Automatic pre-commit fixes

aeon/regression/_dummy.py

@@ -66,7 +66,7 @@ class DummyRegressor(BaseRegressor):
     >>> reg.predict(X_test)[:5]
     array([0.5, 0.5, 0.5, 0.5, 0.5])
     """
-    
+
     _tags = {
         "X_inner_type": ["np-list", "numpy3D"],
         "capability:missing_values": True,

aeon/regression/base.py

@@ -113,29 +113,29 @@ def predict(self, X) -> np.ndarray:
     Parameters
     ----------
     X : ``np.ndarray`` or ``list``
-        Input data, any number of channels, equal length series of shape  
-        ``(n_cases, n_channels, n_timepoints)``  
-        or 2D ``np.array`` (univariate, equal length series) of shape  
-        ``(n_cases, n_timepoints)``  
-        or list of ``numpy`` arrays (any number of channels, unequal length series)  
-        of shape ``[n_cases]``, 2D ``np.array`` ``(n_channels, n_timepoints_i)``,  
-        where ``n_timepoints_i`` is length of series ``i``. Other types are  
+        Input data, any number of channels, equal length series of shape
+        ``(n_cases, n_channels, n_timepoints)``
+        or 2D ``np.array`` (univariate, equal length series) of shape
+        ``(n_cases, n_timepoints)``
+        or list of ``numpy`` arrays (any number of channels, unequal length series)
+        of shape ``[n_cases]``, 2D ``np.array`` ``(n_channels, n_timepoints_i)``,
+        where ``n_timepoints_i`` is length of series ``i``. Other types are
         allowed and converted into one of the above.
 
-        Different estimators have different capabilities to handle different  
-        types of input. If ``self.get_tag("capability:multivariate")`` is ``False``,  
-        they cannot handle multivariate series, so either ``n_channels == 1`` is  
-        ``True`` or ``X`` is 2D of shape ``(n_cases, n_timepoints)``.  
+        Different estimators have different capabilities to handle different
+        types of input. If ``self.get_tag("capability:multivariate")`` is ``False``,
+        they cannot handle multivariate series, so either ``n_channels == 1`` is
+        ``True`` or ``X`` is 2D of shape ``(n_cases, n_timepoints)``.
 
-        If ``self.get_tag("capability:unequal_length")`` is ``False``,  
-        they cannot handle unequal length input. In both situations,  
-        a ``ValueError`` is raised if ``X`` has a characteristic  
+        If ``self.get_tag("capability:unequal_length")`` is ``False``,
+        they cannot handle unequal length input. In both situations,
+        a ``ValueError`` is raised if ``X`` has a characteristic
         that the estimator does not support.
 
     Returns
     -------
     predictions : ``np.ndarray``
-        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.  
+        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.
         Indices correspond to instance indices in ``X``.
     """
         self._check_is_fitted()
@@ -148,48 +148,48 @@ def fit_predict(self, X, y) -> np.ndarray:
         """
     ``Fits`` the regressor and ``predicts`` class labels for ``X``.
 
-    ``fit_predict`` produces prediction estimates using just the train data.  
-    By default, this is through ``10x`` cross-validation, although some estimators  
-    may utilize specialist techniques such as out-of-bag estimates or leave-one-out  
+    ``fit_predict`` produces prediction estimates using just the train data.
+    By default, this is through ``10x`` cross-validation, although some estimators
+    may utilize specialist techniques such as out-of-bag estimates or leave-one-out
     cross-validation.
 
-    Regressors that override ``_fit_predict`` will have the  
+    Regressors that override ``_fit_predict`` will have the
     ``capability:train_estimate`` tag set to ``True``.
 
-    Generally, this will not be the same as fitting on the whole train data  
-    and then making train predictions. To do this, you should call  
+    Generally, this will not be the same as fitting on the whole train data
+    and then making train predictions. To do this, you should call
     ``fit(X, y).predict(X)``.
 
     Parameters
     ----------
     X : ``np.ndarray`` or ``list``
-        Input data, any number of channels, equal length series of shape  
-        ``(n_cases, n_channels, n_timepoints)``  
-        or 2D ``np.array`` (univariate, equal length series) of shape  
-        ``(n_cases, n_timepoints)``  
-        or list of ``numpy`` arrays (any number of channels, unequal length series)  
-        of shape ``[n_cases]``, 2D ``np.array`` ``(n_channels, n_timepoints_i)``,  
-        where ``n_timepoints_i`` is length of series ``i``. Other types are  
+        Input data, any number of channels, equal length series of shape
+        ``(n_cases, n_channels, n_timepoints)``
+        or 2D ``np.array`` (univariate, equal length series) of shape
+        ``(n_cases, n_timepoints)``
+        or list of ``numpy`` arrays (any number of channels, unequal length series)
+        of shape ``[n_cases]``, 2D ``np.array`` ``(n_channels, n_timepoints_i)``,
+        where ``n_timepoints_i`` is length of series ``i``. Other types are
         allowed and converted into one of the above.
 
-        Different estimators have different capabilities to handle different  
-        types of input. If ``self.get_tag("capability:multivariate")`` is ``False``,  
-        they cannot handle multivariate series, so either ``n_channels == 1`` is  
-        ``True`` or ``X`` is 2D of shape ``(n_cases, n_timepoints)``.  
+        Different estimators have different capabilities to handle different
+        types of input. If ``self.get_tag("capability:multivariate")`` is ``False``,
+        they cannot handle multivariate series, so either ``n_channels == 1`` is
+        ``True`` or ``X`` is 2D of shape ``(n_cases, n_timepoints)``.
 
-        If ``self.get_tag("capability:unequal_length")`` is ``False``,  
-        they cannot handle unequal length input. In both situations,  
-        a ``ValueError`` is raised if ``X`` has a characteristic  
+        If ``self.get_tag("capability:unequal_length")`` is ``False``,
+        they cannot handle unequal length input. In both situations,
+        a ``ValueError`` is raised if ``X`` has a characteristic
         that the estimator does not support.
 
     y : ``np.ndarray``
-        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets  
+        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets
         (ground truth) for fitting. Indices correspond to instance indices in ``X``.
 
     Returns
     -------
     predictions : ``np.ndarray``
-        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.  
+        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.
         Indices correspond to instance indices in ``X``.
        """
 
@@ -208,35 +208,35 @@ def score(self, X, y, metric="r2", metric_params=None) -> float:
     Parameters
     ----------
     X : ``np.ndarray`` or ``list``
-        Input data, any number of channels, equal length series of shape  
-        ``(n_cases, n_channels, n_timepoints)``  
-        or 2D ``np.array`` (univariate, equal length series) of shape  
-        ``(n_cases, n_timepoints)``  
-        or list of ``numpy`` arrays (any number of channels, unequal length series)  
-        of shape ``[n_cases]``, 2D ``np.array`` ``(n_channels, n_timepoints_i)``,  
-        where ``n_timepoints_i`` is length of series ``i``. Other types are  
+        Input data, any number of channels, equal length series of shape
+        ``(n_cases, n_channels, n_timepoints)``
+        or 2D ``np.array`` (univariate, equal length series) of shape
+        ``(n_cases, n_timepoints)``
+        or list of ``numpy`` arrays (any number of channels, unequal length series)
+        of shape ``[n_cases]``, 2D ``np.array`` ``(n_channels, n_timepoints_i)``,
+        where ``n_timepoints_i`` is length of series ``i``. Other types are
         allowed and converted into one of the above.
 
-        Different estimators have different capabilities to handle different  
-        types of input. If ``self.get_tag("capability:multivariate")`` is ``False``,  
-        they cannot handle multivariate series, so either ``n_channels == 1`` is  
-        ``True`` or ``X`` is 2D of shape ``(n_cases, n_timepoints)``.  
+        Different estimators have different capabilities to handle different
+        types of input. If ``self.get_tag("capability:multivariate")`` is ``False``,
+        they cannot handle multivariate series, so either ``n_channels == 1`` is
+        ``True`` or ``X`` is 2D of shape ``(n_cases, n_timepoints)``.
 
