feat: Set up comprehensive Python testing infrastructure

.gitignore

@@ -1 +1,92 @@
-.DS_Store
+.DS_Store
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+coverage.xml
+.tox/
+.nox/
+
+# Claude settings
+.claude/*
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Virtual environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# PEP 582
+__pypackages__/
+
+# Celery
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

pyproject.toml

@@ -0,0 +1,76 @@
+[tool.poetry]
+name = "streamlit-auto-filter"
+version = "0.1.0"
+description = "Auto filter dataframes in Streamlit"
+authors = ["Your Name <[email protected]>"]
+readme = "README.md"
+packages = [{include = "streamlit_app.py"}]
+
+[tool.poetry.dependencies]
+python = ">=3.9,<3.9.7 || >3.9.7,<4.0"
+streamlit = "^1.28.0"
+pandas = "^2.0.0"
+
+[tool.poetry.group.test.dependencies]
+pytest = "^7.4.0"
+pytest-cov = "^4.1.0"
+pytest-mock = "^3.11.0"
+
+# Note: Use 'poetry run pytest' for running tests instead of scripts
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py", "*_test.py"]
+python_classes = ["Test*"]
+python_functions = ["test_*"]
+addopts = [
+    "--strict-markers",
+    "--strict-config",
+    "--cov=.",
+    "--cov-report=html:htmlcov",
+    "--cov-report=xml:coverage.xml",
+    "--cov-report=term-missing",
+    "--cov-fail-under=80",
+    "-v"
+]
+markers = [
+    "unit: Unit tests",
+    "integration: Integration tests", 
+    "slow: Slow running tests"
+]
+
+[tool.coverage.run]
+source = ["."]
+omit = [
+    "tests/*",
+    ".venv/*",
+    "venv/*",
+    "*/site-packages/*",
+    "conftest.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__.:",
+    "class .*\\bProtocol\\):",
+    "@(abc\\.)?abstractmethod"
+]
+show_missing = true
+skip_covered = false
+
+[tool.coverage.html]
+directory = "htmlcov"
+
+[tool.coverage.xml]
+output = "coverage.xml"

tests/conftest.py

@@ -0,0 +1,139 @@
+import pytest
+import pandas as pd
+import tempfile
+import os
+from unittest.mock import Mock
+
+
+@pytest.fixture
+def sample_dataframe():
+    """Fixture that provides a sample pandas DataFrame for testing."""
+    return pd.DataFrame({
+        'name': ['Alice', 'Bob', 'Charlie', 'Diana'],
+        'age': [25, 30, 35, 28],
+        'city': ['New York', 'Los Angeles', 'Chicago', 'Houston'],
+        'score': [85.5, 92.0, 78.3, 88.7],
+        'date': pd.to_datetime(['2023-01-01', '2023-02-15', '2023-03-10', '2023-04-22'])
+    })
+
+
+@pytest.fixture
+def empty_dataframe():
+    """Fixture that provides an empty pandas DataFrame."""
+    return pd.DataFrame()
+
+
+@pytest.fixture
+def numeric_dataframe():
+    """Fixture that provides a DataFrame with only numeric columns."""
+    return pd.DataFrame({
+        'col1': [1, 2, 3, 4, 5],
+        'col2': [10.1, 20.2, 30.3, 40.4, 50.5],
+        'col3': [100, 200, 300, 400, 500]
+    })
+
+
+@pytest.fixture
+def categorical_dataframe():
+    """Fixture that provides a DataFrame with categorical columns."""
+    df = pd.DataFrame({
+        'category': ['A', 'B', 'A', 'C', 'B'],
+        'size': ['small', 'medium', 'large', 'small', 'medium']
+    })
+    df['category'] = df['category'].astype('category')
+    df['size'] = df['size'].astype('category')
+    return df
+
+
+@pytest.fixture
+def datetime_dataframe():
+    """Fixture that provides a DataFrame with datetime columns."""
+    return pd.DataFrame({
+        'date1': pd.date_range('2023-01-01', periods=5, freq='D'),
+        'date2': pd.date_range('2023-06-01', periods=5, freq='W'),
+        'value': [1, 2, 3, 4, 5]
+    })
+
+
+@pytest.fixture
+def mixed_types_dataframe():
+    """Fixture that provides a DataFrame with mixed data types."""
+    return pd.DataFrame({
+        'string_col': ['apple', 'banana', 'cherry', 'date'],
+        'int_col': [1, 2, 3, 4],
+        'float_col': [1.1, 2.2, 3.3, 4.4],
+        'bool_col': [True, False, True, False],
+        'date_col': pd.date_range('2023-01-01', periods=4, freq='D')
+    })
+
+
+@pytest.fixture
+def temp_dir():
+    """Fixture that provides a temporary directory."""
+    with tempfile.TemporaryDirectory() as temp_dir:
+        yield temp_dir
+
+
+@pytest.fixture
+def temp_file():
+    """Fixture that provides a temporary file."""
+    with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+        yield temp_file.name
+    os.unlink(temp_file.name)
+
+
+@pytest.fixture
+def mock_streamlit():
+    """Fixture that provides a mock streamlit module."""
+    mock_st = Mock()
+
+    # Mock common streamlit functions
+    mock_st.checkbox = Mock(return_value=True)
+    mock_st.multiselect = Mock(return_value=[])
+    mock_st.columns = Mock(return_value=(Mock(), Mock()))
+    mock_st.slider = Mock(return_value=(0, 100))
+    mock_st.date_input = Mock(return_value=())
+    mock_st.text_input = Mock(return_value="")
+    mock_st.container = Mock()
+    mock_st.dataframe = Mock()
+    mock_st.title = Mock()
+    mock_st.write = Mock()
+
+    return mock_st
+
+
+@pytest.fixture
+def mock_pandas():
+    """Fixture that provides mock pandas functions."""
+    mock_pd = Mock()
+    mock_pd.DataFrame = pd.DataFrame
+    mock_pd.to_datetime = pd.to_datetime
+    mock_pd.read_csv = Mock()
+    return mock_pd
+
+
+@pytest.fixture(autouse=True)
+def reset_environment():
+    """Fixture that resets the environment before each test."""
+    yield
+    # Cleanup code can go here if needed
+
+
+@pytest.fixture
+def large_dataframe():
+    """Fixture that provides a large DataFrame for performance testing."""
+    return pd.DataFrame({
+        'id': range(1000),
+        'value': [i * 2 for i in range(1000)],
+        'category': ['A'] * 500 + ['B'] * 500
+    })
+
+
+@pytest.fixture(params=[
+    pd.DataFrame({'col': [1, 2, 3]}),
+    pd.DataFrame({'col': ['a', 'b', 'c']}),
+    pd.DataFrame({'col': pd.date_range('2023-01-01', periods=3)})
+])
+def parametrized_dataframe(request):
+    """Parametrized fixture that provides different types of DataFrames."""
+    return request.param