Skip to content
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

Feature/propensity stratified evaluation tutorial #408

Conversation

amirj
Copy link
Contributor

@amirj amirj commented May 23, 2021

Description

I just added a new tutorial to represent propensity-based stratified evaluation.

Related Issues

Checklist:

  • I have added tests.
  • I have updated the documentation accordingly.
  • I have updated README.md (if you are adding a new model).
  • I have updated examples/README.md (if you are adding a new example).
  • I have updated datasets/README.md (if you are adding a new dataset).

tutorials/README.md Outdated Show resolved Hide resolved
@tqtg
Copy link
Member

tqtg commented May 23, 2021

@saghiles please take a look and see if you have any comments on this PR?

@saghiles
Copy link
Member

Hi @amirj, thanks for your contribution to Cornac, and congratulation for the good work on propensity stratified evaluation. I went through the tutorial and my overall feedback is as follows.

The current version reads more like a usage example of the PropensityStratifiedEvaluation evaluation method. One would expect the tutorial to be self-contained, it should be possible to understand the core idea behind the proposed propensity-based stratified evaluation without (or very little) reference to the original paper. We can think of it as a blog post describing your contribution along with some code illustrating how to use this new evaluation method in Cornac.

If you think that this may require significant efforts and may take some time to do, I would recommend leveraging the material (code) of the current tutorial to make an example first. Please see Cornac examples format, the example should be a runnable python file supported with comments. If you agree please feel free to create a PR accordingly.

We can then integrate a tutorial on propensity-based stratified evaluation once we have enough materials.

Please let us know what are your thoughts, and thanks again for your contribution.

@tqtg
Copy link
Member

tqtg commented Jun 2, 2021

@amirj do you want to convert this into an example first? Maybe we can prepare a more comprehensive tutorial in the form of notebook with more materials and guiding explanation for users?

@amirj
Copy link
Contributor Author

amirj commented Jun 2, 2021

Thanks @saghiles and @tqtg and sorry for my late response.
Yes, let's convert this into an example first. I'll check the format of examples to convert it. In the meantime, let me know if you have further comments. Thanks.

@amirj
Copy link
Contributor Author

amirj commented Jun 5, 2021

@saghiles @tqtg I just modified this PR to reflect a usage example of propensity stratified evaluation method.

@tqtg
Copy link
Member

tqtg commented Jun 6, 2021

I just did some minor changes and updated the docs. Overall, I'm good with the example.

@saghiles any further comments?

@saghiles
Copy link
Member

saghiles commented Jun 7, 2021

The example looks good to me. If @amirj has no further changes we can merge this PR.

@amirj
Copy link
Contributor Author

amirj commented Jun 7, 2021

Thanks both. It looks great to me. Nice to see people can easily reproduce propensity-based stratified evaluation for any model available in Cornac framework :-)

@saghiles
Copy link
Member

saghiles commented Jun 7, 2021

Since there are no more updates, I'll go ahead and merge this PR. Thanks all!

@saghiles saghiles merged commit 215efd0 into PreferredAI:master Jun 7, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants