-
-
Notifications
You must be signed in to change notification settings - Fork 252
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Replacing PyMC3 plots w/ Arviz plots & sigma Param change [Part 2] #26
Replacing PyMC3 plots w/ Arviz plots & sigma Param change [Part 2] #26
Conversation
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
View / edit / reply to this conversation on ReviewNB MarcoGorelli commented on 2021-01-29T11:58:34Z rather than ignoring warnings, can you do this such that it doesn't produce a warning at all (does specifying OriolAbril commented on 2021-02-04T21:27:27Z It won't work because under the hood conversion in plotting/stats functions does not accept conversion kwargs. Here I would recommend using return_inferencedata, it looks like the trace is only used to call arviz functions. Otherwise, to avoid all warnings, all plots should be called from within a model context so arviz has access to the model instance
CloudChaoszero commented on 2021-02-05T08:03:12Z Thanks for the feedback @MarcoGorelli! I found that Oriol's return_inference param recommendation panned out. |
It won't work because under the hood conversion in plotting/stats functions does not accept conversion kwargs. Here I would recommend using return_inferencedata, it looks like the trace is only used to call arviz functions. Otherwise, to avoid all warnings, all plots should be called from within a model context so arviz has access to the model instance
View entire conversation on ReviewNB |
View / edit / reply to this conversation on ReviewNB OriolAbril commented on 2021-02-04T21:34:37Z
var_names
|
…arnames to var_names
Thanks for the feedback @MarcoGorelli! I found that Oriol's return_inference param recommendation panned out. View entire conversation on ReviewNB |
@@ -76,7 +76,9 @@ | |||
"from theano import tensor as tt\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Did you save the notebooks after having re-run them? The watermarks still show old "last updated" dates
Reply via ReviewNB
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If there's nothing to be updated in this notebook, then perhaps it could be unstaged?
git fetch upstream git checkout upstream/main -- examples/case_studies/multilevel_modeling.ipynb git add examples/case_studies/multilevel_modeling.ipynb git commit -m 'unstage multilevel_modeling' git push
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Acknowledged. Thanks for the snippet!
View / edit / reply to this conversation on ReviewNB OriolAbril commented on 2021-02-07T20:27:27Z Is this still needed? CloudChaoszero commented on 2021-02-08T05:49:03Z Not anymore. Thanks for the note! |
View / edit / reply to this conversation on ReviewNB OriolAbril commented on 2021-02-07T20:27:28Z It looks like the plot output is missing here |
Note on examples/case_studies/LKJ.ipynbFor this line in we get the following FullRank Advi & obj_n_mc Error
What I did here was change the param |
Not anymore. Thanks for the note! View entire conversation on ReviewNB |
Thanks @CloudChaoszero! |
Description
The following is a large PR breakdown of PR #16.
Replace PyMC3 dependent plots with arviz plots in case studies & examples.
Replace parameter
sd
withsigma
(e.g. some examples havepm.Normal(...sd=...)