DBSCAN density reachability and connectivity clustering

dbscan {clustering}

R Documentation

DBSCAN density reachability and connectivity clustering

Description

Generates a density based clustering of arbitrary shape as
introduced in Ester et al. (1996).

Clusters require a minimum no of points (MinPts) within a maximum
distance (eps) around one of its members (the seed). Any point
within eps around any point which satisfies the seed condition
is a cluster member (recursively). Some points may not belong to
any clusters (noise).

Usage

dbscan(data, eps,
    minPts = 5,
    scale = FALSE,
    method = raw,
    seeds = TRUE,
    countmode = NULL,
    filterNoise = FALSE,
    reorder.class = FALSE,
    densityCut = -1);

Arguments

data

data matrix, data.frame, dissimilarity matrix or dist-object. Specify method="dist" if the data should be interpreted as dissimilarity matrix or object. Otherwise Euclidean distances will be used.

eps

Reachability distance, see Ester et al. (1996). [as double]

minPts

Reachability minimum no. Of points, see Ester et al. (1996). [as integer]

scale

scale the data if TRUE. [as boolean]

method

"dist" treats data as distance matrix (relatively fast but memory expensive), "raw" treats data as raw data and avoids calculating a distance matrix (saves memory but may be slow), "hybrid" expects also raw data, but calculates partial distance matrices (very fast with moderate memory requirements). [as dbScanMethods]

seeds

FALSE to not include the isseed-vector in the dbscan-object. [as boolean]

countmode

NULL or vector of point numbers at which to report progress.

Authors

MLkit

Value

the result data is not keeps the same order as the data input!

clr value class

dbscanResult

[Package clustering version 1.0.0.0 Index]