,1,2.6,2,2,7,present
+48,1,2,130,245,0,2,180,0,0.2,2,0,3,absent
+43,1,4,115,303,0,0,181,0,1.2,2,0,3,absent
+47,1,4,112,204,0,0,143,0,0.1,1,0,3,absent
+54,0,2,132,288,1,2,159,1,0,1,1,3,absent
+48,0,3,130,275,0,0,139,0,0.2,1,0,3,absent
+46,0,4,138,243,0,2,152,1,0,2,0,3,absent
+51,0,3,120,295,0,2,157,0,0.6,1,0,3,absent
+58,1,3,112,230,0,2,165,0,2.5,2,1,7,present
+71,0,3,110,265,1,2,130,0,0,1,1,3,absent
+57,1,3,128,229,0,2,150,0,0.4,2,1,7,present
+66,1,4,160,228,0,2,138,0,2.3,1,0,6,absent
+37,0,3,120,215,0,0,170,0,0,1,0,3,absent
+59,1,4,170,326,0,2,140,1,3.4,3,0,7,present
+50,1,4,144,200,0,2,126,1,0.9,2,0,7,present
+48,1,4,130,256,1,2,150,1,0,1,2,7,present
+61,1,4,140,207,0,2,138,1,1.9,1,1,7,present
+59,1,1,160,273,0,2,125,0,0,1,0,3,present
+42,1,3,130,180,0,0,150,0,0,1,0,3,absent
+48,1,4,122,222,0,2,186,0,0,1,0,3,absent
+40,1,4,152,223,0,0,181,0,0,1,0,7,present
+62,0,4,124,209,0,0,163,0,0,1,0,3,absent
+44,1,3,130,233,0,0,179,1,0.4,1,0,3,absent
+46,1,2,101,197,1,0,156,0,0,1,0,7,absent
+59,1,3,126,218,1,0,134,0,2.2,2,1,6,present
+58,1,3,140,211,1,2,165,0,0,1,0,3,absent
+49,1,3,118,149,0,2,126,0,0.8,1,3,3,present
+44,1,4,110,197,0,2,177,0,0,1,1,3,present
+66,1,2,160,246,0,0,120,1,0,2,3,6,present
+65,0,4,150,225,0,2,114,0,1,2,3,7,present
+42,1,4,136,315,0,0,125,1,1.8,2,0,6,present
+52,1,2,128,205,1,0,184,0,0,1,0,3,absent
+65,0,3,140,417,1,2,157,0,0.8,1,1,3,absent
+63,0,2,140,195,0,0,179,0,0,1,2,3,absent
+45,0,2,130,234,0,2,175,0,0.6,2,0,3,absent
+41,0,2,105,198,0,0,168,0,0,1,1,3,absent
+61,1,4,138,166,0,2,125,1,3.6,2,1,3,present
+60,0,3,120,178,1,0,96,0,0,1,0,3,absent
+59,0,4,174,249,0,0,143,1,0,2,0,3,present
+62,1,2,120,281,0,2,103,0,1.4,2,1,7,present
+57,1,3,150,126,1,0,173,0,0.2,1,1,7,absent
+51,0,4,130,305,0,0,142,1,1.2,2,0,7,present
+44,1,3,120,226,0,0,169,0,0,1,0,3,absent
+60,0,1,150,240,0,0,171,0,0.9,1,0,3,absent
+63,1,1,145,233,1,2,150,0,2.3,3,0,6,absent
+57,1,4,150,276,0,2,112,1,0.6,2,1,6,present
+51,1,4,140,261,0,2,186,1,0,1,0,3,absent
+58,0,2,136,319,1,2,152,0,0,1,2,3,present
+44,0,3,118,242,0,0,149,0,0.3,2,1,3,absent
+47,1,3,108,243,0,0,152,0,0,1,0,3,present
+61,1,4,120,260,0,0,140,1,3.6,2,1,7,present
+57,0,4,120,354,0,0,163,1,0.6,1,0,3,absent
+70,1,2,156,245,0,2,143,0,0,1,0,3,absent
+76,0,3,140,197,0,1,116,0,1.1,2,0,3,absent
+67,0,4,106,223,0,0,142,0,0.3,1,2,3,absent
