FeTS

November 10, 2025 ยท View on GitHub

This repo is the implementation of "FeTS: A Feature-Aware Framework for Time Series Forecasting"

Usage

  1. Multivariate datasets can be obtained from Time Series Library (TSlib).

  2. Install Pytorch and other necessary dependencies.

pip install -r requirements.txt
  1. Train and evaluate model. We provide the experiment scripts under the folder ./scripts/. You can reproduce the experiment results as the following examples:
bash ./scripts/ETTh1.sh