pyproject.toml

[tool.poetry]
name = "kdp"
# This version is managed by semantic-release and will be updated automatically during release
version = "1.11.2"
documentation = "https://unicolab.github.io/keras-data-processor/"
repository = "https://github.com/UnicoLab/keras-data-processor"
description = "Data Preprocessing model based on Keras preprocessing layers"
authors = ["Piotr Laczkowski <piotr.laczkowski@gmail.com>"]
license = "MIT"
readme = "README.md"
include = ["docs/getting-started/imgs/kdp_logo.png"]

[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

[tool.poetry.dependencies]
python = ">=3.9,<4.0"
tensorflow = "^2.18.0"
tf-keras = "^2.18.0"
numpy = ">=1.22.0"
pandas = "^2.2.0"
loguru = "^0.7.2"
parameterized = "^0.9.0"

[tool.poetry.group.dev.dependencies]
pre-commit = "^3.6.0"
ipython = "^8.8.0"
pytest = "^8.0.0"
pytest-cov = "^4.1.0"
pytest-mock = "^3.12.0"
pytest-xdist = "^3.5.0"
pytest-benchmark = "^4.0.0"
pytest-timeout = "^2.2.0"
pytest-sugar = "^0.9.7"
pytest-html = "^4.1.1"
pytest-parallel = "^0.1.1"
psutil = "^5.9.0"
ipykernel = "^6.29.3"
pydot = "^2.0.0"
scipy = "^1.12.0"

[tool.poetry.group.doc.dependencies]
mkdocs = "^1.5.3"
mkdocs-material = "^9.5.3"
mkdocs-material-extensions = ">=1.3.1"
mkdocs-gen-files = "^0.5.0"
mkdocstrings-python = "^0.9.0"
mkdocstrings = {extras = ["python"], version = "^0.24.0"}
mkdocs-redirects = "^1.2.2"
mike = ">=2.0.0"
griffe = "^0.25.0"

[tool.pytest.ini_options]
python_paths = "kdp"
testpaths = "test"
# Enable maximum parallel execution for ALL tests with optimizations
addopts = [
    "-n", "auto",
    "--strict-markers",
    "--strict-config",
    "--tb=short",
    "--cov=kdp",
    "--cov-report=term-missing:skip-covered",
    "--cov-report=html:htmlcov",
    "--cov-report=xml",
    "--cov-fail-under=75",
    "--durations=10",
    "--timeout=180",
    "--maxfail=10",
    "--disable-warnings"
]
# Test markers for categorization
markers = [
    "unit: Unit tests that run quickly",
    "integration: Integration tests that may take longer",
    "slow: Tests that take a long time to run",
    "fast: Tests that run very quickly",
    "time_series: Time series specific tests",
    "layers: Layer-specific tests",
    "processor: Processor-specific tests",
    "inference: Inference-related tests",
    "performance: Performance benchmark tests"
]
# Minimum version requirements
minversion = "6.0"
# Test discovery patterns
python_files = ["test_*.py", "*_test.py"]
python_classes = ["Test*"]
python_functions = ["test_*"]
# Timeout for individual tests (5 minutes)
timeout = 300
# Parallel execution settings
filterwarnings = [
    "ignore::DeprecationWarning",
    "ignore::PendingDeprecationWarning",
    "ignore::UserWarning:tensorflow.*",
    "ignore::FutureWarning:tensorflow.*"
]

[tool.coverage.run]
branch = true
omit = [
  "*/__init__.py",
  "*/test_*.py",
  "*/tests/*.py",
  "*/conftest.py",
  "*/venv/*",
  "*/virtualenv/*",
  "*/.venv/*",
  "*/.virtualenv/*",
  "*/env/*",
  "*/.env/*",
  "*/setup.py"
]

[tool.coverage.report]
exclude_lines = [
    "pragma: no cover",
    "def __repr__",
    "if self.debug:",
    "raise AssertionError",
    "raise NotImplementedError",
    "if __name__ == '__main__':",
    "logger",
    "try",
    "except",
    "^\\s*self\\.\\w+(:\\s*[^=]+)?\\s*=.*$",
    "continue",
]

[tool.isort]
profile = "black"
line_length = 120
multi_line_output = 3
include_trailing_comma = true
force_grid_wrap = 0
use_parentheses = true
ensure_newline_before_comments = true

[tool.ruff]
line-length = 120
indent-width = 4
target-version = "py311"
extend-unsafe-fixes = ["D"]

[tool.ruff.lint]
# List of rules: https://docs.astral.sh/ruff/rules
select = [
    # flake8-builtins
    "A",
    # flake8-commas
    "COM812",
    # flake8-comprehensions
    "C4",
    # pydocstyle
    "D",
    # pycodestyle
    "E",
    # Pyflakes
    "F",
    # pyupgrade
    "UP",
    # flake8-bugbear
    "B",
    # flake8-simplify
    "SIM",
    # flake8-implicit-str-concat
    "ISC",
    # pep8-naming
    "N",
    # flake8-annotations
    "ANN",
    # flake8-async
    "ASYNC",
    # flake8-bandid selected
    "S",
    # flake8-print
    "T20",
    # flake8-return
    "RET",
    # flake8-simplify
    "SIM",
    # flake8-unused-arguments
    "ARG",
    # flake8-use-pathlib
    "PTH",
    # eradicate
    "ERA",
    # pandas-vet
    "PD",
]
ignore = [
    "D100",
    "D101",
    "D104",
    "D106",
    # missing-type-self
    "ANN101",
    # missing-type-cls
    "ANN102",
    # missing-type-kwargs
    "ANN003",
    # utf-8 encoding skip
    "UP009",
    # First argument of a method should be named `self`
    "N805",
    # 1 blank line required between summary line and description
    "D205",
    # Missing return type annotation for special method `__init__`
    "ANN204",
    # Avoid using the generic variable name `df` for DataFrames
    "PD901",
    # Unnecessary assignment to `df` before `return` statement
    "RET504",
    # commented code
    "ERA001",
    # Star-arg unpacking after a keyword argument is strongly discouraged
    "B026",
    # Missing type annotation for function argument `self`
    "ANN001",
    # Dynamically typed expressions (typing.Any) are disallowed in `wrapper`
    "ANN401",
    # Unnecessary `elif` after `return` statement
    "RET505",
    # Within an `except` clause, raise exceptions with `raise
    "B904",
    "PD013",
]

# Allow fix for all enabled rules (when `--fix`) is provided.
fixable = ["ALL"]
unfixable = []

[tool.ruff.format]
docstring-code-format = true
quote-style = "double"
# Like Black, indent with spaces, rather than tabs.
indent-style = "space"
# Like Black, respect magic trailing commas.
skip-magic-trailing-comma = false
# Like Black, automatically detect the appropriate line ending.
line-ending = "auto"

[tool.ruff.lint.pydocstyle]
convention = "google"

[tool.ruff.lint.per-file-ignores]
"**/{test,docs}/*" = ["ALL"]