pyproject.toml

[build-system]
build-backend = "setuptools.build_meta"
requires = ["setuptools>=64.0.0", "setuptools_scm>=6.2.0"]

[project]
name = 'molflux'
description = 'A foundational package for molecular predictive modelling'
readme = 'README.md'
requires-python = '>= 3.10'
authors = [{name = 'Exscientia'}]
maintainers = [{name = 'Exscientia'}]
classifiers = [
    'Development Status :: 4 - Beta',
    'Intended Audience :: Science/Research',
    'Natural Language :: English',
    'Operating System :: OS Independent',
    'Programming Language :: Python',
    'Programming Language :: Python :: 3 :: Only',
    'Programming Language :: Python :: 3.10',
    'Programming Language :: Python :: 3.11',
    'Typing :: Typed',
]

dynamic = ['version']

dependencies = [
    'botocore>=1.28.16',
    'boto3>=1.34.0',
    'cloudpathlib[s3]',
    'colorama',
    'datasets>=2.17.0',
    'evaluate',
    'fsspec>=2022.5.0',
    'h5py',
    'joblib',
    'mergedeep',
    'more-itertools',
    'numpy<2.0.0',
    'pandas',
    'pyarrow>=11.0.0',
    'pydantic>=1.10.15,<3',
    'python-dateutil',
    'pyyaml',
    'requests',
    'scikit-learn>=1.4.0',
    'scipy>=1.7.0',
    'tenacity',
    'thefuzz[speedup]',
    'tqdm',
    'typing-extensions'
]

[project.optional-dependencies]
openeye = [
    'openeye-toolkits',
]
rdkit = [
    'mhfp',
    'rdkit>=2023.9.1',  # for SpacialScore (SPS) 2D descriptor
]
catboost = [
    'catboost>=1.2.0; python_version >= "3.11"',
    'catboost',
]
ensemble = [
    'scikit-learn>=1.2.1',
]
lightning = [
    'torch>=2.0',
    'lightning>=2.1',
    'class_resolver',
]
lightning_gp = [
    'torch>=2.0',
    'lightning>=2.1',
    'class_resolver',
    'gpytorch',
]
mapie = [
    'mapie',
    'scikit-learn>=1.2.1',
]
pyod = [
    'combo',
    'pyod',
]
pystan = [
    'pystan>=3',
]
sklearn = [
    'scikit-learn>=1.2.1',
]
tdc = [
    'PyTDC'
]
xgboost = [
    'scikit-learn>=1.2.1',
    'xgboost<2.0.0',  # flip pin once codebase upgraded to new >= 2.0.0 API
]
dev = [
    'nox[uv]>=2024',
    'pre-commit',
]
docs = [
    'sphinx!=5.1.0',
    'sphinx-sitemap',
    'sphinx-inline-tabs',
    'sphinx-book-theme',
    'sphinx_design',
    'sphinx-toolbox',
    'sphinx_togglebutton',
    'jupytext>=1.11.2',
    'myst-nb',
    'ipywidgets',
    'rdkit>=2023.9.1',
    'matplotlib',
    'catboost>=1.2.0',
    'mapie',
]
tests = [
    'coverage[toml]',
    'moto[server]',
    'pytest',
    'mock',
]
typing = [
    'mypy',
    'types-pytz',
    'types-PyYAML',
    'types-setuptools',
    'types-python-dateutil',
    'types-mock',
    'types-requests',
]

### Datasets entry points

[project.entry-points.'fsspec.specs']
s3 = 'molflux.datasets.filesystems.S3FileSystem'

[project.entry-points.'molflux.datasets.plugins.core']
esol = 'molflux.datasets.builders.esol.esol'
ani1x = 'molflux.datasets.builders.ani1x.ani1x'
ani2x = 'molflux.datasets.builders.ani2x.ani2x'
gdb9 = 'molflux.datasets.builders.gdb9.gdb9'
pcqm4m_v2 = 'molflux.datasets.builders.pcqm4m_v2.pcqm4m_v2'
spice = 'molflux.datasets.builders.spice.spice'

[project.entry-points.'molflux.datasets.plugins.tdc']
tdc_admet_benchmarks = 'molflux.datasets.builders.tdc.tdc_admet'