+45,1,4,142,309,0,2,147,1,0,2,3,7,present
+45,1,4,104,208,0,2,148,1,3,2,0,3,absent
+39,0,3,94,199,0,0,179,0,0,1,0,3,absent
+42,0,3,120,209,0,0,173,0,0,2,0,3,absent
+56,1,2,120,236,0,0,178,0,0.8,1,0,3,absent
+58,1,4,146,218,0,0,105,0,2,2,1,7,present
+35,1,4,120,198,0,0,130,1,1.6,2,0,7,present
+58,1,4,150,270,0,2,111,1,0.8,1,0,7,present
+41,1,3,130,214,0,2,168,0,2,2,0,3,absent
+57,1,4,110,201,0,0,126,1,1.5,2,0,6,absent
+42,1,1,148,244,0,2,178,0,0.8,1,2,3,absent
+62,1,2,128,208,1,2,140,0,0,1,0,3,absent
+59,1,1,178,270,0,2,145,0,4.2,3,0,7,absent
+41,0,2,126,306,0,0,163,0,0,1,0,3,absent
+50,1,4,150,243,0,2,128,0,2.6,2,0,7,present
+59,1,2,140,221,0,0,164,1,0,1,0,3,absent
+61,0,4,130,330,0,2,169,0,0,1,0,3,present
+54,1,4,124,266,0,2,109,1,2.2,2,1,7,present
+54,1,4,110,206,0,2,108,1,0,2,1,3,present
+52,1,4,125,212,0,0,168,0,1,1,2,7,present
+47,1,4,110,275,0,2,118,1,1,2,1,3,present
+66,1,4,120,302,0,2,151,0,0.4,2,0,3,absent
+58,1,4,100,234,0,0,156,0,0.1,1,1,7,present
+64,0,3,140,313,0,0,133,0,0.2,1,0,7,absent
+50,0,2,120,244,0,0,162,0,1.1,1,0,3,absent
+44,0,3,108,141,0,0,175,0,0.6,2,0,3,absent
+67,1,4,120,237,0,0,71,0,1,2,0,3,present
+49,0,4,130,269,0,0,163,0,0,1,0,3,absent
+57,1,4,165,289,1,2,124,0,1,2,3,7,present
+63,1,4,130,254,0,2,147,0,1.4,2,1,7,present
+48,1,4,124,274,0,2,166,0,0.5,2,0,7,present
+51,1,3,100,222,0,0,143,1,1.2,2,0,3,absent
+60,0,4,150,258,0,2,157,0,2.6,2,2,7,present
+59,1,4,140,177,0,0,162,1,0,1,1,7,present
+45,0,2,112,160,0,0,138,0,0,2,0,3,absent
+55,0,4,180,327,0,1,117,1,3.4,2,0,3,present
+41,1,2,110,235,0,0,153,0,0,1,0,3,absent
+60,0,4,158,305,0,2,161,0,0,1,0,3,present
+54,0,3,135,304,1,0,170,0,0,1,0,3,absent
+42,1,2,120,295,0,0,162,0,0,1,0,3,absent
+49,0,2,134,271,0,0,162,0,0,2,0,3,absent
+46,1,4,120,249,0,2,144,0,0.8,1,0,7,present
+56,0,4,200,288,1,2,133,1,4,3,2,7,present
+66,0,1,150,226,0,0,114,0,2.6,3,0,3,absent
+56,1,4,130,283,1,2,103,1,1.6,3,0,7,present
+49,1,3,120,188,0,0,139,0,2,2,3,7,present
+54,1,4,122,286,0,2,116,1,3.2,2,2,3,present
+57,1,4,152,274,0,0,88,1,1.2,2,1,7,present
+65,0,3,160,360,0,2,151,0,0.8,1,0,3,absent
+54,1,3,125,273,0,2,152,0,0.5,3,1,3,absent
+54,0,3,160,201,0,0,163,0,0,1,1,3,absent
+62,1,4,120,267,0,0,99,1,1.8,2,2,7,present
+52,0,3,136,196,0,2,169,0,0.1,2,0,3,absent
+52,1,2,134,201,0,0,158,0,0.8,1,1,3,absent
