rmontanana/mdlp
1
1
Fork 0
mirror of https://github.com/rmontanana/mdlp.git synced 2025-08-16 16:05:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add more tests to cover new integrity checks

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2025-07-02 11:47:52 +02:00
parent 2fe31ee453
commit b9cab7f61c
5 changed files with 130 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
Makefile
View File

@@ -28,11 +28,7 @@ install: ## Install the project
test: ## Build Debug version and run tests
@echo ">>> Building Debug version and running tests..."
@if [ ! -d $(f_debug) ]; then \
$(MAKE) debug; \
else \
echo ">>> Debug build already exists, skipping build."; \
fi
@$(MAKE) debug;
@cp -r tests/datasets $(f_debug)/tests/datasets
@cd $(f_debug)/tests && ctest --output-on-failure -j 8
@cd $(f_debug)/tests && $(lcov) --capture --directory ../ --demangle-cpp --ignore-errors source,source --ignore-errors mismatch --output-file coverage.info >/dev/null 2>&1; \

2
README.md
View File

@@ -1,7 +1,7 @@
[![Build](https://github.com/rmontanana/mdlp/actions/workflows/build.yml/badge.svg)](https://github.com/rmontanana/mdlp/actions/workflows/build.yml)
[![Quality Gate Status](https://sonarcloud.io/api/project_badges/measure?project=rmontanana_mdlp&metric=alert_status)](https://sonarcloud.io/summary/new_code?id=rmontanana_mdlp)
[![Reliability Rating](https://sonarcloud.io/api/project_badges/measure?project=rmontanana_mdlp&metric=reliability_rating)](https://sonarcloud.io/summary/new_code?id=rmontanana_mdlp)
[![Coverage Badge](https://img.shields.io/badge/Coverage-91,5%25-green)](html/index.html)
[![Coverage Badge](https://img.shields.io/badge/Coverage-96,1%25-green)](html/index.html)
[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/rmontanana/mdlp)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14245443.svg)](https://doi.org/10.5281/zenodo.14245443)

17
src/Discretizer.cpp
View File

@@ -17,7 +17,7 @@ namespace mdlp {
if (cutPoints.size() < 2) {
throw std::runtime_error("Discretizer not fitted yet or no valid cut points found");
}
discretizedData.clear();
discretizedData.reserve(data.size());
// CutPoints always have at least two items
@@ -40,9 +40,6 @@ namespace mdlp {
void Discretizer::fit_t(const torch::Tensor& X_, const torch::Tensor& y_)
{
// Validate tensor properties for security
if (!X_.is_contiguous() || !y_.is_contiguous()) {
throw std::invalid_argument("Tensors must be contiguous");
}
if (X_.sizes().size() != 1 || y_.sizes().size() != 1) {
throw std::invalid_argument("Only 1D tensors supported");
}
@@ -58,7 +55,7 @@ namespace mdlp {
if (X_.numel() == 0) {
throw std::invalid_argument("Tensors cannot be empty");
}
auto num_elements = X_.numel();
samples_t X(X_.data_ptr<precision_t>(), X_.data_ptr<precision_t>() + num_elements);
labels_t y(y_.data_ptr<int>(), y_.data_ptr<int>() + num_elements);
@@ -67,9 +64,6 @@ namespace mdlp {
torch::Tensor Discretizer::transform_t(const torch::Tensor& X_)
{
// Validate tensor properties for security
if (!X_.is_contiguous()) {
throw std::invalid_argument("Tensor must be contiguous");
}
if (X_.sizes().size() != 1) {
throw std::invalid_argument("Only 1D tensors supported");
}
@@ -79,7 +73,7 @@ namespace mdlp {
if (X_.numel() == 0) {
throw std::invalid_argument("Tensor cannot be empty");
}
auto num_elements = X_.numel();
samples_t X(X_.data_ptr<precision_t>(), X_.data_ptr<precision_t>() + num_elements);
auto result = transform(X);
@@ -88,9 +82,6 @@ namespace mdlp {
torch::Tensor Discretizer::fit_transform_t(const torch::Tensor& X_, const torch::Tensor& y_)
{
// Validate tensor properties for security
if (!X_.is_contiguous() || !y_.is_contiguous()) {
throw std::invalid_argument("Tensors must be contiguous");
}
if (X_.sizes().size() != 1 || y_.sizes().size() != 1) {
throw std::invalid_argument("Only 1D tensors supported");
}
@@ -106,7 +97,7 @@ namespace mdlp {
if (X_.numel() == 0) {
throw std::invalid_argument("Tensors cannot be empty");
}
auto num_elements = X_.numel();
samples_t X(X_.data_ptr<precision_t>(), X_.data_ptr<precision_t>() + num_elements);
labels_t y(y_.data_ptr<int>(), y_.data_ptr<int>() + num_elements);

