Skip to content
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.

Sign up for GitHub

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

Jump to bottom

refactoring to handle (very) degenerate beliefs #15

Open
wants to merge 71 commits into
base: main
Choose a base branch
from
Open

refactoring to handle (very) degenerate beliefs #15

wants to merge 71 commits into from

Conversation

cecileane
Copy link
Member

  • not complete: more work needed
  • used for a simulation study that did not have degenerate factors

bstkj and others added 30 commits May 18, 2024 16:43
@bstkj
generalized beliefs: start
ea8411f
@bstkj
generalized beliefs: marginalization + tests
c5052a6
@bstkj
integratebelief! for generalizedBelief
a460691
@bstkj
propagate_belief! for generalizedBelief
6551af2
@cecileane
adhere to code style blue; new abstract type
22089da
@cecileane
Belief → CanonicalBelief
e162701
@bstkj
Fix div!
39dad1b
@bstkj
Fix mult!
9405101
@bstkj
Use svd instead of qr in marg!
2c6e86d
@bstkj
Edits to extend!
6a51789
@bstkj
propagate_belief! between generalized and canonical beliefs
cc22e5a
@bstkj
refactor init_beliefs_allocate, init_beliefs_assignfactors start
97d4503
@bstkj
refactor init_beliefs_allocate, init_beliefs_assignfactors: cont
1bd5c6f
@bstkj
Merge remote-tracking branch 'origin' into degenerate_factor
e173f53
@bstkj
small edits
5fa404e
@bstkj
Small edits
fe3bddf
@bstkj
allocate mix of generalized and canonical beliefs
e055e8c
@bstkj
Note on marginalizing out variables with no data below
4573c89
@bstkj
assign mix of degen and non-degen factors: start
204f7c9
@bstkj
clique tree calibration w/ non-det and det factors
678d330
@bstkj
move degenerate.jl into beliefs.jl and beliefupdates.jl
faedb90
@bstkj
tidy up beliefupdates.jl
6a8be4f
@bstkj
update score.jl
5f56829
@bstkj
AbstractFactorBelief -> AbstractFactor
dc5d9da
@bstkj
proper test suite for generalized beliefs: start
1329008
@bstkj
Add network for generalized beliefs tests
ffb80ff
@bstkj
Adjust other tests: start
6556251
@bstkj
Adjust other tests: continue
2f0f7b3
@bstkj
Bug fix. All tests pass
62ed7ed
@bstkj
small edits
4888d7b
bstkj and others added 26 commits October 1, 2024 20:16
@bstkj
allow mult regularization options for optimization
99b60e8
@bstkj
counterexample to marginalize nodata variables from factor
50eb0d9
@bstkj
generalized belief, multivariate BM: add test
e758170
@bstkj
genbelief, MvFullBM: add test
dd6cbd6
@bstkj
Break cluster2fams into simpler components
21a52e9
@cecileane
docstring expanded, and questions
66e8120
@bstkj
example: degenerate extended family
1412660
@cecileane
check for no missing intermediate node: start
9971bb5
@bstkj
Fix bug in extend, gen belief MvBM tests pass
3ba6cb2
@bstkj
use node2fixed in allocatebeliefs
5f0f06a
@bstkj
clean up allocatebeliefs
01d5be0
@bstkj
clean up beliefs, beliefupdates
f85124c
@cecileane
check for no missing intermediate node: cont
94eb1ee
@bstkj
Store Q, R params in same matrix
f8f6bc1
@bstkj
debug marginalize noninscope variables in factor: start
4954636
@cecileane
no missing intermediate node check: test started
1ab8509
@cecileane
no missing intermediate node check: done
d2fa8b9
@bstkj
marginalize noninscope variables in factor: add test
0a16f3c
@bstkj
LKJ trans for MvFullBM optimization
8358229
@bstkj
LKJ trans debug
b209234
@bstkj
log-cholesky param for variance-rate
7660634
@bstkj
Hack to adjust optimization stepsize
b97b165
@bstkj
reduce StaticArrays for homogeneousBM, beliefs
d2f242c
@bstkj
terminate calibration early: start
c9f6bf1
@bstkj
Handle non-positive variance exception in optimize
dccbae9
@bstkj
adjust calibration threshold
bf4fba5
@cecileane cecileane requested a review from bstkj March 5, 2025 14:57
@codecov Codecov
Copy link

codecov bot commented Mar 6, 2025 •
edited
Loading

Codecov Report

Attention: Patch coverage is 86.45066% with 92 lines in your changes missing coverage. Please review.

Files with missing lines Patch % Lines
src/evomodels/homogeneousbrownianmotion.jl 61.72% 31 Missing ⚠️
src/beliefs.jl 89.28% 21 Missing ⚠️
src/calibration.jl 63.46% 19 Missing ⚠️
src/score.jl 33.33% 14 Missing ⚠️
src/beliefupdates.jl 97.98% 6 Missing ⚠️
src/utils.jl 96.29% 1 Missing ⚠️
Files with missing lines Coverage Δ
src/clustergraphbeliefs.jl 87.78% <100.00%> (ø)
src/evomodels/evomodels.jl 68.91% <100.00%> (ø)
src/utils.jl 97.67% <96.29%> (-0.64%) ⬇️
src/beliefupdates.jl 96.84% <97.98%> (+3.99%) ⬆️
src/score.jl 74.13% <33.33%> (-15.45%) ⬇️
src/calibration.jl 90.20% <63.46%> (-7.45%) ⬇️
src/beliefs.jl 91.98% <89.28%> (+3.02%) ⬆️
src/evomodels/homogeneousbrownianmotion.jl 76.12% <61.72%> (-18.83%) ⬇️

... and 2 files with indirect coverage changes

🚀 New features to boost your workflow:
  • ❄ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bstkj bstkj Awaiting requested review from bstkj

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@cecileane @bstkj