alterlab-aeon

Aeon Time Series Machine Learning

Overview

Aeon is a scikit-learn compatible Python toolkit for time series machine learning. It provides state-of-the-art algorithms for classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.

When to Use This Skill

Apply this skill when:

• Classifying or predicting from time series data
• Detecting anomalies or change points in temporal sequences
• Clustering similar time series patterns
• Forecasting future values
• Finding repeated patterns (motifs) or unusual subsequences (discords)
• Comparing time series with specialized distance metrics
• Extracting features from temporal data

Does NOT Trigger

Scenario	Use Instead
Zero-shot forecasting with a pretrained foundation model, no training	alterlab-timesfm
ARIMA/SARIMAX with coefficient tables, residual diagnostics, and econometric inference	alterlab-statsmodels
Plain tabular features (no temporal ordering) for classification/regression	alterlab-scikit-learn
Physiological signal processing (ECG/EEG/EDA peaks, HRV)	alterlab-neurokit2

Installation

uv pip install "aeon>=1.6"     # core; Python 3.11–3.14
uv pip install "aeon[dl]"      # + TensorFlow/Keras for the deep-learning estimators
uv pip install stumpy          # soft dependency of MatrixProfileTransformer

Examples are verified against aeon 1.6.0 (current as of 2026-09). The 1.x line reorganised modules — forecasters live under aeon.forecasting.stats, series anomaly detectors under aeon.anomaly_detection.series.*, similarity search under aeon.similarity_search.subsequence / .whole_series — so if an import fails, check the current API reference rather than assuming an older path.

Core Capabilities

1. Time Series Classification

Categorize time series into predefined classes. See references/classification.md for complete algorithm catalog.

Quick Start:

from aeon.classification.convolution_based import RocketClassifier
from aeon.datasets import load_classification

# Load data
X_train, y_train = load_classification("GunPoint", split="train")
X_test, y_test = load_classification("GunPoint", split="test")

# Train classifier
clf = RocketClassifier(n_kernels=10000)
clf.fit(X_train, y_train)
accuracy = clf.score(X_test, y_test)

Algorithm Selection:

• Speed + Performance: MiniRocketClassifier, Arsenal
• Maximum Accuracy: HIVECOTEV2, InceptionTimeClassifier
• Interpretability: ShapeletTransformClassifier, Catch22Classifier
• Small Datasets: KNeighborsTimeSeriesClassifier with DTW distance

2. Time Series Regression

Predict continuous values from time series. See references/regression.md for algorithms.

Quick Start:

from aeon.regression.convolution_based import RocketRegressor
from aeon.datasets import load_regression

X_train, y_train = load_regression("Covid3Month", split="train")
X_test, y_test = load_regression("Covid3Month", split="test")

reg = RocketRegressor()
reg.fit(X_train, y_train)
predictions = reg.predict(X_test)

3. Time Series Clustering

Group similar time series without labels. See references/clustering.md for methods.

Quick Start:

from aeon.clustering import TimeSeriesKMeans

clusterer = TimeSeriesKMeans(
    n_clusters=3,
    distance="dtw",
    averaging_method="ba"
)
labels = clusterer.fit_predict(X_train)
centers = clusterer.cluster_centers_

4. Forecasting

Predict future time series values. See references/forecasting.md for forecasters.

Quick Start:

from aeon.forecasting.stats import ARIMA

# Orders are separate args (p, d, q) — not an `order` tuple.
forecaster = ARIMA(p=1, d=1, q=1)
forecaster.fit(y_train)

# predict(y) takes the series to forecast from and returns ONE float,
# `horizon` steps past the end of y (default 1). Calling predict() with no
# series raises TypeError in aeon 1.6.
next_step = forecaster.predict(y_train)

# For a multi-step path, use iterative_forecast (returns a 1D ndarray):
y_pred = forecaster.iterative_forecast(y_train, prediction_horizon=5)

5. Anomaly Detection

Identify unusual patterns or outliers. See references/anomaly_detection.md for detectors.

