Image plot of cluster segments overlaid by neighbourhood graph.
# S4 method for kcca
image(x, which = 1:2, npoints = 100,
xlab = "", ylab = "", fastcol = TRUE, col=NULL,
clwd=0, graph=TRUE, ...)
An object of class "kcca"
.
Index number of dimensions of input space to plot.
Number of grid points for image.
If TRUE
, a greedy algorithm is used for the
background colors of the segments, which may result in neighbouring
segments having the same color. If FALSE
, neighbouring
segments always have different colors at a speed penalty.
Vector of background colors for the segments.
Line width of contour lines at cluster boundaries, use
larger values for npoints
than the default to get smooth
lines. (Warning: We really need a smarter way to draw cluster
boundaries!)
Logical, add a neighborhood graph to the plot?
Graphical parameters.
This works only for "kcca"
objects, no method is available for
"kccasimple" objects.