feat: Add complete Python testing infrastructure with Poetry

.gitignore

@@ -0,0 +1,85 @@
+# 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/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Virtual environments
+venv/
+ENV/
+env/
+.venv/
+.env
+
+# IDEs
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+.DS_Store
+
+# Claude settings
+.claude/*
+
+# Project specific
+models/
+*.pth
+*.pkl
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Note: Do NOT ignore poetry.lock or uv.lock files

pyproject.toml

@@ -0,0 +1,106 @@
+[tool.poetry]
+name = "active-learning-project"
+version = "0.1.0"
+description = "Active learning project for machine learning"
+authors = ["Your Name <your.email@example.com>"]
+readme = "README.md"
+packages = [{include = "*.py"}]
+
+[tool.poetry.dependencies]
+python = "^3.8"
+certifi = ">=2020.6.20"
+numpy = ">=1.18.5"
+Pillow = ">=8.3.2"
+six = ">=1.15.0"
+torch = ">=1.5.0"
+torchvision = ">=0.6.0"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.0"
+
+[tool.poetry.scripts]
+test = "pytest:main"
+tests = "pytest:main"
+
+[tool.pytest.ini_options]
+minversion = "7.0"
+addopts = [
+    "-ra",
+    "--strict-markers",
+    "--cov=.",
+    "--cov-branch",
+    "--cov-report=term-missing",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-fail-under=80",
+    "-vv"
+]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+markers = [
+    "unit: marks tests as unit tests (fast, isolated)",
+    "integration: marks tests as integration tests (may have external dependencies)",
+    "slow: marks tests as slow running"
+]
+filterwarnings = [
+    "error",
+    "ignore::UserWarning",
+    "ignore::DeprecationWarning"
+]
+
+[tool.coverage.run]
+source = ["."]
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/venv/*",
+    "*/.venv/*",
+    "*/virtualenv/*",
+    "*/dist/*",
+    "*/build/*",
+    "*.egg-info/*",
+    "setup.py",
+    "conftest.py",
+    "*/.pytest_cache/*",
+    "*/.coverage*",
+    "*/htmlcov/*",
+    "active_learning.py",
+    "active_learning_basics.py",
+    "advanced_active_learning.py",
+    "diversity_sampling.py",
+    "pytorch_clusters.py",
+    "uncertainty_sampling.py"
+]
+
+[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__.:",
+    "if TYPE_CHECKING:",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod"
+]
+show_missing = true
+precision = 2
+fail_under = 80
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

tests/conftest.py

@@ -0,0 +1,131 @@
+import os
+import sys
+import tempfile
+from pathlib import Path
+from unittest.mock import Mock, patch
+
+import pytest
+import torch
+
+# Add the project root to the Python path
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+
+@pytest.fixture
+def temp_dir():
+    """Create a temporary directory for test files."""
+    with tempfile.TemporaryDirectory() as tmpdir:
+        yield Path(tmpdir)
+
+
+@pytest.fixture
+def mock_model():
+    """Create a mock PyTorch model for testing."""
+    model = Mock()
+    model.eval = Mock(return_value=model)
+    model.train = Mock(return_value=model)
+    model.parameters = Mock(return_value=[torch.zeros(1)])
+    model.state_dict = Mock(return_value={'layer': torch.zeros(1)})
+    return model
+
+
+@pytest.fixture
+def sample_data():
+    """Provide sample data for testing."""
+    return {
+        'features': torch.randn(10, 5),
+        'labels': torch.randint(0, 2, (10,)),
+        'texts': ['sample text'] * 10
+    }
+
+
+@pytest.fixture
+def mock_dataset():
+    """Create a mock dataset for testing."""
+    dataset = Mock()
+    dataset.__len__ = Mock(return_value=100)
+    dataset.__getitem__ = Mock(return_value=(torch.randn(5), 0))
+    return dataset
+
+
+@pytest.fixture
+def csv_data(temp_dir):
+    """Create temporary CSV files for testing."""
+    csv_content = "text,label\nSample text 1,0\nSample text 2,1\n"
+
+    # Create test CSV files
+    for subdir in ['training_data', 'validation_data', 'evaluation_data']:
+        dir_path = temp_dir / subdir
+        dir_path.mkdir()
+
+        for filename in ['related.csv', 'not_related.csv']:
+            file_path = dir_path / filename
+            file_path.write_text(csv_content)
+
+    # Create unlabeled data
+    unlabeled_dir = temp_dir / 'unlabeled_data'
+    unlabeled_dir.mkdir()
+    unlabeled_content = "text\nUnlabeled sample 1\nUnlabeled sample 2\n"
+    (unlabeled_dir / 'unlabeled_data.csv').write_text(unlabeled_content)
+
+    return temp_dir
+
+
+@pytest.fixture
+def mock_config():
+    """Provide a mock configuration object."""
+    return {
+        'batch_size': 32,
+        'learning_rate': 0.001,
+        'epochs': 10,
+        'device': 'cpu',
+        'model_path': 'models/',
+        'random_seed': 42
+    }
+
+
+@pytest.fixture(autouse=True)
+def reset_random_seeds():
+    """Reset random seeds before each test for reproducibility."""
+    import random
+    import numpy as np
+
+    random.seed(42)
+    np.random.seed(42)
+    torch.manual_seed(42)
+    if torch.cuda.is_available():
+        torch.cuda.manual_seed_all(42)
+
+
+@pytest.fixture
+def capture_stdout():
+    """Capture stdout for testing print statements."""
+    from io import StringIO
+
+    captured_output = StringIO()
+    with patch('sys.stdout', new=captured_output):
+        yield captured_output
+
+
+@pytest.fixture
+def mock_file_operations():
+    """Mock file operations for testing."""
+    with patch('builtins.open', create=True) as mock_open:
+        mock_file = Mock()
+        mock_open.return_value.__enter__ = Mock(return_value=mock_file)
+        mock_open.return_value.__exit__ = Mock(return_value=None)
+        yield mock_open, mock_file
+
+
+@pytest.fixture
+def device():
+    """Provide the appropriate device for testing."""
+    return torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+
+# Markers for different test types
+def pytest_configure(config):
+    """Configure pytest with custom markers."""
+    config.addinivalue_line("markers", "unit: Unit tests (fast, isolated)")
+    config.addinivalue_line("markers", "integration: Integration tests")
+    config.addinivalue_line("markers", "slow: Slow running tests")