Anomaly Detection

The 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.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.

Collection anomaly detectors

ClassificationAdapter(classifier[, random_state])	Basic classifier adapter for collection anomaly detection.
OutlierDetectionAdapter(detector[, random_state])	Basic outlier detection adapter for collection anomaly detection.
BaseCollectionAnomalyDetector()	Abstract base class for collection anomaly detectors.
ROCKAD([n_estimators, n_kernels, normalise, ...])	ROCKET-based whole-series Anomaly Detector (ROCKAD).

Series anomaly detectors

Distance-based

CBLOF([n_clusters, clustering_estimator, ...])	CBLOF for Anomaly Detection.
KMeansAD([n_clusters, window_size, stride, ...])	KMeans anomaly detector.
LeftSTAMPi([window_size, n_init_train, ...])	LeftSTAMPi anomaly detector.
LOF([n_neighbors, algorithm, leaf_size, ...])	Local Outlier Factor (LOF) algorithm for anomaly detection.
MERLIN([min_length, max_length, max_iterations])	MERLIN anomaly detector.
STOMP([window_size, ignore_trivial, ...])	STOMP anomaly detector.
ROCKAD([n_estimators, n_kernels, normalise, ...])	ROCKET-based Semi-Supervised Anomaly Detector (ROCKAD).

Distribution-based

COPOD([n_jobs, window_size, stride])	COPOD for anomaly detection.
DWT_MLEAD([start_level, ...])	DWT-MLEAD anomaly detector.

Outlier-Detection

IsolationForest([n_estimators, max_samples, ...])	Isolation Forest for anomaly detection.
OneClassSVM([nu, kernel, degree, gamma, ...])	OneClassSVM for anomaly detection.
STRAY([alpha, k, knn_algorithm, p, ...])	STRAY: robust anomaly detection in data streams with concept drift.

Adapters

PyODAdapter(pyod_model[, window_size, stride])

Adapter for PyOD anomaly detection models to be used in the Aeon framework.

Base

BaseSeriesAnomalyDetector(axis)

Base class for series anomaly detection algorithms.

Base

BaseAnomalyDetector()

Anomaly detection base class.