search

openjournals / joss-reviews

Reviews for the Journal of Open Source Software
Creative Commons Zero v1.0 Universal
721 stars 38 forks source link

[REVIEW]: ChiRP: Chinese Restaurant Process Mixtures for Regression and Clustering #1287

Closed whedon closed 5 years ago

whedon commented 5 years ago

Submitting author: @stablemarkets (Arman Oganisian) Repository: https://github.com/stablemarkets/ChiRP Version: 1.0.0 Editor: @pjotrp Reviewer: @agisga Archive: 10.5281/zenodo.2591600

Status

status

Status badge code:

HTML: <a href="http://joss.theoj.org/papers/3b83a0a3f1220f97657a1075b78e480a"><img src="http://joss.theoj.org/papers/3b83a0a3f1220f97657a1075b78e480a/status.svg"></a>
Markdown: [![status](http://joss.theoj.org/papers/3b83a0a3f1220f97657a1075b78e480a/status.svg)](http://joss.theoj.org/papers/3b83a0a3f1220f97657a1075b78e480a)

Reviewers and authors:

Please avoid lengthy details of difficulties in the review thread. Instead, please create a new issue in the target repository and link to those issues (especially acceptance-blockers) in the review thread below. (For completists: if the target issue tracker is also on GitHub, linking the review thread in the issue or vice versa will create corresponding breadcrumb trails in the link target.)

Reviewer instructions & questions

@agisga, please carry out your review in this issue by updating the checklist below. If you cannot edit the checklist please:

  1. Make sure you're logged in to your GitHub account
  2. Be sure to accept the invite at this URL: https://github.com/openjournals/joss-reviews/invitations

The reviewer guidelines are available here: https://joss.theoj.org/about#reviewer_guidelines. Any questions/concerns please let @pjotrp know.

✨ Please try and complete your review in the next two weeks ✨

Review checklist for @agisga

Conflict of interest

Code of Conduct

General checks

Functionality

Documentation

Software paper

whedon commented 5 years ago

Hello human, I'm @whedon, a robot that can help you with some common editorial tasks. @agisga it looks like you're currently assigned as the reviewer for this paper :tada:.

:star: Important :star:

If you haven't already, you should seriously consider unsubscribing from GitHub notifications for this (https://github.com/openjournals/joss-reviews) repository. As a reviewer, you're probably currently watching this repository which means for GitHub's default behaviour you will receive notifications (emails) for all reviews 😿

To fix this do the following two things:

  1. Set yourself as 'Not watching' https://github.com/openjournals/joss-reviews:

watching

  1. You may also like to change your default settings for this watching repositories in your GitHub profile here: https://github.com/settings/notifications

notifications

For a list of things I can do to help you, just type:

@whedon commands
whedon commented 5 years ago 
Attempting PDF compilation. Reticulating splines etc...
whedon commented 5 years ago

:point_right: Check article proof :page_facing_up: :point_left:

pjotrp commented 5 years ago

@stablemarkets, we are starting review in this issue tracker. To expedite the review process do you mind going through above list of check boxes and make sure they can be ticked (you can't tick them). Also check the PDF output carefully. Ping us here when you are done.

stablemarkets commented 5 years ago

Hi @pjotrp. Thank you for working on this.

I've provided responses to several items in the check list below:

General checks

Functionality

Documentation

pjotrp commented 5 years ago

Thank you. @agisga feel free to start review. Guide lines are at the top of this page.

agisga commented 5 years ago

Hi!

I have reviewed this submission. Generally it is pretty good. My review is given below.

Summary:

This submission is an R package that implements several Bayesian models from the family of Chinese Restaurant Process (CRP) mixtures. The methods implemented in ChiRP can be used for regression, binary classification, clustering, and related inference tasks. These are very common data analysis tasks, which one commonly encounters in many scientific disciplines. However, the author seems to be motivated specifically by biomedical applications. The advantages of the ChiRP models against alternative methods, include their nonparametric nature, the ability to return interval estimates, and to obtain posterior distributions for predictions as well as for cluster assignments on training and test data. In particular, unlike many other clustering algorithms, here the number of clusters is not specified a priori, and is determined automatically from the data (although an initial number of clusters needs to be given to kick off the MCMC sampler). The package website including model description and examples is really informative and great (in addition, the R Shiny tutorial based on Dirichlet Processes is just awesome). The R code is well-documented, and includes automated tests too. Code quality seems to be good (based on a very quick look through each of the source code files). I'm not an expert on the methodology but, running and tweaking the provided examples, the package code seems to be doing what it's supposed to do. Some minor issues are listed below.

Potential Issues:

None of these are serious issues.

pjotrp commented 5 years ago

Thank you @agisga! @stablemarkets if you can address these points quickly we can publish!

stablemarkets commented 5 years ago

Hi @pjotrp and @agisga. Thank you for your thorough review! Thanks especially for reviewing the companion web site - extremely helpful.

