skills.rest
tamagusko
tamaguskoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

aeon

Applies time series machine learning algorithms for classification, regression, clustering, forecasting, and anomaly detection.

Updated Oct 7, 2022
Search Tags:#machine learning#time series#forecasting#classification#anomaly detection#clustering#aeon
One-click install
npx skills add https://github.com/tamagusko/linux-cfg --skill aeon-tamagusko
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aeon
Source: https://github.com/tamagusko/linux-cfg/tree/main/dotfiles/claude/skills/aeon
Command: npx skills add https://github.com/tamagusko/linux-cfg --skill aeon-tamagusko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires aeon, and includes references (resource) components.

What problem does it solve? Standard machine learning libraries lack specialized algorithms for temporal data, making tasks like time series classification, anomaly detection, and motif discovery difficult to implement correctly. ## Core Features & Use Cases - Full Time Series ML Toolkit: Classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search with scikit-learn compatible APIs. - Specialized Distances and Features: Elastic distance metrics (DTW, ERP, LCSS) and feature extractors (ROCKET, Catch22, shapelets) designed for temporal data. - Use Case: A researcher analyzing sensor readings can classify equipment states with RocketClassifier, detect anomalous subsequences with STOMP, and benchmark results against published UCR archive baselines. ## Quick Start Use the aeon skill to train a time series classifier on my dataset and report its accuracy against a baseline.

Frequently Asked Questions about aeon

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I classify time series data in Python?▼

Use aeon's RocketClassifier for fast, strong baseline performance: fit it on training arrays of shape (n_samples, n_channels, n_timepoints) and call score on test data. For maximum accuracy, try HIVECOTEV2 or InceptionTimeClassifier instead.

What is the best algorithm for time series anomaly detection?▼

STOMP is a strong default for subsequence anomaly detection using matrix profiles, while IsolationForest works well for point anomalies without training data. Choose based on whether anomalies are single points, subsequences, or collective patterns.

Does aeon work with scikit-learn pipelines?▼

Yes, aeon estimators follow the scikit-learn API with fit, predict, and score methods, so they integrate into sklearn Pipelines and GridSearchCV. ROCKET features can also feed any sklearn classifier like RandomForestClassifier.

When should I use DTW distance instead of Euclidean?▼

Use DTW when time series have temporal shifts, speed variations, or phase differences, since it allows elastic alignment. Use Euclidean when series are already aligned and you need faster computation.

What data format does aeon expect for time series?▼

Aeon expects collections as arrays with shape (n_samples, n_channels, n_timepoints) for both univariate and multivariate series. Normalize data with the Normalizer transformer and impute missing values before fitting most algorithms.

Related Skills

Explore More Data & Analytics Skills→
teradata-labsteradata-labs
7

td-plot

Generate time series visualizations and UAF SQL workflows with TD_PLOT.

Official
Advanced
Wesley1600Wesley1600

data-analysis

Analyze CSV, JSON, and Parquet datasets with exploratory analysis and visualizations.

Community
Advanced
K-Dense-AIK-Dense-AI
41.1k

aeon

Applies time series machine learning algorithms for classification, regression, clustering, forecasting, and anomaly detection.

Official
Advanced
vasilyu1983vasilyu1983
73

ai-ml-timeseries

Forecast time series data with LightGBM, Transformers, and SHAP.

Community
Advanced