[MNT] Automated pre-commit hook update (#85)

* Automated `pre-commit` hook update

* fixes

---------

Co-authored-by: MatthewMiddlehurst <25731235+MatthewMiddlehurst@users.noreply.github.com>
Co-authored-by: MatthewMiddlehurst <pfm15hbu@gmail.com>

Author: tsml-actions-bot[bot]

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v6.0.0
     hooks:
     - id: check-ast
     - id: check-added-large-files
@@ -14,8 +14,6 @@ repos:
     - id: debug-statements
     - id: end-of-file-fixer
     - id: fix-byte-order-marker
-    - id: fix-encoding-pragma
-      args: ["--remove"]
     - id: name-tests-test
       args: ["--pytest-test-first"]
     - id: requirements-txt-fixer
@@ -28,39 +26,39 @@ repos:
         args: [ "--create", "--python-folders", "tsml" ]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.9
+    rev: v0.12.9
     hooks:
       - id: ruff
         args: [ "--fix" ]
 
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.16.0
+    rev: v3.20.0
     hooks:
       - id: pyupgrade
-        args: [ "--py38-plus" ]
+        args: [ "--py310-plus" ]
 
   - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
+    rev: 6.0.1
     hooks:
       - id: isort
         name: isort (python)
         args: [ "--profile=black", "--multi-line=3" ]
 
   - repo: https://github.com/pycqa/flake8
-    rev: 7.1.0
+    rev: 7.3.0
     hooks:
       - id: flake8
         additional_dependencies: [ flake8-bugbear, flake8-print, Flake8-pyproject ]
         args: [ "--max-line-length=88", "--extend-ignore=E203" ]
 
   - repo: https://github.com/psf/black
-    rev: 24.4.2
+    rev: 25.1.0
     hooks:
       - id: black
         language_version: python3
 
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.5
+    rev: 1.9.1
     hooks:
       - id: nbqa-isort
         additional_dependencies: [ isort ]
@@ -73,7 +71,7 @@ repos:
         args: [ "--nbqa-dont-skip-bad-cells", "--extend-ignore=E402,E203", "--max-line-length=88" ]
 
   - repo: https://github.com/mgedmin/check-manifest
-    rev: "0.49"
+    rev: "0.50"
     hooks:
       - id: check-manifest
         stages: [ manual ]

tsml/base.py

@@ -7,7 +7,6 @@
 ]
 
 from abc import ABCMeta
-from typing import List, Tuple, Union
 
 import numpy as np
 from numpy.random import RandomState
@@ -28,12 +27,12 @@ def _validate_data(
         y: object = "no_validation",
         reset: bool = True,
         **check_params,
-    ) -> Union[
-        Tuple[np.ndarray, object],
-        Tuple[List[np.ndarray], object],
-        np.ndarray,
-        List[np.ndarray],
-    ]:
+    ) -> (
+        tuple[np.ndarray, object]
+        | tuple[list[np.ndarray], object]
+        | np.ndarray
+        | list[np.ndarray]
+    ):
         """Validate input data and set or check the `n_features_in_` attribute.
 
         Uses the `scikit-learn` 1.2.1 `_validate_data` function as a base.
@@ -111,10 +110,10 @@ def _validate_data(
 
     def _convert_X(
         self,
-        X: Union[np.ndarray, List[np.ndarray]],
+        X: np.ndarray | list[np.ndarray],
         pad_unequal: bool = False,
         concatenate_channels: bool = False,
-    ) -> Union[np.ndarray, List[np.ndarray]]:
+    ) -> np.ndarray | list[np.ndarray]:
         dtypes = _safe_tags(self)["X_types"]
 
         if isinstance(X, np.ndarray) and X.ndim == 3:
@@ -191,7 +190,7 @@ def _convert_X(
 
         raise ValueError("Unable to convert X, please check the estimator tags.")
 
-    def _check_n_features(self, X: Union[np.ndarray, List[np.ndarray]], reset: bool):
+    def _check_n_features(self, X: np.ndarray | list[np.ndarray], reset: bool):
         """Set the `n_features_in_` attribute, or check against it.
 
