Prune Clusters from a Clustering

Creates a (static) copy of a clustering where a fraction of the weight or the number of clusters with the lowest weights were pruned.

Usage

prune_clusters(dsc, threshold = 0.05, weight = TRUE)

Arguments

dsc

The DSC object to be pruned.

threshold

The numeric vector of probabilities for the quantile.

weight

should a fraction of the total weight in the clustering be pruned? Otherwise a fraction of clusters is pruned.

Value

Returns an object of class DSC_Static.

See also

DSC_Static

Other DSC: DSC(), DSC_Macro(), DSC_Micro(), DSC_R(), DSC_SlidingWindow(), DSC_Static(), DSC_TwoStage(), animate_cluster(), evaluate.DSC, get_assignment(), plot.DSC(), predict, read_saveDSC, recluster()

Author

Michael Hahsler

Examples

# 3 clusters with 10% noise
stream <- DSD_Gaussians(k=3, noise=0.1)

dbstream <- DSC_DBSTREAM(r=0.1)
update(dbstream, stream, 500)
dbstream
#> DBSTREAM 
#> Class: DSC_DBSTREAM, DSC_Micro, DSC_R, DSC 
#> Number of micro-clusters: 13 
#> Number of macro-clusters: 3 
plot(dbstream, stream)


# prune lightest micro-clusters for 20% of the weight of the clustering
static <- prune_clusters(dbstream, threshold=0.2)
static
#> Static clustering 
#> Class: DSC_Static, DSC_Micro, DSC_R, DSC 
#> Number of micro-clusters: 6 
plot(static, stream)