+60,1,4,117,230,1,0,160,1,1.4,1,2,7,present
+63,0,4,108,269,0,0,169,1,1.8,2,2,3,present
+66,1,4,112,212,0,2,132,1,0.1,1,1,3,present
+42,1,4,140,226,0,0,178,0,0,1,0,3,absent
+64,1,4,120,246,0,2,96,1,2.2,3,1,3,present
+54,1,3,150,232,0,2,165,0,1.6,1,0,7,absent
+46,0,3,142,177,0,2,160,1,1.4,3,0,3,absent
+67,0,3,152,277,0,0,172,0,0,1,1,3,absent
+56,1,4,125,249,1,2,144,1,1.2,2,1,3,present
+34,0,2,118,210,0,0,192,0,0.7,1,0,3,absent
+57,1,4,132,207,0,0,168,1,0,1,0,7,absent
+64,1,4,145,212,0,2,132,0,2,2,2,6,present
+59,1,4,138,271,0,2,182,0,0,1,0,3,absent
+50,1,3,140,233,0,0,163,0,0.6,2,1,7,present
+51,1,1,125,213,0,2,125,1,1.4,1,1,3,absent
+54,1,2,192,283,0,2,195,0,0,1,1,7,present
+53,1,4,123,282,0,0,95,1,2,2,2,7,present
+52,1,4,112,230,0,0,160,0,0,1,1,3,present
+40,1,4,110,167,0,2,114,1,2,2,0,7,present
+58,1,3,132,224,0,2,173,0,3.2,1,2,7,present
+41,0,3,112,268,0,2,172,1,0,1,0,3,absent
+41,1,3,112,250,0,0,179,0,0,1,0,3,absent
+50,0,3,120,219,0,0,158,0,1.6,2,0,3,absent
+54,0,3,108,267,0,2,167,0,0,1,0,3,absent
+64,0,4,130,303,0,0,122,0,2,2,2,3,absent
+51,0,3,130,256,0,2,149,0,0.5,1,0,3,absent
+46,0,2,105,204,0,0,172,0,0,1,0,3,absent
+55,1,4,140,217,0,0,111,1,5.6,3,0,7,present
+45,1,2,128,308,0,2,170,0,0,1,0,3,absent
+56,1,1,120,193,0,2,162,0,1.9,2,0,7,absent
+66,0,4,178,228,1,0,165,1,1,2,2,7,present
+38,1,1,120,231,0,0,182,1,3.8,2,0,7,present
+62,0,4,150,244,0,0,154,1,1.4,2,0,3,present
+55,1,2,130,262,0,0,155,0,0,1,0,3,absent
+58,1,4,128,259,0,2,130,1,3,2,2,7,present
+43,1,4,110,211,0,0,161,0,0,1,0,7,absent
+64,0,4,180,325,0,0,154,1,0,1,0,3,absent
+50,0,4,110,254,0,2,159,0,0,1,0,3,absent
+53,1,3,130,197,1,2,152,0,1.2,3,0,3,absent
+45,0,4,138,236,0,2,152,1,0.2,2,0,3,absent
+65,1,1,138,282,1,2,174,0,1.4,2,1,3,present
+69,1,1,160,234,1,2,131,0,0.1,2,1,3,absent
+69,1,3,140,254,0,2,146,0,2,2,3,7,present
+67,1,4,100,299,0,2,125,1,0.9,2,2,3,present
+68,0,3,120,211,0,2,115,0,1.5,2,0,3,absent
+34,1,1,118,182,0,2,174,0,0,1,0,3,absent
+62,0,4,138,294,1,0,106,0,1.9,2,3,3,present
+51,1,4,140,298,0,0,122,1,4.2,2,3,7,present
+46,1,3,150,231,0,0,147,0,3.6,2,0,3,present
+67,1,4,125,254,1,0,163,0,0.2,2,2,7,present
+50,1,3,129,196,0,0,163,0,0,1,0,3,absent
+42,1,3,120,240,1,0,194,0,0.8,3,0,7,absent
+56,0,4,134,409,0,2,150,1,1.9,2,2,7,present
+41,1,4,110,172,0,2,158,0,0,1,0,7,present
+42,0,4,102,265,0,2,122,0,0.6,2,0,3,absent
+53,1,3,130,246,1,2,173,0,0,1,3,3,absent
+43,1,3,130,315,0,0,162,0,1.9,1,1,3,absent
+56,1,4,132,184,0,2,105,1,2.1,2,1,6,present
+52,1,4,108,233,1,0,147,0,0.1,1,3,7,absent
+62,0,4,140,394,0,2,157,0,1.2,2,0,3,absent
+70,1,3,160,269,0,0,112,1,2.9,2,1,7,present
+54,1,4,140,239,0,0,160,0,1.2,1,0,3,absent
+70,1,4,145,174,0,0,125,1,2.6,3,0,7,present
+54,1,2,108,309,0,0,156,0,0,1,0,7,absent
+35,1,4,126,282,0,2,156,1,0,1,0,7,present
+48,1,3,124,255,1,0,175,0,0,1,2,3,absent
+55,0,2,135,250,0,2,161,0,1.4,2,0,3,absent
+58,0,4,100,248,0,2,122,0,1,2,0,3,absent
+54,0,3,110,214,0,0,158,0,1.6,2,0,3,absent
+69,0,1,140,239,0,0,151,0,1.8,1,2,3,absent
+77,1,4,125,304,0,2,162,1,0,1,3,3,present
+68,1,3,118,277,0,0,151,0,1,1,1,7,absent
+58,1,4,125,300,0,2,171,0,0,1,2,7,present
+60,1,4,125,258,0,2,141,1,2.8,2,1,7,present
+51,1,4,140,299,0,0,173,1,1.6,1,0,7,present
+55,1,4,160,289,0,2,145,1,0.8,2,1,7,present
+52,1,1,152,298,1,0,178,0,1.2,2,0,7,absent
+60,0,3,102,318,0,0,160,0,0,1,1,3,absent
+58,1,3,105,240,0,2,154,1,0.6,2,0,7,absent
+64,1,3,125,309,0,0,131,1,1.8,2,0,7,present
+37,1,3,130,250,0,0,187,0,3.5,3,0,3,absent
+59,1,1,170,288,0,2,159,0,0.2,2,0,7,present
+51,1,3,125,245,1,2,166,0,2.4,2,0,3,absent
+43,0,3,122,213,0,0,165,0,0.2,2,0,3,absent
+58,1,4,128,216,0,2,131,1,2.2,2,3,7,present
+29,1,2,130,204,0,2,202,0,0,1,0,3,absent
+41,0,2,130,204,0,2,172,0,1.4,1,0,3,absent
+63,0,3,135,252,0,2,172,0,0,1,0,3,absent
+51,1,3,94,227,0,0,154,1,0,1,1,7,absent
+54,1,3,120,258,0,2,147,0,0.4,2,0,7,absent
+44,1,2,120,220,0,0,170,0,0,1,0,3,absent
+54,1,4,110,239,0,0,126,1,2.8,2,1,7,present
+65,1,4,135,254,0,2,127,0,2.8,2,1,7,present
+57,1,3,150,168,0,0,174,0,1.6,1,0,3,absent
+63,1,4,130,330,1,2,132,1,1.8,1,3,7,present
+35,0,4,138,183,0,0,182,0,1.4,1,0,3,absent
+41,1,2,135,203,0,0,132,0,0,2,0,6,absent
+62,0,3,130,263,0,0,97,0,1.2,2,1,7,present
+43,0,4,132,341,1,2,136,1,3,2,0,7,present
+58,0,1,150,283,1,2,162,0,1,1,0,3,absent
+52,1,1,118,186,0,2,190,0,0,2,0,6,absent
+61,0,4,145,307,0,2,146,1,1,2,0,7,present
+39,1,4,118,219,0,0,140,0,1.2,2,0,7,present
+45,1,4,115,260,0,2,185,0,0,1,0,3,absent
+52,1,4,128,255,0,0,161,1,0,1,1,7,present
+62,1,3,130,231,0,0,146,0,1.8,2,3,7,absent
+62,0,4,160,164,0,2,145,0,6.2,3,3,7,present
+53,0,4,138,234,0,2,160,0,0,1,0,3,absent