         Uses the `scikit-learn` 1.2.1 `_check_n_features` function as a base.
@@ -251,9 +250,7 @@ def _more_tags(self) -> dict:
         return _DEFAULT_TAGS
 
     @classmethod
-    def get_test_params(
-        cls, parameter_set: Union[str, None] = None
-    ) -> Union[dict, List[dict]]:
+    def get_test_params(cls, parameter_set: str | None = None) -> dict | list[dict]:
         """Return unit test parameter settings for the estimator.
 
         Parameters
@@ -272,7 +269,7 @@ def get_test_params(
 
 
 def _clone_estimator(
-    base_estimator: BaseEstimator, random_state: Union[None, int, RandomState] = None
+    base_estimator: BaseEstimator, random_state: None | int | RandomState = None
 ) -> BaseEstimator:
     """Clone an estimator and set the random state if available."""
     estimator = clone(base_estimator)

tsml/compose/_channel_ensemble.py

@@ -8,7 +8,6 @@
 __all__ = ["ChannelEnsembleClassifier", "ChannelEnsembleRegressor"]
 
 from abc import ABCMeta
-from typing import List, Union
 
 import numpy as np
 from sklearn.base import ClassifierMixin, RegressorMixin
@@ -220,7 +219,7 @@ class ChannelEnsembleClassifier(ClassifierMixin, _BaseChannelEnsemble):
     def __init__(self, estimators, remainder="drop", random_state=None):
         super().__init__(estimators, remainder, random_state)
 
-    def fit(self, X: Union[np.ndarray, List[np.ndarray]], y: np.ndarray) -> object:
+    def fit(self, X: np.ndarray | list[np.ndarray], y: np.ndarray) -> object:
         """Fit the estimator to training data.
 
         Parameters
@@ -268,7 +267,7 @@ def fit(self, X: Union[np.ndarray, List[np.ndarray]], y: np.ndarray) -> object:
         self.estimators_ = estimators_
         return self
 
-    def predict(self, X: Union[np.ndarray, List[np.ndarray]]) -> np.ndarray:
+    def predict(self, X: np.ndarray | list[np.ndarray]) -> np.ndarray:
         """Predicts labels for sequences in X.
 
         Parameters
@@ -294,7 +293,7 @@ def predict(self, X: Union[np.ndarray, List[np.ndarray]]) -> np.ndarray:
             [self.classes_[int(np.argmax(prob))] for prob in self.predict_proba(X)]
         )
 
-    def predict_proba(self, X: Union[np.ndarray, List[np.ndarray]]) -> np.ndarray:
+    def predict_proba(self, X: np.ndarray | list[np.ndarray]) -> np.ndarray:
         """Predicts labels probabilities for sequences in X.
 
         Parameters
@@ -334,9 +333,7 @@ def _more_tags(self) -> dict:
         }
 
     @classmethod
-    def get_test_params(
-        cls, parameter_set: Union[str, None] = None
-    ) -> Union[dict, List[dict]]:
+    def get_test_params(cls, parameter_set: str | None = None) -> dict | list[dict]:
         """Return unit test parameter settings for the estimator.
 
         Parameters
@@ -430,7 +427,7 @@ class ChannelEnsembleRegressor(RegressorMixin, _BaseChannelEnsemble):
     def __init__(self, estimators, remainder="drop", random_state=None):
         super().__init__(estimators, remainder, random_state)
 
-    def fit(self, X: Union[np.ndarray, List[np.ndarray]], y: np.ndarray) -> object:
+    def fit(self, X: np.ndarray | list[np.ndarray], y: np.ndarray) -> object:
         """Fit the estimator to training data.
 
         Parameters
@@ -468,7 +465,7 @@ def fit(self, X: Union[np.ndarray, List[np.ndarray]], y: np.ndarray) -> object:
         self.estimators_ = estimators_
         return self
 
-    def predict(self, X: Union[np.ndarray, List[np.ndarray]]) -> np.ndarray:
+    def predict(self, X: np.ndarray | list[np.ndarray]) -> np.ndarray:
         """Predicts labels for sequences in X.
 
         Parameters
@@ -501,9 +498,7 @@ def _more_tags(self) -> dict:
         return {"X_types": ["np_list", "3darray"], "equal_length_only": False}
 
     @classmethod
-    def get_test_params(
-        cls, parameter_set: Union[str, None] = None
-    ) -> Union[dict, List[dict]]:
+    def get_test_params(cls, parameter_set: str | None = None) -> dict | list[dict]:
         """Return unit test parameter settings for the estimator.
 