### Features entry points

[project.entry-points.'molflux.features.plugins.core']
# generic
exploded = 'molflux.features.representations.core.generic.exploded:Exploded'
character_count = 'molflux.features.representations.core.generic.character_count:CharacterCount'
sum = 'molflux.features.representations.core.generic.sum:Sum'

[project.entry-points.'molflux.features.plugins.openeye']
# canonical
canonical_oemol = 'molflux.features.representations.openeye.canonical.oemol:CanonicalOemol'
canonical_smiles = 'molflux.features.representations.openeye.canonical.smiles:CanonicalSmiles'
# descriptors
aromatic_ring_count = 'molflux.features.representations.openeye.descriptors.aromatic_ring_count:AromaticRingCount'
molecular_weight = 'molflux.features.representations.openeye.descriptors.molecular_weight:MolecularWeight'
net_charge = 'molflux.features.representations.openeye.descriptors.net_charge:NetCharge'
num_acceptors = 'molflux.features.representations.openeye.descriptors.num_acceptors:NumAcceptors'
num_donors = 'molflux.features.representations.openeye.descriptors.num_donors:NumDonors'
rotatable_bonds = 'molflux.features.representations.openeye.descriptors.rotatable_bonds:RotatableBonds'
tpsa = 'molflux.features.representations.openeye.descriptors.tpsa:TPSA'
x_log_p = 'molflux.features.representations.openeye.descriptors.x_log_p:XLogP'
# fingerprints
circular = 'molflux.features.representations.openeye.fingerprints.circular:Circular'
lingo = 'molflux.features.representations.openeye.fingerprints.lingo:Lingo'
maccs = 'molflux.features.representations.openeye.fingerprints.maccs:MACCS'
path = 'molflux.features.representations.openeye.fingerprints.path:Path'
tree = 'molflux.features.representations.openeye.fingerprints.tree:Tree'
# shape
hermite = 'molflux.features.representations.openeye.shape.hermite:Hermite'


[project.entry-points.'molflux.features.plugins.rdkit']
# descriptors
rdkit_descriptors_2d = 'molflux.features.representations.rdkit.descriptors.rdkit_descriptors_2d:RdkitDescriptors_2d'
# fingerprints
atom_pair = 'molflux.features.representations.rdkit.fingerprints.atom_pair:AtomPair'
atom_pair_unfolded = 'molflux.features.representations.rdkit.fingerprints.atom_pair_unfolded:AtomPairUnfolded'
avalon = 'molflux.features.representations.rdkit.fingerprints.avalon:Avalon'
layered = 'molflux.features.representations.rdkit.fingerprints.layered:Layered'
maccs_rdkit = 'molflux.features.representations.rdkit.fingerprints.maccs:MACCSRdkit'
map_light = 'molflux.features.representations.rdkit.fingerprints.map_light:MapLight'
mhfp = 'molflux.features.representations.rdkit.fingerprints.mhfp:MHFP'
mhfp_unfolded = 'molflux.features.representations.rdkit.fingerprints.mhfp_unfolded:MHFPUnfolded'
morgan = 'molflux.features.representations.rdkit.fingerprints.morgan:Morgan'
morgan_unfolded = 'molflux.features.representations.rdkit.fingerprints.morgan_unfolded:MorganUnfolded'
pattern = 'molflux.features.representations.rdkit.fingerprints.pattern:Pattern'
topological = 'molflux.features.representations.rdkit.fingerprints.topological:Topological'
topological_torsion = 'molflux.features.representations.rdkit.fingerprints.topological_torsion:TopologicalTorsion'
topological_torsion_unfolded = 'molflux.features.representations.rdkit.fingerprints.topological_torsion_unfolded:TopologicalTorsionUnfolded'
toxicophores = 'molflux.features.representations.rdkit.fingerprints.toxicophores:Toxicophores'
# reaction
drfp = 'molflux.features.representations.rdkit.reaction.drfp:DRFP'
### Splits entry points

