pyproject.toml

[build-system]
requires = ["setuptools>=64", "setuptools_scm[toml]>=8"]
build-backend = "setuptools.build_meta"

[project]
name = "skrub"
dynamic = ["version", "readme"]
description = "Prepping tables for machine learning"
authors = [
    { name="Patricio Cerda", email="patricio.cerda@inria.fr"},
]
classifiers = [
    "Development Status :: 4 - Beta",
    "Environment :: Console",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: BSD License",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Topic :: Scientific/Engineering",
    "Topic :: Software Development :: Libraries",
]
requires-python = ">=3.9"
dependencies = [
    "numpy>=1.23.5",
    "packaging>=23.1",
    "pandas>=1.5.3",
    "scikit-learn>=1.2.1",
    "scipy>=1.9.3",
    "jinja2>=3.1.2",
    "matplotlib>=3.4.3",
]

[tool.setuptools.dynamic]
version = { file = "skrub/VERSION.txt" }
readme = { file = "README.rst" }

[project.optional-dependencies]
dev = [
    "ipykernel",
    "ipython",
    "jupyterlab",
]
doc = [
    "jupyterlite-sphinx",
    "jupyterlite-pyodide-kernel",
    "numpydoc",
    "pydata-sphinx-theme",
    "seaborn",
    "sphinx",
    "sphinx-copybutton",
    "sphinx-gallery",
    "sphinxext-opengraph",
    "statsmodels",
    "pyarrow",
]
lint = [
    "black==23.3.0",
    "ruff==0.4.8",
    "pre-commit",
]
optional = [
    "pyarrow",
    "polars",
]
transformers = [
    "sentence-transformers",
]
test = [
    "numpydoc",
    "pytest",
    "pytest-cov",
    "pytest-xdist",
]

[project.urls]
Homepage = "https://skrub-data.org/"
Source = "https://github.com/skrub-data/skrub"
Issues = "https://github.com/skrub-data/skrub/issues"

[tool.setuptools]
packages = ["skrub"]

[tool.pixi.project]
channels = ["conda-forge", "pytorch"]
platforms = ["linux-64", "osx-arm64", "osx-64", "win-64"]

[tool.pixi.dependencies]
numpy = ">=1.23.5"
packaging = ">=23.1"
pandas = ">=1.5.3"
scikit-learn = ">=1.2.1"
scipy = ">=1.9.3"
jinja2 = ">=3.1.2"
matplotlib = ">=3.4.3"

[tool.pixi.feature.doc.dependencies]
jupyterlite-sphinx = "*"
jupyterlite-pyodide-kernel = "*"
matplotlib = "*"
numpydoc = "*"
pydata-sphinx-theme = "*"
seaborn = "*"
sphinx = "*"
sphinx-copybutton = "*"
sphinx-gallery = "*"
sphinxext-opengraph = "*"
statsmodels = "*"

[tool.pixi.feature.lint.dependencies]
black = "==23.3.0"
ruff = "==0.4.8"
pre-commit = "*"

[tool.pixi.feature.optional.dependencies]
pyarrow = "*"
polars = "*"

[tool.pixi.feature.transformers]
# pytorch is not anymore released on osx-64 platform
platforms = ["linux-64", "osx-arm64", "win-64"]

[tool.pixi.feature.transformers.dependencies]
pytorch = { version = ">=2.4.1,<3", channel = "pytorch" }
transformers = "*"
sentence-transformers = ">=3.0,<4"

[tool.pixi.feature.test.dependencies]
numpydoc = "*"
pytest = "*"
pytest-cov = "*"
pytest-xdist = "*"

[tool.pixi.feature.dev.dependencies]
ipykernel = "*"
ipython = "*"
jupyterlab = "*"

[tool.pixi.pypi-dependencies]
skrub = { path = ".", editable = true }

[tool.pixi.feature.min-dependencies.dependencies]
numpy = "==1.23.5"
pandas = "==1.5.3"
scikit-learn = "==1.2.1"
scipy = "==1.9.3"
jinja2 = "==3.1.2"
matplotlib = "==3.4.3"

[tool.pixi.feature.min-optional-dependencies.dependencies]
pyarrow = "==15.0.2"
polars = "==0.20.15"

[tool.pixi.feature.py309.dependencies]
python = "~=3.9.0"

