aeon-toolkit/aeon

A toolkit for time series machine learning and deep learning

What it solves

aeon provides a unified, reliable toolkit for machine learning tasks involving time series data. It addresses the fragmentation in the field by offering a single, consistent library that covers everything from basic classification and forecasting to complex anomaly detection and deep learning, ensuring users have access to high-quality, research-backed implementations.

How it works

The library is designed to be compatible with scikit-learn, meaning it uses a familiar API structure (fit/predict) that makes it easy to integrate into existing data science workflows. Many of the algorithms included are contributed and maintained by the original researchers who developed them, ensuring that the code is a faithful representation of the published methods. It supports a wide range of tasks, including deep learning, through a modular architecture.

Who it’s for

aeon is built for data scientists, researchers, and developers who need to perform time series analysis. It is particularly useful for those who require state-of-the-art algorithms, need to perform reproducible benchmarking, or want to apply deep learning techniques to time series data without reinventing the wheel.

Highlights

  • Broad Scope: Supports classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search.
  • Research-Grade: Many implementations are provided by the original authors of the algorithms.
  • Scikit-Learn Compatible: Uses a consistent, easy-to-learn API that integrates seamlessly with standard Python data tools.
  • Deep Learning Support: Includes Keras/TensorFlow implementations of leading architectures like InceptionTime and ResNet.
  • Benchmarking Focused: Includes tools for reproducible experimental evaluation, grounded in published comparative studies.

Related

  • Project
    tslearn-team/tslearn

    A machine learning toolkit for time series analysis in Python that provides specialized tools for classification, clustering, and regression of sequential data.

  • Project
    sktime/sktime

    A Python library providing a unified interface for time series analysis, including forecasting, classification, and clustering, compatible with scikit-learn.

  • Project
    skforecast/skforecast

    A Python library for time series forecasting that provides a unified API for scikit-learn compatible ML models, statistical methods, and zero-shot foundation models.

  • Project
    johannfaouzi/pyts

    A Python package for time series classification that provides tools for preprocessing, transformation, and state-of-the-art classification algorithms.

  • Project
    Nixtla/mlforecast

    A scalable framework for time series forecasting that allows any scikit-learn compatible machine learning model to be used for forecasting millions of series.