Update pre-commit (#368)

* Update pre-commit to use ruff

* Run ruff with new configuration

* Additional fixes requested by ruff

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: jessegrabowski

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.5.0
+  rev: v4.6.0
   hooks:
     -   id: check-merge-conflict
     -   id: check-toml
@@ -10,37 +10,18 @@ repos:
     -   id: no-commit-to-branch
         args: [--branch, main]
     -   id: trailing-whitespace
-- repo: https://github.com/PyCQA/isort
-  rev: 5.13.2
+
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: v0.5.5
   hooks:
-    - id: isort
-      name: isort
-- repo: https://github.com/asottile/pyupgrade
-  rev: v3.15.0
-  hooks:
-    - id: pyupgrade
-      args: [--py37-plus]
-- repo: https://github.com/psf/black
-  rev: 24.1.1
-  hooks:
-    - id: black
-    - id: black-jupyter
-- repo: https://github.com/PyCQA/pylint
-  rev: v3.0.3
-  hooks:
-    - id: pylint
-      args: [--rcfile=.pylintrc]
-      files: ^pymc_experimental/
+    - id: ruff
+      args: [ --fix, --unsafe-fixes, --exit-non-zero-on-fix ]
+    - id: ruff-format
+      types_or: [ python, pyi, jupyter ]
+
 - repo: https://github.com/MarcoGorelli/madforhooks
   rev: 0.4.1
   hooks:
     - id: no-print-statements
       exclude: _version.py
       files: ^pymc_experimental/
-- repo: local
-  hooks:
-    - id: no-relative-imports
-      name: No relative imports
-      entry: from \.[\.\w]* import
-      types: [python]
-      language: pygrep

notebooks/SARMA Example.ipynb

@@ -1554,7 +1554,7 @@
     "        hdi_forecast.coords[\"time\"].values,\n",
     "        *hdi_forecast.isel(observed_state=0).values.T,\n",
     "        alpha=0.25,\n",
-    "        color=\"tab:blue\"\n",
+    "        color=\"tab:blue\",\n",
     "    )\n",
     "ax.set_title(\"Porcupine Graph of 10-Period Forecasts (parameters estimated on all data)\")\n",
     "plt.show()"
@@ -2692,7 +2692,7 @@
     "    *forecast_hdi.values.T,\n",
     "    label=\"Forecast 94% HDI\",\n",
     "    color=\"tab:orange\",\n",
-    "    alpha=0.25\n",
+    "    alpha=0.25,\n",
     ")\n",
     "ax.legend()\n",
     "plt.show()"

notebooks/Structural Timeseries Modeling.ipynb

@@ -1657,7 +1657,7 @@
     "        nile.index,\n",
     "        *component_hdi.smoothed_posterior.sel(state=state).values.T,\n",
     "        color=\"tab:blue\",\n",
-    "        alpha=0.15\n",
+    "        alpha=0.15,\n",
     "    )\n",
     "    axis.set_title(state.title())"
    ]
@@ -1706,7 +1706,7 @@
     "    *hdi.smoothed_posterior.sum(dim=\"state\").values.T,\n",
     "    color=\"tab:blue\",\n",
     "    alpha=0.15,\n",
-    "    label=\"HDI 94%\"\n",
+    "    label=\"HDI 94%\",\n",
     ")\n",
     "ax.legend()\n",
     "plt.show()"
@@ -2750,7 +2750,7 @@
     "ax.fill_between(\n",
     "    blossom_data.index,\n",
     "    *hdi_post.predicted_posterior_observed.isel(observed_state=0).values.T,\n",
-    "    alpha=0.25\n",
+    "    alpha=0.25,\n",
     ")\n",
     "blossom_data.plot(ax=ax)"
    ]

pymc_experimental/__init__.py

@@ -13,6 +13,10 @@
 #   limitations under the License.
 import logging
 
+from pymc_experimental import distributions, gp, statespace, utils
+from pymc_experimental.inference.fit import fit
+from pymc_experimental.model.marginal_model import MarginalModel
+from pymc_experimental.model.model_api import as_model
 from pymc_experimental.version import __version__
 
