Example data | k nearest neighbors | Reuse and reduce a search | Query new points | Fixed-radius nearest neighbors | Reduce a stored radius | Shared nearest neighbors | Neighbor-distance diagnostics | Connected components | Sorting results | Using non-Euclidean distances | Search strategies and performance | Important details | Reference
Package: dbscan 1.2.8
dbscan: Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Related Algorithms
A fast reimplementation of several density-based algorithms of the DBSCAN family. Includes the clustering algorithms DBSCAN (density-based spatial clustering of applications with noise) and HDBSCAN (hierarchical DBSCAN), the ordering algorithm OPTICS (ordering points to identify the clustering structure), shared nearest neighbor clustering, and the outlier detection algorithms LOF (local outlier factor) and GLOSH (global-local outlier score from hierarchies). The implementations use the kd-tree data structure (from library ANN) for faster k-nearest neighbor search. An R interface to fast kNN and fixed-radius NN search is also provided. Hahsler, Piekenbrock and Doran (2019) <doi:10.18637/jss.v091.i01>.
Authors:
dbscan_1.2.8.tar.gz
dbscan_1.2.8.zip(r-4.7-x86_64)dbscan_1.2.8.zip(r-4.7-arm64)dbscan_1.2.8.zip(r-4.6-x86_64)dbscan_1.2.8.zip(r-4.6-arm64)dbscan_1.2.8.zip(r-4.5-x86_64)
dbscan_1.2.8.tgz(r-4.6-x86_64)dbscan_1.2.8.tgz(r-4.6-arm64)dbscan_1.2.8.tgz(r-4.5-x86_64)dbscan_1.2.8.tgz(r-4.5-arm64)
dbscan_1.2.8.tar.gz(r-4.7-arm64)dbscan_1.2.8.tar.gz(r-4.7-x86_64)dbscan_1.2.8.tar.gz(r-4.6-arm64)dbscan_1.2.8.tar.gz(r-4.6-x86_64)
dbscan_1.2.8.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
dbscan/json (API)
| # Install 'dbscan' in R: |
| install.packages('dbscan', repos = c('https://mhahsler.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/mhahsler/dbscan/issues
Pkgdown/docs site:https://michael.hahsler.net
Datasets:
clusteringdbscandensity-based-clusteringhdbscanlofopticscpp
Last updated from:b4acdee7e2. Checks:15 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel-arm64 | OK | 172 | ||
| linux-devel-x86_64 | OK | 227 | ||
| source / vignettes | OK | 547 | ||
| linux-release-arm64 | OK | 168 | ||
| linux-release-x86_64 | OK | 193 | ||
| macos-release-arm64 | OK | 297 | ||
| macos-release-x86_64 | OK | 574 | ||
| macos-oldrel-arm64 | OK | 116 | ||
| macos-oldrel-x86_64 | OK | 392 | ||
| windows-devel-arm64 | OK | 312 | ||
| windows-devel-x86_64 | OK | 249 | ||
| windows-release-arm64 | OK | 327 | ||
| windows-release-x86_64 | OK | 207 | ||
| windows-oldrel-x86_64 | OK | 189 | ||
| wasm-release | OK | 134 |
Exports:adjacencylistas.dendrogramas.reachabilityaugmentclplotcompscoredistdbcvdbscanextractDBSCANextractFOSCextractXifrNNglancegloshhdbscanhullplotis.corepointjpclustkNNkNNdistkNNdistplotlofmrdistnclusternnoiseopticspointdensitysNNsNNclusttidy
Nearest-Neighbor Search and Graphs
Last update: 2026-09-27
Started: 2026-09-27
Using Hierarchical DBSCAN (HDBSCAN)
Hierarchical DBSCAN | DBSCAN* vs cutting the HDBSCAN* tree | Simplified Tree | Cluster Stability Scores | Global-Local Outlier Score from Hierarchies | A Larger Clustering Example | Performance | References
Last update: 2026-09-27
Started: 2017-03-17
Outlier Detection with dbscan
Example data | Low point density | Local Outlier Factor (LOF) | GLOSH and HDBSCAN | Turning scores into candidates | DBSCAN noise is not an outlier score | Practical workflow | References
Last update: 2026-09-27
Started: 2026-09-27
Nearest-Neighbor Clustering with jpclust and sNNclust
Shared nearest neighbors | Example data | Jarvis--Patrick clustering | Shared nearest neighbor clustering | Reuse a nearest-neighbor search | Inspect the shared-neighbor graph | Use a precomputed distance matrix | Which method should you use? | References
Last update: 2026-09-27
Started: 2026-09-27
Ordering Points With OPTICS
Create an OPTICS ordering | Read the reachability plot | Choose minPts and eps | Extract a DBSCAN-like clustering | Extract clusters with the Xi method | Convert the ordering to a dendrogram | Predict labels for new observations | Use another distance measure | References
Last update: 2026-09-27
Started: 2026-09-27
Fast Density-based Clustering (DBSCAN and OPTICS)
Preamble | Introduction | Density-based clustering | The dbscan package | Performance Comparison | Concluding Remarks | Acknowledgments | Technical Note on OPTICS cluster extraction
Last update: 2026-09-27
Started: 2026-09-26
Getting started with dbscan
Installation | A first clustering | Prepare your own data | Choose minPts and eps | Assign new observations | When DBSCAN is not the best starting point | Next steps
Last update: 2026-09-26
Started: 2026-09-26
Using dbscan from Python
Last update: 2026-09-26
Started: 2026-09-26
Using dbscan with tidyverse
Last update: 2026-09-26
Started: 2026-09-26
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Find Connected Components in a Nearest-neighbor Graph | components comps comps.dist comps.frNN comps.kNN comps.sNN |
| Density-Based Clustering Validation Index (DBCV) | DBCV dbcv |
| DBCV Paper Datasets | Dataset_1 Dataset_2 Dataset_3 Dataset_4 DBCV_datasets |
| Density-based Spatial Clustering of Applications with Noise (DBSCAN) | DBSCAN dbscan is.corepoint predict.dbscan_fast print.dbscan_fast |
| Turn an dbscan clustering object into a tidy tibble | augment augment.dbscan augment.general_clustering augment.hdbscan dbscan_tidiers glance glance.dbscan glance.general_clustering glance.hdbscan tidy tidy.dbscan tidy.general_clustering tidy.hdbscan |
| Coercions to Dendrogram | as.dendrogram as.dendrogram.default as.dendrogram.hclust as.dendrogram.hdbscan as.dendrogram.reachability dendrogram |
| DS3: Spatial data with arbitrary shapes | DS3 |
| Framework for the Optimal Extraction of Clusters from Hierarchies | extractFOSC |
| Find the Fixed Radius Nearest Neighbors | adjacencylist.frNN frNN frnn print.frNN print.frnn sort.frNN |
| Global-Local Outlier Score from Hierarchies | GLOSH glosh |
| Hierarchical DBSCAN (HDBSCAN) | coredist HDBSCAN hdbscan mrdist plot.hdbscan predict.hdbscan print.hdbscan |
| Plot Clusters | clplot hullplot |
| Jarvis-Patrick Clustering | jpclust print.general_clustering |
| Find the k Nearest Neighbors | adjacencylist.kNN kNN knn print.kNN sort.kNN |
| Calculate and Plot k-Nearest Neighbor Distances | kNNdist kNNdistplot |
| Local Outlier Factor Score | LOF lof |
| Moons Data | moons |
| Number of Clusters, Noise Points, and Observations | ncluster nnoise nobs |
| NN - Nearest Neighbors Superclass | adjacencylist adjacencylist.NN NN plot.NN sort.NN |
| Ordering Points to Identify the Clustering Structure (OPTICS) | as.dendrogram.optics as.reachability.optics extractDBSCAN extractXi OPTICS optics plot.optics predict.optics print.optics |
| Calculate Local Density at Each Data Point | density pointdensity |
| Reachability Distances | as.reachability as.reachability.dendrogram plot.reachability print.reachability reachability reachability_plot |
| Find Shared Nearest Neighbors | print.sNN sNN snn sort.sNN |
| Shared Nearest Neighbor Clustering | sNNclust snnclust |