sc12L {T4cluster} | R Documentation |
Spectral Clustering by Li and Guo (2012)
Description
Li and Guo proposed to construct an affinity matrix
and adjust the matrix by neighbor propagation. Then, standard spectral clustering from the symmetric, normalized graph laplacian is applied.
Usage
sc12L(data, k = 2, sigma = 1, ...)
Arguments
data |
an |
k |
the number of clusters (default: 2). |
sigma |
common bandwidth parameter (default: 1). |
... |
extra parameters including
|
Value
a named list of S3 class T4cluster
containing
- cluster
a length-
vector of class labels (from
).
- eigval
eigenvalues of the graph laplacian's spectral decomposition.
- embeds
an
low-dimensional embedding.
- algorithm
name of the algorithm.
References
Li X, Guo L (2012). “Constructing Affinity Matrix in Spectral Clustering Based on Neighbor Propagation.” Neurocomputing, 97, 125–130. ISSN 09252312.
See Also
Examples
# -------------------------------------------------------------
# clustering with 'iris' dataset
# -------------------------------------------------------------
## PREPARE
data(iris)
X = as.matrix(iris[,1:4])
lab = as.integer(as.factor(iris[,5]))
## EMBEDDING WITH PCA
X2d = Rdimtools::do.pca(X, ndim=2)$Y
## CLUSTERING WITH DIFFERENT K VALUES
cl2 = sc12L(X, k=2)$cluster
cl3 = sc12L(X, k=3)$cluster
cl4 = sc12L(X, k=4)$cluster
## VISUALIZATION
opar <- par(no.readonly=TRUE)
par(mfrow=c(1,4), pty="s")
plot(X2d, col=lab, pch=19, main="true label")
plot(X2d, col=cl2, pch=19, main="sc12L: k=2")
plot(X2d, col=cl3, pch=19, main="sc12L: k=3")
plot(X2d, col=cl4, pch=19, main="sc12L: k=4")
par(opar)