feat: add comprehensive Python testing infrastructure

.gitignore

@@ -0,0 +1,149 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# PEP 582
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# PyTorch
+*.pth
+*.pt
+
+# Weights and Biases
+wandb/
+
+# IDE files
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Claude Code settings
+.claude/*

pyproject.toml

@@ -0,0 +1,93 @@
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry]
+name = "qualiclip"
+version = "1.0.0"
+description = "Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment"
+authors = ["Lorenzo Agnolucci", "Leonardo Galteri", "Marco Bertini"]
+readme = "README.md"
+homepage = "https://github.com/miccunifi/QualiCLIP"
+repository = "https://github.com/miccunifi/QualiCLIP"
+license = "CC-BY-NC-4.0"
+packages = [{include = "clip"}]
+
+[tool.poetry.dependencies]
+python = "^3.10"
+torch = "2.1.1"
+torchvision = "0.16.1"
+pandas = "2.1.3"
+matplotlib = "3.8.2"
+pyyaml = "6.0.1"
+dotmap = "1.3.30"
+scipy = "1.11.4"
+tqdm = "4.66.1"
+ftfy = "6.1.1"
+regex = "2023.10.3"
+openpyxl = "3.1.2"
+kornia = "0.7.1"
+wandb = "0.16.1"
+einops = "0.7.0"
+scikit-learn = "1.3.2"
+plotly = "5.18.0"
+umap-learn = "0.5.5"
+
+[tool.poetry.group.test.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.1"
+
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "--strict-markers",
+    "--strict-config",
+    "--verbose",
+    "--cov=clip",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-report=term-missing",
+    "--cov-fail-under=80"
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests", 
+    "slow: Slow tests that take longer to run"
+]
+filterwarnings = [
+    "error",
+    "ignore::UserWarning",
+    "ignore::DeprecationWarning"
+]
+
+[tool.coverage.run]
+source = ["clip"]
+omit = [
+    "tests/*",
+    "*/tests/*",
+    "*/__pycache__/*",
+    "*/venv/*",
+    "*/.venv/*"
+]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "if self.debug:",
+    "if settings.DEBUG",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if 0:",
+    "if __name__ == .__main__.:"
+]
+show_missing = true
+precision = 2
+
+[tool.coverage.html]
+directory = "htmlcov"

tests/conftest.py

@@ -0,0 +1,125 @@
+"""Shared pytest fixtures for QualiCLIP testing."""
+
+import os
+import tempfile
+import shutil
+from pathlib import Path
+from typing import Generator, Dict, Any
+import pytest
+import torch
+from PIL import Image
+import numpy as np
+
+
+@pytest.fixture
+def temp_dir() -> Generator[Path, None, None]:
+    """Create a temporary directory for testing."""
+    temp_path = Path(tempfile.mkdtemp())
+    try:
+        yield temp_path
+    finally:
+        shutil.rmtree(temp_path)
+
+
+@pytest.fixture
+def sample_image() -> Image.Image:
+    """Create a sample RGB image for testing."""
+    # Create a simple 224x224 RGB image with random colors
+    np.random.seed(42)  # For reproducible tests
+    image_array = np.random.randint(0, 255, (224, 224, 3), dtype=np.uint8)
+    return Image.fromarray(image_array, mode='RGB')
+
+
+@pytest.fixture
+def sample_image_path(temp_dir: Path, sample_image: Image.Image) -> Path:
+    """Save sample image to temporary file and return path."""
+    image_path = temp_dir / "sample_image.png"
+    sample_image.save(image_path)
+    return image_path
+
+
+@pytest.fixture
+def sample_tensor() -> torch.Tensor:
+    """Create a sample normalized tensor for testing."""
+    torch.manual_seed(42)  # For reproducible tests
+    return torch.randn(1, 3, 224, 224)
+
+
+@pytest.fixture
+def device() -> torch.device:
+    """Get the appropriate device for testing."""
+    return torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+
+@pytest.fixture
+def mock_model_config() -> Dict[str, Any]:
+    """Mock model configuration for testing."""
+    return {
+        "embed_dim": 512,
+        "image_resolution": 224,
+        "vision_layers": 12,
+        "vision_width": 768,
+        "vision_patch_size": 32,
+        "context_length": 77,
+        "vocab_size": 49408,
+        "transformer_width": 512,
+        "transformer_heads": 8,
+        "transformer_layers": 12
+    }
+
+
+@pytest.fixture
+def mock_transforms():
+    """Mock image transforms for testing."""
+    import torchvision.transforms as transforms
+    return transforms.Compose([
+        transforms.ToTensor(),
+        transforms.Normalize(
+            mean=[0.48145466, 0.4578275, 0.40821073], 
+            std=[0.26862954, 0.26130258, 0.27577711]
+        ),
+    ])
+
+
+@pytest.fixture
+def sample_batch_images(sample_tensor: torch.Tensor) -> torch.Tensor:
+    """Create a batch of sample images for testing."""
+    return sample_tensor.repeat(4, 1, 1, 1)  # Batch size of 4
+
+
+@pytest.fixture
+def mock_tokenizer_vocab(temp_dir: Path) -> Path:
+    """Create a mock BPE vocabulary file for testing."""
+    vocab_path = temp_dir / "test_vocab.txt.gz"
+    # Create a minimal vocab file for testing
+    import gzip
+    with gzip.open(vocab_path, 'wt', encoding='utf-8') as f:
+        f.write("hello world\n")
+        f.write("test token\n")
+    return vocab_path
+
+
+@pytest.fixture(autouse=True)
+def cleanup_cuda():
+    """Clean up CUDA memory after each test if available."""
+    yield
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+
+
+@pytest.fixture
+def set_random_seeds():
+    """Set random seeds for reproducible testing."""
+    torch.manual_seed(42)
+    np.random.seed(42)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed(42)
+        torch.cuda.manual_seed_all(42)
+
+
+@pytest.fixture
+def original_working_dir():
+    """Store and restore original working directory."""
+    original_dir = os.getcwd()
+    yield original_dir
+    os.chdir(original_dir)