hugo-strang/silhouette-upper-bound

An upper bound of the Average Silhouette Width.

47
/ 100
Emerging

This project helps data scientists, researchers, or analysts evaluate the quality of their clustering results more accurately. It takes a dissimilarity matrix, which describes how different data points are, and provides a data-dependent upper bound for the Average Silhouette Width (ASW) score. This output allows you to understand how close your specific clustering solution is to the best possible outcome for your data.

Available on PyPI.

Use this if you need to objectively assess the performance of your clustering algorithms and want to know the maximum ASW score realistically achievable for your dataset.

Not ideal if you are looking for a tool to perform the clustering itself, as this project focuses solely on evaluating existing clusterings.

cluster-analysis data-evaluation machine-learning-metrics unsupervised-learning
Maintenance 10 / 25
Adoption 4 / 25
Maturity 24 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 02, 2026

Commits (30d)

0

Dependencies

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hugo-strang/silhouette-upper-bound"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.