SubClu: The SubClu Algorithm for Subspace Clustering

In subspace: Interface to OpenSubspace

Description

The SubClu Algorithm follows a bottom-up framework, in which one-dimensional clusters are generated with DBSCAN and then each cluster is expanded one dimension at a time into a dimension that is known to have a cluster that only differs in one dimension from this cluster. This expansion is done using DBSCAN with the same parameters that were used for the original DBSCAN that produced the clusters.

Usage

SubClu(data, epsilon = 4, minSupport = 4)

Arguments

data	A Matrix of input data.
epsilon	size of environment parameter for DBSCAN
minSupport	minimum number of points parameter for DBSCAN

References

Karin Kailing, Hans-Peter Kriegel and Peer Kröger Density-Connected Subspace Clustering for High-Dimensional Data

See Also

Other subspace.clustering.algorithms: CLIQUE; FIRES; P3C; ProClus

Examples

data("subspace_dataset")
SubClu(subspace_dataset,epsilon=1,minSupport=5)

Example output

OpenJDK 64-Bit Server VM warning: Can't detect initial thread stack location - find_vma failed
Subspace clustering generated by the package Subspace, containing 4 clusters.Warning message:
system call failed: Cannot allocate memory 

subspace documentation built on May 2, 2019, 11:11 a.m.