Add qs2 option for saving model objects #1125
Conversation
VisruthSK
changed the title
VisruthSK
changed the title
|
Should be good once #1127 is merged. |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## master #1125 +/- ##
==========================================
+ Coverage 87.14% 87.28% +0.14%
==========================================
Files 14 14
Lines 5973 5955 -18
==========================================
- Hits 5205 5198 -7
+ Misses 768 757 -11 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
|
The code changes look great. I haven't had a chance to actually try it yet, but I'll do that sometime soon. I also still need to take a look at the vignette changes. |
| Storage is even faster if you discard results you do not need to save. | ||
| The following example saves only posterior draws and discards | ||
| sampler diagnostics, user-specified initial values, and profiling data. | ||
|
|
||
| ```{r save_object_qs_small, eval = FALSE} | ||
| # Load posterior draws into the fitted model object and omit other output. | ||
| fit$draws() | ||
| # Save the object to a file. | ||
| qs::qsave(x = fit, file = "fit.qs") | ||
| # Read the object. | ||
| fit2 <- qs::qread("fit.qs") |
There was a problem hiding this comment.
I realized that this section of the vignette was outdated even before your changes. This doesn't really work to omit other output anymore (unrelated to your changes).
I think people can either save the whole fit object or they can choose to just save the posterior draws themselves separate from the fit object if they want to avoid saving the other contents of the object.
So I kept your changes to the vignette that show how to use save_object with the new format, but I'm just going to delete this second section.
|
For reasons unrelated to the new qs2 format I deleted one section of the vignette (see comment above). I think this is ready to be merged now once it finishes running the checks again. Thanks @VisruthSK! |
|
The failure on macOS-latest (release) is unrelated, so I'll go ahead and merge now. The two macOS ones have these intermittent failures on GHA with several of the install_cmdstan tests. Not even failures to install, just different console output than we're expecting. |
Fixes #1040 by offering the option to use the qs2 format which performed well in tests across model sizes.