Simulate infections

[sbfnk]

Description

This PR closes #509

It re-introduces the simulate_infections function, this time to simulate from given parameters (at the minimum, a trajectory of R and the number of initial infections). It also adds truncation to the simulation model (which had been missing).

Doing so required a small change to extract_parameter_samples which won't affect any existing functionality.

Initial submission checklist

• My PR is based on a package issue and I have explicitly linked it.
• I have tested my changes locally (using devtools::test() and devtools::check()).
• I have added or updated unit tests where necessary.
• I have updated the documentation if required and rebuilt docs if yes (using devtools::document()).
• I have followed the established coding standards (and checked using lintr::lint_package()).
• I have added a news item linked to this PR.

After the initial Pull Request

• I have reviewed Checks for this PR and addressed any issues as far as I am able.

[jamesmbaazam]

Thanks, Seb. Neat enhancement. I've left a few non-earth-shattering comments.

[sbfnk]

Thanks, @jamesmbaazam. Added your suggestions and a few tests which revealed few minor issues in the stan code which have now been fixed.

[seabbs]

From an overall functionality perspective this looks good to me. One note about a testing gap that is somewhat optional.

I think wait for @jamesmbaazam to be happy with the software dev side and then merge.

[github-actions]

This is how benchmark results would change (along with a 95% confidence interval in relative change) if 8eb1b5d is merged into main:

• ✔️default: 31.6s -> 36s [-0.03%, +28.21%]
• ✔️no_delays: 35.6s -> 37.7s [-22.76%, +34.88%]
• ✔️random_walk: 8.96s -> 9.23s [-6.75%, +12.9%]
• ✔️stationary: 24.9s -> 18.4s [-92.81%, +40.53%]
• ✔️uncertain: 52.7s -> 52.1s [-18.93%, +16.82%]
  Further explanation regarding interpretation and methodology can be found in the documentation.

[jamesmbaazam]

Thanks, Seb. LGTM.

[github-actions]

This is how benchmark results would change (along with a 95% confidence interval in relative change) if 3c1ad81 is merged into main:

• ✔️default: 32s -> 32.6s [-4.11%, +7.3%]
• ✔️no_delays: 34.6s -> 34.9s [-16.24%, +18.16%]
• ✔️random_walk: 30.2s -> 9.25s [-229.87%, +91.14%]
• ✔️stationary: 17.7s -> 17.6s [-15.61%, +14.89%]
• ✔️uncertain: 52.5s -> 51.3s [-16.94%, +12.48%]
  Further explanation regarding interpretation and methodology can be found in the documentation.