Add standardization for x and y to Emulator

[sgreenbury]

Closes #645.

This PR:

• Adds x_transform and y_transform as optional tranforms within the Emulator base class
• Adds API to the __init__ of emulators to support setting this as standardize_x and standardize_y (StandardizeTransform())
• Has the following defaults:
  • GPs: standardize_x=False (periodic functions are affected when True), standardize_y=True
  • MLPs: standardize_x=True, standardize_y=True
  • Other emulators: standardize_x=False, standardize_y=False

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[codecov-commenter]

Codecov Report

❌ Patch coverage is 95.45455% with 3 lines in your changes missing coverage. Please review.
✅ Project coverage is 80.36%. Comparing base (7ac689c) to head (25257a5).

Files with missing lines	Patch %	Lines
autoemulate/experimental/emulators/base.py	85.71%	3 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #650      +/-   ##
==========================================
+ Coverage   80.35%   80.36%   +0.01%     
==========================================
  Files         156      156              
  Lines       11202    11248      +46     
==========================================
+ Hits         9001     9040      +39     
- Misses       2201     2208       +7     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[github-actions]

Coverage report

Click to see where and how coverage changed

File	Statements	Missing	Coverage	Coverage (new stmts)	Lines missing
autoemulate/experimental/emulators
base.py					87, 96, 102-107
ensemble.py
gradient_boosting.py
lightgbm.py
polynomials.py
radial_basis_functions.py
random_forest.py
svm.py
autoemulate/experimental/emulators/gaussian_process
exact.py
autoemulate/experimental/emulators/nn
mlp.py
autoemulate/experimental/learners
base.py
tests
test_compare.py
tests/experimental
test_experimental_gaussian_process_exact.py
test_experimental_transformed.py
Project Total

This report was generated by python-coverage-comment-action

[radka-j]

I like the default choices.

[radka-j]

Is it worth setting the default here to True (at least for the y) like with the MLP?

[radka-j]

On the other hand, I'm not sure it makes a big difference in this case and v0 doesn't standardise either.

[sgreenbury]

From discussing, we think that having the defaults as False remains worthwhile so that users can opt-in to standardization and search over it in the model comparison loop still (e.g. x_transforms_list=[[], [StandardizeTransform()]])

[radka-j]

Looks great, thanks!