-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Bones #43
Bones #43
Conversation
@@ -16,7 +16,7 @@ def _load(self, path:str) -> None: | |||
posterior = pickle.load(file) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@beckynevin is the posterior the only object we'll do any diagnostics on? If we wanted to expand to include the likelihood (e.g., SNLE) in a beta version, do you know if that would require significant structural changes?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What would using the likelihood require? Would it require running the MCMC chain to get to the posterior? Or are you talking about evaluating the likelihood itself? Both would require significant structural changes; the former would require the package to handle MCMCing while the later I think would require redesigning the metrics.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I was thinking if people wanted to stop at the Likelihood and not go to the Posterior.
I don't think we've talked about metrics/diagnostics for that, but I wasn't sure if you had any schemes going in that direction.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'm not advocating for adding more tools to get a posterior from the likelihood.
Major rewrite