 _log = logging.getLogger("pmx")
@@ -23,7 +27,14 @@
         handler = logging.StreamHandler()
         _log.addHandler(handler)
 
-from pymc_experimental import distributions, gp, statespace, utils
-from pymc_experimental.inference.fit import fit
-from pymc_experimental.model.marginal_model import MarginalModel
-from pymc_experimental.model.model_api import as_model
+
+__all__ = [
+    "distributions",
+    "gp",
+    "statespace",
+    "utils",
+    "fit",
+    "MarginalModel",
+    "as_model",
+    "__version__",
+]

pymc_experimental/distributions/continuous.py

@@ -19,10 +19,9 @@
 The imports from pymc are not fully replicated here: add imports as necessary.
 """
 
-from typing import Tuple, Union
-
 import numpy as np
 import pytensor.tensor as pt
+
 from pymc import ChiSquared, CustomDist
 from pymc.distributions import transforms
 from pymc.distributions.dist_math import check_parameters
@@ -39,19 +38,19 @@ class GenExtremeRV(RandomVariable):
     name: str = "Generalized Extreme Value"
     signature = "(),(),()->()"
     dtype: str = "floatX"
-    _print_name: Tuple[str, str] = ("Generalized Extreme Value", "\\operatorname{GEV}")
+    _print_name: tuple[str, str] = ("Generalized Extreme Value", "\\operatorname{GEV}")
 
     def __call__(self, mu=0.0, sigma=1.0, xi=0.0, size=None, **kwargs) -> TensorVariable:
         return super().__call__(mu, sigma, xi, size=size, **kwargs)
 
     @classmethod
     def rng_fn(
         cls,
-        rng: Union[np.random.RandomState, np.random.Generator],
+        rng: np.random.RandomState | np.random.Generator,
         mu: np.ndarray,
         sigma: np.ndarray,
         xi: np.ndarray,
-        size: Tuple[int, ...],
+        size: tuple[int, ...],
     ) -> np.ndarray:
         # Notice negative here, since remainder of GenExtreme is based on Coles parametrization
         return stats.genextreme.rvs(c=-xi, loc=mu, scale=sigma, random_state=rng, size=size)

pymc_experimental/distributions/discrete.py

@@ -14,6 +14,7 @@
 
 import numpy as np
 import pymc as pm
+
 from pymc.distributions.dist_math import betaln, check_parameters, factln, logpow
 from pymc.distributions.shape_utils import rv_size_is_none
 from pytensor import tensor as pt

pymc_experimental/distributions/histogram_utils.py

@@ -13,18 +13,17 @@
 #   limitations under the License.
 
 
-from typing import Dict
-
 import numpy as np
 import pymc as pm
+
 from numpy.typing import ArrayLike
 
 __all__ = ["quantile_histogram", "discrete_histogram", "histogram_approximation"]
 
 
 def quantile_histogram(
     data: ArrayLike, n_quantiles=1000, zero_inflation=False
-) -> Dict[str, ArrayLike]:
+) -> dict[str, ArrayLike]:
     try:
         import xhistogram.core
     except ImportError as e:
@@ -34,7 +33,7 @@ def quantile_histogram(
         import dask.dataframe
     except ImportError:
         dask = None
-    if dask and isinstance(data, (dask.dataframe.Series, dask.dataframe.DataFrame)):
+    if dask and isinstance(data, dask.dataframe.Series | dask.dataframe.DataFrame):
         data = data.to_dask_array(lengths=True)
     if zero_inflation:
         zeros = (data == 0).sum(0)
@@ -67,7 +66,7 @@ def quantile_histogram(
     return result
 
 
-def discrete_histogram(data: ArrayLike, min_count=None) -> Dict[str, ArrayLike]:
+def discrete_histogram(data: ArrayLike, min_count=None) -> dict[str, ArrayLike]:
     try:
         import xhistogram.core
     except ImportError as e:
@@ -78,7 +77,7 @@ def discrete_histogram(data: ArrayLike, min_count=None) -> Dict[str, ArrayLike]:
     except ImportError:
         dask = None
 
