pyproject.toml

[build-system]
build-backend = "setuptools.build_meta"
requires = ["setuptools>=66", "setuptools_scm[toml]>=3.5.0", "wheel"]

[project]
name = "catalystcoop.pudl"
description = "An open data processing pipeline for US energy data"
readme = { file = "README.rst", content-type = "text/x-rst" }
authors = [{ name = "Catalyst Cooperative", email = "pudl@catalyst.coop" }]
requires-python = ">=3.11,<3.12"
dynamic = ["version"]
license = { file = "LICENSE.txt" }
dependencies = [
    "addfips>=0.4",
    "alembic>=1.12",
    "boto3>=1.28.55",
    "bottleneck>=1.3.4", # pandas[performance]
    "build>=1.0",
    "catalystcoop.dbfread>=3.0,<3.1",
    "catalystcoop.ferc-xbrl-extractor>=1.2.0,<2",
    "click>=8.1",
    "coloredlogs>=14.0", # Dagster requires 14.0
    "conda-lock>=2.5.1",
    "coverage>=7",
    "dagster>=1.5.6",
    "dagster-postgres>=0.21.6,<1", # Update when dagster-postgres graduates to 1.x
    "dask>=2023",
    "datapackage>=1.15,<2", # Transition datastore to use frictionless.
    "datasette>=0.64",
    "doc8>=1.1",
    "email-validator>=1.0.3", # pydantic[email]
    "fsspec>=2023",
    "furo>=2022.4.7",
    "gcsfs>=2023",
    "geopandas>=0.14",
    "grpcio==1.59.2", # Required by dagster, binary dependencies are flaky
    "grpcio-health-checking==1.59.2", # Required by dagster, binary dependencies are flaky
    "grpcio-status==1.59.2", # Required by dagster, binary dependencies are flaky
    "hypothesis>=6.87",
    "jinja2>=3.1",
    "jupyter",
    "matplotlib>=3.8",
    "nbconvert>=7",
    "nbformat>=5.9",
    "networkx>=3.2",
    "numba>=0.58", # pandas[performance]
    "numexpr>=2.8.0", # pandas[performance]
    "numpy>=1.26,<2.0a0",
    "openpyxl>=3.0.10", # pandas[excel]
    "pandas>=2.1",
    "pandera>=0.17.2",
    "pre-commit>=3",
    "pyarrow>=14.0.1", # pandas[parquet]
    "pydantic>=2.4",
    "pydantic-settings>=2",
    "pytest>=7.4",
    "pytest-cov>=4.1",
    "pytest-console-scripts>=1.4",
    "pytest-mock>=3.11",
    "pytest-xdist>=3.3",
    "python-dotenv>=1",
    "pyxlsb>=1.0.9", # pandas[excel]
    "pyyaml>=6",
    "readthedocs-sphinx-ext>=2",
    "recordlinkage",
    "responses>=0.23",
    "ruff>=0.1",
    "scikit-learn>=1.3",
    "scipy>=1.11",
    "Shapely>=2",
    "sphinx-autoapi>=3",
    "sphinx-issues>=1.2",
    "sphinx-reredirects>=0.1.2",
    "sphinx>=7",
    "sphinxcontrib_bibtex>=2.6",
    "sqlalchemy>=2",
    "timezonefinder>=6.2",
    "xlrd>=2.0.1", # pandas[excel]
    "xlsxwriter>=3.1", # pandas[excel]
]
classifiers = [
    "Development Status :: 3 - Alpha",
    "Environment :: Console",
    "Intended Audience :: Science/Research",
    "License :: OSI Approved :: MIT License",
    "Natural Language :: English",
    "Operating System :: OS Independent",
    "Programming Language :: Python :: 3 :: Only",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python",
    "Topic :: Scientific/Engineering",
]
keywords = [
    "analysis",
    "climate change",
    "coal",
    "data",
    "economics",
    "eia 860",
    "eia 861",
    "eia 923",
    "electricity",
    "emissions",
    "energy",
    "epa ampd",
    "epa cems",
    "ferc form 1",
    "ferc form 2",
    "ferc form 6",
    "ferc form 60",
    "ferc form 714",
    "finance",
    "fossil fuel",
    "natural gas",
    "oil",
    "policy",
    "utility",
]

