scikit-learn / scikit-learn/scikit-learn
Request to update "Choosing the Right Estimator" Graphic (scikit-learn algorithm cheat sheet)
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 67.3k
- Forks
- 27.4k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 58
Description
Describe the issue linked to the documentation
As seen here:
https://scikit-learn.org/stable/tutorial/machine_learning_map/index.html
One of the "tough luck" paths that go through the clustering section appear to say this is the case when there are >10k samples.
Suggest a potential alternative/fix
However, with modern computational hardware, and the optimized implementation of DBSCAN in Scikit-learn, it appears that it may be helpful to recommend DBSCAN as a possible solution for datasets containing <100K or even <1M datapoints for clustering in reasonable amounts of time on CPU.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the Choosing the Right Estimator graphic at the linked scikit-learn tutorial page and inspect the clustering paths around the >10k-sample recommendation. Research whether DBSCAN is practical below 100K or 1M samples on CPU, then update the graphic only if the evidence supports a revised recommendation and the scope is agreed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100