Merge branch 'main' into ajb/code_cov

.pre-commit-config.yaml

@@ -29,7 +29,7 @@ repos:
         args: [ "--create", "--python-folders", "aeon" ]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.2
+    rev: v0.8.3
     hooks:
       - id: ruff
         args: [ "--fix"]

README.md

@@ -149,3 +149,8 @@ If you use `aeon` we would appreciate a citation of the following [paper](https:
 ```
 
 If you let us know about your paper using `aeon`, we will happily list it [here](https://www.aeon-toolkit.org/en/stable/papers_using_aeon.html).
+
+## 💬 Further information
+
+`aeon` was forked from `sktime` `v0.16.0` in 2022 by an initial group of eight core
+developers.

aeon/classification/deep_learning/_lite_time.py

@@ -96,11 +96,13 @@ class LITETimeClassifier(BaseClassifier):
         The keras optimizer used for training.
     loss : str, default = "categorical_crossentropy"
         The name of the keras training loss.
-    metrics : str or list[str], default="accuracy"
-        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 are
-        provided, all will be used for evaluation.
+    metrics : str or list[str|function|keras.metrics.Metric], default="accuracy"
+        the evaluation metrics to use during training. each of this can be a
+        string, function or a keras.metrics.metric instance (for details, see
+        https://keras.io/api/metrics/).
+        if a single string metric is provided, it will be used as the only
+        metric. if a list of metrics are provided, all will be used for
+        evaluation.
 
     References
     ----------
@@ -398,11 +400,13 @@ class IndividualLITEClassifier(BaseDeepClassifier):
         The keras optimizer used for training.
     loss : str, default = "categorical_crossentropy"
         The name of the keras training loss.
-    metrics : str or list[str], default="accuracy"
-        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 are
-        provided, all will be used for evaluation.
+    metrics : str or list[str|function|keras.metrics.Metric], default="accuracy"
+        the evaluation metrics to use during training. each of this can be a
+        string, function or a keras.metrics.metric instance (for details, see
+        https://keras.io/api/metrics/).
+        if a single string metric is provided, it will be used as the only
+        metric. if a list of metrics are provided, all will be used for
+        evaluation.
 
     References
     ----------

aeon/regression/base.py

@@ -76,7 +76,7 @@ def fit(self, X, y) -> BaseCollectionEstimator:
             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,
+            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
@@ -122,7 +122,7 @@ def predict(self, X) -> np.ndarray:
             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,
+            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

aeon/transformations/collection/base.py

@@ -62,20 +62,19 @@ def fit(self, X, y=None):
         Parameters
         ----------
         X : np.ndarray or list
-            Input data, any number of channels, equal length series of shape ``(
-            n_cases, n_channels, 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.
+            Data to fit transform to, of valid collection type. Input data,
+            any number of channels, equal length series of shape ``(
+            n_cases, n_channels, 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,
+            types of input. If ``self.get_tag("capability:multivariate")`` is False,
             they cannot handle multivariate series. 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 to handle.
-              Data to fit transform to, of valid collection type.
         y : np.ndarray, default=None
             1D np.array of float or str, of shape ``(n_cases)`` - class labels
             (ground truth) for fitting indices corresponding to instance indices in X.
@@ -117,20 +116,20 @@ def transform(self, X, y=None):
         Parameters
         ----------
         X : np.ndarray or list
-            Input data, any number of channels, equal length series of shape ``(
-            n_cases, n_channels, 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.
+            Data to fit transform to, of valid collection type. Input data,
+            any number of channels, equal length series of shape ``(
+            n_cases, n_channels, 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,
+            types of input. If ``self.get_tag("capability:multivariate")`` is False,
             they cannot handle multivariate series. 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 to handle.
-              Data to fit transform to, of valid collection type.
+
         y : np.ndarray, default=None
             1D np.array of float or str, of shape ``(n_cases)`` - class labels
             (ground truth) for fitting indices corresponding to instance indices in X.
@@ -171,20 +170,19 @@ def fit_transform(self, X, y=None):
         Parameters
         ----------
         X : np.ndarray or list
-            Input data, any number of channels, equal length series of shape ``(
-            n_cases, n_channels, 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.
+            Data to fit transform to, of valid collection type. Input data,
+            any number of channels, equal length series of shape ``(n_cases,
+            n_channels, 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,
+            types of input. If ``self.get_tag("capability:multivariate")`` is False,
             they cannot handle multivariate series. 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 to handle.
-              Data to fit transform to, of valid collection type.
         y : np.ndarray, default=None
             1D np.array of float or str, of shape ``(n_cases)`` - class labels
             (ground truth) for fitting indices corresponding to instance indices in X.
@@ -222,20 +220,19 @@ def inverse_transform(self, X, y=None):
         Parameters
         ----------
         X : np.ndarray or list
-            Input data, any number of channels, equal length series of shape ``(
-            n_cases, n_channels, 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.
+            Data to fit transform to, of valid collection type. Input data,
+            any number of channels, equal length series of shape ``(
+            n_cases, n_channels, 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,
+            types of input. If ``self.get_tag("capability:multivariate")`` is False,
             they cannot handle multivariate series. 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 to handle.
-              Data to fit transform to, of valid collection type.
         y : np.ndarray, default=None
             1D np.array of float or str, of shape ``(n_cases)`` - class labels
             (ground truth) for fitting indices corresponding to instance indices in X.

pyproject.toml

@@ -58,9 +58,11 @@ dependencies = [
 [project.optional-dependencies]
 # soft dependencies
 all_extras = [
-    "esig>=0.9.7; platform_system != 'Darwin' and python_version < '3.11'",
+    # Upper bound set as <1.0.0 as 1.0 dropped support for python 3.9. We will remove
+    # the upper bound once we also drop support for python 3.9 later in 2025.
+    "esig>=0.9.7,<1.0.0; platform_system != 'Darwin' and python_version < '3.11'",
     "imbalanced-learn",
-    "matplotlib>=3.3.2",
+    "matplotlib>=3.3.2",  # Remove upper bound
     "pycatch22>=0.4.5",
     "pyod>=1.1.3",
     "prts>=1.0.0.0",