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"]
keywords = ["keras", "tensorflow", "preprocessing", "tabular", "feature-engineering"]
# Poetry derives the Python-version and license classifiers from the fields
# above; only the ones it cannot infer are listed here.
classifiers = [
    "Development Status :: 4 - Beta",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
]

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

[tool.poetry.dependencies]
# The package uses PEP 604 unions (`X | Y`) in annotations that are evaluated at
# import time, so 3.10 is the real floor -- `import kdp` fails on 3.9.
python = ">=3.10,<4.0"
tensorflow = "^2.18.0"
# Declared explicitly rather than inherited from TensorFlow: the package targets
# the Keras 3 API directly (`import keras`) instead of the `tf.keras`
# compatibility shim, so the requirement belongs here.
keras = ">=3.5,<4.0"
numpy = ">=1.22.0"
pandas = "^2.2.0"
loguru = "^0.7.2"

[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"
parameterized = "^0.9.0"
psutil = "^5.9.0"
ipykernel = "^6.29.3"
pydot = "^2.0.0"
scipy = "^1.12.0"
# Used by the scripts in examples/, which are referenced from the docs and were
# not runnable from a plain `poetry install`.
matplotlib = "^3.8.0"
scikit-learn = "^1.4.0"

[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"

# Pytest is configured by pytest.ini (plus the pytest-fast/parallel/ultrafast
# variants). A [tool.pytest.ini_options] block used to live here too, but
# pytest.ini takes precedence over pyproject.toml, so it never applied -- which
# hid the fact that it set the invalid key `python_paths` (the option is
# `pythonpath`) and omitted the `micro` and `smoke` markers that CI selects
# under --strict-markers.

[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 = 88
multi_line_output = 3
include_trailing_comma = true
force_grid_wrap = 0
use_parentheses = true
ensure_newline_before_comments = true

[tool.ruff]
# Matches the formatter default the codebase is written against.
line-length = 88
indent-width = 4
target-version = "py310"
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.flake8-unused-arguments]
# `layer_creator` callables and Keras hooks accept **kwargs they never read.
ignore-variadic-names = true

[tool.ruff.lint.pycodestyle]
# The formatter wraps code at `line-length`; prose in docstrings and comments is
# allowed to run wider before E501 fires.
max-line-length = 120

[tool.ruff.lint.per-file-ignores]
# `*` does not cross directory separators, so the previous "**/{test,docs}/*"
# pattern silently missed everything under test/layers/ and friends.
"test/**" = ["ALL"]
"docs/**" = ["ALL"]
# Developer entry points: printing to stdout is the point, os.path is fine in a
# one-off script, and they are not part of the published API surface.
"scripts/**" = ["T20", "ANN", "D", "N806", "PTH", "S603", "S607"]
# `X_train` and friends are the conventional ML spelling.
"examples/**" = ["T20", "ANN", "D", "N806", "PTH"]
# Keras fixes the signatures of `call`, `build` and `__init__`: `training` and
# `**kwargs` must be accepted whether or not a given layer reads them, and the
# `tf.while_loop` condition callable must accept the full loop-variable tuple.
"kdp/layers/**" = ["ARG002"]
"kdp/moe.py" = ["ARG002"]