Add DANRA tutorial notebook with pytest-nbmake

[sadamov]

Description

Add a hello_world_danra.ipynb notebook to docs/notebooks/ providing a step-by-step guide for running a full model training using DANRA data. This improves onboarding and showcases neural-lam's capabilities.

Note: The COSMO equivalent has been split into a separate issue: #587

Stale PR: #202 (thank you @Jayant-kernel!)
Current PR: #577 builds on top of #202

Proposed notebook contents

1. Install Neural-LAM with all dependencies (PDM + ipykernel)
2. Data loading and preprocessing using tests/datastore_examples/mllam/danra.example.yaml
3. Model configuration and HiLAM graph generation
4. Training on CPU (with --flags)
5. Evaluation and visualization using built-in maps and charts + wandb

Additional considerations

• Use a small subset of DANRA data for quick execution
• Include explanations for each step
• Highlight key parameters and their effects
• Provide tips for scaling to larger datasets

[joeloskarsson]

I agree that this would be great! While we could make it as a notebook, I also think such a "getting started guide" should be part of #61. More reason to put some effort into a proper documentation setup 😅

[Eshaan-byte]

Hi @sadamov can I work on this issue? Thank you!

[Jayant-kernel]

@sadamov @joeloskarsson
i! I’d like to work on this issue (#69) as a GSoC 2026 applicant.

I’m interested in contributing a HelloWorld.ipynb example that helps new users run a minimal end-to-end workflow in neural-lam (data loading / setup / basic model run, depending on what you prefer for the first example).

My plan is to start with a small, reviewable PR:

Create the notebook skeleton with a clear step-by-step flow

Add short explanations/comments for each step

Test that it runs with the current setup instructions

Update README/docs links if needed

If this sounds good, could you please assign me to the issue?
I’ll start with a draft PR quickly and share progress there.