-
Notifications
You must be signed in to change notification settings - Fork 3
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
Issue 266: Fix kernel bug #267
Conversation
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #267 +/- ##
==========================================
+ Coverage 93.34% 93.40% +0.05%
==========================================
Files 45 45
Lines 451 455 +4
==========================================
+ Hits 421 425 +4
Misses 30 30 ☔ View full report in Codecov by Sentry. |
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.
This seems to work... I'm a bit uncomfortable that of you generate data e.g. y_t = missing
then you have to pre-pend something like fill(missing, length(obs.pmf))
to then infer parameters.
But I think this kind of clunkiness is being improved by other PRs/issues.
Yes, in #268 hopefully (and if not does seem like its own issue beyond the bug fix) |
* add partial option * reverse partial if gate * add a test for new partial functionality * simplify LatentDelay * simplify LatentDelay --------- Co-authored-by: Samuel Brand <[email protected]>
Closes #226 but adding a
partial = false
option to the observation kernel generating funciton, adds tests for this, and uses this inLatentDelay
method.Still not loving how this shifts complexity into the error model here. Holding this though as thinking about making a abstract type for observation error models where this could be offloaded and if we have that then this would seem to be less of a problem.