Extract the parameters of a distribution

Some distributions (such as dist_inflated() and dist_transformed()) are defined in terms of another distribution, which returns a distribution as one of their parameters. By default, this underlying distribution is returned as-is in a column of the parameters() result. Setting recursive = TRUE will recursively compute the parameters of these inner distributions, returning a flat data frame of all parameters.

parameters(x, ...)

# S3 method for class 'distribution'
parameters(x, recursive = FALSE, ...)

Arguments

x

The distribution(s).

...

Additional arguments used by methods.

recursive

If TRUE, parameters which are themselves distributions (such as the base distribution of a dist_inflated() or dist_transformed()) are recursively expanded into their own parameters instead of being returned as a distribution.

Value

A data frame of parameters, with one row per distribution and one column per parameter. The result never contains data frame (or distribution) columns.

Examples

dist <- c(
  dist_normal(1:2),
  dist_poisson(3),
  dist_multinomial(size = c(4, 3),
  prob = list(c(0.3, 0.5, 0.2), c(0.1, 0.5, 0.4)))
  )
parameters(dist)
#>   mu sigma  l  s             p
#> 1  1     1 NA NA          NULL
#> 2  2     1 NA NA          NULL
#> 3 NA    NA  3 NA          NULL
#> 4 NA    NA NA  4 0.3, 0.5, 0.2
#> 5 NA    NA NA  3 0.1, 0.5, 0.4

# Distribution-valued parameters (such as the inflated distribution
# below) are returned as-is by default.
infl_dist <- dist_inflated(dist_negative_binomial(10, 0.6), prob = 0.5)
parameters(infl_dist)
#>          dist x   p
#> 1 NB(10, 0.6) 0 0.5

# With recursive = TRUE, the inflated distribution's parameters are
# expanded into a flat data frame.
parameters(infl_dist, recursive = TRUE)
#>   dist.n dist.p x   p
#> 1     10    0.6 0 0.5