Set up correct OHE labels for subsets that use default model labels

[ejm714]

Fixes #234

#229 introduced a bug whereby the new columns added to the labels file were in a different order than what is on the model. This PR fixes that by setting up the correct one hot encoded labels in the preprocess_labels validator rather than instantiate_model. Using the use_default_model_labels, we know whether the labels file should contain columns (with all zeroes) for species that are not present in the labels but are on the base model. Using a pd.Categorical before get_dummies allows us to generate these columns.

Running zamba train --config tests/assets/sample_train_config.yaml now works; the labels file has three species present in zamba but trains a model that outputs the full set of 32 labels.

[netlify]

✅ Deploy Preview for silly-keller-664934 ready!

Name	Link
🔨 Latest commit	0fdbc20
🔍 Latest deploy log	https://app.netlify.com/sites/silly-keller-664934/deploys/63334834199b35000819d6d2
😎 Deploy Preview	https://deploy-preview-236--silly-keller-664934.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site settings.

[pjbull]

This looks nicer to me!

[github-actions]

🚀 Deployed on https://deploy-preview-236--silly-keller-664934.netlify.app

[codecov-commenter]

Codecov Report

Merging #236 (0fdbc20) into master (0a894a5) will increase coverage by 0.0%.
The diff coverage is 100.0%.

Additional details and impacted files

@@          Coverage Diff           @@
##           master    #236   +/-   ##
======================================
  Coverage    87.2%   87.2%           
======================================
  Files          28      28           
  Lines        1961    1962    +1     
======================================
+ Hits         1710    1711    +1     
  Misses        251     251           

Impacted Files	Coverage Δ
zamba/models/model_manager.py	84.3% <ø> (-0.5%)	⬇️
zamba/models/config.py	96.9% <100.0%> (+<0.1%)	⬆️
zamba/models/utils.py	100.0% <100.0%> (ø)

[pjbull]

LGTM