stream - Infrastructure for Data Stream Mining - R package

A framework for data stream modeling and associated data mining tasks such as clustering and classification. The development of this package was supported in part by NSF IIS-0948893 and NIH R21HG005912.

Additional packages in the stream family are: streamMOA.

Installation

• Stable CRAN version: install from within R.
• Current development version: Download package from AppVeyor or install via install_git("mhahsler/stream") (needs devtools)

Example

R> library("stream")
R> stream <- DSD_Gaussians(k=3, noise=0)

# create micro-clusters via sampling
R> sample <- DSC_Sample(k=20)
R> update(sample, stream, 500)
R> sample
Reservoir sampling
Class: DSC_Sample, DSC_Micro, DSC_R, DSC 
Number of micro-clusters: 20 

# recluster micro-clusters
R> kmeans <- DSC_Kmeans(k=3)
R> recluster(kmeans, sample)
R> plot(kmeans, stream, type="both")

Further Information

• Development version of stream on github.
• stream package vignette with complete examples.
• stream reference manual

Maintainer: Michael Hahsler