posterior
posterior copied to clipboard
stan-dev
The posterior R package
### Summary This PR aims to address (at least part of) #184 by implementing weighted `rvar`s. Currently, `rvar`s cannot contain weights, and weighting of them can only be done by...
#### Summary This would fix #280. I am revisiting r_eff while implementing the weighted MCSE and ESS, which should take this into account (if draws are from MCMC). I implemented...
#### Summary This would fix #355. As it is affecting `summarise_draws`, which is one of the main functions in `posterior`, I think this change needs to be considered carefully. It...
Pinging off discussion in #306, it might be good to have warning levels to set the verbosity of warnings for common things (like needing to merge chains). We would need...
If a summary function that returns a character is used in `summarise_draws`, it makes all columns `` which messes up formatting. ```r example_draws() |> summarise_draws(char_fun = \(x) "word", mean) ```...
My workflow is pretty data.table based. It would be nice to have a format like `draws_df` that uses the data.table backend. I think this would be semi copy-paste heavy wrt...
Are there simple ways (can be internal functions) to apply a function to each chain of a `draws` or `rvar` object? For a `draws` object, I can do: ```r example_draws()...
The discussion about a data.table format reminded me of something I wanted to bring up for a while. I wonder if we can have a non-rvar format that can handle...
#### Summary Now that some improved index-handling code is in, I thought I'd take a second attempt at rollups of summaries of variables with indices. This is a PR that...
Currently the `pareto_*` summary functions return named vectors without the preceding `pareto_`. e.g. `pareto_convergence_rate` returns a numeric named `convergence_rate`. This was done as the function names were deemed too long...