115
tests/Discretizer_unittest.cpp
View File

@@ -13,6 +13,15 @@
#include "BinDisc.h"
#include "CPPFImdlp.h"
#define EXPECT_THROW_WITH_MESSAGE(stmt, etype, whatstring) EXPECT_THROW( \
try { \
stmt; \
} catch (const etype& ex) { \
EXPECT_EQ(whatstring, std::string(ex.what())); \
throw; \
} \
, etype)
namespace mdlp {
const float margin = 1e-4;
static std::string set_data_path()
@@ -270,4 +279,110 @@ namespace mdlp {
EXPECT_EQ(computed[i], expected[i]);
}
}
TEST(Discretizer, TransformEmptyData)
{
Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
samples_t empty_data = {};
EXPECT_THROW_WITH_MESSAGE(disc->transform(empty_data), std::invalid_argument, "Data for transformation cannot be empty");
delete disc;
}
TEST(Discretizer, TransformNotFitted)
{
Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
samples_t data = { 1.0f, 2.0f, 3.0f };
EXPECT_THROW_WITH_MESSAGE(disc->transform(data), std::runtime_error, "Discretizer not fitted yet or no valid cut points found");
delete disc;
}
TEST(Discretizer, TensorValidationFit)
{
Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
auto X = torch::tensor({ 1.0f, 2.0f, 3.0f }, torch::kFloat32);
auto y = torch::tensor({ 1, 2, 3 }, torch::kInt32);
// Test non-1D tensors
auto X_2d = torch::tensor({ {1.0f, 2.0f}, {3.0f, 4.0f} }, torch::kFloat32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_t(X_2d, y), std::invalid_argument, "Only 1D tensors supported");
auto y_2d = torch::tensor({ {1, 2}, {3, 4} }, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_t(X, y_2d), std::invalid_argument, "Only 1D tensors supported");
// Test wrong tensor types
auto X_int = torch::tensor({ 1, 2, 3 }, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_t(X_int, y), std::invalid_argument, "X tensor must be Float32 type");
auto y_float = torch::tensor({ 1.0f, 2.0f, 3.0f }, torch::kFloat32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_t(X, y_float), std::invalid_argument, "y tensor must be Int32 type");
// Test mismatched sizes
auto y_short = torch::tensor({ 1, 2 }, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_t(X, y_short), std::invalid_argument, "X and y tensors must have same number of elements");
// Test empty tensors
auto X_empty = torch::tensor({}, torch::kFloat32);
auto y_empty = torch::tensor({}, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_t(X_empty, y_empty), std::invalid_argument, "Tensors cannot be empty");
delete disc;
}
TEST(Discretizer, TensorValidationTransform)
{
Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
// First fit with valid data
auto X_fit = torch::tensor({ 1.0f, 2.0f, 3.0f, 4.0f }, torch::kFloat32);
auto y_fit = torch::tensor({ 1, 2, 3, 4 }, torch::kInt32);
disc->fit_t(X_fit, y_fit);
// Test non-1D tensor
auto X_2d = torch::tensor({ {1.0f, 2.0f}, {3.0f, 4.0f} }, torch::kFloat32);
EXPECT_THROW_WITH_MESSAGE(disc->transform_t(X_2d), std::invalid_argument, "Only 1D tensors supported");
// Test wrong tensor type
auto X_int = torch::tensor({ 1, 2, 3 }, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->transform_t(X_int), std::invalid_argument, "X tensor must be Float32 type");
// Test empty tensor
auto X_empty = torch::tensor({}, torch::kFloat32);
EXPECT_THROW_WITH_MESSAGE(disc->transform_t(X_empty), std::invalid_argument, "Tensor cannot be empty");
delete disc;
}
TEST(Discretizer, TensorValidationFitTransform)
{
Discretizer* disc = new BinDisc(4, strategy_t::UNIFORM);
auto X = torch::tensor({ 1.0f, 2.0f, 3.0f }, torch::kFloat32);
auto y = torch::tensor({ 1, 2, 3 }, torch::kInt32);
// Test non-1D tensors
auto X_2d = torch::tensor({ {1.0f, 2.0f}, {3.0f, 4.0f} }, torch::kFloat32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_transform_t(X_2d, y), std::invalid_argument, "Only 1D tensors supported");
auto y_2d = torch::tensor({ {1, 2}, {3, 4} }, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_transform_t(X, y_2d), std::invalid_argument, "Only 1D tensors supported");
// Test wrong tensor types
auto X_int = torch::tensor({ 1, 2, 3 }, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_transform_t(X_int, y), std::invalid_argument, "X tensor must be Float32 type");
auto y_float = torch::tensor({ 1.0f, 2.0f, 3.0f }, torch::kFloat32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_transform_t(X, y_float), std::invalid_argument, "y tensor must be Int32 type");
// Test mismatched sizes
auto y_short = torch::tensor({ 1, 2 }, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_transform_t(X, y_short), std::invalid_argument, "X and y tensors must have same number of elements");
// Test empty tensors
auto X_empty = torch::tensor({}, torch::kFloat32);
auto y_empty = torch::tensor({}, torch::kInt32);
EXPECT_THROW_WITH_MESSAGE(disc->fit_transform_t(X_empty, y_empty), std::invalid_argument, "Tensors cannot be empty");
delete disc;
}
}

9
tests/FImdlp_unittest.cpp
View File

@@ -167,6 +167,15 @@ namespace mdlp {
indices = { 1, 2, 0 };
}
TEST_F(TestFImdlp, SortIndicesOutOfBounds)
{
// Test for out of bounds exception in sortIndices
samples_t X_long = { 1.0f, 2.0f, 3.0f };
labels_t y_short = { 1, 2 };
EXPECT_THROW_WITH_MESSAGE(sortIndices(X_long, y_short), std::out_of_range, "Index out of bounds in sort comparison");
}
TEST_F(TestFImdlp, TestShortDatasets)
{
vector<precision_t> computed;