- Python 3.7
- matplotlib == 3.5.1
- numpy == 1.21.6
- pandas == 1.3.4
- scikit-learn == 1.0.2
- torch == 1.10.2
Dependencies can be installed using the following command:
pip install -r requirements.txt
Train and evaluate the model. We provide all the tasks under the folder ./scripts/.
The datasets used in the paper can be obtained from the repo Informer.
The required data files should be put into data/ETT/
folder.
We appreciate the following GitHub repos a lot for their valuable code and efforts.
- Informer (https://github.com/zhouhaoyi/Informer2020)
- Autoformer (https://github.com/thuml/Autoformer)
- Time-Series-Library (https://github.com/thuml/Time-Series-Library)