Team-RADDISH / ParticleDA.jl

https://team-raddish.github.io/ParticleDA.jl/dev/
MIT License
15 stars 5 forks source link

Add linear Gaussian model type + validation notebook #237

Closed matt-graham closed 1 year ago

matt-graham commented 1 year ago

Adds wrapper type for linear Gaussian models in which filtering can be performed using both Kalman filter (exact) and particle filters (approximate), for the purposes of validating the particle filter implementations. A Pluto notebook validating that the particle filter estimates of the mean and variance parameters of the filtering distributions asymptotically converge to their true values as the ensemble size tends to infinity is also added.

codecov-commenter commented 1 year ago

Codecov Report

Merging #237 (5d5b096) into master (9b39f66) will increase coverage by 0.04%. The diff coverage is n/a.

:mega: This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more

@@            Coverage Diff             @@
##           master     #237      +/-   ##
==========================================
+ Coverage   91.17%   91.22%   +0.04%     
==========================================
  Files           7        7              
  Lines         374      376       +2     
==========================================
+ Hits          341      343       +2     
  Misses         33       33              
Impacted Files Coverage Δ
src/ParticleDA.jl 89.24% <0.00%> (+0.11%) :arrow_up:
src/params.jl 85.71% <0.00%> (+2.38%) :arrow_up:

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

giordano commented 1 year ago

What version of MPI.jl do you have in the active environment?

]st -m MPI

After #235 you'll need to do

]resolve
up

in the Pkg REPL to re-resolve and update the environmemt.

DanGiles commented 1 year ago

Yes, that would do it. Thanks Mose. My misunderstanding of how the Project.toml files work. Happy to merge this now @matt-graham, thanks for the updates.