[ENH] Added load_model functionality to InceptionTimeRegressor and LITETimeRegressor

aeon/regression/deep_learning/_inception_time.py

@@ -336,6 +336,39 @@ def _predict(self, X) -> np.ndarray:
 
         return ypreds
 
+    @classmethod
+    def load_model(cls, model_paths):
+        """
+        Load pre-trained regressors instead of fitting.
+
+        This enables full use of the estimator's functionality such as predict.
+
+        Parameters
+        ----------
+        model_paths : list of str (list of paths including the
+                                    model names and extension)
+            List of file paths to the saved .keras models of each regressor.
+
+        Returns
+        -------
+        InceptionTimeRegressor
+            An instance of InceptionTimeRegressor with the pre-trained models loaded.
+        """
+        assert isinstance(
+            model_paths, list
+        ), "model_paths should be a list of paths to the models"
+
+        regressor = cls(n_regressors=len(model_paths))
+        regressor.regressors_ = []
+
+        for path in model_paths:
+            ind_regressor = IndividualInceptionRegressor()
+            ind_regressor.load_model(path)
+            regressor.regressors_.append(ind_regressor)
+
+        regressor.is_fitted = True
+        return regressor
+
     @classmethod
     def _get_test_params(cls, parameter_set="default"):
         """Return testing parameter settings for the estimator.

aeon/regression/deep_learning/_lite_time.py

@@ -262,6 +262,39 @@ def _predict(self, X) -> np.ndarray:
 
         return vals
 
+    @classmethod
+    def load_model(cls, model_paths):
+        """
+        Load pre-trained regressors instead of fitting.
+
+        This enables full use of the estimator's functionality such as predict.
+
+        Parameters
+        ----------
+        model_paths : list of str (list of paths including the
+                                    model names and extension)
+            List of file paths to the saved .keras models of each regressor.
+
+        Returns
+        -------
+        LITETimeRegressor
+            An instance of LITETimeRegressor with the pre-trained models loaded.
+        """
+        assert isinstance(
+            model_paths, list
+        ), "model_paths should be a list of paths to the models"
+
+        regressor = cls(n_regressors=len(model_paths))
+        regressor.regressors_ = []
+
+        for path in model_paths:
+            ind_regressor = IndividualLITERegressor()
+            ind_regressor.load_model(path)
+            regressor.regressors_.append(ind_regressor)
+
+        regressor.is_fitted = True
+        return regressor
+
     @classmethod
     def _get_test_params(cls, parameter_set="default"):
         """Return testing parameter settings for the estimator.

aeon/regression/deep_learning/tests/test_inception_time.py

@@ -0,0 +1,55 @@
+"""Tests for save/load functionality of InceptionTimeRegressor."""
+
+import glob
+import os
+import tempfile
+
+import numpy as np
+import pytest
+
+from aeon.regression.deep_learning import InceptionTimeRegressor
+from aeon.testing.data_generation import make_example_3d_numpy
+from aeon.utils.validation._dependencies import _check_soft_dependencies
+
+
+@pytest.mark.skipif(
+    not _check_soft_dependencies("tensorflow", severity="none"),
+    reason="skip test if required soft dependency not available",
+)
+def test_save_load_inceptiontime_regressor():
+    """Test saving and loading for InceptionTimeRegressor."""
+    with tempfile.TemporaryDirectory() as temp:
+        temp_dir = os.path.join(temp, "")
+
+        X, y = make_example_3d_numpy(
+            n_cases=10,
+            n_channels=1,
+            n_timepoints=12,
+            return_y=True,
+            regression_target=True,
+        )
+
+        model = InceptionTimeRegressor(
+            n_epochs=1,
+            random_state=42,
+            save_best_model=True,
+            file_path=temp_dir,
+            n_regressors=1,
+        )
+        model.fit(X, y)
+
+        y_pred_orig = model.predict(X)
+
+        model_files = glob.glob(
+            os.path.join(temp_dir, f"{model.best_file_name}*.keras")
+        )
+
+        loaded_model = InceptionTimeRegressor.load_model(model_paths=model_files)
+
+        assert isinstance(loaded_model, InceptionTimeRegressor)
+
+        preds = loaded_model.predict(X)
+        assert isinstance(preds, np.ndarray)
+
+        assert len(preds) == len(y)
+        np.testing.assert_array_almost_equal(preds, y_pred_orig, decimal=4)

aeon/regression/deep_learning/tests/test_lite_time.py

@@ -0,0 +1,55 @@
+"""Tests for save/load functionality of LITETimeRegressor."""
+
+import glob
+import os
+import tempfile
+
+import numpy as np
+import pytest
+
+from aeon.regression.deep_learning import LITETimeRegressor
+from aeon.testing.data_generation import make_example_3d_numpy
+from aeon.utils.validation._dependencies import _check_soft_dependencies
+
+
+@pytest.mark.skipif(
+    not _check_soft_dependencies("tensorflow", severity="none"),
+    reason="skip test if required soft dependency not available",
+)
+def test_save_load_litetimeregressor_regressor():
+    """Test saving and loading for LITETimeRegressor."""
+    with tempfile.TemporaryDirectory() as temp:
+        temp_dir = os.path.join(temp, "")
+
+        X, y = make_example_3d_numpy(
+            n_cases=10,
+            n_channels=1,
+            n_timepoints=12,
+            return_y=True,
+            regression_target=True,
+        )
+
+        model = LITETimeRegressor(
+            n_epochs=1,
+            random_state=42,
+            save_best_model=True,
+            file_path=temp_dir,
+            n_regressors=1,
+        )
+        model.fit(X, y)
+
+        y_pred_orig = model.predict(X)
+
+        model_files = glob.glob(
+            os.path.join(temp_dir, f"{model.best_file_name}*.keras")
+        )
+
+        loaded_model = LITETimeRegressor.load_model(model_paths=model_files)
+
+        assert isinstance(loaded_model, LITETimeRegressor)
+
+        preds = loaded_model.predict(X)
+        assert isinstance(preds, np.ndarray)
+
+        assert len(preds) == len(y)
+        np.testing.assert_array_almost_equal(preds, y_pred_orig, decimal=4)