Crandore Hub

discoCVI

Implementation of the DISCO Metric for Internal Clustering Evaluation

Implementation of the DISCO (Density-based Internal Score for Clusterings with nOise) metric, a cluster validity index for evaluating density-based clustering results without ground truth labels. DISCO is the first index to explicitly assess the quality of noise point assignments in addition to cluster quality. It uses density-connectivity distance derived from a minimum spanning tree of the mutual-reachability graph, providing interpretable, bounded scores in [-1, 1]. Higher scores indicate better clustering. Based on Beer et al. (2025) <doi:10.48550/arXiv.2503.00127>.

Versions across snapshots

VersionRepositoryFileSize
0.1.1 rolling linux/jammy R-4.5 discoCVI_0.1.1.tar.gz 107.8 KiB
0.1.1 rolling linux/noble R-4.5 discoCVI_0.1.1.tar.gz 107.7 KiB
0.1.1 rolling source/ R- discoCVI_0.1.1.tar.gz 70.6 KiB
0.1.1 latest linux/jammy R-4.5 discoCVI_0.1.1.tar.gz 107.8 KiB
0.1.1 latest linux/noble R-4.5 discoCVI_0.1.1.tar.gz 107.7 KiB
0.1.1 latest source/ R- discoCVI_0.1.1.tar.gz 70.6 KiB
0.1.1 2026-04-23 source/ R- discoCVI_0.1.1.tar.gz 0 B

Dependencies (latest)

Imports

Suggests