aeon — машинное обучение на временных рядах

★ 7.0 · data

aeon is a Claude Code skill that handles time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. It wraps the aeon 1.x Python toolkit (stable at v1.4.0) with a scikit-learn compatible API, providing algorithms such as RocketClassifier, HIVECOTEV2, TimeSeriesKMeans with DTW, ARIMA, STOMP, and ClaSPSegmenter for both univariate and multivariate sequences. Installation requires Python 3.10+ via `uv pip install "aeon>=1.4,<2"`; deep learning estimators are available through the `aeon[all_extras]` extra. The skill is built for ML engineers and data scientists working with temporal or sequential data — use cases range from demand forecasting and sensor fault detection to ECG classification and behavioral pattern clustering.