QB3 / sparse-ho

Fast hyperparameter settings for non-smooth estimators:
http://qb3.github.io/sparse-ho
BSD 3-Clause "New" or "Revised" License
38 stars 15 forks source link

Write and test docstrings for models #111

Closed mathurinm closed 3 years ago

mathurinm commented 3 years ago

After writing this I think Lasso, ElasticNet, WeightedLasso and Logistic regression could inherit from a common class. This would make a lot of code less duplicated.

I think it allowed me to catch a few bugs. I have written lots of TODO.

closes #110

codecov-io commented 3 years ago

Codecov Report

Merging #111 (0decd91) into master (95c2647) will increase coverage by 0.95%. The diff coverage is 74.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #111      +/-   ##
==========================================
+ Coverage   78.07%   79.03%   +0.95%     
==========================================
  Files          41       41              
  Lines        3070     3034      -36     
  Branches      336      325      -11     
==========================================
+ Hits         2397     2398       +1     
+ Misses        577      544      -33     
+ Partials       96       92       -4     
Flag Coverage Δ
unittests ∅ <ø> (∅)

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
sparse_ho/tests/test_docstring_parameters.py 75.53% <ø> (+2.87%) :arrow_up:
sparse_ho/models/logreg.py 86.66% <33.33%> (+3.03%) :arrow_up:
sparse_ho/models/wlasso.py 85.87% <50.00%> (+1.89%) :arrow_up:
sparse_ho/models/enet.py 88.99% <60.00%> (+4.76%) :arrow_up:
sparse_ho/models/svm.py 70.85% <66.66%> (+0.13%) :arrow_up:
sparse_ho/models/svr.py 80.24% <92.85%> (+0.07%) :arrow_up:
sparse_ho/algo/forward.py 66.66% <100.00%> (ø)
sparse_ho/algo/implicit_forward.py 89.36% <100.00%> (-0.23%) :arrow_down:
sparse_ho/models/lasso.py 85.14% <100.00%> (+3.54%) :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 95c2647...0decd91. Read the comment docs.

mathurinm commented 3 years ago

@Klopfe as per @QB3 the remaining todos concern functions written mostly for SVM and SVR that you know better, so we leave it for another PR when you have time