-        If ``self.get_tag("capability:unequal_length")`` is ``False``,  
-        they cannot handle unequal length input. In both situations,  
-        a ``ValueError`` is raised if ``X`` has a characteristic  
+        If ``self.get_tag("capability:unequal_length")`` is ``False``,
+        they cannot handle unequal length input. In both situations,
+        a ``ValueError`` is raised if ``X`` has a characteristic
         that the estimator does not have the capability for.
 
     y : ``np.ndarray``
-        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets  
+        1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets
         (ground truth) for fitting. Indices correspond to instance indices in ``X``.
 
     metric : ``Union[str, callable]``, default=``"r2"``
-        Defines the scoring metric to test the fit of the model.  
+        Defines the scoring metric to test the fit of the model.
         For supported string arguments, check ``sklearn.metrics.get_scorer_names``.
 
     metric_params : ``dict``, default=``None``
-        Contains parameters to be passed to the scoring function.  
+        Contains parameters to be passed to the scoring function.
         If ``None``, no parameters are passed.
 
     Returns
@@ -285,7 +285,7 @@ def _fit(self, X, y):
                List of 2D ``np.ndarray`` of shape ``(n_cases)``.
 
         y : ``np.ndarray``
-             1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets  
+             1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets
              for fitting. Indices correspond to instance indices in ``X``.
 
        Returns
@@ -316,10 +316,10 @@ def _predict(self, X) -> np.ndarray:
            - If ``self.get_tag("X_inner_type")`` equals ``"np-list"``:
              List of 2D ``np.ndarray`` of shape ``(n_cases)``.
 
-        Returns 
+        Returns
         -------
         predictions : ``np.ndarray``
-           1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.  
+           1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.
            Indices correspond to instance indices in ``X``.
         """
 
@@ -339,13 +339,13 @@ def _fit_predict(self, X, y) -> np.ndarray:
             List of 2D ``np.ndarray`` of shape ``(n_cases)``.
 
         y : ``np.ndarray``
-           1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets  
+           1D ``np.array`` of ``float``, of shape ``(n_cases)`` - regression targets
            (ground truth) for fitting, with indices corresponding to instance indices in ``X``.
 
          Returns
         -------
         predictions : ``np.ndarray``
-           1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.  
+           1D ``np.array`` of ``float``, of shape ``(n_cases)`` - predicted regression labels.
            Indices correspond to instance indices in ``X``.
         """
 

aeon/regression/compose/_ensemble.py

@@ -30,7 +30,7 @@ class RegressorEnsemble(BaseCollectionEnsemble, BaseRegressor):
         If ``None``, all estimators have equal weight.
     cv : ``None``, ``int``, or ``sklearn`` cross-validation object, default=``None``
         Only used if ``weights`` is a ``float``. Specifies the cross-validation strategy
-        to estimate model performance. 
+        to estimate model performance.
         If ``None``, predictions are obtained using each estimator's ``fit_predict`` method.
         If ``int`` or ``sklearn`` object, it is passed directly to ``cross_val_predict`` from ``sklearn``.
     metric : ``sklearn`` performance metric function, default=``None``

aeon/regression/compose/_pipeline.py

@@ -14,18 +14,18 @@ class RegressorPipeline(BaseCollectionPipeline, BaseRegressor):
     The ``RegressorPipeline`` compositor chains transformers and a single regressor.
     The pipeline is constructed with a list of ``aeon`` transformers and a regressor,
     i.e., estimators following the ``BaseTransformer`` and ``BaseRegressor`` interface.
-    
+
     The transformer list can be either unnamed (a simple list of transformers) or named
     (a list of ``(str, estimator)`` pairs).
 
     For a list of transformers ``trafo1``, ``trafo2``, ..., ``trafoN`` and a regressor ``reg``,
     the pipeline behaves as follows:
-    
+
     - ``fit(X, y)``: Runs ``trafo1.fit_transform(X)``, then sequentially applies
       ``trafo2.fit_transform()`` to the output of ``trafo1``, and so on.
       Finally, ``reg.fit()`` is run with ``X`` being the output of ``trafoN.fit_transform()``,
       while ``y`` remains unchanged.
-    
+
     - ``predict(X)``: Sequentially applies ``trafo1.transform()``, then ``trafo2.transform()``, etc.
       The final transformed ``X`` is passed to ``reg.predict()``, and the output is returned.
 
@@ -67,8 +67,7 @@ class RegressorPipeline(BaseCollectionPipeline, BaseRegressor):
     RegressorPipeline(regressor=DummyRegressor(),
                       transformers=[AutocorrelationFunctionTransformer(n_lags=10)])
     >>> y_pred = pipeline.predict(X_test)
-   """
-
+    """
 
     _tags = {
         "X_inner_type": ["numpy3D", "np-list"],

aeon/regression/deep_learning/_cnn.py

@@ -67,18 +67,18 @@ class TimeCNNRegressor(BaseDeepRegressor):
 optimizer : ``keras.optimizer``, default = ``tf.keras.optimizers.Adam()``
     The Keras optimizer used for training.
 metrics : ``str`` or ``list`` of ``str``, default = ``"mean_squared_error"``
-    The evaluation metrics to use during training. If a single string metric is provided,  
+    The evaluation metrics to use during training. If a single string metric is provided,
     it will be used as the only metric. If a list of metrics is provided, all will be used for evaluation.
 callbacks : ``keras.callbacks.Callback`` or ``list`` of ``keras.callbacks.Callback``, default = ``None``
     The default list of callbacks includes ``ModelCheckpoint``.
 file_path : ``str``
     File path for saving the best model (if checkpointing is used as a callback).
 save_best_model : ``bool``, default = ``False``
-    Whether or not to save the best model. If the ``ModelCheckpoint`` callback is used  
-    by default, setting this to ``True`` prevents the automatic deletion of the best  
+    Whether or not to save the best model. If the ``ModelCheckpoint`` callback is used
+    by default, setting this to ``True`` prevents the automatic deletion of the best
     saved model, allowing the user to choose the file name.
 save_last_model : ``bool``, default = ``False``
-    Whether or not to save the last trained model using the base class method  
+    Whether or not to save the last trained model using the base class method
     ``save_last_model_to_file``.
 save_init_model : ``bool``, default = ``False``
     Whether to save the initial model.
@@ -91,12 +91,12 @@ class TimeCNNRegressor(BaseDeepRegressor):
 
 Notes
 -----
-Adapted from the implementation by Fawaz et al.  
+Adapted from the implementation by Fawaz et al.
 Source: `https://github.com/hfawaz/dl-4-tsc/blob/master/classifiers/cnn.py`
 
 References
 ----------
-.. [1] Zhao et al., "Convolutional Neural Networks for Time Series Classification,"  
+.. [1] Zhao et al., "Convolutional Neural Networks for Time Series Classification,"
    *Journal of Systems Engineering and Electronics*, 28(1), 2017.
 
 Examples
@@ -329,4 +329,4 @@ def _get_test_params(cls, parameter_set="default"):
             "avg_pool_size": 4,
         }
 
-        return [param]
+        return [param]

aeon/regression/deep_learning/_disjoint_cnn.py

@@ -1,4 +1,4 @@
-"""""DisjointCNN regressor."""
+""" ""DisjointCNN regressor."""
 
 __maintainer__ = ["hadifawaz1999"]
 __all__ = ["DisjointCNNRegressor"]
@@ -108,7 +108,7 @@ class DisjointCNNRegressor(BaseDeepRegressor):
         The name of the file of the init model.
     callbacks : keras callback or list of callbacks, default=``None``
         The default list of callbacks are set to ``ModelCheckpoint`` and ``ReduceLROnPlateau``.
-    
+
     Notes
     -----
     Adapted from the implementation from:
@@ -371,8 +371,7 @@ def _get_test_params(cls, parameter_set="default"):
             Parameters to create testing instances of the class.
             Each ``dict`` contains parameters to construct an "interesting" test instance, i.e.,
             ``MyClass(**params)`` or ``MyClass(**params[i])`` creates a valid test instance.
-            """
-
+        """
         param1 = {
             "n_epochs": 3,
             "batch_size": 4,
@@ -393,4 +392,4 @@ def _get_test_params(cls, parameter_set="default"):
             "use_mini_batch_size": True,
         }
 
-        return [param1, param2]
+        return [param1, param2]

aeon/regression/deep_learning/_encoder.py

@@ -108,6 +108,7 @@ class EncoderRegressor(BaseDeepRegressor):
     for Artificial Intelligence, 120--129 2018.
 
     """
+
     def __init__(
         self,
         n_epochs=100,