A generic wrapper around posterior::draws_df()
with
opinionated defaults to extract the posterior samples for the
nowcast ("pp_inf_obs"
from the stan
code). The functionality of
this function can be used directly on the output of epinowcast()
using
the supplied summary.epinowcast()
method.
Arguments
- fit
A
cmdstanr
fit object.- obs
An observation
data.frame
containingreference_date
columns of the same length as the number of rows in the posterior and the most up to date observation for each date. This is used to align the posterior with the observations. The easiest source of this data is the output of latest output ofenw_preprocess_data()
orenw_latest_data()
.
Value
A data.frame
of posterior samples for the nowcast prediction.
This uses observed data where available and the posterior prediction
where not.
See also
Functions used for postprocessing of model fits
enw_add_latest_obs_to_nowcast()
,
enw_nowcast_summary()
,
enw_posterior()
,
enw_pp_summary()
,
enw_quantiles_to_long()
,
enw_summarise_samples()
Examples
fit <- enw_example("nowcast")
enw_nowcast_samples(fit$fit[[1]], fit$latest[[1]])
#> reference_date report_date .group max_confirm location age_group confirm
#> 1: 2021-08-03 2021-08-22 1 149 DE 00+ 149
#> 2: 2021-08-03 2021-08-22 1 149 DE 00+ 149
#> 3: 2021-08-03 2021-08-22 1 149 DE 00+ 149
#> 4: 2021-08-03 2021-08-22 1 149 DE 00+ 149
#> 5: 2021-08-03 2021-08-22 1 149 DE 00+ 149
#> ---
#> 19996: 2021-08-22 2021-08-22 1 45 DE 00+ 45
#> 19997: 2021-08-22 2021-08-22 1 45 DE 00+ 45
#> 19998: 2021-08-22 2021-08-22 1 45 DE 00+ 45
#> 19999: 2021-08-22 2021-08-22 1 45 DE 00+ 45
#> 20000: 2021-08-22 2021-08-22 1 45 DE 00+ 45
#> cum_prop_reported delay prop_reported .chain .iteration .draw sample
#> 1: 1 19 0 1 1 1 149
#> 2: 1 19 0 1 2 2 149
#> 3: 1 19 0 1 3 3 149
#> 4: 1 19 0 1 4 4 149
#> 5: 1 19 0 1 5 5 149
#> ---
#> 19996: 1 0 1 2 496 996 409
#> 19997: 1 0 1 2 497 997 362
#> 19998: 1 0 1 2 498 998 272
#> 19999: 1 0 1 2 499 999 247
#> 20000: 1 0 1 2 500 1000 189