-    if dask and isinstance(data, (dask.dataframe.Series, dask.dataframe.DataFrame)):
+    if dask and isinstance(data, dask.dataframe.Series | dask.dataframe.DataFrame):
         data = data.to_dask_array(lengths=True)
     mid, count_uniq = np.unique(data, return_counts=True)
     if min_count is not None:
@@ -153,7 +152,7 @@ def histogram_approximation(name, dist, *, observed, **h_kwargs):
         import dask.dataframe
     except ImportError:
         dask = None
-    if dask and isinstance(observed, (dask.dataframe.Series, dask.dataframe.DataFrame)):
+    if dask and isinstance(observed, dask.dataframe.Series | dask.dataframe.DataFrame):
         observed = observed.to_dask_array(lengths=True)
     if np.issubdtype(observed.dtype, np.integer):
         histogram = discrete_histogram(observed, **h_kwargs)

pymc_experimental/distributions/multivariate/__init__.py

@@ -1 +1,3 @@
 from pymc_experimental.distributions.multivariate.r2d2m2cp import R2D2M2CP
+
+__all__ = ["R2D2M2CP"]

pymc_experimental/distributions/multivariate/r2d2m2cp.py

@@ -14,7 +14,7 @@
 
 
 from collections import namedtuple
-from typing import Sequence, Tuple, Union
+from collections.abc import Sequence
 
 import numpy as np
 import pymc as pm
@@ -26,8 +26,8 @@
 def _psivar2musigma(
     psi: pt.TensorVariable,
     explained_var: pt.TensorVariable,
-    psi_mask: Union[pt.TensorLike, None],
-) -> Tuple[pt.TensorVariable, pt.TensorVariable]:
+    psi_mask: pt.TensorLike | None,
+) -> tuple[pt.TensorVariable, pt.TensorVariable]:
     sign = pt.sign(psi - 0.5)
     if psi_mask is not None:
         # any computation might be ignored for ~psi_mask
@@ -55,7 +55,7 @@ def _R2D2M2CP_beta(
     psi: pt.TensorVariable,
     *,
     psi_mask,
-    dims: Union[str, Sequence[str]],
+    dims: str | Sequence[str],
     centered=False,
 ) -> pt.TensorVariable:
     """R2D2M2CP beta prior.
@@ -120,7 +120,7 @@ def _R2D2M2CP_beta(
 def _broadcast_as_dims(
     *values: np.ndarray,
     dims: Sequence[str],
-) -> Union[Tuple[np.ndarray, ...], np.ndarray]:
+) -> tuple[np.ndarray, ...] | np.ndarray:
     model = pm.modelcontext(None)
     shape = [len(model.coords[d]) for d in dims]
     ret = tuple(np.broadcast_to(v, shape) for v in values)
@@ -135,7 +135,7 @@ def _psi_masked(
     positive_probs_std: pt.TensorLike,
     *,
     dims: Sequence[str],
-) -> Tuple[Union[pt.TensorLike, None], pt.TensorVariable]:
+) -> tuple[pt.TensorLike | None, pt.TensorVariable]:
     if not (
         isinstance(positive_probs, pt.Constant) and isinstance(positive_probs_std, pt.Constant)
     ):
@@ -172,10 +172,10 @@ def _psi_masked(
 
 def _psi(
     positive_probs: pt.TensorLike,
-    positive_probs_std: Union[pt.TensorLike, None],
+    positive_probs_std: pt.TensorLike | None,
     *,
     dims: Sequence[str],
-) -> Tuple[Union[pt.TensorLike, None], pt.TensorVariable]:
+) -> tuple[pt.TensorLike | None, pt.TensorVariable]:
     if positive_probs_std is not None:
         mask, psi = _psi_masked(
             positive_probs=pt.as_tensor(positive_probs),
@@ -194,9 +194,9 @@ def _psi(
 
