Skip to content

CSTCloudOps/TShape

 
 

Repository files navigation

TShape: Rescuing Machine Learning Models from Complex Shapelet Anomalies (ISSRE2025)

Get Started

Installation

Prerequisites (environment manager like conda, pipenv or poetry is recommended)

  • python >= 3.9, < 3.13

Using pip to install the suite from Pypi

pip install -r requirements.txt

Run

Access to data

First, please put datasets(AIOPS, UCR, TODS, NAB, Yahoo, WSD) under datasets folder

Train and Test

python main.py

Baselines

Baselines can be found at https://github.com/dawnvince/EasyTSAD

Results of baselines can be found at http://adeval.cstcloud.cn

About

A Unified Framework for Complex Shape Anomaly Detection in Time Series

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 93.1%
  • Shell 6.9%