[project.scripts]
metadata_to_rst = "pudl.convert.metadata_to_rst:main"
epacems_to_parquet = "pudl.convert.epacems_to_parquet:main"
ferc_to_sqlite = "pudl.ferc_to_sqlite.cli:main"
pudl_datastore = "pudl.workspace.datastore:main"
pudl_etl = "pudl.cli.etl:main"
pudl_setup = "pudl.workspace.setup_cli:main"
state_demand = "pudl.analysis.state_demand:main"
pudl_check_fks = "pudl.etl.check_foreign_keys:main"
# pudl_territories currently blows up memory usage to 100+ GB.
# See https://github.com/catalyst-cooperative/pudl/issues/1174
# pudl_territories = "pudl.analysis.service_territory:main"

[project.urls]
"Homepage" = "https://catalyst.coop/pudl/"
"Source" = "https://github.com/catalyst-cooperative/pudl"
"Documentation" = "https://catalystcoop-pudl.readthedocs.io"
"Release Notes" = "https://catalystcoop-pudl.readthedocs.io/en/latest/release_notes.html"
"Issue Tracker" = "https://github.com/catalyst-cooperative/pudl/issues"
"Support" = "https://github.com/catalyst-cooperative/pudl/discussions"
"Funding" = "https://catalyst.coop/support-the-pudl-project/"

[project.optional-dependencies]
dev = [
    "dagster-webserver>=1.5.6",
    "jupyterlab>3.2",
    "jupyter-resource-usage",
    "pygraphviz",
]

[tool.setuptools]
include-package-data = true

[tool.setuptools.packages.find]
where = ["src"]

[tool.setuptools_scm]

[tool.ruff]
select = [
    "A", # flake8-builtins
    # "ARG", # unused arguments
    # "B", # flake8-bugbear
    "C", # Limit cyclomatic complexity using mccabe
    "D", # pydocstyle errors
    "E", # pycodestyle errors
    "EXE", # executable file issues
    # "ERA", # eradicate: find commented out code
    "F", # pyflakes
    "I", # isort
    "ISC", # implicit string concatenation
    "N", # pep8-naming
    "NPY", # NumPy specific checks
    "PD", # pandas checks
    "PGH", # pygrep-hooks
    # "PL", # pylint
    # "PT", # pytest style
    "PTH", # use pathlib
    "Q", # flake8-quotes
    "RET", # check return values
    "RSE", # unnecessary parenthises on raised exceptions
    "S", # flake8-bandit
    "SIM", # flake8-simplify
    # "T", # print statements found
    "UP", # pyupgrade (use modern python syntax)
    "W", # pycodestyle warnings
]
ignore = [
    "D401", # Require imperative mood in docstrings.
    "D417",
    "E501", # Overlong lines.
    "E203", # Space before ':' (black recommends to ignore)
    "E226", # Missing whitespace around arithmetic operator
    "E266", # Too many leading `#` before block comment
    "PD003", # Use of isna rather than isnull
    "PD004", # Use of notna rather than notnull
    "PD008", # Use of df.at[] rather than df.loc[]
    "PD010", # Use of df.stack()
    "PD013", # Use of df.unstack()
    "PD015", # Use of pd.merge() rather than df.merge()
    "PD901", # df as variable name
    "RET504", # Ignore unnecessary assignment before return
    "S101", # Use of assert
]

# Assume Python 3.11
target-version = "py311"
line-length = 88

# Don't automatically concatenate strings -- sometimes we forget a comma!
unfixable = ["ISC"]

[tool.ruff.format]
quote-style = "double"
exclude = ["migrations/versions/*"]

[tool.ruff.per-file-ignores]
"__init__.py" = ["F401"] # Ignore unused imports
"test/*" = ["D"]
"migrations/*" = ["D", "Q"]

[tool.ruff.isort]
known-first-party = ["pudl"]