[project.entry-points.'molflux.splits.plugins.core']
ordered_split = 'molflux.splits.strategies.core.ordered_split:OrderedSplit'
stratified_ordered_split = 'molflux.splits.strategies.core.stratified_ordered_split:StratifiedOrderedSplit'
group_k_fold = 'molflux.splits.strategies.core.group_k_fold:GroupKFold'
group_shuffle_split = 'molflux.splits.strategies.core.group_shuffle_split:GroupShuffleSplit'
k_fold = 'molflux.splits.strategies.core.k_fold:KFold'
leave_one_group_out = 'molflux.splits.strategies.core.leave_one_group_out:LeaveOneGroupOut'
leave_p_groups_out = 'molflux.splits.strategies.core.leave_p_groups_out:LeavePGroupsOut'
linear_split = 'molflux.splits.strategies.core.linear_split:LinearSplit'
linear_split_with_rotation = 'molflux.splits.strategies.core.linear_split_with_rotation:LinearSplitWithRotation'
shuffle_split = 'molflux.splits.strategies.core.shuffle_split:ShuffleSplit'
stratified_k_fold = 'molflux.splits.strategies.core.stratified_k_fold:StratifiedKFold'
stratified_shuffle_split = 'molflux.splits.strategies.core.stratified_shuffle_split:StratifiedShuffleSplit'
time_series_split = 'molflux.splits.strategies.core.time_series_split:TimeSeriesSplit'

[project.entry-points.'molflux.splits.plugins.openeye']
scaffold = 'molflux.splits.strategies.openeye.scaffold:Scaffold'

[project.entry-points.'molflux.splits.plugins.rdkit']
scaffold_rdkit = 'molflux.splits.strategies.rdkit.scaffold:Scaffold'
tanimoto_rdkit = 'molflux.splits.strategies.rdkit.tanimoto:Tanimoto'

### Modelzoo entry points

[project.entry-points.'molflux.modelzoo.plugins.core']
average_regressor = 'molflux.modelzoo.models.core.average_regressor:AverageRegressor'
average_features_regressor = 'molflux.modelzoo.models.core.average_features_regressor:AverageFeaturesRegressor'

[project.entry-points.'molflux.modelzoo.plugins.catboost']
cat_boost_regressor = 'molflux.modelzoo.models.catboost.catboost_regressor:CatBoostRegressor'
cat_boost_classifier = 'molflux.modelzoo.models.catboost.catboost_classifier:CatBoostClassifier'

[project.entry-points.'molflux.modelzoo.plugins.ensemble']
ensemble_regressor = 'molflux.modelzoo.models.ensemble.ensemble_regressor:EnsembleRegressor'
ensemble_classifier = 'molflux.modelzoo.models.ensemble.ensemble_classifier:EnsembleClassifier'

[project.entry-points.'molflux.modelzoo.plugins.fortuna']
fortuna_mlp_regressor = 'molflux.modelzoo.models.fortuna.fortuna_mlp_regressor:FortunaMLPRegressor'

[project.entry-points.'molflux.modelzoo.plugins.lightning']
lightning_mlp_regressor = 'molflux.modelzoo.models.lightning.mlp_regressor.mlp_model:LightningMLPRegressor'

[project.entry-points.'molflux.modelzoo.plugins.lightning_gp']
lightning_gp_regressor = 'molflux.modelzoo.models.lightning_gp.gp_model:LightningGPRegressor'

[project.entry-points.'molflux.modelzoo.plugins.mapie']
mapie_regressor = 'molflux.modelzoo.models.mapie.mapie_regressor:MapieRegressor'

[project.entry-points.'molflux.modelzoo.plugins.pyod']
abod_detector = 'molflux.modelzoo.models.pyod.abod_detector:ABODDetector'
cblof_detector = 'molflux.modelzoo.models.pyod.cblof_detector:CBLOFDetector'
hbos_detector = 'molflux.modelzoo.models.pyod.hbos_detector:HBOSDetector'
isolation_forest_detector = 'molflux.modelzoo.models.pyod.isolation_forest_detector:IsolationForestDetector'
knn_detector = 'molflux.modelzoo.models.pyod.knn_detector:KNNDetector'
mcd_detector = 'molflux.modelzoo.models.pyod.mcd_detector:MCDDetector'
ocsvm_detector = 'molflux.modelzoo.models.pyod.ocsvm_detector:OCSVMDetector'
pca_detector = 'molflux.modelzoo.models.pyod.pca_detector:PCADetector'

