search

JuliaAI / MLJLinearModels.jl

Generalized Linear Regressions Models (penalized regressions, robust regressions, ...)
MIT License
80 stars 13 forks source link

proper level checks #73

Closed tlienart closed 4 years ago

tlienart commented 4 years ago

Cleaner solution to https://github.com/alan-turing-institute/MLJ.jl/issues/540

xRef: https://github.com/alan-turing-institute/MLJ.jl/issues/540

Not gonna lie, this was a PITA; but at least now levels passed down by MLJ are preserved even if there's no example for a given class.

codecov-commenter commented 4 years ago

Codecov Report

Merging #73 into master will decrease coverage by 0.05%. The diff coverage is 98.61%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master      #73      +/-   ##
==========================================
- Coverage   95.69%   95.64%   -0.06%     
==========================================
  Files          21       21              
  Lines         790      803      +13     
==========================================
+ Hits          756      768      +12     
- Misses         34       35       +1
Impacted Files Coverage Δ
src/mlj/classifiers.jl 100.00% <ø> (ø)
src/mlj/interface.jl 87.71% <94.11%> (-1.57%) :arrow_down:
src/fit/analytical.jl 100.00% <100.00%> (ø)
src/fit/default.jl 83.33% <100.00%> (+0.98%) :arrow_up:
src/fit/iwls.jl 100.00% <100.00%> (ø)
src/fit/newton.jl 100.00% <100.00%> (ø)
src/fit/proxgrad.jl 95.00% <100.00%> (ø)
src/glr/constructors.jl 100.00% <100.00%> (ø)
src/glr/d_logistic.jl 100.00% <100.00%> (ø)
src/glr/utils.jl 90.90% <100.00%> (ø)
... and 3 more

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 4ce79b5...cc660e8. Read the comment docs.