Description Usage Arguments Details Value Author(s) References See Also Examples
Summarizes and plots the estimate of the partition in a Bayesian cluster analysis model.
1 2 3 4 |
object |
an object of class |
x |
an object of class |
data |
the dataset contained in a |
dx |
for |
xgrid |
for |
dxgrid |
for |
... |
other inputs to |
Summarizes and plots the clustering estimates returned by the functions minVI
and minbinder.ext
. In plots, data points are colored according to cluster membership. For nrow(x)=1
, the data points are plotted against the density (which is estimated via a call to density
if not provided). For nrow(x)=2
the data points are plotted, and for nrow(x)>2
, the data points are plotted in the space spanned by the first two principal components.
method |
the optimization method used to obtain the point estimate. |
k |
(a vector of) the number of clusters in the point estimate. Returns a vector if |
n.c |
the number of point estimates in the object. |
t |
a list of length |
value |
(a vector of) the posterior expected loss. Returns a vector if |
Sara Wade, sara.wade@eng.cam.ac.uk
Wade, S. and Ghahramani, Z. (2015) Bayesian cluster analysis: Point estimation and credible balls. Submitted. arXiv:1505.03339.
minVI
and minbinder.ext
1 2 3 4 5 6 7 8 9 10 11 12 13 | data(galaxy.draw)
data(galaxy.fit)
data(galaxy.pred)
x=data.frame(x=galaxy.fit$x)
# Find representative partition of posterior
psm=comp.psm(galaxy.draw)
galaxy.VI=minVI(psm,galaxy.draw,method=("all"),include.greedy=TRUE)
summary(galaxy.VI)
plot(galaxy.VI,data=x,dx=galaxy.fit$fx,xgrid=galaxy.pred$x,dxgrid=galaxy.pred$fx)
galaxy.B=minbinder.ext(psm,galaxy.draw,method=("all"),include.greedy=TRUE)
summary(galaxy.B)
plot(galaxy.B,data=x,dx=galaxy.fit$fx,xgrid=galaxy.pred$x,dxgrid=galaxy.pred$fx)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.