stream (version 1.1-1)

get_assignment: Assignment Data Points to Clusters

Description

Get the assignment of data points to clusters in a DSC (nearest-neighbor).

Usage

get_assignment(dsc, points, type=c("auto", "micro", "macro"), 
  method="auto", ...)

Arguments

dsc

The DSC object with the clusters for assignment.

points

The points to be assigned as a data.frame.

type

Use micro- or macro-clusters in DSC for assignment. Auto used the class of dsc to decide.

method

assignment method "model" uses the assignment model of the underlying algorithm (unassigned points return NA). "nn" performs nearest neighbor assignment using Euclidean distance. "auto" uses model

...

Additional arguments are passed on.

Value

• A vector containing the assignment of each point. NA means that a data point was not assigned to a cluster.

Details

Each data point is assigned either using the original model's assignment rule or Euclidean nearest neighbor assignment.

See Also

DSC

Examples

stream <- DSD_Gaussians(k=3, d=2, noise=.05)

tnn <- DSC_tNN(r=.1, noise=.05)
update(tnn, stream, n=100)

# find the assignment for the next 100 points to 
# micro-clusters in dsc. This uses the model's assignemnt function
points <- get_points(stream, n=100)
a <- get_assignment(tnn, points)
a

# show the assigned points as blue circles and the unassigned points 
# as blue dots
plot(tnn, stream)
points(points[!is.na(a),], col="blue")
points(points[is.na(a),], col="blue", pch=20)

# use nearest neighbor assignment instead 
get_assignment(tnn, points, method="nn")