[REVIEW]: SpatialGEV: Fast Bayesian inference for spatial extreme value models in R

[editorialbot]

Submitting author: @meixichen (Meixi Chen)
Repository: https://github.com/meixichen/SpatialGEV
Branch with paper.md (empty if default branch): joss
Version: v1.0.1
Editor: @vissarion
Reviewers: @fabian-s, @fernandomayer
Archive: Pending

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/e13a0debdab2d59bb8bc0eefb55aa8ac"><img src="https://joss.theoj.org/papers/e13a0debdab2d59bb8bc0eefb55aa8ac/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/e13a0debdab2d59bb8bc0eefb55aa8ac/status.svg)](https://joss.theoj.org/papers/e13a0debdab2d59bb8bc0eefb55aa8ac)

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) by leaving comments 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

@fabian-s & @fernandomayer, your review will be checklist based. Each of you will have a separate checklist that you should update when carrying out your review.
First of all you need to run this command in a separate comment to create the checklist:

@editorialbot generate my checklist

The reviewer guidelines are available here: https://joss.readthedocs.io/en/latest/reviewer_guidelines.html. Any questions/concerns please let @vissarion know.

✨ Please start on your review when you are able, and be sure to complete your review in the next six weeks, at the very latest ✨

Checklists

📝 Checklist for @fabian-s

[editorialbot]

Hello humans, I'm @editorialbot, a robot that can help you with some common editorial tasks.

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

@editorialbot commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@editorialbot generate pdf

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.90  T=0.03 s (2017.8 files/s, 242489.1 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
R                               37            146            932           2086
C/C++ Header                    15            234           1139           1342
Markdown                         2             61              0            327
TeX                              2             52              0            304
YAML                             2             12              6             58
C++                              2              4              2             53
Rmd                              2            138            511             44
-------------------------------------------------------------------------------
SUM:                            62            647           2590           4214
-------------------------------------------------------------------------------

Commit count by author:

   156	meixichen
    23	m372chen
     9	mlysy
     3	Meixi Chen

[editorialbot]

Paper file info:

📄 Wordcount for paper.md is 2092

✅ The paper includes a Statement of need section

[editorialbot]

License info:

🟡 License found: GNU General Public License v3.0 (Check here for OSI approval)

[editorialbot]

Reference check summary (note 'MISSING' DOIs are suggestions that need verification):

OK DOIs

- None

MISSING DOIs

- No DOI given, and none found for title: Fast and Scalable Approximate Inference for Spatia...
- 10.2307/2287970 may be a valid DOI for title: Accurate Approximations for Posterior Moments and ...
- No DOI given, and none found for title: Inference and computation with generalized additiv...
- 10.1016/j.spasta.2022.100599 may be a valid DOI for title: The SPDE approach for Gaussian and non-Gaussian fi...
- 10.1016/s0167-4730(98)00015-0 may be a valid DOI for title: Extreme Value Modelling of Hurricane Wind Speeds
- 10.1198/016214506000000780 may be a valid DOI for title: Bayesian Spatial Modeling of Extreme Precipitation...
- 10.1007/s10687-009-0098-2 may be a valid DOI for title: A Comparison Study of Extreme Precipitation from S...
- 10.1002/env.2301 may be a valid DOI for title: Bayesian Hierarchical Modeling of Extreme Hourly P...
- 10.1016/j.jhydrol.2015.09.023 may be a valid DOI for title: A Spatial Model to Examine Rainfall Extremes in Co...
- 10.1201/b10905-6 may be a valid DOI for title: MCMC Using Hamiltonian Dynamics
- No DOI given, and none found for title: The No-U-Turn Sampler: Adaptively Setting Path Len...
- No DOI given, and none found for title: RStan: the R interface to Stan
- 10.1007/s13253-009-0010-1 may be a valid DOI for title: Continuous Spatial Process Models for Spatial Extr...
- No DOI given, and none found for title: Bayesian Spatial Modelling with R-INLA
- 10.1111/j.1467-9868.2011.00777.x may be a valid DOI for title: An explicit link between Gaussian fields and Gauss...
- No DOI given, and none found for title: TMB: Automatic Differentiation and Laplace Approxi...
- No DOI given, and none found for title: A Unifying View of Sparse Approximate Gaussian Pro...
- No DOI given, and none found for title: Understanding the Stochastic Partial Differential ...
- No DOI given, and none found for title: SpatialExtremes: Modelling Spatial Extremes
- No DOI given, and none found for title: \textttmgcv: Mixed GAM Computation Vehicle with Au...
- No DOI given, and none found for title: \textttevgam: An R Package for Generalized Additiv...

INVALID DOIs

- None

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[fabian-s]

Review checklist for @fabian-s

Conflict of interest

• I confirm that I have read the JOSS conflict of interest (COI) policy and that: I have no COIs with reviewing this work or that any perceived COIs have been waived by JOSS for the purpose of this review.

Code of Conduct

• I confirm that I read and will adhere to the JOSS code of conduct.

General checks

• Repository: Is the source code for this software available at the https://github.com/meixichen/SpatialGEV?
• License: Does the repository contain a plain-text LICENSE or COPYING file with the contents of an OSI approved software license?
• Contribution and authorship: Has the submitting author (@meixichen) made major contributions to the software? Does the full list of paper authors seem appropriate and complete?
• Substantial scholarly effort: Does this submission meet the scope eligibility described in the JOSS guidelines
• Data sharing: If the paper contains original data, data are accessible to the reviewers. If the paper contains no original data, please check this item.
• Reproducibility: If the paper contains original results, results are entirely reproducible by reviewers. If the paper contains no original results, please check this item.
• Human and animal research: If the paper contains original data research on humans subjects or animals, does it comply with JOSS's human participants research policy and/or animal research policy? If the paper contains no such data, please check this item.

Functionality

• Installation: Does installation proceed as outlined in the documentation?
• Functionality: Have the functional claims of the software been confirmed?
• Performance: If there are any performance claims of the software, have they been confirmed? (If there are no claims, please check off this item.)

Documentation

• A statement of need: Do the authors clearly state what problems the software is designed to solve and who the target audience is?
• Installation instructions: Is there a clearly-stated list of dependencies? Ideally these should be handled with an automated package management solution.
• Example usage: Do the authors include examples of how to use the software (ideally to solve real-world analysis problems).
• Functionality documentation: Is the core functionality of the software documented to a satisfactory level (e.g., API method documentation)?
• Automated tests: Are there automated tests or manual steps described so that the functionality of the software can be verified?
• Community guidelines: Are there clear guidelines for third parties wishing to 1) Contribute to the software 2) Report issues or problems with the software 3) Seek support

Software paper

• Summary: Has a clear description of the high-level functionality and purpose of the software for a diverse, non-specialist audience been provided?
• A statement of need: Does the paper have a section titled 'Statement of need' that clearly states what problems the software is designed to solve, who the target audience is, and its relation to other work?
• State of the field: Do the authors describe how this software compares to other commonly-used packages?
• Quality of writing: Is the paper well written (i.e., it does not require editing for structure, language, or writing quality)?
• References: Is the list of references complete, and is everything cited appropriately that should be cited (e.g., papers, datasets, software)? Do references in the text use the proper citation syntax?

[fabian-s]

@meixichen could you try finding/adding the missing DOIs? (see above)

[vissarion]

Thanks @fabian-s for noting this. @meixichen please also try to reduce the length of the submission (following this pre-review-comment #6861 (comment))

[meixichen]

Thanks for reviewing this manuscript and package. I will shorten the paper and add the missing DOIs.

[meixichen]

@editorialbot generate pdf

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[meixichen]

@editorialbot check repository

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.90  T=0.03 s (2015.3 files/s, 237836.6 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
R                               37            146            932           2086
C/C++ Header                    15            234           1139           1342
TeX                              2             54              0            314
Markdown                         2             46              0            196
YAML                             2             12              6             58
C++                              2              4              2             53
Rmd                              2            138            511             44
-------------------------------------------------------------------------------
SUM:                            62            634           2590           4093
-------------------------------------------------------------------------------

Commit count by author:

   158	meixichen
    23	m372chen
     9	mlysy
     3	Meixi Chen

[editorialbot]

Paper file info:

📄 Wordcount for paper.md is 847

✅ The paper includes a Statement of need section

[editorialbot]

License info:

🟡 License found: GNU General Public License v3.0 (Check here for OSI approval)

[meixichen]

@editorialbot generate pdf

[meixichen]

@editorialbot check repository

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.90  T=0.03 s (1911.5 files/s, 227994.9 lines/s)
-------------------------------------------------------------------------------
Language                     files          blank        comment           code
-------------------------------------------------------------------------------
R                               37            146            932           2086
C/C++ Header                    15            234           1139           1342
TeX                              2             54              0            314
Markdown                         2             55              0            265
YAML                             2             12              6             58
C++                              2              4              2             53
Rmd                              2            138            511             44
-------------------------------------------------------------------------------
SUM:                            62            643           2590           4162
-------------------------------------------------------------------------------

Commit count by author:

   159	meixichen
    23	m372chen
     9	mlysy
     3	Meixi Chen

[editorialbot]

Paper file info:

📄 Wordcount for paper.md is 1494

✅ The paper includes a Statement of need section

[editorialbot]

License info:

🟡 License found: GNU General Public License v3.0 (Check here for OSI approval)

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[meixichen]

Hello, I wonder if 1494 word count is still considered too long? Thanks!

[fabian-s]

Contribution and authorship:

Seems like only @meixichen has a meaningful number of commits here -- what are the contributions of the other two authors? The only commit of @mlysy from 4 years ago (meixichen/SpatialGEV@47be58e) seems more like housekeeping to me and, in any case, git blame (https://github.com/meixichen/SpatialGEV/blame/master/inst/include/SpatialGEV/utils.hpp) seems to indicate that very little none of the code committed by them back then still remains part of the codebase?

[fabian-s]

Automated tests: test coverage seems to be rather low, see meixichen/SpatialGEV#14

[fabian-s]

Community guidelines: you should add a CONTRIBUTING.md or similar to the repo, see https://contributing.md/example/ e.g.

[fabian-s]

Functionality:
Neither the package vignette nor the JOSS paper provide examples or details on how covariate information is included in the model. Are these linear effects? If so, how are the coefficients sampled and based on which priors? Do the covariates need to be scaled/centered?

[fabian-s]

Documentation:
Your github README.md and your vignette use y as the first argument to spatialGEV_fit, the package and the JOSS paper use data, this seems to have diverged.

[fabian-s]

@meixichen any news re. my questions/requests above?

[meixichen]

@meixichen any news re. my questions/requests above?

@fabian-s Regarding meixichen/SpatialGEV#14 I have merged joss with master and added more unittests. Test coverage is close to 90% now https://app.codecov.io/github/meixichen/SpatialGEV/tree/master

I am still working on the other requests and will reply here after I am done with them. For authorship, many conversations about functionalities and code design were done off-line or over emails. Some of mlysy's code were in the joss branch and were not reflected in master, but now after merging the joss into master we should see it.

[meixichen]

Hello @fabian-s , regarding the issues you flagged, I have made the following changes:

• Automated tests: I have included more thorough unittests for the package. The test coverage is now 96%.
• Community guidelines: I have included CONTRIBUTING.md
• Functionality documentation: I have included a section in the vignette explaning how to include covariates in the model.
• Contribution and authorship: As mentioned in a previous comment, many conversations about functionalities and code design were done off-line or over emails. Some of mlysy's code were in the joss branch and were not reflected in master, but now after merging the joss into master we should see it.
• Performance: We demonstrated the accuracy of the approximations used in the package in the simulation studies in the vignette.
• Diverged branches: The branch joss has been merged into master.

Any comments or suggestions? Thank you very much!

[vissarion]

Hi @fernandomayer just checking if there are any issues that blocks you to start with your review.

[fabian-s]

Thanks, I closed the issue.

The example with covariates in your vignette does not work: https://github.com/meixichen/SpatialGEV/blob/61466b5dde6e5f36965f2244fd8034224076cac3/vignettes/SpatialGEV-vignette.Rmd#L314C1-L340C1 is all just error messages...? If I re-compile it locally, it works fine, though:

I don't really think it makes sense to include this vignette "pre-compiled" as you're doing now, it doesn't take that long to run and it's bad practice to do so anyway, to avoid exactly this kind of problem. You also provide the wrong paths to your image files in that pre-compiled fake vignette (the paths are `figures/bla.png', but the files are not in that subdirectory, it does not exist....)

@vissarion not sure what your editorial standards are re. R packages.
This is currently not fully standards compliant and would not pass R CMD check --as-cran, see meixichen/SpatialGEV#22, but I can check off all checklist items in good conscience here.

[vissarion]

@fabian-s there are no editorial standard specifically for R packages. The general rule "packaged appropriately according to common community standards for the programming language being used", could mean that R CMD check should pass but not necessarily R CMD check --as-cran. But still I am not saying that R CMD check is a requirement for JOSS acceptance but rather a useful tool to indicate if the submitted software is appropriately packaged.

[fabian-s]

sure, I know, I also do editor-stuff for JOSS - that's why I said your standards ;)

FWIW, the NOTES/WARNINGS/ERROS don't seem that serious to me, the package can be installed in the standard way and it runs, including examples etc.

If it were my call, I would still request to make it CRAN-compliant s.t. the version of the package presented in the paper is more similar/identical to the respective CRAN version.

[vissarion]

I agree that it would be nice to make it CRAN-compliant. Though I would not like this to be a blocking issue. To my understanding there is not much work towards this goal (and in any case maybe that work will be done anyways to update the current CRAN package). @meixichen do you agree to make this package pass R CMD check --as-cran in the course of JOSS submission?

[meixichen]

@fabian-s @vissarion I agree with you both. I have pushed the new changes on the vignette, which is now no longer pre-compiled. Passed the check for me:

checking files in 'vignettes' ... OK
* checking examples ... OK
* checking for unstated dependencies in 'tests' ... OK
* checking tests ... [41s] OK
  Running 'testthat.R' [41s]
* checking for unstated dependencies in vignettes ... OK
* checking package vignettes ... OK
* checking re-building of vignette outputs ... [410s] OK
* checking PDF version of manual ... [21s] OK
* checking HTML version of manual ... OK
* DONE

[fabian-s]

Passed the check for me:

for me as well

[fernandomayer]

Hi @fernandomayer just checking if there are any issues that blocks you to start with your review.

@vissarion Sorry for the delay. I'll be starting my review this week, planning to finalise it mid-next week.