Metric DBSCAN

RESOURCE

Abstract

SAND2025-11725O Metric DBSCAN is an implementation of the popular DBSCAN clustering algorithm that works in general metric spaces. DBSCAN is a clustering algorithm, a fundamental building block in machine learning. It takes a set of objects and, given some notion of distance, identifies coherent groups of objects. With Metric DBSCAN, users can provide an arbitrary function to compute distance. Nearly all existing implementations of DBSCAN restrict distance to one of a few formulations. Metric DBScan accomplishes this cleanly and efficiently. The Python source code is on Github. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
Developers:
Dalbey, Keith [1][2][3] Whetzel, Jonathan [1][2][3] Wilson, Andrew [1][2][3] Gooding, Renee [1][2][3] Jones, Jessica [1][2][3] DeLayo, Daniel [1][2][3] Sharan, Nitin [1][2][3]
  1. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  3. Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
Release Date:
2024-04-05
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Programming Languages:
Python
Version:
1.0.0
Licenses:
BSD 3-clause "New" or "Revised" License
Sponsoring Org.:
Code ID:
167245
Site Accession Number:
SCR #3011.0
Research Org.:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Dalbey, Keith, Whetzel, Jonathan, Wilson, Andrew, Gooding, Renee, Jones, Jessica, DeLayo, Daniel, and Sharan, Nitin. Metric DBSCAN. Computer Software. https://github.com/sandialabs/metric_dbscan. USDOE. 05 Apr. 2024. Web. doi:10.11578/dc.20251016.17.
Dalbey, Keith, Whetzel, Jonathan, Wilson, Andrew, Gooding, Renee, Jones, Jessica, DeLayo, Daniel, & Sharan, Nitin. (2024, April 05). Metric DBSCAN. [Computer software]. https://github.com/sandialabs/metric_dbscan. https://doi.org/10.11578/dc.20251016.17.
Dalbey, Keith, Whetzel, Jonathan, Wilson, Andrew, Gooding, Renee, Jones, Jessica, DeLayo, Daniel, and Sharan, Nitin. "Metric DBSCAN." Computer software. April 05, 2024. https://github.com/sandialabs/metric_dbscan. https://doi.org/10.11578/dc.20251016.17.
@misc{ doecode_167245,
title = {Metric DBSCAN},
author = {Dalbey, Keith and Whetzel, Jonathan and Wilson, Andrew and Gooding, Renee and Jones, Jessica and DeLayo, Daniel and Sharan, Nitin},
abstractNote = {SAND2025-11725O Metric DBSCAN is an implementation of the popular DBSCAN clustering algorithm that works in general metric spaces. DBSCAN is a clustering algorithm, a fundamental building block in machine learning. It takes a set of objects and, given some notion of distance, identifies coherent groups of objects. With Metric DBSCAN, users can provide an arbitrary function to compute distance. Nearly all existing implementations of DBSCAN restrict distance to one of a few formulations. Metric DBScan accomplishes this cleanly and efficiently. The Python source code is on Github. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.},
doi = {10.11578/dc.20251016.17},
url = {https://doi.org/10.11578/dc.20251016.17},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20251016.17}},
year = {2024},
month = {apr}
}