[shmh40]

Rename to WeatherGenerator's terms (LatentDecoder with embed_target_coords, target_readout and pred_head; DataReaderObs.get_target returning ReaderData fields; DTRange; hp_nbours; init_time/fstep), configure runs with a yml config in WeatherGenerator's layout (training_config/validation_config, the obs stream as in config/streams/, --config/--options), and add a train_latent_decoder entry point. Normalise targets with the obs store's own means and vars. Drop the fp16 year-store reader and fold the dataset into run_train.py. Add the licence header to every file.

Description

Issue Number

Is this PR a draft? Mark it as draft.

Checklist before asking for review

• I have performed a self-review of my code
• My changes comply with basic sanity checks:
  • I have fixed formatting issues with ./scripts/actions.sh lint
  • I have run unit tests with ./scripts/actions.sh unit-test
  • I have documented my code and I have updated the docstrings.
  • I have added unit tests, if relevant
• I have tried my changes with data and code:
  • I have run the integration tests with ./scripts/actions.sh integration-test
  • (bigger changes) I have run a full training and I have written in the comment the run_id(s): launch-slurm.py --time 60
  • (bigger changes and experiments) I have shared a hegdedoc in the github issue with all the configurations and runs for this experiments
• I have informed and aligned with people impacted by my change:
  • for config changes: the MatterMost channels and/or a design doc
  • for changes of dependencies: the MatterMost software development channel

FastEvaluation

• I have updated the public documentation if necessary