Add a temporal validation period to synthetic control and interrupted time series experiments

[drbenvincent]

• Closes #364
• Updates one of the synthetic control and one of the interrupted time series notebooks with quick demos of using the validation period
• This also corrects an error I found in the tests where test_its was testing synthetic control rather than interrupted time series

TODO

• [X] Implement for synthetic control
• [X] Implement for interrupted time series
• [x] Calculate Bayesian $R^2$ value separately for training period and validation period
• [x] Report Bayesian $R^2$ (including validation period where relevant) in the summary method instead of the plot title
• [x] Streamline the implementation - do we really need separate classes, or can we just add a intervention_time kwarg and add in additional logic to the existing classes?
• [x] Ensure class diagram is updated before requesting a review
• [x] Check docstrings are ok and doctests pass
• [x] Add test coverage
• [x] Test for ValueError when validation_time >= treatment_time

---

📚 Documentation preview 📚: https://causalpy--367.org.readthedocs.build/en/367/

[review-notebook-app[bot]]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[drbenvincent]

Good progress so far. But we are missing separate Bayesian $R^2$ for training and validation phases.

Synthetic control figure:

Interrupted time series figure:

[codecov[bot]]

Codecov Report

Attention: Patch coverage is 90.47619% with 4 lines in your changes missing coverage. Please review.

Project coverage is 85.81%. Comparing base (f6fd97c) to head (444e363).

Files	Patch %	Lines
causalpy/pymc_experiments.py	83.33%	4 Missing :warning:

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #367 +/- ## ========================================== + Coverage 85.60% 85.81% +0.20% ========================================== Files 22 22 Lines 1716 1748 +32 ========================================== + Hits 1469 1500 +31 - Misses 247 248 +1 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[drbenvincent]

Based on one of @cetagostini 's PR's (https://github.com/pymc-labs/CausalPy/pull/368), I'm wondering if we should add a small feature to calculate a ROPE based on the validation period. Something a bit like this:

Any thoughts/comments welcome. I'm not convinced this is a good idea yet - especially because once we add in actual time series models then the credible interval will increase as we forecast further into the future.