[project.entry-points.'molflux.modelzoo.plugins.pystan']
sparse_linear_regressor = 'molflux.modelzoo.models.pystan.sparse_linear_regressor:SparseLinearRegressor'
ordinal_classifier = 'molflux.modelzoo.models.pystan.ordinal_classifier:OrdinalClassifier'

[project.entry-points.'molflux.modelzoo.plugins.sklearn']
corrected_nb_classifier = 'molflux.modelzoo.models.sklearn.corrected_nb_classifier:CorrectedNBClassifier'
coverage_nb_classifier = 'molflux.modelzoo.models.sklearn.coverage_nb_classifier:CoverageNBClassifier'
bernoulli_nb_classifier = 'molflux.modelzoo.models.sklearn.bernoulli_nb_classifier:BernoulliNBClassifier'
dummy_classifier = 'molflux.modelzoo.models.sklearn.dummy_classifier:DummyClassifier'
extra_trees_classifier = 'molflux.modelzoo.models.sklearn.extra_trees_classifier:ExtraTreesClassifier'
extra_trees_regressor = 'molflux.modelzoo.models.sklearn.extra_trees_regressor:ExtraTreesRegressor'
gradient_boosting_classifier = 'molflux.modelzoo.models.sklearn.gradient_boosting_classifier:GradientBoostingClassifier'
gradient_boosting_regressor = 'molflux.modelzoo.models.sklearn.gradient_boosting_regressor:GradientBoostingRegressor'
kernel_ridge_regressor = 'molflux.modelzoo.models.sklearn.kernel_ridge_regressor:KernelRidgeRegressor'
knn_classifier = 'molflux.modelzoo.models.sklearn.knn_classifier:KNNClassifier'
knn_regressor = 'molflux.modelzoo.models.sklearn.knn_regressor:KNNRegressor'
linear_discriminant_analysis_classifier = 'molflux.modelzoo.models.sklearn.linear_discriminant_analysis_classifier:LinearDiscriminantAnalysisClassifier'
linear_regressor = 'molflux.modelzoo.models.sklearn.linear_regressor:LinearRegressor'
logistic_regressor = 'molflux.modelzoo.models.sklearn.logistic_regressor:LogisticRegressor'
mlp_classifier = 'molflux.modelzoo.models.sklearn.mlp_classifier:MLPClassifier'
mlp_regressor = 'molflux.modelzoo.models.sklearn.mlp_regressor:MLPRegressor'
pipeline_pilot_nb_classifier = 'molflux.modelzoo.models.sklearn.pipeline_pilot_nb_classifier:PipelinePilotNBClassifier'
pls_regressor = 'molflux.modelzoo.models.sklearn.pls_regressor:PLSRegressor'
random_forest_regressor = 'molflux.modelzoo.models.sklearn.random_forest_regressor:RandomForestRegressor'
random_forest_classifier = 'molflux.modelzoo.models.sklearn.random_forest_classifier:RandomForestClassifier'
ridge_regressor = 'molflux.modelzoo.models.sklearn.ridge_regressor:RidgeRegressor'
sklearn_pipeline_classifier = 'molflux.modelzoo.models.sklearn.sklearn_pipeline.sklearn_pipeline_classifier:SklearnPipelineClassifier'
sklearn_pipeline_regressor = 'molflux.modelzoo.models.sklearn.sklearn_pipeline.sklearn_pipeline_regressor:SklearnPipelineRegressor'
support_vector_classifier = 'molflux.modelzoo.models.sklearn.support_vector_classifier:SupportVectorClassifier'
support_vector_regressor = 'molflux.modelzoo.models.sklearn.support_vector_regressor:SupportVectorRegressor'

[project.entry-points.'molflux.modelzoo.plugins.xgboost']
xg_boost_regressor = 'molflux.modelzoo.models.xgboost.xgboost_regressor:XGBoostRegressor'
xg_boost_classifier = 'molflux.modelzoo.models.xgboost.xgboost_classifier:XGBoostClassifier'