 
 def _phi(
-    variables_importance: Union[pt.TensorLike, None],
-    variance_explained: Union[pt.TensorLike, None],
-    importance_concentration: Union[pt.TensorLike, None],
+    variables_importance: pt.TensorLike | None,
+    variance_explained: pt.TensorLike | None,
+    importance_concentration: pt.TensorLike | None,
     *,
     dims: Sequence[str],
 ) -> pt.TensorVariable:
@@ -210,15 +210,15 @@ def _phi(
         variables_importance = pt.as_tensor(variables_importance)
         if importance_concentration is not None:
             variables_importance *= importance_concentration
-        return pm.Dirichlet("phi", variables_importance, dims=broadcast_dims + [dim])
+        return pm.Dirichlet("phi", variables_importance, dims=[*broadcast_dims, dim])
     elif variance_explained is not None:
         if len(model.coords[dim]) <= 1:
             raise TypeError("Can't use variance explained with less than two variables")
         phi = pt.as_tensor(variance_explained)
     else:
         phi = _broadcast_as_dims(1.0, dims=dims)
     if importance_concentration is not None:
-        return pm.Dirichlet("phi", importance_concentration * phi, dims=broadcast_dims + [dim])
+        return pm.Dirichlet("phi", importance_concentration * phi, dims=[*broadcast_dims, dim])
     else:
         return phi
 
@@ -233,12 +233,12 @@ def R2D2M2CP(
     *,
     dims: Sequence[str],
     r2: pt.TensorLike,
-    variables_importance: Union[pt.TensorLike, None] = None,
-    variance_explained: Union[pt.TensorLike, None] = None,
-    importance_concentration: Union[pt.TensorLike, None] = None,
-    r2_std: Union[pt.TensorLike, None] = None,
-    positive_probs: Union[pt.TensorLike, None] = 0.5,
-    positive_probs_std: Union[pt.TensorLike, None] = None,
+    variables_importance: pt.TensorLike | None = None,
+    variance_explained: pt.TensorLike | None = None,
+    importance_concentration: pt.TensorLike | None = None,
+    r2_std: pt.TensorLike | None = None,
+    positive_probs: pt.TensorLike | None = 0.5,
+    positive_probs_std: pt.TensorLike | None = None,
     centered: bool = False,
 ) -> R2D2M2CPOut:
     """R2D2M2CP Prior.
@@ -413,7 +413,7 @@ def R2D2M2CP(
             year = {2023}
         }
     """
-    if not isinstance(dims, (list, tuple)):
+    if not isinstance(dims, list | tuple):
         dims = (dims,)
     *broadcast_dims, dim = dims
     input_sigma = pt.as_tensor(input_sigma)
@@ -438,7 +438,7 @@ def R2D2M2CP(
         r2,
         phi,
         psi,
-        dims=broadcast_dims + [dim],
+        dims=[*broadcast_dims, dim],
         centered=centered,
         psi_mask=mask,
     )

pymc_experimental/distributions/timeseries.py

@@ -1,10 +1,10 @@
 import warnings
-from typing import List, Union
 
 import numpy as np
 import pymc as pm
 import pytensor
 import pytensor.tensor as pt
+
 from pymc.distributions.dist_math import check_parameters
 from pymc.distributions.distribution import (
     Distribution,
@@ -26,7 +26,7 @@
 from pytensor.tensor.random.op import RandomVariable
 
 
-def _make_outputs_info(n_lags: int, init_dist: Distribution) -> List[Union[Distribution, dict]]:
+def _make_outputs_info(n_lags: int, init_dist: Distribution) -> list[Distribution | dict]:
     """
     Two cases are needed for outputs_info in the scans used by DiscreteMarkovRv. If n_lags = 1, we need to throw away
     the first dimension of init_dist_ or else markov_chain will have shape (steps, 1, *batch_size) instead of
@@ -142,7 +142,7 @@ def dist(cls, P=None, logit_P=None, steps=None, init_dist=None, n_lags=1, **kwar
 
         if init_dist is not None:
             if not isinstance(init_dist, TensorVariable) or not isinstance(
-                init_dist.owner.op, (RandomVariable, SymbolicRandomVariable)
+                init_dist.owner.op, RandomVariable | SymbolicRandomVariable
             ):
                 raise ValueError(
                     f"Init dist must be a distribution created via the `.dist()` API, "