-
Notifications
You must be signed in to change notification settings - Fork 33
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
Cmdstanr option #537
Cmdstanr option #537
Conversation
4374687
to
0d54c93
Compare
84455e6
to
5683d25
Compare
3e33ae9
to
0a32e57
Compare
All checks now passing except windows one which looks unrelated. |
Agree, I see this in multiple places including the |
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 looks really great and I think its all in place. I've just done a read through and will play with the new functionality and then review again
d53ce57
to
113eb77
Compare
This reverts commit e57ae76.
Co-authored-by: Sam Abbott <[email protected]>
01df6e2
to
b1c54a4
Compare
* add cmdstan backend * add cmdstanr model * generalise extract functions * create general fit_model function * initial values for cmdstanr * move stan model creation to create func * make dist_fit cmdstanr ready * make estimate_infections cmdstanr ready * make estimate_secondary cmdstanr ready * make estimate_truncation cmdstanr ready * make simulate_infections cmdstanr ready * gitignore for binaries * add cmdstanr as suggest * make forecast_secondary cmdstanr ready * update stanargs test * make simulations work with updated options * add globals * tests for cmdstanr backend * update actions * updates in response to lintr * don't use future_lapply for cmdstanr * backend-specific success criteria * use epinowcast action for installing cmdstan * improve .gitignore for compiled stan files * deactivate testing on windows for now * Revert "use epinowcast action for installing cmdstan" This reverts commit e57ae76. * Apply suggestions from code review Co-authored-by: Sam Abbott <[email protected]> * match arguments in `stan_model` * don't match args$method but explictly stop instead * put choices in argument --------- Co-authored-by: Sam Abbott <[email protected]>
* add cmdstan backend * add cmdstanr model * generalise extract functions * create general fit_model function * initial values for cmdstanr * move stan model creation to create func * make dist_fit cmdstanr ready * make estimate_infections cmdstanr ready * make estimate_secondary cmdstanr ready * make estimate_truncation cmdstanr ready * make simulate_infections cmdstanr ready * gitignore for binaries * add cmdstanr as suggest * make forecast_secondary cmdstanr ready * update stanargs test * make simulations work with updated options * add globals * tests for cmdstanr backend * update actions * updates in response to lintr * don't use future_lapply for cmdstanr * backend-specific success criteria * use epinowcast action for installing cmdstan * improve .gitignore for compiled stan files * deactivate testing on windows for now * Revert "use epinowcast action for installing cmdstan" This reverts commit e57ae76. * Apply suggestions from code review Co-authored-by: Sam Abbott <[email protected]> * match arguments in `stan_model` * don't match args$method but explictly stop instead * put choices in argument --------- Co-authored-by: Sam Abbott <[email protected]>
Closes #48 by implementing a
backend = "cmdstanr"
option.This contains everything in #472 except the profiling bits (which don't seem supported by
rstan
).This necessitated some (ultimately probably positive) streamlining of how the stan arguments are constructed for the different models.