Open m-d-grunnill opened 4 days ago
Good point, this isn't something that can be achieved with the current lhs_prcc()
function. Hmm. One option would be to allow the parameters_df
argument to take one of two forms:
ppf()
functions that transform the uniform samples into any desired distribution.Having a quick look through lhs_and_prcc.py
, I think this could be achieved with relatively few modifications to the code — I've written a proof-of-concept as a PR if you're interested. Feel free to accept, reject, rewrite :smile:
Currently the lhs_prcc function only supports sampling from the uniform distribution.
In a previous issue @robmoss mentioned his package lhs. This package may provide features for overcoming this issue.