Merge branch 'main' into fix-dataset-root-3088

Author: satwiksps

.pre-commit-config.yaml

@@ -27,7 +27,7 @@ repos:
         args: [ "--create", "--python-folders", "aeon" ]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.14.4
+    rev: v0.14.5
     hooks:
       - id: ruff
         args: [ "--fix"]
@@ -53,7 +53,7 @@ repos:
         args: [ "--max-line-length=88", "--extend-ignore=E203" ]
 
   - repo: https://github.com/psf/black
-    rev: 25.9.0
+    rev: 25.11.0
     hooks:
       - id: black
         language_version: python3

aeon/anomaly_detection/series/distance_based/_rockad.py

@@ -85,7 +85,7 @@ class ROCKAD(BaseSeriesAnomalyDetector):
     >>> detector.fit(X_train)
     ROCKAD(...)
     >>> detector.predict(X_test)
-    array([0.        , 0.00554713, 0.0699094 , 0.22881059, 0.32382585,
+    array([0.        , 0.00554713, 0.06990941, 0.22881059, 0.32382585,
            0.43652154, 0.43652154, 0.43652154, 0.43652154, 0.43652154,
            0.43652154, 0.43652154, 0.43652154, 0.43652154, 0.43652154,
            0.52382585, 0.65200875, 0.80313368, 0.85194345, 1.        ])

aeon/classification/deep_learning/_inception_time.py

@@ -1,5 +1,7 @@
 """InceptionTime and Inception classifiers."""
 
+from __future__ import annotations
+
 __maintainer__ = ["hadifawaz1999"]
 __all__ = ["InceptionTimeClassifier"]
 
@@ -251,7 +253,7 @@ def __init__(
 
         super().__init__()
 
-    def _fit(self, X, y):
+    def _fit(self, X: np.ndarray, y: np.ndarray) -> InceptionTimeClassifier:
         """Fit the ensemble of IndividualInceptionClassifier models.
 
         Parameters
@@ -307,7 +309,7 @@ def _fit(self, X, y):
 
         return self
 
-    def _predict(self, X) -> np.ndarray:
+    def _predict(self, X: np.ndarray) -> np.ndarray:
         """Predict the labels of the test set using InceptionTime.
 
         Parameters
@@ -328,7 +330,7 @@ def _predict(self, X) -> np.ndarray:
             ]
         )
 
-    def _predict_proba(self, X) -> np.ndarray:
+    def _predict_proba(self, X: np.ndarray) -> np.ndarray:
         """Predict the proba of labels of the test set using InceptionTime.
 
         Parameters
@@ -351,24 +353,30 @@ def _predict_proba(self, X) -> np.ndarray:
         return probs
 
     @classmethod
-    def load_model(self, model_path, classes):
-        """Load pre-trained classifiers instead of fitting.
+    def load_model(
+        self, model_path: list[str], classes: np.ndarray
+    ) -> InceptionTimeClassifier:
+        """Load pre-trained keras models from disk instead of fitting.
 
+        Pretrained models should be saved using "save_best_model"
+        or "save_last_model" boolean parameter.
         When calling this function, all functionalities can be used
-        such as predict, predict_proba, etc. with the loaded models.
+        such as predict, predict_proba etc. with the loaded model.
 
         Parameters
         ----------
         model_path : list of str (list of paths including the model names and extension)
-            The directory where the models will be saved including the model
-            names with a ".keras" extension.
-        classes : np.ndarray
+            The complete path (including file name and '.keras' extension)
+            from which the pre-trained model's weights and configuration
+            are loaded.
+         classes : np.ndarray
             The set of unique classes the pre-trained loaded model is trained
             to predict during the classification task.
+        Example: model_path="path/to/file/best_model.keras"
 
         Returns
         -------
-        None
+        InceptionTimeClassifier
         """
         assert (
             type(model_path) is list

aeon/classification/deep_learning/_lite_time.py

@@ -1,5 +1,7 @@
 """LITETime and LITE classifiers."""
 
+from __future__ import annotations
+
 __maintainer__ = ["hadifawaz1999"]
 __all__ = ["LITETimeClassifier"]
 
@@ -193,7 +195,7 @@ def __init__(
 
         super().__init__()
 
-    def _fit(self, X, y):
+    def _fit(self, X: np.ndarray, y: np.ndarray) -> LITETimeClassifier:
         """Fit the ensemble of IndividualLITEClassifier models.
 