+43,1,4,120,177,0,2,120,1,2.5,2,0,7,present
+47,1,3,138,257,0,2,156,0,0,1,0,3,absent
+52,1,2,120,325,0,0,172,0,0.2,1,0,3,absent
+68,1,3,180,274,1,2,150,1,1.6,2,0,7,present
+39,1,3,140,321,0,2,182,0,0,1,0,3,absent
+53,0,4,130,264,0,2,143,0,0.4,2,0,3,absent
+62,0,4,140,268,0,2,160,0,3.6,3,2,3,present
+51,0,3,140,308,0,2,142,0,1.5,1,1,3,absent
+60,1,4,130,253,0,0,144,1,1.4,1,1,7,present
+65,1,4,110,248,0,2,158,0,0.6,1,2,6,present
+65,0,3,155,269,0,0,148,0,0.8,1,0,3,absent
+60,1,3,140,185,0,2,155,0,3,2,0,3,present
+60,1,4,145,282,0,2,142,1,2.8,2,2,7,present
+54,1,4,120,188,0,0,113,0,1.4,2,1,7,present
+44,1,2,130,219,0,2,188,0,0,1,0,3,absent
+44,1,4,112,290,0,2,153,0,0,1,1,3,present
+51,1,3,110,175,0,0,123,0,0.6,1,0,3,absent
+59,1,3,150,212,1,0,157,0,1.6,1,0,3,absent
+71,0,2,160,302,0,0,162,0,0.4,1,2,3,absent
+61,1,3,150,243,1,0,137,1,1,2,0,3,absent
+55,1,4,132,353,0,0,132,1,1.2,2,1,7,present
+64,1,3,140,335,0,0,158,0,0,1,0,3,present
+43,1,4,150,247,0,0,171,0,1.5,1,0,3,absent
+58,0,3,120,340,0,0,172,0,0,1,0,3,absent
+60,1,4,130,206,0,2,132,1,2.4,2,2,7,present
+58,1,2,120,284,0,2,160,0,1.8,2,0,3,present
+49,1,2,130,266,0,0,171,0,0.6,1,0,3,absent
+48,1,2,110,229,0,0,168,0,1,3,0,7,present
+52,1,3,172,199,1,0,162,0,0.5,1,0,7,absent
+44,1,2,120,263,0,0,173,0,0,1,0,7,absent
+56,0,2,140,294,0,2,153,0,1.3,2,0,3,absent
+57,1,4,140,192,0,0,148,0,0.4,2,0,6,absent
+67,1,4,160,286,0,2,108,1,1.5,2,3,3,present
Author	SHA1	Message	Date
Ricardo Montañana Gómez	22e846f47f	Fix discrete feature discretizer once they are rediscretized in the algorithm	2025-08-24 12:44:09 +02:00
Ricardo Montañana Gómez	7c01646726	Complete proposal with only discretizing numeric features	2025-08-24 01:09:25 +02:00
Ricardo Montañana Gómez	0c7452e35b	Update fimdlp version and change tests	2025-08-22 20:16:15 +02:00
Ricardo Montañana	74b391907a	Restart proposal	2025-08-21 19:20:03 +02:00
Ricardo Montañana	1aa3b609e5	Fix adult numeric features mistake	2025-08-21 19:01:10 +02:00
Ricardo Montañana	f1a2349245	Fix discretize only numerics in tests	2025-08-21 12:56:41 +02:00
Ricardo Montañana	8578d68c57	Add make info command	2025-08-21 01:21:24 +02:00
Ricardo Montañana	9f9369269a	Fix ld that was discretizing all input features	2025-08-19 12:29:54 +02:00
Ricardo Montañana	89142f8997	Update version number	2025-07-19 22:47:32 +02:00