What is the Aeon toolkit used for?

Aeon is a scikit-learn compatible Python toolkit specifically built for time series machine learning tasks like forecasting, classification, clustering, and anomaly detection.

How does this skill integrate with Claude Code?

This skill provides Claude with domain-specific knowledge of the Aeon library, allowing it to generate accurate code, select the right algorithms, and troubleshoot temporal data issues.

Does this skill support multivariate time series?

Yes, Aeon and this skill provide algorithms and patterns specifically designed for both univariate and multivariate time series data.

Is Aeon compatible with scikit-learn pipelines?

Yes, Aeon is designed to be fully compatible with scikit-learn, meaning you can use its components within standard pipelines, grid searches, and cross-validation modules.

Can I use this skill for deep learning tasks?

Yes, the skill includes implementation patterns for deep learning architectures such as InceptionTime, ResNet, and FCN optimized for temporal data.

Aeon Time Series ML

Name: Aeon Time Series ML
Author: BbgnsurfTech

byBbgnsurfTech

•

データサイエンスとML

Provides a comprehensive toolkit for time series machine learning including classification, forecasting, and anomaly detection using scikit-learn compatible APIs.

概要

Aeon is a specialized Python framework designed for temporal data analysis, offering state-of-the-art algorithms that go beyond standard machine learning approaches. It enables developers and data scientists to perform complex tasks such as time series classification, regression, clustering, and motif discovery within a familiar scikit-learn compatible environment. Whether you are detecting anomalies in sensor data, forecasting financial trends, or segmenting temporal sequences, this skill provides the patterns and implementations needed to handle univariate and multivariate time series efficiently using advanced methods like ROCKET and HIVE-COTE.

主な機能

Advanced time series classification and regression with ROCKET and HIVE-COTE algorithms.
Comprehensive forecasting tools including ARIMA, TCN, and deep learning architectures.
Robust anomaly detection and segmentation for identifying unusual patterns or change points.
Seamless integration with scikit-learn pipelines and automated feature extraction.
Extensive library of specialized temporal distance metrics like DTW, MSM, and ERP.
3 GitHub stars

ユースケース

Detecting equipment failures or security breaches through temporal anomaly detection.
Categorizing physiological signals such as ECG or EEG data for medical diagnostics.
Predicting future values in financial markets or industrial sensor datasets.

概要

主な機能

Advanced time series classification and regression with ROCKET and HIVE-COTE algorithms.
Comprehensive forecasting tools including ARIMA, TCN, and deep learning architectures.
Robust anomaly detection and segmentation for identifying unusual patterns or change points.
Seamless integration with scikit-learn pipelines and automated feature extraction.
Extensive library of specialized temporal distance metrics like DTW, MSM, and ERP.
3 GitHub stars

ユースケース

Detecting equipment failures or security breaches through temporal anomaly detection.
Categorizing physiological signals such as ECG or EEG data for medical diagnostics.
Predicting future values in financial markets or industrial sensor datasets.