Add torch default dtype constant

[sgreenbury]

Closes #537.

This PR:

• Adds TorchDefaultDType = tf.float32 for use as a const across codebase
• Adds some dtype handling for simulators so that returned y has same dtype as input x

Question:

• An alternative would be to allow dtype for outputs and inputs of simulator to be set on the __init__ - would this be useful?
• I replaced .float32 where I think it makes sense but there could be other places such as in tutorials where there is some handling missing.

[github-actions]

Coverage report

Click to see where and how coverage changed

File	Statements	Missing	Coverage	Coverage (new stmts)	Lines missing
autoemulate/experimental
types.py
autoemulate/experimental/data
utils.py
autoemulate/experimental/emulators
polynomials.py
autoemulate/experimental/learners
base.py
autoemulate/experimental/simulations
base.py					110
epidemic.py
experimental_design.py					71
tests
test_compare.py
tests/experimental
conftest.py
test_experimental_base_simulator.py
test_experimental_preprocessors.py
Project Total

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

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 80.22%. Comparing base (cecf95d) to head (11b35b7).

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #619      +/-   ##
==========================================
+ Coverage   80.20%   80.22%   +0.02%     
==========================================
  Files         155      155              
  Lines       11132    11136       +4     
==========================================
+ Hits         8928     8934       +6     
+ Misses       2204     2202       -2     

☔ 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.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB