AI-WQ-package
A python package to support forecast submission, visualisation and evaluation for S2S ML/AI prediction project
What it is and what it does
AI-WQ-package is a research-focused Python library for the ECMWF AI Weather Quest competition. It provides tools to download training data, develop and evaluate sub-seasonal forecast models, and submit forecasts to the competition platform. The package wraps xarray for efficient NetCDF-based data handling and integrates dask for parallel computation, numpy for numerical operations, scipy for scientific algorithms, pandas for tabular data, matplotlib and cartopy for visualization, and requests for API communication.
The package is explicitly marked as sandbox-level software under active development and not suitable for operational use. It is intended for research, testing, and competition participation only. Support is best-effort through community channels rather than official ECMWF support.
Use it for:
- Download and prepare sub-seasonal weather training datasets for developing machine learning forecast models.
- Evaluate AI-based forecast predictions against ground truth using the competition's evaluation framework.
- Submit forecast results to the ECMWF AI Weather Quest competition platform.
- Visualize sub-seasonal forecast data and model outputs using integrated matplotlib and cartopy tools.
- Prototype and iterate on forecast models in a research environment with built-in data pipeline support.
Worth the install?
AI-flagged interpretation of the facts on this page — verify before relying
Supports participation in the ECMWF AI Weather Quest competition by enabling forecast submission, evaluation of sub-seasonal forecasts, and training data download for AI-based weather prediction models.
Yes, if you are actively participating in the ECMWF AI Weather Quest competition or conducting research on sub-seasonal forecasting. The low install friction, active maintenance, and permissive license support research use. No, if you need production-grade weather forecasting tools or operational deployment—the package explicitly disclaims such use and is sandbox-level software.
Install
ai-wq-package on PyPI
pip
pip install ai-wq-packageuv
uv add ai-wq-packagepoetry
poetry add ai-wq-packageInstalling AI-WQ-package
Before you install
Low friction installation with a pure Python wheel. Active maintenance as of the latest release. Requires 9 runtime dependencies; consider a virtual environment if these conflict with your existing setup.
License in practice
Licensed under Apache License 2.0 (permissive). Suitable for research and competition use; explicitly not intended for operational or production deployment.
Quickstart
python3 -m pip install AI-WQ-package
import ai_wq_package
# Download training data, develop forecasts, submit to competition
Requires Python 3.8 or higher; installation guidance specifies Linux.
Verify before relying
- Whether the package's data download and submission features remain functional outside the competition window or require active competition registration.
- Performance characteristics when working with large multi-year training datasets via dask.
- Compatibility of cartopy visualization with non-Linux systems.
Package facts
| License | not declared (permissive) |
| Python support | supports the current Python release (>=3.8) |
| Install friction | low — pure-Python wheel |
| Runtime dependencies | 9 — numpy, xarray, dask, pandas, scipy, netCDF4, requests, matplotlib, cartopy |
| Maintenance | actively maintained — 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 122,264/month — #11,957 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: ai_wq_package-3.29-py3-none-any.whl
Tags
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to…
permissive · top 100 on PyPI
huggingface-hubClient library and CLI tool for downloading,…
permissive · top 100 on PyPI
langchainLangChain provides a framework for building…
permissive · top 1,000 on PyPI
hf-xethf-xet provides chunk-based deduplication and…
permissive · top 1,000 on PyPI
tokenizersTokenizers converts raw text into token…
permissive · top 1,000 on PyPI
transformersTransformers provides a unified framework for…
permissive · top 1,000 on PyPI
earthkit-utilsProvides shared utilities and helper functions…
permissive · top 15,000 on PyPI
earthkit-meteoComputes meteorological quantities (potential…
permissive · top 15,000 on PyPI
ecmwf-opendataDownloads ECMWF open meteorological data using…
permissive · top 15,000 on PyPI
ecmwf-api-clientPython client for accessing ECMWF's IFS…
permissive · top 15,000 on PyPI
herbie-dataHerbie downloads numerical weather prediction…
permissive · top 15,000 on PyPI
accuweatherAsync Python wrapper for fetching current…
permissive · top 15,000 on PyPI
properscoringProperscoring provides strictly proper scoring…
permissive · top 15,000 on PyPI
ecmwf-datastores-clientPython client for the ECMWF Data Stores Service…
permissive · top 15,000 on PyPI
stactools-met-office-deterministicGenerates STAC (SpatioTemporal Asset Catalog)…
permissive · top 5,000 on PyPI
cdsapicdsapi is a Python client for the Copernicus…
permissive · top 15,000 on PyPI