-
Notifications
You must be signed in to change notification settings - Fork 116
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
Readability improvement #482
Conversation
… Also exported aic, aicc, bic so that these methods can be accessed from GLM module directly
Codecov Report
@@ Coverage Diff @@
## master #482 +/- ##
==========================================
+ Coverage 85.12% 87.44% +2.31%
==========================================
Files 7 7
Lines 827 900 +73
==========================================
+ Hits 704 787 +83
+ Misses 123 113 -10
Continue to review full report at Codecov.
|
Bump. Can we merge this? @nalimilan Aside from you who else might be good to ping? |
I have a suggested fix for a typo (GitHub won't let me apply it myself 🤔) but otherwise looks good to me. Thanks for the contribution! |
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.
gotta un-wrap these lines (or indent +2 spaces) or else they'll break the list formatting. otherwise looks good!
@mousum-github if you enable "contributors can push changes to my branch" or something like that in the PR options, we can apply these changes before merging. Otherwise we'll have to wait on you to accept the suggestions. |
|
||
Note that the canonical link for negative binomial regression is `NegativeBinomialLink`, but | ||
in practice one typically uses `LogLink`. | ||
|
||
```jldoctest methods |
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.
This is quite a long example to show on the home page. Also given how simple most of these functions are I'm not sure it's super useful to show all of them. How about adding some of these to the "Linear Model" example section instead?
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.
okay
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.
Except coef
, r2
, aic
and prediction
, others are moved to the Linear Regression
example.
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.
I'd rather move everything there to keep the home page simple. Actually we should probably also rework existing examples as it's not super logical to illustrate passing contrasts before even showing how to fit a model... We could move contents to other pages and improve them.
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.
Shall we start a different PR for something like Reorganise GLM documentation
or continue updating this PR only?
My thought of keeping r2
, aic
and prediction
along with fitting a model at the beginning is, these functionality most of the linear models consumers are looking for.
Looking for your thought.
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.
Yeah I think it's reasonable to go ahead adding the example here and reorganize documentation separately.
@mousum-github Can you please update the repo settings so that folks can directly edit the PR? Also would be great if the comments can be addressed and prepared for merging. |
Corrected a type error, and changed `includs` to `includes`. Co-authored-by: Alex Arslan <[email protected]>
removed the definition of `bic`. Co-authored-by: Dave Kleinschmidt <[email protected]>
removed the definition of `dof`. Co-authored-by: Dave Kleinschmidt <[email protected]>
Co-authored-by: Milan Bouchet-Valat <[email protected]>
removed the definition of `aic` from here. Co-authored-by: Milan Bouchet-Valat <[email protected]>
Co-authored-by: Milan Bouchet-Valat <[email protected]>
Apologies, @ViralBShah @kleinschmidt For the time being, shall I add the four of you as collaborators to the repo? |
Yes just add the others. Not necessary to add me. |
Hi - I am aware that there is a lot of progress on all PRs in GLM including this. I was out of the station for the last couple of weeks. |
No problem at all! Thanks for your efforts here and I hope you enjoyed your time away. |
Should this be merged? |
|
||
Note that the canonical link for negative binomial regression is `NegativeBinomialLink`, but | ||
in practice one typically uses `LogLink`. | ||
|
||
```jldoctest methods |
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.
I'd rather move everything there to keep the home page simple. Actually we should probably also rework existing examples as it's not super logical to illustrate passing contrasts before even showing how to fit a model... We could move contents to other pages and improve them.
Co-authored-by: Milan Bouchet-Valat <[email protected]>
Co-authored-by: Milan Bouchet-Valat <[email protected]>
Co-authored-by: Milan Bouchet-Valat <[email protected]>
Co-authored-by: Milan Bouchet-Valat <[email protected]>
Co-authored-by: Milan Bouchet-Valat <[email protected]>
Is this good to merge? |
The suggestion is committed. Co-authored-by: Milan Bouchet-Valat <[email protected]>
Thanks! |
In this PR, to improve the readability of the GLM document, we have:
aic
,aicc
,bic
,dispersion
so that, users can access these methods fromGLM
directly