thuml/Time-Series-Library

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

62
/ 100
Established

This library helps deep learning researchers evaluate and develop advanced deep time series models. It takes raw time series data as input and provides outputs for tasks like long- and short-term forecasting, identifying anomalies, filling in missing data (imputation), and classifying time series patterns. It's designed for researchers specializing in deep learning, particularly those working with time series data.

11,714 stars. Actively maintained with 5 commits in the last 30 days.

Use this if you are a deep learning researcher focused on time series analysis and need a robust codebase to test cutting-edge models or build your own for various tasks.

Not ideal if you are an end-user practitioner looking for a ready-to-use application or a low-code solution for time series problems without deep learning research involvement.

time-series-forecasting anomaly-detection data-imputation time-series-classification deep-learning-research
No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

11,714

Forks

1,868

Language

Python

License

MIT

Last pushed

Feb 23, 2026

Commits (30d)

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/Time-Series-Library"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.