Closed khosravipasha closed 3 years ago
Few changes that might want to do:
fully_factorized_circuit
which might have more than a few variables, leads to having Mult nodes with many children, might want to replace with equivalent fully factorized but only with 2 children per Mult node.Merging #92 (17e63c4) into master (8b45db2) will decrease coverage by
0.82%
. The diff coverage is97.56%
.
@@ Coverage Diff @@
## master #92 +/- ##
==========================================
- Coverage 70.31% 69.49% -0.83%
==========================================
Files 38 38
Lines 2850 2993 +143
==========================================
+ Hits 2004 2080 +76
- Misses 846 913 +67
Impacted Files | Coverage Δ | |
---|---|---|
src/ProbabilisticCircuits.jl | 100.00% <ø> (ø) |
|
src/structurelearner/rat_spn.jl | 97.40% <97.40%> (ø) |
|
src/plain_prob_nodes.jl | 100.00% <100.00%> (ø) |
|
src/gradient_based_learning.jl | 45.40% <0.00%> (-16.81%) |
:arrow_down: |
src/queries/marginal_flow.jl | 53.15% <0.00%> (-3.59%) |
:arrow_down: |
src/queries/sample.jl | 45.45% <0.00%> (-0.55%) |
:arrow_down: |
src/Utils/Utils.jl | ||
src/Utils/misc.jl | 41.33% <0.00%> (+0.54%) |
:arrow_up: |
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact)
,ø = not affected
,? = missing data
Powered by Codecov. Last update 8b45db2...17e63c4. Read the comment docs.
Allows to make RAT-spn structures in Juice