stream (version 0.1-1)

animation: Animates the plotting of a DSD and the clustering process

Description

Generates an animation of a data stream or a data steam clustering.

Usage

animate_data(dsd, n=1000, interval=.1, 
    pointInterval=100, horizon=5*pointInterval, 
    outdir=NULL,...)
animate_cluster(dsc, dsd, macro=NULL, n=1000, interval=.1, 
    pointInterval=100, horizon=5*pointInterval, 
    evaluationMethod=NULL, outdir=NULL,...)

Arguments

dsd

a DSD object

dsc

a DSC object

macro

a DSC_macro object used for reclustering when performing evaluations.

n

the number of points to be plotted

interval

the time interval between each frame

pointInterval

the number of new points needed before a new frame is created

horizon

the max number of data points to be shown at a time

evaluationMethod

the evaluation method that should be graphed below the animation

outdir

the location of where the animation (animated gif) should be saved

...

extra arguments for plot.

Details

It generates several plots and strings them together to form an animation. This is particularly useful to see the behavior of moving data sets. If no outdir is specified the function will animate the progress while clustering.

See Also

evaluate_cluster for stream evaluation without animation.

Examples

dsd <- DSD_GaussianMoving()
animate_data(dsd, 500,  xlim=c(-.2,1.2), ylim=c(-.2,1.2), 
    pointInterval=20)

reset_stream(dsd)
dsc <- DSC_tNN(.1, alpha=.2, lambda=.03, decay_interval=1, minweight=.1)

### Note: type is a parameter passed on to plot (for DSC)
reset_stream(dsd)
animate_cluster(dsc, dsd, n=500, interval=.01,
       pointInterval=10, xlim=c(-.5,1.5),ylim=c(-.5,1.5), 
       type="macro")

reset_stream(dsd)
animate_cluster(dsc, dsd, n=600, interval=.01,
       pointInterval=20, xlim=c(-.5,1.5),ylim=c(-.5,1.5), 
       type="macro", eval="crand")