Time-Series-Library

# Time Series Library (TSLib)
TSLib is an open-source library for deep learning researchers, especially for deep time series analysis.

> **中文文档**：[README_zh.md](./README_zh.md)

We provide a neat code base to evaluate advanced deep time series models or develop your model, which covers five mainstream tasks: **long- and short-term forecasting, imputation, anomaly detection, and classification.**

:triangular_flag_on_post:**News** (2026.04) Due to the limited bandwidth of the current maintainers, we will not be actively adding new features to this library. Since the library was originally released three years ago, many of its benchmarks may no longer be meaningful for evaluating the effectiveness or progress of current research. However, the baseline implementations remain correct. We therefore recommend seeking out newer benchmarks.

:triangular_flag_on_post:**News** (2025.12) Many thanks to the great work from [ailuntz](https://github.com/thuml/Time-Series-Library/pull/805), which provides an updated requirements and docker deployment, as well as a well-organized document. This is quite meaningful to this project and beginners.

:triangular_flag_on_post:**News** (2025.11) Considering the rapid development of Large Time Series Models (LTSMs), we have newly added a [[zero-shot forecasting]](https://github.com/thuml/Time-Series-Library/blob/main/exp/exp_zero_shot_forecasting.py) feature in TSLib. You can try [this script](https://github.com/thuml/Time-Series-Library/blob/main/scripts/long_term_forecast/ETT_script/LTSM.sh) to evaluate LTSMs.

:triangular_flag_on_post:**News** (2025.10) Given the recent confusion among researchers regarding minor improvements on standard benchmarks, we propose the [[Accuracy Law]](https://arxiv.org/abs/2510.02729) to characterize the objectives of deep time series forecasting tasks, which can be used to identify saturated datasets.

:triangular_flag_on_post:**News** (2024.10) We have included [[TimeXer]](https://arxiv.org/abs/2402.19072), which defined a practical forecasting paradigm: Forecasting with Exogenous Variables. Considering both practicability and computation efficiency, we believe the new forecasting paradigm defined in TimeXer can be the "right" task for future research.

:triangular_flag_on_post:**News** (2024.10) Our lab has open-sourced [[OpenLTM]](https://github.com/thuml/OpenLTM), which provides a distinct pretrain-finetuning paradigm compared to TSLib. If you are interested in Large Time Series Models, you may find this repository helpful.

:triangular_flag_on_post:**News** (2024.07) We wrote a comprehensive survey of [[Deep Time Series Models]](https://arxiv.org/abs/2407.13278) with a rigorous benchmark based on TSLib. In this paper, we summarized the design principles of current time series models supported by insightful experiments, hoping to be helpful to future research.

:triangular_flag_on_post:**News** (2024.04) Many thanks for the great work from [frecklebars](https://github.com/thuml/Tim