Quick Start:

import numpy as np
from aeon.anomaly_detection.series.distance_based import STOMP

detector = STOMP(window_size=50)
anomaly_scores = detector.fit_predict(y)

# Higher scores indicate anomalies
threshold = np.percentile(anomaly_scores, 95)
anomalies = anomaly_scores > threshold

6. Segmentation

Partition time series into regions with change points. See references/segmentation.md.

Quick Start:

from aeon.segmentation import ClaSPSegmenter

segmenter = ClaSPSegmenter()
change_points = segmenter.fit_predict(y)

7. Similarity Search

Find similar patterns within or across time series. See references/similarity_search.md.

Quick Start:

from aeon.similarity_search.subsequence import MASS

# Searchers are fitted on a collection shaped (n_cases, n_channels, n_timepoints)
X = y.reshape(1, 1, -1)
query = X[0, :, 100:150]                  # (n_channels, length) — length must match

searcher = MASS(length=50, normalize=True).fit(X)
indexes, distances = searcher.predict(query, k=3)   # rows are (case, timestamp)

aeon 1.6 no longer ships a StompMotif estimator. For motifs/discords compute a matrix profile with aeon.transformations.series.MatrixProfileTransformer (needs stumpy): its minima mark motifs and its maxima discords.

Feature Extraction and Transformations

Transform time series for feature engineering. See references/transformations.md.

ROCKET Features:

from aeon.transformations.collection.convolution_based import Rocket

rocket = Rocket()
X_features = rocket.fit_transform(X_train)

# Use features with any sklearn classifier
from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier()
clf.fit(X_features, y_train)

Statistical Features:

from aeon.transformations.collection.feature_based import Catch22

catch22 = Catch22()
X_features = catch22.fit_transform(X_train)

Preprocessing:

from aeon.transformations.collection import MinMaxScaler, Normalizer

scaler = Normalizer()  # Z-normalization
X_normalized = scaler.fit_transform(X_train)

Distance Metrics

Specialized temporal distance measures. See references/distances.md for complete catalog.

Usage:

from aeon.distances import dtw_distance, dtw_pairwise_distance

# Single distance
distance = dtw_distance(x, y, window=0.1)

# Pairwise distances
distance_matrix = dtw_pairwise_distance(X_train)

# Use with classifiers
from aeon.classification.distance_based import KNeighborsTimeSeriesClassifier

clf = KNeighborsTimeSeriesClassifier(
    n_neighbors=5,
    distance="dtw",
    distance_params={"window": 0.2}
)

Available Distances:

• Elastic: DTW, DDTW, WDTW, ERP, EDR, LCSS, TWE, MSM
• Lock-step: Euclidean, Manhattan, Minkowski
• Shape-based: Shape DTW, SBD

Deep Learning Networks

Neural architectures for time series. See references/networks.md. These estimators need the aeon[dl] extra (TensorFlow ≥ 2.14 / Keras 3, Python < 3.14).

Architectures:

• Convolutional: FCNClassifier, ResNetClassifier, InceptionTimeClassifier
• Recurrent: RecurrentNetwork, TCNNetwork
• Autoencoders: AEFCNClusterer, AEResNetClusterer

Usage:

from aeon.classification.deep_learning import InceptionTimeClassifier

clf = InceptionTimeClassifier(n_epochs=100, batch_size=32)
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)

Datasets and Benchmarking

Load standard benchmarks and evaluate performance. See references/datasets_benchmarking.md.

