nubank / fklearn

fklearn: Functional Machine Learning
Apache License 2.0
1.51k stars 164 forks source link

Including LGBM parameters to lgbm_classification_learner #211

Closed nicolas-behar closed 1 year ago

nicolas-behar commented 2 years ago

Status

IN DEVELOPMENT

Todo list

Background context

Some of the already implemented LGBM parameters can't be used by the lgbm_classification_learner function.

Description of the changes proposed in the pull request

We are including these parameters by changing the lgbm.train call function with these parameters, that can be passed by the user if needed.

Related PRs

https://github.com/nubank/fklearn/pull/197

codecov-commenter commented 2 years ago

Codecov Report

Merging #211 (4e5837e) into master (3cd7bec) will decrease coverage by 0.35%. The diff coverage is 93.19%.

@@            Coverage Diff             @@
##           master     #211      +/-   ##
==========================================
- Coverage   94.69%   94.33%   -0.36%     
==========================================
  Files          25       34       +9     
  Lines        1507     2120     +613     
  Branches      203      280      +77     
==========================================
+ Hits         1427     2000     +573     
- Misses         48       83      +35     
- Partials       32       37       +5     
Impacted Files Coverage Δ
src/fklearn/causal/validation/cate.py 0.00% <0.00%> (ø)
src/fklearn/data/datasets.py 100.00% <ø> (ø)
src/fklearn/tuning/parameter_tuners.py 79.48% <ø> (ø)
src/fklearn/tuning/selectors.py 90.47% <ø> (ø)
src/fklearn/validation/validator.py 91.20% <88.88%> (-3.08%) :arrow_down:
src/fklearn/preprocessing/splitting.py 95.00% <92.59%> (-0.84%) :arrow_down:
src/fklearn/causal/cate_learning/meta_learners.py 93.02% <93.02%> (ø)
src/fklearn/training/calibration.py 96.36% <94.73%> (-3.64%) :arrow_down:
src/fklearn/training/transformation.py 93.95% <95.12%> (+0.02%) :arrow_up:
src/fklearn/validation/evaluators.py 93.95% <96.29%> (+4.32%) :arrow_up:
... and 19 more

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