Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
PR SummaryLow Risk Overview Written by Cursor Bugbot for commit 849e146. This will update automatically on new commits. Configure here. |
Codecov Report❌ Patch coverage is Additional details and impacted files@@ Coverage Diff @@
## main #2347 +/- ##
==========================================
- Coverage 93.15% 93.13% -0.03%
==========================================
Files 79 79
Lines 12523 12610 +87
==========================================
+ Hits 11666 11744 +78
- Misses 857 866 +9 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
|
I think this PR is removing some .nc files |
Do the MMM notebooks require them? These files are quite large. |
|
Yes, for now we do. We might remove it later (but should be a different PR :) ) |
This reverts commit 99e1ae1.
Agreed; files restored. |
|
Thanks @ColtAllen I will check this one in the upcoming days 💪 |
Description
This PR brings the CLV API more in line with that of MMM by making the following change:
The old API will still be supported until v1.0. All notebooks have been updated with the new API.
This change is needed for improved model persistence (see related issue) which will be addressed in follow-up PRs.
Discussion Needed
Currently, covariates are parametrized as
model configkwargs. For user convenience, is it also worth adding separate parameters for covariates? Would look like this:Related Issue
Checklist
pre-commit.ci autofixto auto-fix.📚 Documentation preview 📚: https://pymc-marketing--2347.org.readthedocs.build/en/2347/