The package repository has been updated with edits that address your feedback (see below for details). I think the paper.md file will need to be recompiled for the edits to be visible?

  1. I added DOIs to all but two references in paper.bib. I could not find DOIs for two of the papers. One is an ArXiv paper (currently unpublished) so I think it has no DOI yet. For both papers, URLs are provided. Hope this is okay.

  2. Thanks! I've added an acknowledgements sections to the paper mentioning these individuals.

  3. I've added two citations to seminal CRP papers - Ferguson 1973, Blackwell 1973 - to the first paragraph when introducing CRPs.

  4. Contribution instructions have been added to both the ChiRP repository and the companion site. Users can contribute by proposing modifications to the base code or by adding usage examples to the companion site.

  5. testthat warnings: Thanks for catching this! I looked into it. The warning is triggered when someone specifies and init_k with a length greater than 1. In error_checks(), I run a single check that returns an error if init_k is not numeric, or if init_k is not a scalar (e.g. length 2), or if init_k<0. If init_k is of length 2, an error is indeed returned so the test is passed. However, evaluating init_k<0, yields a length 2 logical vector while the other two conditions in the check yield length 1 logicals. So it shoots a warning saying it will only use the first element of init_k<0 to evaluate the entire check. I fixed this by doing a nested check: first making sure init_k is numeric and length 1. Then, if that is passed, check to make sure if init_k>0. If it's not, throw an error message at the user. This passes the automated test without shooting an additional warning since init_k<0is evaluated only when we are sure init_k is a scalar.

  6. I'm not sure but the ARCHIVE link is probably not working since I haven't archived the paper yet. According to review process it seems like we only archive after the review process is completed?

  7. Thanks for catching these typos: I've renamed helper/functions_pdp.r, fixed the notation rendering on the site, as well as spell-checked each of the three pages on the companion site.

pjotrp commented 5 years ago

Excellent. @agisga can you run through those points and confirm you are happy?

agisga commented 5 years ago

@pjotrp

Everything looks good to me!

I don't think there is a new article proof. So, can't check that. But I have looked at all new commits in the ChiRP repo, and also confirmed that the automated tests now run without warnings.

I don't know how strict JOSS is about having DOIs for every article reference, but in my opinion it's fine to have those two DOIs missing, especially because URLs are provided. Thus, I have checked the last checkbox. I leave the final decision up to you.

pjotrp commented 5 years ago

Thank you for the thorough review @agisga. @stablemarkets: to finalize your submission and accept your paper in JOSS, we need two things. First, can you confirm that all references in your bibliography have a DOI in the bibliography (if one exists).

Second, we need you to deposit a copy of your software repository (including any revisions made during the JOSS review process) with a data-archiving service.

To do so:

  1. Create a GitHub release of the current version of your software repository
  2. Deposit that release with Zenodo, figshare, or a similar DOI issuer.
  3. Post a comment here with the DOI for the release.
pjotrp commented 5 years ago

@whedon generate pdf

whedon commented 5 years ago 
Attempting PDF compilation. Reticulating splines etc...
whedon commented 5 years ago

:point_right: Check article proof :page_facing_up: :point_left:

stablemarkets commented 5 years ago

Hi @pjotrp,

I confirm all references in my bibliography have a DOI where available. I've deposited my repository (including revisions discussed here) to Zenodo. Here is the DOI badge:

DOI

pjotrp commented 5 years ago

@whedon set 10.5281/zenodo.2591600 as archive

whedon commented 5 years ago

OK. 10.5281/zenodo.2591600 is the archive.

pjotrp commented 5 years ago

@whedon accept

whedon commented 5 years ago 
Attempting dry run of processing paper acceptance...
whedon commented 5 years ago

PDF failed to compile for issue #1287 with the following error:

/app/vendor/ruby-2.4.4/lib/ruby/2.4.0/find.rb:43:in block in find': No such file or directory - tmp/1287 (Errno::ENOENT) from /app/vendor/ruby-2.4.4/lib/ruby/2.4.0/find.rb:43:incollect!' from /app/vendor/ruby-2.4.4/lib/ruby/2.4.0/find.rb:43:in find' from /app/vendor/bundle/ruby/2.4.0/bundler/gems/whedon-01ece1d1d135/lib/whedon/processor.rb:57:infind_paper_paths' from /app/vendor/bundle/ruby/2.4.0/bundler/gems/whedon-01ece1d1d135/bin/whedon:73:in compile' from /app/vendor/bundle/ruby/2.4.0/gems/thor-0.20.3/lib/thor/command.rb:27:inrun' from /app/vendor/bundle/ruby/2.4.0/gems/thor-0.20.3/lib/thor/invocation.rb:126:in invoke_command' from /app/vendor/bundle/ruby/2.4.0/gems/thor-0.20.3/lib/thor.rb:387:indispatch' from /app/vendor/bundle/ruby/2.4.0/gems/thor-0.20.3/lib/thor/base.rb:466:in start' from /app/vendor/bundle/ruby/2.4.0/bundler/gems/whedon-01ece1d1d135/bin/whedon:116:in<top (required)>' from /app/vendor/bundle/ruby/2.4.0/bin/whedon:23:in load' from /app/vendor/bundle/ruby/2.4.0/bin/whedon:23:in