         Parameters
@@ -239,7 +241,7 @@ def _fit(self, X, y):
 
         return self
 
-    def _predict(self, X) -> np.ndarray:
+    def _predict(self, X: np.ndarray) -> np.ndarray:
         """Predict the labels of the test set using LITETime.
 
         Parameters
@@ -260,7 +262,7 @@ def _predict(self, X) -> np.ndarray:
             ]
         )
 
-    def _predict_proba(self, X) -> np.ndarray:
+    def _predict_proba(self, X: np.ndarray) -> np.ndarray:
         """Predict the proba of labels of the test set using LITETime.
 
         Parameters
@@ -283,24 +285,30 @@ def _predict_proba(self, X) -> np.ndarray:
         return probs
 
     @classmethod
-    def load_model(self, model_path, classes):
-        """Load pre-trained classifiers instead of fitting.
+    def load_model(
+        self, model_path: list[str], classes: np.ndarray
+    ) -> LITETimeClassifier:
+        """Load pre-trained keras models from disk instead of fitting.
 
+        Pretrained models should be saved using "save_best_model"
+        or "save_last_model" boolean parameter.
         When calling this function, all functionalities can be used
-        such as predict, predict_proba, etc. with the loaded models.
+        such as predict, predict_proba etc. with the loaded model.
 
         Parameters
         ----------
         model_path : list of str (list of paths including the model names and extension)
-            The director where the models will be saved including the model
-            names with a ".keras" extension.
-        classes : np.ndarray
+            The complete path (including file name and '.keras' extension)
+            from which the pre-trained model's weights and configuration
+            are loaded.
+         classes : np.ndarray
             The set of unique classes the pre-trained loaded model is trained
             to predict during the classification task.
+        Example: model_path="path/to/file/best_model.keras"
 
         Returns
         -------
-        None
+        LITETimeClassifier
         """
         assert (
             type(model_path) is list

aeon/classification/deep_learning/base.py

@@ -22,6 +22,8 @@ class name: BaseDeepClassifier
 because we can generalise tags, _predict and _predict_proba
 """
 
+from __future__ import annotations
+
 __maintainer__ = ["hadifawaz1999"]
 __all__ = ["BaseDeepClassifier"]
 
@@ -178,17 +180,20 @@ def save_last_model_to_file(self, file_path="./"):
         """
         self.model_.save(file_path + self.last_file_name + ".keras")
 
-    def load_model(self, model_path, classes):
+    def load_model(self, model_path: str, classes: np.ndarray) -> None:
         """Load a pre-trained keras model instead of fitting.
 
+        Pretrained model should be saved using "save_last_model" or
+        "save_best_model" boolean parameter.
         When calling this function, all functionalities can be used
         such as predict, predict_proba etc. with the loaded model.
 
         Parameters
         ----------
         model_path : str (path including model name and extension)
-            The directory where the model will be saved including the model
-            name with a ".keras" extension.
+            The complete path (including file name and '.keras' extension)
+            from which the pre-trained model's weights and configuration
+            are loaded.
             Example: model_path="path/to/file/best_model.keras"
         classes : np.ndarray
             The set of unique classes the pre-trained loaded model is trained

aeon/clustering/averaging/_ba_petitjean.py

@@ -186,7 +186,7 @@ def petitjean_barycenter_average(
     return barycenter
 
 
-@njit(cache=True, fastmath=True)
+@njit(cache=True, fastmath=True, parallel=True)
 def _ba_one_iter_petitjean(
     barycenter: np.ndarray,
     X: np.ndarray,

aeon/clustering/averaging/_kasba_average.py

@@ -248,7 +248,7 @@ def _kasba_refine_one_iter(
     for i in shuffled_indices:
         curr_ts = X[i]
         curr_alignment, _ = _get_alignment_path(
-            center=barycenter,
+            center=barycenter_copy,
             ts=curr_ts,
             distance=distance,
             window=window,

aeon/clustering/averaging/tests/test_kasba.py

@@ -63,9 +63,9 @@ def test_kasba_ba_expected():
     ],
 )
 def test_kasba_ba_uni(distance, init_barycenter):
-    """Test kasba dba functionality."""
+    """Test kasba ba functionality."""
     distance = distance[0]
-    X_train_uni = make_example_3d_numpy(10, 1, 10, random_state=1, return_y=False)
+    X_train_uni = make_example_3d_numpy(20, 1, 10, random_state=1, return_y=False)
 
     params = {
         "window": 0.2,
@@ -92,7 +92,6 @@ def test_kasba_ba_uni(distance, init_barycenter):
     assert average_ts_uni.shape == X_train_uni[0].shape
     assert np.allclose(average_ts_uni, call_directly_average_ts_uni)
 
