miguelgfierro
commented
1 year ago - [x] Consider adding comments in the markdown of https://github.com/Music-Recommendation-Engine-Project/Music-Recommendation-Engine/blob/main/ETL_users_songs.ipynb
- [x] Same with the algo notebooks
- [x] Create libraries following https://github.com/miguelgfierro/project_template
- [ ] Create a MLOps solution with test and GitHub actions https://github.com/miguelgfierro/project_template
- [ ] Consider ANNOY https://github.com/spotify/annoy or others
- [x] Precision and recall shouldn't be a class, it should be a function
- [ ] Consider using the metrics in Recommenders or Scikit learn
- [x] Update the release with comments like https://github.com/microsoft/recommenders/releases/tag/1.1.1
- [ ] Try to use ranking metrics: nDCG, precision@k, etc.
- [x] Work with smaller PRs. See https://github.com/Music-Recommendation-Engine-Project/Music-Recommendation-Engine/pull/2#pullrequestreview-1338803556
- [x] The tag is typically a number, not a string https://github.com/Music-Recommendation-Engine-Project/Music-Recommendation-Engine/tree/Reco. Here an example: https://pypi.org/project/lightgbm/#history In this tutorial you can see how to rename a tag https://github.com/miguelgfierro/codebase/wiki/Git-tutorial