'

whedon commented 5 years ago 

OK DOIs

- 10.1007/978-3-319-18968-0 is OK
- 10.1080/10618600.2000.10474879 is OK
- 10.1016/j.jmp.2011.08.004 is OK
- 10.2307/2334940 is OK
- 10.1080/10618600.2012.735624 is OK
- 10.1111/1467-9868.00265 is OK
- 10.1214/aos/1176342360 is OK
- 10.1214/aos/1176342372 is OK

MISSING DOIs

- https://doi.org/10.1145/1015330.1015439 may be missing for title: Dirichlet process mixtures of generalized linear models
- https://doi.org/10.2172/1212177 may be missing for title: A Bayesian Nonparametric Model for Zero-Inflated Outcomes: Prediction, Clustering, and Causal Estimation

INVALID DOIs

- None
pjotrp commented 5 years ago

@arfon can you check why the PDF is failing?

arfon commented 5 years ago

@whedon generate pdf

whedon commented 5 years ago 
Attempting PDF compilation. Reticulating splines etc...
whedon commented 5 years ago

:point_right: Check article proof :page_facing_up: :point_left:

arfon commented 5 years ago

@whedon check references

whedon commented 5 years ago 
Attempting to check references...
whedon commented 5 years ago 

OK DOIs

- 10.1007/978-3-319-18968-0 is OK
- 10.1080/10618600.2000.10474879 is OK
- 10.1016/j.jmp.2011.08.004 is OK
- 10.2307/2334940 is OK
- 10.1080/10618600.2012.735624 is OK
- 10.1111/1467-9868.00265 is OK
- 10.1214/aos/1176342360 is OK
- 10.1214/aos/1176342372 is OK

MISSING DOIs

- None

INVALID DOIs

- None
pjotrp commented 5 years ago

@whedon accept

whedon commented 5 years ago 
Attempting dry run of processing paper acceptance...
whedon commented 5 years ago 

OK DOIs

- 10.1007/978-3-319-18968-0 is OK
- 10.1080/10618600.2000.10474879 is OK
- 10.1016/j.jmp.2011.08.004 is OK
- 10.2307/2334940 is OK
- 10.1080/10618600.2012.735624 is OK
- 10.1111/1467-9868.00265 is OK
- 10.1214/aos/1176342360 is OK
- 10.1214/aos/1176342372 is OK

MISSING DOIs

- None

INVALID DOIs

- None
whedon commented 5 years ago

Check final proof :point_right: https://github.com/openjournals/joss-papers/pull/575

If the paper PDF and Crossref deposit XML look good in https://github.com/openjournals/joss-papers/pull/575, then you can now move forward with accepting the submission by compiling again with the flag deposit=true e.g.

@whedon accept deposit=true
pjotrp commented 5 years ago

ping eic @openjournals/joss-eics

arfon commented 5 years ago

@whedon accept deposit=true

whedon commented 5 years ago 
Doing it live! Attempting automated processing of paper acceptance...
whedon commented 5 years ago

🚨🚨🚨 THIS IS NOT A DRILL, YOU HAVE JUST ACCEPTED A PAPER INTO JOSS! 🚨🚨🚨

Here's what you must now do:

  1. Check final PDF and Crossref metadata that was deposited :point_right: https://github.com/openjournals/joss-papers/pull/576
  2. Wait a couple of minutes to verify that the paper DOI resolves https://doi.org/10.21105/joss.01287
  3. If everything looks good, then close this review issue.

  4. Party like you just published a paper! 🎉🌈🦄💃👻🤘

    Any issues? notify your editorial technical team...

arfon commented 5 years ago

@agisga - many thanks for your review and to @pjotrp for editing this submission ✨

@stablemarkets - your paper is now accepted into JOSS :zap::rocket::boom:

whedon commented 5 years ago

:tada::tada::tada: Congratulations on your paper acceptance! :tada::tada::tada:

If you would like to include a link to your paper from your README use the following code snippets:

Markdown:
[![DOI](http://joss.theoj.org/papers/10.21105/joss.01287/status.svg)](https://doi.org/10.21105/joss.01287)

HTML:
<a style="border-width:0" href="https://doi.org/10.21105/joss.01287">
  <img src="http://joss.theoj.org/papers/10.21105/joss.01287/status.svg" alt="DOI badge" >
</a>

reStructuredText:
.. image:: http://joss.theoj.org/papers/10.21105/joss.01287/status.svg
   :target: https://doi.org/10.21105/joss.01287

This is how it will look in your documentation:

DOI

We need your help!

Journal of Open Source Software is a community-run journal and relies upon volunteer effort. If you'd like to support us please consider doing either one (or both) of the the following: