A python package to support forecast submission, visualisation and evaluation for S2S ML/AI prediction project
Project description
AI Weather Quest (AI-WQ-package)
Disclaimer: This package is provided for research and competition participation purposes only. It is not intended for use in any operational or production context. It is not an officially supported ECMWF software product.
Overview
AI-WQ-package is a Python library that supports participation in the ECMWF AI Weather Quest, a competition to develop and evaluate AI-based sub-seasonal forecasts.
The package enables you to:
- Submit forecasts to the AI Weather Quest competition.
- Evaluate sub-seasonal forecasts using tools developed by the AI Weather Quest team.
- Download training data for developing sub-seasonal forecast models.
It builds on xarray for efficient NetCDF-based data handling.
Installation
To install the AI-WQ-package on Linux, run the following command:
python3 -m pip install AI-WQ-package
For guidance on installing Python 3 or pip, refer to the official documentation.
Dependencies
The AI-WQ-package requires the following dependencies:
- numpy (version 1.23 or higher)
- xarray (version 2024.09.0 or higher)
- dask (version 2024.9.0)
- pandas (version 2.2.3 or higher)
- scipy (version 1.14.1 or higher)
- netCDF4 (version 1.7.2 or higher)
- requests (versions 2.32.2 or higher)
- matplotlib (versions 3.8 or higher)
- cartopy (versions 0.22 or higher)
If these dependencies conflict with your current working environment, consider installing the package in a new virtual environment.
Upgrading the Package
To upgrade to the latest version, run:
python3 -m pip install --upgrade AI-WQ-package
This project is being actively developed. New updates may be released periodically with detailed annoucements given on the ECMWF-hosted forum.
Software Maturity
| Attribute | Status |
|---|---|
| Maturity |  |
| Support level | Best effort — no guaranteed response time |
| Operational use | Not suitable for operational use |
[!IMPORTANT] This software is Sandbox, is under active development, and subject to ECMWF's guidelines on Software Maturity. Releases are intended for testing, evaluation, and collaboration rather than production deployment.
License
This project is licensed under the Apache License 2.0. See the LICENSE file for the full text.
Support
This package is not officially supported by ECMWF. Community contributions and questions are welcome via GitHub Issues on the upstream repository or on the ECMWF Community Forum.
For general ECMWF-related enquiries, please use the ECMWF Service Desk.
Documentation
Full documentation is available on ReadTheDocs:
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ai_wq_package-3.9.tar.gz.
File metadata
- Download URL: ai_wq_package-3.9.tar.gz
- Upload date:
- Size: 35.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c7bab11d3878b5721bdfc192c4750971fd0f7954c7479f3a903b9f7073f4d954
|
|
| MD5 |
b0c61808d3c6326810af201f6de43ad7
|
|
| BLAKE2b-256 |
13f0f39ab7b2347ca4de225602e878871c1a87a52ba6f3ed42ffcf239dc776b1
|
File details
Details for the file ai_wq_package-3.9-py3-none-any.whl.
File metadata
- Download URL: ai_wq_package-3.9-py3-none-any.whl
- Upload date:
- Size: 39.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
14fe41fcf8661c904559c0312c8270c160c39bc440b3ec70f8d8c6dd592cc500
|
|
| MD5 |
c019577e0674c294a5366f4ef6034cbc
|
|
| BLAKE2b-256 |
6aa4ec461a92b4479ee12f301d26aa88c76748cc15fee07f5dadc6c9733671a4
|