### Metrics entry points

[project.entry-points.'molflux.metrics.plugins.classification']
accuracy = 'molflux.metrics.classification.accuracy:Accuracy'
balanced_accuracy = 'molflux.metrics.classification.balanced_accuracy:BalancedAccuracy'
diversity_roc = 'molflux.metrics.classification.diversity_roc:DiversityRoc'
f1_score = 'molflux.metrics.classification.f1_score:F1Score'
matthews_corrcoef = 'molflux.metrics.classification.matthews_corrcoef:MatthewsCorrcoef'
precision = 'molflux.metrics.classification.precision:Precision'
average_precision = 'molflux.metrics.classification.average_precision:AveragePrecision'
recall = 'molflux.metrics.classification.recall:Recall'
roc_auc = 'molflux.metrics.classification.roc_auc:RocAuc'
top_k_accuracy = 'molflux.metrics.classification.top_k_accuracy:TopKAccuracy'
top_k_accuracy_roc = 'molflux.metrics.classification.top_k_accuracy_roc:TopKAccuracyRoc'
validity_roc = 'molflux.metrics.classification.validity_roc:ValidityRoc'

[project.entry-points.'molflux.metrics.plugins.regression']
explained_variance = 'molflux.metrics.regression.explained_variance:ExplainedVariance'
max_error = 'molflux.metrics.regression.max_error:MaxError'
mean_absolute_error = 'molflux.metrics.regression.mean_absolute_error:MeanAbsoluteError'
mean_squared_error = 'molflux.metrics.regression.mean_squared_error:MeanSquaredError'
root_mean_squared_error = 'molflux.metrics.regression.root_mean_squared_error:RootMeanSquaredError'
median_absolute_error = 'molflux.metrics.regression.median_absolute_error:MedianAbsoluteError'
out_of_sample_r2 = 'molflux.metrics.regression.out_of_sample_r2:OutOfSampleR2'
pearson = 'molflux.metrics.regression.pearson:Pearson'
proportion_within_fold = 'molflux.metrics.regression.proportion_within_fold:ProportionWithinFold'
r2 = 'molflux.metrics.regression.r2:R2'
spearman = 'molflux.metrics.regression.spearman:Spearman'

[project.entry-points.'molflux.metrics.plugins.uncertainty']
coefficient_of_variation = 'molflux.metrics.uncertainty.coefficient_of_variation:CoefficientOfVariation'
expected_calibration_error = 'molflux.metrics.uncertainty.expected_calibration_error:ExpectedCalibrationError'
calibration_gap = 'molflux.metrics.uncertainty.calibration_gap:CalibrationGap'
gaussian_nll = 'molflux.metrics.uncertainty.gaussian_nll:GaussianNLL'
prediction_interval_coverage = 'molflux.metrics.uncertainty.prediction_interval_coverage:PredictionIntervalCoverage'
prediction_interval_width = 'molflux.metrics.uncertainty.prediction_interval_width:PredictionIntervalWidth'
uncertainty_based_rejection = 'molflux.metrics.uncertainty.uncertainty_based_rejection:UncertaintyBasedRejection'

[project.urls]
documentation = 'https://exscientia.github.io/molflux/'
repository = 'https://github.com/exscientia/molflux.git'
issue-tracker = 'https://github.com/exscientia/molflux/issues'
changelog = 'https://github.com/exscientia/molflux/src/main/CHANGELOG.md'

[tool.black]
include = '/src/.*\.pyi?$|/tests/.*\.pyi?$|/docs/.*\.pyi?$'
line-length = 88
target-version = ['py38', 'py39', 'py310', 'py311']

[tool.coverage.paths]
source = ['src/molflux/', '.cache/nox/*/lib/*/site-packages/molflux/']

[tool.coverage.report]
show_missing = true

[tool.coverage.run]
branch = true
source_pkgs = ['molflux']

[tool.isort]
known_first_party = "molflux"
profile = "black"
src_paths = ["src", "tests"]

[tool.mypy]
cache_dir = ".cache/mypy_cache"
disallow_incomplete_defs = true
disallow_subclassing_any = false
disallow_untyped_decorators = false
disallow_untyped_defs = true
explicit_package_bases = true
files = ['src/', 'tests/', 'noxfile.py']
ignore_missing_imports = true
mypy_path = 'src'
namespace_packages = true
no_implicit_optional = true
plugins = ['pydantic.mypy']
warn_redundant_casts =true
warn_return_any = true
warn_unreachable = true
warn_unused_ignores = true
show_error_codes = true