[tool.pixi.feature.py310.dependencies]
python = "~=3.10.0"

[tool.pixi.feature.py311.dependencies]
python = "~=3.11.0"

[tool.pixi.feature.py312.dependencies]
python = "~=3.12.0"

[tool.pixi.feature.doc.tasks]
build-doc = { cmd = "make html", cwd = "doc" }
build-doc-quick = { cmd = "make html-noplot", cwd = "doc" }
clean-doc = { cmd = "rm -rf _build/ && rm -rf auto_examples/ && rm -rf reference/generated/", cwd = "doc" }

[tool.pixi.feature.lint.tasks]
lint = { cmd = "pre-commit install && pre-commit run -v --all-files --show-diff-on-failure" }

[tool.pixi.feature.test.tasks]
test = { cmd = "pytest -vsl --cov=skrub --cov-report=xml skrub" }

[tool.pixi.environments]
lint = ["lint"]
doc = ["optional", "doc", "transformers"]
test = ["optional", "test"]
dev = ["dev", "optional", "doc", "lint", "test", "transformers"]
ci-py309-min-deps = ["py309", "min-dependencies", "test"]
ci-py309-min-optional-deps = ["py309", "min-dependencies", "min-optional-dependencies", "test"]
ci-py311-transformers = ["py311", "transformers", "test"]
ci-py312-latest-deps = ["py312", "test"]
ci-py312-latest-optional-deps = ["py312", "optional", "test"]

[tool.black]
line-length = 88
target_version = ['py310', 'py311']
preview = true
# Exclude irrelevant directories for formatting
exclude = '''
/(
    \.eggs
  | \.git
  | \.mypy_cache
  | \.vscode
  | \.pytest_cache
  | \.idea
  | build
  | dist
)/
'''

[tool.ruff]
# max line length for black
line-length = 88
target-version = "py38"
exclude=[
    ".git",
    "__pycache__",
    "dist",
    "doc/_build",
    "doc/auto_examples",
    "build",
]

[tool.ruff.lint]
# all rules can be found here: https://beta.ruff.rs/docs/rules/
select = ["E", "F", "W", "I"]
ignore=[
    # space before : (needed for how black formats slicing)
    "E203",
    # do not assign a lambda expression, use a def
    "E731",
    # do not use variables named 'l', 'O', or 'I'
    "E741",
]

[tool.ruff.lint.per-file-ignores]
# It's fine not to put the import at the top of the file in the examples
# folder.
"examples/*"=["E402"]
"doc/conf.py"=["E402"]

[tool.pytest.ini_options]
filterwarnings = [
    # Turn deprecation warnings into errors
    "error::FutureWarning",
    "error::DeprecationWarning",

    # Ignore warning from np.in1d since the future behavior is already the desired
    # behavior. TODO remove when numpy min version >= 1.25.
    'ignore:elementwise\ comparison\ failed:FutureWarning',
    # TODO remove when pandas min version >= 2.2.0
    'ignore:.*utcfromtimestamp\(\) is deprecated.*:DeprecationWarning',
    # TODO remove when joblib min version >= 1.4.0
    'ignore:.*ast\.Num is deprecated.*:DeprecationWarning',
    # TODO remove when joblib min version >= 1.4.0
    'ignore:.*ast\.NameConstant is deprecated.*:DeprecationWarning',
    # TODO remove when joblib min version >= 1.4.0
    'ignore:.*Attribute n is deprecated.*:DeprecationWarning',
    # FIXME we need to decided what to do with pyarrow that is required by pandas >= 3.0
    'ignore:(?s).*Pyarrow will become a required dependency of pandas.*:DeprecationWarning',
    # accessing .values on a pandas dataframe raises this warning after numpy 1.25;
    # should be addressed in pandas
    'ignore:np.find_common_type is deprecated.*:DeprecationWarning',
    'ignore:.*distutils Version classes are deprecated.*',
    'ignore:.*`resume_download` is deprecated.*',
    'ignore:.*`clean_up_tokenization_spaces` was not set.*',
    'ignore:The current process just got forked.*',
    'ignore:.*`clean_up_tokenization_spaces` was not set.*',
]
addopts = "--doctest-modules"
doctest_optionflags = "NORMALIZE_WHITESPACE ELLIPSIS"