Add prior predictive example notebook

[juanitorduz]

• Add prior predictive plot.
• Fix the double scaling bug.
• Typo from Fix typo in Control Section of MMM Example notebook #784

---

📚 Documentation preview 📚: https://pymc-marketing--787.org.readthedocs.build/en/787/

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[juanitorduz]

When adding the prior-predictive step, the processing is wrong:

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 93.86%. Comparing base (f6a1a37) to head (16d3656).
Report is 183 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #787      +/-   ##
==========================================
- Coverage   93.90%   93.86%   -0.04%     
==========================================
  Files          28       28              
  Lines        2951     2950       -1     
==========================================
- Hits         2771     2769       -2     
- Misses        180      181       +1     

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

[wd60622]

Would the self.y be getting scaled twice?
If you remove the sample_prior_predictive lines, this doesn't happen, right?

[juanitorduz]

The bug was fixed in b765b38 . This one was hard to catch, see #788

[wd60622]

Is it then the combination of build_model and _data_setter? As the sample_posterior_predictive method will call _data_setter but not the build_model...

[wd60622]

Notebook looks good! Just question but not a blocker

[juanitorduz]

Is it then the combination of build_model and _data_setter? As the sample_posterior_predictive method will call _data_setter but not the build_model...

I think we need to take a detailed look at how this is happening and that is why I created the issue above 😬. Let me merge this one and then work on the other issue.