[[tool.mypy.overrides]]
check_untyped_defs = true
disallow_untyped_defs = false
module = 'tests.*'

[[tool.mypy.overrides]]
check_untyped_defs = true
disallow_untyped_decorators = false
disallow_untyped_defs = false
module = 'noxfile'

[tool.pytest.ini_options]
addopts = ["-rv", "--strict-markers", "--strict-config", "--doctest-modules", "--color=yes"]
cache_dir = ".cache/pytest_cache"
filterwarnings = [
    "error",
    # [core]
    # https://moyix.blogspot.com/2022/09/someones-been-messing-with-my-subnormals.html
    "ignore:The value of the smallest subnormal for .* type is zero:UserWarning:numpy.core.getlimits",
    # [datasets]
    "ignore::pytest.PytestUnraisableExceptionWarning",
    "ignore:The 'strict' parameter is no longer needed on Python 3:DeprecationWarning:urllib3.poolmanager",
    # ignore deprecated usage of pyarrow.concat_table() by datasets since pyarrow 14.0 release
    "ignore:promote has been superseded by mode='default':FutureWarning:datasets.table",
    # [features]
    # allow UserWarning raised by mhfp library when passing an empty SMILES for featurisation
    "ignore:The length of the shingling is 0, which results in an empty set and an all zero folded fingerprint:UserWarning:mhfp.encoder",
    # [modelzoo.core]
    # ignore potential UserWarnings stemming from minimal datasets used for testing
    "ignore:The least populated class in y has only .* members, which is less than n_splits.*:UserWarning:sklearn.model_selection[.*]",
    # allow RuntimeWarning sometimes raised deep into scipy when calculating prediction intervals for average regressor
    "ignore:invalid value encountered in multiply:RuntimeWarning:scipy.stats._distn_infrastructure",
    # [modelzoo.lightning]
    # ignore unhandled deprecated usage of pkg_resources from lightning_utilities
    "ignore:pkg_resources is deprecated as an API:DeprecationWarning",
    "ignore:distutils Version classes are deprecated. Use packaging.version instead:DeprecationWarning",
    "ignore:Deprecated call to:DeprecationWarning",
    # allow PossibleUserWarnings during training
    "ignore:The .* does not have many workers which may be a bottleneck",
    "ignore:The number of training batches .* is smaller than the logging interval",
    "ignore:Total length of `dict` across ranks is zero. Please make sure this was your intention:UserWarning",
    "ignore: Starting from v1.9.0, `tensorboardX` has been removed as a dependency of the `lightning.pytorch` package:UserWarning",
    "ignore: GPU available but not used.",
    # [modelzoo.lightning_gp]
    # ignore warnings on predicting using GPyTorch models on their training data
    "ignore:The input matches the stored training data. Did you forget to call model.train()?",
    # ignore warnings on empty DataLoaders in lightning models
    "ignore:Total length of `DataLoader` across ranks is zero. Please make sure this was your intention.",
    "ignore:Total length of `CombinedLoader` across ranks is zero. Please make sure this was your intention.",
    # [modelzoo.mapie]
    # ignore unhandled DataConversionWarning raised internally by mapie
    "ignore:A column-vector y was passed when a 1d array was expected. Please change the shape of y::sklearn.utils.validation",
    # allow our own warning when loading a pre-trained MAPIE model
    "ignore:Model loaded with an unlinked input estimator. This is expected if loading a pre-trained MAPIE model:UserWarning:molflux.modelzoo.models.mapie.mapie_regressor",
    # [modelzoo.pyod]
    # allow UserWarning sometimes raised by pyod on training
    "ignore:n_neighbors is set to the number of training points minus 1:UserWarning:pyod.models.abod",
    # ignore unhandled FutureWarning raised internally by pyod
    "ignore:The default value of `n_init` will change:FutureWarning",
    # allow sklearn.exceptions.ConvergenceWarning sometimes raised internally by pyod during training stemming from mock test data
    "ignore:Number of distinct clusters .* found smaller than n_clusters",
    # ignore UserWarning sometimes raised internally by pyod during training stemming from mock test data
    "ignore:The chosen clustering for CBLOF forms .* clusterswhich is inconsistent with n_clusters:UserWarning:pyod.models.cblof",
    # allow internal RuntimeWarning pyod warnings
    "ignore:divide by zero encountered in scalar divide:RuntimeWarning:pyod.models.cblof",
    "ignore:invalid value encountered in scalar divide:RuntimeWarning:pyod.models.cblof",
    "ignore:Degrees of freedom <= 0 for slice:RuntimeWarning",
    "ignore:invalid value encountered in divide:RuntimeWarning",
    "ignore:invalid value encountered in scalar divide:RuntimeWarning",
    # [modelzoo.pystan]
    # ignore unhandled internal marshmallow warning raised by pystan
    "ignore:The 'missing' argument to fields is deprecated. Use 'load_default' instead::marshmallow.fields",
    # ignore unhandled internal aiohttp warning raised by pystan
    "ignore:It is recommended to use web.AppKey instances for keys",
    # ignore unhandled internal pystan DeprecationWarnings
    "ignore:.* is deprecated:DeprecationWarning",
    # [modelzoo.sklearn]
    # ignore ConvergenceWarnings during tests
    "ignore:Stochastic Optimizer.*Maximum iterations (.*) reached and the optimization hasn't converged yet",
    # [modelzoo.xgboost]
    # ignore warnings about constant input arrays
    "ignore:An input array is constant; the correlation coefficient is not defined",
    # ignore speed
    "ignore:The iteration is not making good progress",
]
log_cli = true
log_cli_level = "WARNING"
log_cli_format = "%(levelname)s:%(name)s: %(message)s"
minversion = "6.0"
norecursedirs = [
    'src/molflux/datasets/builders',
    'src/molflux/features/representations',
    'src/molflux/splits/strategies',
    'src/molflux/modelzoo/models',
    'tests/*/*/mock_data',
]
testpaths = ['src', 'tests']
xfail_strict = true