-    # EDR and shape_dtw with random values don't update the barycenter so skipping
     if distance not in ["shape_dtw", "edr"]:
         # Test not just returning the init barycenter
         assert not np.array_equal(average_ts_uni, init_barycenter)
@@ -144,7 +143,11 @@ def test_kasba_distance_params(distance):
     """Test kasba with various distance parameters."""
     distance_params = distance[1]
     distance = distance[0]
-    X_train_uni = make_example_3d_numpy(10, 1, 10, random_state=1, return_y=False)
+    if distance == "soft_dtw":
+        # Skip for now and add back when soft-dtw refactored
+        return
+
+    X_train_uni = make_example_3d_numpy(20, 1, 10, random_state=1, return_y=False)
 
     for key in distance_params:
         curr_param = {key: distance_params[key]}

aeon/clustering/deep_learning/tests/test_deep_clusterer_io.py

@@ -0,0 +1,52 @@
+"""Tests for loading Keras models in deep autoencoder clusterers."""
+
+import tempfile
+from pathlib import Path
+
+import numpy as np
+import pytest
+
+from aeon.clustering.deep_learning._ae_abgru import AEAttentionBiGRUClusterer
+from aeon.clustering.deep_learning._ae_bgru import AEBiGRUClusterer
+from aeon.clustering.deep_learning._ae_dcnn import AEDCNNClusterer
+from aeon.clustering.deep_learning._ae_drnn import AEDRNNClusterer
+from aeon.clustering.deep_learning._ae_fcn import AEFCNClusterer
+from aeon.clustering.deep_learning._ae_resnet import AEResNetClusterer
+from aeon.utils.validation._dependencies import _check_soft_dependencies
+
+ALL_DEEP_CLUSTERERS = [
+    AEAttentionBiGRUClusterer,
+    AEBiGRUClusterer,
+    AEDCNNClusterer,
+    AEDRNNClusterer,
+    AEFCNClusterer,
+    AEResNetClusterer,
+]
+
+
+@pytest.mark.skipif(
+    not _check_soft_dependencies("tensorflow", severity="none"),
+    reason="TensorFlow not installed.",
+)
+@pytest.mark.parametrize("cls", ALL_DEEP_CLUSTERERS)
+def test_deep_clusterer_load_model(cls):
+    """Test that all deep autoencoder clusterers load saved Keras models correctly."""
+    X = np.random.randn(4, 10, 1).astype(np.float32)
+    params = cls._get_test_params()[0]
+    params["n_epochs"] = 1
+    params["save_best_model"] = True
+
+    with tempfile.TemporaryDirectory() as tmp:
+        params["file_path"] = tmp + "/"
+        model = cls(**params)
+        model.fit(X)
+        trained_estimator = model._estimator
+        saved = list(Path(tmp).glob("*.keras"))
+        assert saved, f"No .keras file saved for {cls.__name__}"
+        model_path = str(saved[0])
+        loaded = cls(**params)
+        loaded.load_model(model_path, trained_estimator)
+        assert loaded.model_ is not None, f"Loaded model_ is None for {cls.__name__}"
+        assert hasattr(loaded.model_, "predict"), f"Invalid model_ for {cls.__name__}"
+        preds = loaded.predict(X)
+        assert preds.shape[0] == X.shape[0], f"Predict failed for {cls.__name__}"

aeon/clustering/tests/test_k_shape.py

@@ -7,13 +7,13 @@
 from aeon.datasets import load_basic_motions
 from aeon.utils.validation._dependencies import _check_estimator_deps
 
-expected_results = [2, 2, 2, 0, 0]
+expected_results = [1, 1, 1, 2, 2]
 
-inertia = 0.5645477840468736
+inertia = 0.5753409783429747
 
-expected_iters = 2
+expected_iters = 4
 
-expected_labels = [0, 2, 1, 1, 1]
+expected_labels = [2, 1, 0, 2, 2]
 
 
 @pytest.mark.skipif(