stream (version 1.3-0)

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, horizon = 100, n = 1000, wait = .1, plot.args = NULL, ...)
animate_cluster(dsc, dsd, measure = NULL, horizon = 100, n = 1000,
  type=c("auto", "micro", "macro"), assign="micro",
  assignmentMethod=c("auto","model", "nn"),
  noise = c("class", "exclude"),
  wait=.1, plot.args = NULL, ...)

Arguments

dsd

a DSD object

dsc

a DSC object

horizon

the number of points displayed at once/used for evaluation.

n

the number of points to be plotted

measure

the evaluation measure that should be graphed below the animation

type

evaluate "micro" or "macro"-clusters? "auto" chooses micro if dsc is of class DSC_micro and no macro is given. Otherwise macro is used.

assign

assign new points to the closest "micro" or "macro"-cluster to calculate the evaluation measure.

assignmentMethod

how to assign data points to micro-clusters. Options are "model" and "nn" (nearest neighbor). "auto" uses model if available and nn otherwise.

noise

how to handle noise for calculating the evaluation measure (as a separate class or excluded).

wait

the time interval between each frame

plot.args

a list with plotting parameters for the clusters.

...

extra arguments are added to plot.args.

Details

Animations are recorded using the library animation and can be replayed (which gives a smoother experience since the is no more computation done) and saved in various formats (see Examples section below).

See Also

evaluate_cluster for stream evaluation without animation. See ani.replay for replaying and saving animations.

Examples

# NOT RUN {
stream <- DSD_Benchmark(1)
animate_data(stream, horizon=100, n=5000, xlim=c(0,1), ylim=c(0,1))

### animations can be replayed with the animation package
library(animation)
animation::ani.options(interval=.1) ## change speed
ani.replay()

### animations can also be saved as HTML, animated gifs, etc.
saveHTML(ani.replay())

### animate the clustering process with evaluation
### Note: we choose to exclude noise points from the evaluation
###       measure calculation, even if the algorithm would assign
###       them to a cluster.
reset_stream(stream)
dbstream <- DSC_DBSTREAM(r=.04, lambda=.1, gaptime=100, Cm=3,
  shared_density=TRUE, alpha=.2)

animate_cluster(dbstream, stream, horizon=100, n=5000,
  measure="crand", type="macro", assign="micro", noise = "exclude",
  plot.args = list(xlim=c(0,1), ylim=c(0,1), shared = TRUE))
# }