[tool.ruff]
cache-dir = ".cache/ruff"
extend-exclude = ["src/molflux/version.py"]  # dynamically generated
line-length = 88
src = ["src/molflux", "tests"]
namespace-packages = ["src/molflux"]
respect-gitignore = true
show-fixes = true

[tool.ruff.lint]
select = [ # https://beta.ruff.rs/docs/rules/
    # "A",  # flake8-builtins
    # "ARG", # flake8-unused-arguments
    "B", # flake8-bugbear
    # "BLE", # flake8-blind-except
    "COM", # flake8-commas
    "C4", # flake8-comprehensions
    # "C90", # mccabe
    # "D", # pydocstyle
    "DTZ", # flake8-datetimz
    "E",  # pycodestyle error
    # "ERA", # eradicate
    "F", # Pyflakes
    # "G", # flake8-logging-format
    "I", # isort
    # "ISC", # flake8-implicit-str-concat
    # "N", # pep8-naming
    # "NPY", # NumPy-specific rules
    "Q", # flake8-quotes
    "PD", # pandas-vet
    # "PIE", # flake8-pie
    # "PL", # Pylint
    # "PT", # flake8-pytest-style
    # "PTH", # flake8-use-pathlib
    "RSE",  # flake8-raise
    "RUF", # Ruff-specific rules
    "S", # flake8-bandit
    # "SIM", # flake8-simplify
    "TCH", # flake8-type-checking
    "TID", # flake8-tidy-imports
    # "TRY", # tryceratops
    "T20", # flake8-print
    "UP", # pyupgrade
    "W", # pycodestyle warning
    "YTT", # flake8-2020
]
ignore = ["E501", "S101", "PD901", "PD003", "UP035", "UP007", "UP038", "TCH003"]

[tool.ruff.lint.per-file-ignores]
"docs/source/conf.py" = ["ERA"]
"src/molflux/__init__.py" = ["F401"]
"src/molflux/*/__init__.py" = ["F401"]
"src/molflux/metrics/classification/*" = ["PLR0913"]
"src/molflux/metrics/regression/*" = ["PLR0913"]
"src/molflux/metrics/uncertainty/*" = ["PLR0913"]
"tests/*" = ["ARG001", "D", "S101", "PLR2004"]
"noxfile.py" = ["T201"]

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

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

[tool.setuptools_scm]
local_scheme = "dirty-tag"
write_to = "src/molflux/version.py"