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

[tool.ruff.mccabe]
max-complexity = 10

[tool.ruff.flake8-quotes]
docstring-quotes = "double"
inline-quotes = "double"
multiline-quotes = "double"

[tool.doc8]
max-line-length = 88
ignore-path = ["docs/ferc/form1", "docs/_build"]

[tool.pytest.ini_options]
testpaths = "./"
filterwarnings = [
    "ignore:distutils Version classes are deprecated:DeprecationWarning",
    "ignore:Deprecated call to `pkg_resources.declare_namespace:DeprecationWarning",
    "ignore:Deprecated call to.*declare_namespace:DeprecationWarning:pkg_resources",
    "ignore:Deprecated call to:DeprecationWarning:google.rpc",
    "ignore:Feature names only support names:FutureWarning:sklearn.utils.validation",
    "ignore:In a future version, the Index constructor:FutureWarning:pandas.core.reshape.merge",
    "ignore:Integration of FERC 714:UserWarning:pudl.extract.ferc714",
    "ignore:Integration of EIA 861:UserWarning:pudl.extract.eia861",
    "ignore:pkg_resources is deprecated as an API.:DeprecationWarning",
    "ignore:Subclassing validator classes is not intended to be part of their public API.:DeprecationWarning",
    "ignore:Subclassing validator classes:DeprecationWarning:tableschema",
    "ignore:The Shapely GEOS version:UserWarning:geopandas[.*]",
    "ignore:Unknown extension:UserWarning:openpyxl.worksheet[.*]",
    "ignore:The `__fields__` attribute is deprecated:pydantic.PydanticDeprecatedSince20:unittest.mock",
    "ignore:The `__fields_set__` attribute is deprecated:pydantic.PydanticDeprecatedSince20:unittest.mock",
    "ignore:The `__fields__` attribute is deprecated:pydantic.PydanticDeprecatedSince20:pydantic.main",
    "ignore:The `__fields_set__` attribute is deprecated:pydantic.PydanticDeprecatedSince20:pydantic.main",
    "ignore:The `update_forward_refs` method is deprecated:pydantic.PydanticDeprecatedSince20:pydantic.main",
    "ignore:Support for class-based `config` is deprecated:pydantic.PydanticDeprecatedSince20:pydantic._internal._config",
    "ignore:Pydantic V1 style `@validator` validators are deprecated:pydantic.PydanticDeprecatedSince20:ferc_xbrl_extractor.instance",
    "ignore:The `update_forward_refs` method is deprecated:pydantic.PydanticDeprecatedSince20:ferc_xbrl_extractor.taxonomy",
    "once:Could not infer format, so each element will be parsed individually, falling back to `dateutil`.:UserWarning:pudl.extract.eia_bulk_elec",
    "once:In a future version:FutureWarning:pudl.helpers",
    "once:open_binary is deprecated:DeprecationWarning:pudl.glue.ferc1_eia",
    "once:open_text is deprecated:DeprecationWarning:pudl.glue.ferc1_eia",
    "once:The behavior of DataFrame concatenation with empty or all-NA entries is deprecated.:FutureWarning",
]

addopts = "--verbose --pdbcls=IPython.terminal.debugger:TerminalPdb"
log_format = "%(asctime)s [%(levelname)8s] %(name)s:%(lineno)s %(message)s"
log_date_format = "%Y-%m-%d %H:%M:%S"
log_cli = "true"
log_cli_level = "DEBUG"
doctest_optionflags = [
    "NORMALIZE_WHITESPACE",
    "IGNORE_EXCEPTION_DETAIL",
    "ELLIPSIS",
]

[tool.conda-lock]
channels = ["conda-forge", "defaults"]
platforms = [
    # "linux-aarch64",
    "linux-64",
    "osx-64",
    "osx-arm64",
    # "win-64",
]
channel-priority = "strict"
name = "pudl-dev"

[tool.conda-lock.dependencies]
google-cloud-sdk = ">=452"
nodejs = ">=20"
pandoc = ">=2"
pip = ">=23"
prettier = ">=3.0"
python = ">=3.11,<3.12"
sqlite = ">=3.43"
curl = ">=8.4.0"