Load Datasets:

from aeon.datasets import load_classification, load_regression

# Classification
X_train, y_train = load_classification("ArrowHead", split="train")

# Regression
X_train, y_train = load_regression("Covid3Month", split="train")

Benchmarking:

from aeon.benchmarking.results_loaders import get_estimator_results

# Compare with published results (estimators + datasets are lists)
published = get_estimator_results(estimators=["ROCKET"], datasets=["GunPoint"])

Common Workflows

Classification Pipeline

from aeon.transformations.collection import Normalizer
from aeon.classification.convolution_based import RocketClassifier
from sklearn.pipeline import Pipeline

pipeline = Pipeline([
    ('normalize', Normalizer()),
    ('classify', RocketClassifier())
])

pipeline.fit(X_train, y_train)
accuracy = pipeline.score(X_test, y_test)

Feature Extraction + Traditional ML

from aeon.transformations.collection.convolution_based import Rocket
from sklearn.ensemble import GradientBoostingClassifier

# Extract features
rocket = Rocket()
X_train_features = rocket.fit_transform(X_train)
X_test_features = rocket.transform(X_test)

# Train traditional ML
clf = GradientBoostingClassifier()
clf.fit(X_train_features, y_train)
predictions = clf.predict(X_test_features)

Anomaly Detection with Visualization

import numpy as np
import matplotlib.pyplot as plt
from aeon.anomaly_detection.series.distance_based import STOMP

detector = STOMP(window_size=50)
scores = detector.fit_predict(y)

plt.figure(figsize=(15, 5))
plt.subplot(2, 1, 1)
plt.plot(y, label='Time Series')
plt.subplot(2, 1, 2)
plt.plot(scores, label='Anomaly Scores', color='red')
plt.axhline(np.percentile(scores, 95), color='k', linestyle='--')
plt.show()

Best Practices

Data Preparation

1. Normalize: Most algorithms benefit from z-normalization

   from aeon.transformations.collection import Normalizer
   normalizer = Normalizer()
   X_train = normalizer.fit_transform(X_train)
   X_test = normalizer.transform(X_test)
   

2. Handle Missing Values: Impute before analysis

   from aeon.transformations.collection import SimpleImputer
   imputer = SimpleImputer(strategy='mean')
   X_train = imputer.fit_transform(X_train)
   

3. Check Data Format: Aeon expects shape (n_samples, n_channels, n_timepoints)

Model Selection

1. Start Simple: Begin with ROCKET variants before deep learning
2. Use Validation: Split training data for hyperparameter tuning
3. Compare Baselines: Test against simple methods (1-NN Euclidean, Naive)
4. Consider Resources: ROCKET for speed, deep learning if GPU available

Algorithm Selection Guide

For Fast Prototyping:

• Classification: MiniRocketClassifier
• Regression: MiniRocketRegressor
• Clustering: TimeSeriesKMeans with Euclidean

For Maximum Accuracy:

• Classification: HIVECOTEV2, InceptionTimeClassifier
• Regression: InceptionTimeRegressor
• Forecasting: ARIMA, TCNForecaster

For Interpretability:

• Classification: ShapeletTransformClassifier, Catch22Classifier
• Features: Catch22, TSFresh

For Small Datasets:

• Distance-based: KNeighborsTimeSeriesClassifier with DTW
• Avoid: Deep learning (requires large data)

Reference Documentation

Detailed information available in references/:

• classification.md - All classification algorithms
• regression.md - Regression methods
• clustering.md - Clustering algorithms
• forecasting.md - Forecasting approaches
• anomaly_detection.md - Anomaly detection methods
• segmentation.md - Segmentation algorithms
• similarity_search.md - Pattern matching and motif discovery
• transformations.md - Feature extraction and preprocessing
• distances.md - Time series distance metrics
• networks.md - Deep learning architectures
• datasets_benchmarking.md - Data loading and evaluation tools

Additional Resources

• Documentation: https://www.aeon-toolkit.org/
• GitHub: https://github.com/aeon-toolkit/aeon
• Examples: https://www.aeon-toolkit.org/en/stable/examples.html
• API Reference: https://www.aeon-toolkit.org/en/stable/api_reference.html