final bits and docs for refactor

Author: MatthewMiddlehurst

aeon/anomaly_detection/base.py

@@ -11,40 +11,35 @@
 
 
 class BaseAnomalyDetector(BaseAeonEstimator):
-    """todo base class docs."""
+    """Anomaly detection base class."""
 
     _tags = {
-        # todo
+        "fit_is_empty": True,
+        "requires_y": False,
     }
 
     def __init__(self):
         super().__init__()
 
     @abstractmethod
     def fit(self, X, y=None):
-        """Fit time series anomaly detector to X.
+        """Fit anomaly detector to X, optionally to y.
 
-        If the tag ``fit_is_empty`` is true, this just sets the ``is_fitted`` tag to
-        true. Otherwise, it checks ``self`` can handle ``X``, formats ``X`` into
-        the structure required by ``self`` then passes ``X`` (and possibly ``y``) to
-        ``_fit``.
+        State change:
+            Changes state to "fitted".
+
+        Writes to self:
+        _is_fitted : flag is set to True.
 
         Parameters
         ----------
-        X : one of aeon.base._base_series.VALID_SERIES_INPUT_TYPES
-            The time series to fit the model to.
-            A valid aeon time series data structure. See
-            aeon.base._base_series.VALID_SERIES_INPUT_TYPES for aeon supported types.
-        y : one of aeon.base._base_series.VALID_SERIES_INPUT_TYPES, default=None
-            The target values for the time series.
-            A valid aeon time series data structure. See
-            aeon.base._base_series.VALID_SERIES_INPUT_TYPES for aeon supported types.
-        axis : int
-            The time point axis of the input series if it is 2D. If ``axis==0``, it is
-            assumed each column is a time series and each row is a time point. i.e. the
-            shape of the data is ``(n_timepoints, n_channels)``. ``axis==1`` indicates
-            the time series are in rows, i.e. the shape of the data is
-            ``(n_channels, n_timepoints)``.
+        X : Series or Collection, any supported type
+            Data to fit anomaly detector to, of python type as follows:
+                Series: 2D np.ndarray shape (n_channels, n_timepoints)
+                Collection: 3D np.ndarray shape (n_cases, n_channels, n_timepoints)
+                or list of 2D np.ndarray, case i has shape (n_channels, n_timepoints_i)
+        y : Series, default=None
+            Additional data, e.g., labels for anomaly detector.
 
         Returns
         -------
@@ -59,16 +54,11 @@ def predict(self, X) -> np.ndarray:
 
         Parameters
         ----------
-        X : one of aeon.base._base_series.VALID_SERIES_INPUT_TYPES
-            The time series to fit the model to.
-            A valid aeon time series data structure. See
-            aeon.base._base_series.VALID_SERIES_INPUT_TYPES for aeon supported types.
-        axis : int, default=1
-            The time point axis of the input series if it is 2D. If ``axis==0``, it is
-            assumed each column is a time series and each row is a time point. i.e. the
-            shape of the data is ``(n_timepoints, n_channels)``. ``axis==1`` indicates
-            the time series are in rows, i.e. the shape of the data is
-            ``(n_channels, n_timepoints)``.
+        X : Series or Collection, any supported type
+            Data to fit anomaly detector to, of python type as follows:
+                Series: 2D np.ndarray shape (n_channels, n_timepoints)
+                Collection: 3D np.ndarray shape (n_cases, n_channels, n_timepoints)
+                or list of 2D np.ndarray, case i has shape (n_channels, n_timepoints_i)
 
         Returns
         -------
@@ -84,20 +74,11 @@ def fit_predict(self, X, y=None) -> np.ndarray:
 
         Parameters
         ----------
-        X : one of aeon.base._base_series.VALID_SERIES_INPUT_TYPES
-            The time series to fit the model to.
-            A valid aeon time series data structure. See
-            aeon.base._base_series.VALID_INPUT_TYPES for aeon supported types.
-        y : one of aeon.base._base_series.VALID_SERIES_INPUT_TYPES, default=None
-            The target values for the time series.
-            A valid aeon time series data structure. See
-            aeon.base._base_series.VALID_SERIES_INPUT_TYPES for aeon supported types.
-        axis : int, default=1
-            The time point axis of the input series if it is 2D. If ``axis==0``, it is
-            assumed each column is a time series and each row is a time point. i.e. the
-            shape of the data is ``(n_timepoints, n_channels)``. ``axis==1`` indicates
-            the time series are in rows, i.e. the shape of the data is
-            ``(n_channels, n_timepoints)``.
+        X : Series or Collection, any supported type
+            Data to fit anomaly detector to, of python type as follows:
+                Series: 2D np.ndarray shape (n_channels, n_timepoints)
+                Collection: 3D np.ndarray shape (n_cases, n_channels, n_timepoints)
+                or list of 2D np.ndarray, case i has shape (n_channels, n_timepoints_i)
 
         Returns
         -------

aeon/anomaly_detection/collection/_classification.py

@@ -1,7 +1,7 @@
 """Adapter to use classification algorithms for collection anomaly detection."""
 
