MetOffice / MetOffice/ai4c_hackathon
Create tutorial notebook based on climate bench
- Dominant language
- Jupyter Notebook
- Stars
- 2
- Forks
- 3
- Avg merge
- 1m
- Merged PRs (30d)
- 1
Description
https://github.com/duncanwp/ClimateBench/blob/main/prepare_data.py
https://github.com/duncanwp/ClimateBench
https://github.com/neuromatch/climate-course-content/blob/main/tutorials/W2D4_AIandClimateChange/W2D4_Tutorial2.ipynb
- [ ] Download climate bench data to GWS
- [ ] data exploration notebook
- [ ] training pipeline https://github.com/duncanwp/ClimateBench/blob/main/baseline_models/Original_RF_model.ipynb
- [ ] inference & evaluation
- [ ] hyperparameter tuning
- [ ] explainable AI
Contributor guide
No contributing guide indexed for this repository
Research direction
Read prepare_data.py and the linked Original_RF_model.ipynb, then compare their workflow with W2D4_Tutorial2.ipynb. Run the ClimateBench data preparation first and organize a notebook covering download, exploration, training, inference and evaluation, tuning, and explainable AI. Done means all six checklist stages are represented and runnable.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- jupyter-notebook, python, scikit-learn
- Domain
- data, documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100