         Parameters

tsml/datasets/_data_io.py

@@ -1,7 +1,6 @@
 """Data loading functions."""
 
 import os
-from typing import Tuple, Union
 
 import numpy as np
 
@@ -19,10 +18,10 @@
 
 def load_from_ts_file(
     file_path: str,
-    replace_missing_vals_with: Union[str, int, float] = "NaN",
-    X_dtype: Union[None, type] = None,
-    y_dtype: Union[None, type] = None,
-) -> Union[np.ndarray, list, Tuple[np.ndarray, np.ndarray], Tuple[list, np.ndarray]]:
+    replace_missing_vals_with: str | int | float = "NaN",
+    X_dtype: None | type = None,
+    y_dtype: None | type = None,
+) -> np.ndarray | list | tuple[np.ndarray, np.ndarray] | tuple[list, np.ndarray]:
     """Load data from a .ts file into a 3D numpy array or list of 2D numpy arrays.
 
     If the data to be loaded is equal length, a 3D numpy array will be returned. If the
@@ -425,8 +424,8 @@ def load_from_ts_file(
 
 
 def load_minimal_chinatown(
-    split: Union[None, str] = None
-) -> Tuple[np.ndarray, np.ndarray]:
+    split: None | str = None,
+) -> tuple[np.ndarray, np.ndarray]:
     """Load MinimalChinatown time series classification problem.
 
     This is an equal length univariate time series classification problem. It is a
@@ -459,8 +458,8 @@ def load_minimal_chinatown(
 
 
 def load_unequal_minimal_chinatown(
-    split: Union[None, str] = None
-) -> Tuple[list, np.ndarray]:
+    split: None | str = None,
+) -> tuple[list, np.ndarray]:
     """Load UnequalMinimalChinatown time series classification problem.
 
     This is an unequal length univariate time series classification problem. It is a
@@ -495,8 +494,8 @@ def load_unequal_minimal_chinatown(
 
 
 def load_equal_minimal_japanese_vowels(
-    split: Union[None, str] = None
-) -> Tuple[np.ndarray, np.ndarray]:
+    split: None | str = None,
+) -> tuple[np.ndarray, np.ndarray]:
     """Load the EqualMinimalJapaneseVowels time series classification problem.
 
     This is an equal length multivariate time series classification problem. It is a
@@ -530,8 +529,8 @@ def load_equal_minimal_japanese_vowels(
 
 
 def load_minimal_japanese_vowels(
-    split: Union[None, str] = None
-) -> Tuple[list, np.ndarray]:
+    split: None | str = None,
+) -> tuple[list, np.ndarray]:
     """Load the MinimalJapaneseVowels time series classification problem.
 
     This is an unequal length multivariate time series classification problem. It is a
@@ -565,8 +564,8 @@ def load_minimal_japanese_vowels(
 
 
 def load_minimal_gas_prices(
-    split: Union[None, str] = None
-) -> Tuple[np.ndarray, np.ndarray]:
+    split: None | str = None,
+) -> tuple[np.ndarray, np.ndarray]:
     """Load the MinimalGasPrices time series extrinsic regression problem.
 
     This is an equal length univariate time series regression problem. It is a
@@ -596,8 +595,8 @@ def load_minimal_gas_prices(
 
 
 def load_unequal_minimal_gas_prices(
-    split: Union[None, str] = None
-) -> Tuple[list, np.ndarray]:
+    split: None | str = None,
+) -> tuple[list, np.ndarray]:
     """Load the UnequalMinimalGasPrices time series extrinsic regression problem.
 
     This is an unequal length univariate time series regression problem. It is a
@@ -629,8 +628,8 @@ def load_unequal_minimal_gas_prices(
 
 def _load_provided_dataset(
     name: str,
-    split: Union[None, str] = None,
-) -> Union[Tuple[np.ndarray, np.ndarray], Tuple[list, np.ndarray]]:
+    split: None | str = None,
+) -> tuple[np.ndarray, np.ndarray] | tuple[list, np.ndarray]:
     """Load baked in time series datasets.
 
     Loads data from the provided tsml dataset files only.