 __maintainer__ = []
-
+__all__ = ["ClassificationAdapter"]
 
 from sklearn.base import ClassifierMixin
 from sklearn.ensemble import RandomForestClassifier
@@ -30,7 +30,7 @@ class ClassificationAdapter(BaseCollectionAnomalyDetector):
     """
 
     _tags = {
-        "X_inner_type": "numpy2D",
+        "fit_is_empty": False,
         "requires_y": True,
     }
 

aeon/anomaly_detection/collection/_outlier_detection.py

@@ -1,6 +1,7 @@
 """Adapter to use outlier detection algorithms for collection anomaly detection."""
 
 __maintainer__ = []
+__all__ = ["OutlierDetectionAdapter"]
 
 from sklearn.base import OutlierMixin
 from sklearn.ensemble import IsolationForest
@@ -29,6 +30,7 @@ class OutlierDetectionAdapter(BaseCollectionAnomalyDetector):
 
     _tags = {
         "X_inner_type": "numpy2D",
+        "fit_is_empty": False,
     }
 
     def __init__(self, detector, random_state=None):

aeon/anomaly_detection/collection/base.py

@@ -55,11 +55,6 @@ class BaseCollectionAnomalyDetector(BaseCollectionEstimator, BaseAnomalyDetector
         Dictionary containing dynamic tag values which have been set at runtime.
     """
 
-    _tags = {
-        "fit_is_empty": False,
-        "requires_y": False,
-    }
-
     def __init__(self):
         super().__init__()
 

aeon/anomaly_detection/series/base.py

@@ -76,12 +76,6 @@ class BaseSeriesAnomalyDetector(BaseSeriesEstimator, BaseAnomalyDetector):
         Setting this class variable will convert the input data to the chosen axis.
     """
 
-    _tags = {
-        "X_inner_type": "np.ndarray",  # One of VALID_SERIES_INNER_TYPES
-        "fit_is_empty": True,
-        "requires_y": False,
-    }
-
     def __init__(self, axis):
         super().__init__(axis=axis)
 

docs/api_reference/anomaly_detection.rst

@@ -3,25 +3,38 @@
 Anomaly Detection
 =================
 
-The :mod:`aeon.anomaly_detection` module contains algorithms and composition tools for time series classification.
+The :mod:`aeon.anomaly_detection` module contains algorithms and composition tools for
+time series anomaly detection.
 
 All detectors in `aeon`  can be listed using the `aeon.utils.discovery.all_estimators` utility,
 using ``estimator_types="anomaly-detector"``, optionally filtered by tags.
-Valid tags can be listed by calling the function `aeon.utils.discovery.all_tags_for_estimator`.
+Valid tags can be listed by calling the function `aeon.utils.tags.all_tags_for_estimator`.
 
 Each detector in this module specifies its supported input data format, output data
 format, and learning type as an overview table in its documentation. Some detectors
 support multiple learning types.
 
-.. note::
 
-    Not all algorithm families are currently implemented. The documentation includes
-    placeholders for planned categories which will be supported in future.
+Collection anomaly detectors
+----------------------------
+
+.. currentmodule:: aeon.anomaly_detection.collection
+
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
+
+    BaseCollectionAnomalyDetector
+    ClassificationAdapter
+    OutlierDetectionAdapter
+
+Series anomaly detectors
+------------------------
 
 Distance-based
---------------
+~~~~~~~~~~~~~~
 
-.. currentmodule:: aeon.anomaly_detection.distance_based
+.. currentmodule:: aeon.anomaly_detection.series.distance_based
 
 .. autosummary::
     :toctree: auto_generated/
@@ -37,9 +50,9 @@ Distance-based
     ROCKAD
 
 Distribution-based
------------------
+~~~~~~~~~~~~~~~~~~
 
-.. currentmodule:: aeon.anomaly_detection.distribution_based
+.. currentmodule:: aeon.anomaly_detection.series.distribution_based
 
 .. autosummary::
     :toctree: auto_generated/
@@ -48,47 +61,40 @@ Distribution-based
     COPOD
     DWT_MLEAD
 
-Encoding-based
---------------
-
-The algorithms for this family are not implemented yet.
-
-Forecasting-based
------------------
-
-The algorithms for this family are not implemented yet.
-
 Outlier-Detection
------------------
+~~~~~~~~~~~~~~~~~
 
-.. currentmodule:: aeon.anomaly_detection.outlier_detection
+.. currentmodule:: aeon.anomaly_detection.series.outlier_detection
 
 .. autosummary::
     :toctree: auto_generated/
     :template: class.rst
 
     IsolationForest
-    PyODAdapter
     STRAY
 
-Reconstruction-based
---------------------
+Adapters
+~~~~~~~~
 
-The algorithms for this family are not implemented yet.
+.. currentmodule:: aeon.anomaly_detection.series
 
+.. autosummary::
+    :toctree: auto_generated/
+    :template: class.rst
 
-Whole-series
-------------
+    PyODAdapter
 
-.. currentmodule:: aeon.anomaly_detection.collection
+Base
+~~~~
+
+.. currentmodule:: aeon.anomaly_detection.series
 
 .. autosummary::
     :toctree: auto_generated/
     :template: class.rst
 
-    BaseCollectionAnomalyDetector
-    ClassificationAdapter
-    OutlierDetectionAdapter
+    BaseSeriesAnomalyDetector
+
 
 Base
 ----