mllam/neural-lam

Add DANRA tutorial notebook with pytest-nbmake

Open

#69 opened on Aug 19, 2024

View on GitHub
 (32 comments) (0 reactions) (1 assignee)Python (276 forks)auto 404
documentationgood first issue

Repository metrics

Stars
 (282 stars)
PR merge metrics
 (PR metrics pending)

Description

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

Contributor guide

Research direction
Inspect existing PRs #202 and #577, review the example data config and model setup, then create a notebook that runs on CPU with a small DANRA subset and verify it passes pytest nbmake tests.
Tech stack
python
Domain
machine learningdata
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Git
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75