Model-Based Clustering of Network Data

Description

Clustering unilayer and multilayer network data by means of finite mixtures is the main utility of netClust.

Details

The DESCRIPTION file:

Index of help topics:

netClust-package        Model-Based Clustering of Network Data
netData                 Dataset: netData
netDataID               Dataset: netDataID
netEM_multilayer        Returns the EM object for multilayer network
netEM_unilayer          Returns the EM object for unilayer network
rcpparma_hello_world    Set of functions in example RcppArmadillo
                        package

Provides model-based clustering for weighted networks. Core functions: netEM_unilayer() and netEM_multilayer().

Author(s)

NA

Maintainer: Shuchismita Sarkar <ssarkar@bgsu.edu>

References

Melnykov, V., Sarkar, S. and Melnykov, Y., 2021. On finite mixture modeling and model-based clustering of directed weighted multilayer networks. Pattern Recognition, 112, p.107641.

Examples

data(netData) ## Read network data 
data(netDataID) ## Read original ID for network data

n <- dim(netData)[1] ## number of nodes of the network
p <- dim(netData)[4] ## number of layers of the network
K <- 2               ## number of clusters 
y <- netData

eps=0.0001
RndStrtUni= 5
RndStrtMult= 10
SmEMUni= 3
SmEMMult= 5
ItrSmEM=5
burn = 10*n
ItrMCMC= 100*n
sSigma = 1
sPsi = 1
a=0



#########################################################
### Run unilayer network EM seperately for each layer ###
#########################################################

for (MatC in 1:p){
  
  x <- array(0, dim = c(n,n,2))
  for (i in 1:n){
    for (j in 1:n){
      x[i,j,] <- y[i,j,,MatC]
    }
  }
  
  E <- netEM_unilayer(x, K, eps, RndStrtUni, SmEMUni, ItrSmEM, burn, ItrMCMC, sSigma,a)
  cat("Unilayer network", "Original ID", netDataID, "\n")
  cat("Unilayer network", "Feature", MatC, "Assigned ID", E$id, "\n")
  
}

##################################
### Run multilayer network EM  ###
##################################

E <- netEM_multilayer(y,K,p, eps, RndStrtMult, SmEMMult, ItrSmEM, burn, ItrMCMC, sSigma, sPsi, n, a)
cat("Multilayer network", "Original ID", netDataID, "\n")
cat("Multilayer network", "Assigned ID", E$id, "\n")

Set of functions in example RcppArmadillo package

Description

These four functions are created when RcppArmadillo.package.skeleton() is invoked to create a skeleton packages.

Usage

rcpparma_hello_world()
rcpparma_outerproduct(x)
rcpparma_innerproduct(x)
rcpparma_bothproducts(x)

Arguments

Details

These are example functions which should be largely self-explanatory. Their main benefit is to demonstrate how to write a function using the Armadillo C++ classes, and to have to such a function accessible from R.

Value

rcpparma_hello_world() does not return a value, but displays a message to the console.

rcpparma_outerproduct() returns a numeric matrix computed as the outer (vector) product of x.

rcpparma_innerproduct() returns a double computer as the inner (vector) product of x.

rcpparma_bothproducts() returns a list with both the outer and inner products.

Author(s)

Dirk Eddelbuettel

References

See the documentation for Armadillo, and RcppArmadillo, for more details.

Examples

  x <- sqrt(1:4)
  rcpparma_innerproduct(x)
  rcpparma_outerproduct(x)

Dataset: netData

Description

Network data with 20 nodes and 2 layers

Usage

data("netData")

Format

The format is: num [1:20, 1:20, 1:2, 1:2] 0 0 0 0 0 0 0 0 0 0 ...

Details

Dataset demonstrating multilayer network

Source

Sarkar, S. (2020)

References

Sarkar, S. (2019) On the use of transformations for modeling multidimensional heterogeneous data, The University of Alabama Libraries Digital Collections

Examples

data(netData)
## maybe str(netData) ; plot(netData) ...

Dataset: netDataID

Description

ID for netData dataset

Usage

data("netDataID")

Format

A data frame with 30 observations on the following 1 variable.

netDataID

a numeric vector

Details

ID for the dataset demonstrating multilayer network

Source

Sarkar, S. (2020)

References

Sarkar, S. (2019) On the use of transformations for modeling multidimensional heterogeneous data, The University of Alabama Libraries Digital Collections

Examples

data(netDataID)
## maybe str(netDataID) ; plot(netDataID) ...

Returns the EM object for multilayer network

Description

Returns the EM object for multilayer network

Usage

netEM_multilayer(
  y,
  K,
  p,
  eps,
  num_rand_start,
  num_run_smallEM,
  max_itr_smallEM,
  burn,
  MCMC_itr,
  sigma_mult,
  psi_mult,
  n,
  alpha
)

Arguments

Value

EM object

Returns the EM object for unilayer network

Description

Returns the EM object for unilayer network

Usage

netEM_unilayer(
  x,
  K,
  eps,
  num_rand_start,
  num_run_smallEM,
  max_itr_smallEM,
  burn,
  MCMC_itr,
  sigma_mult,
  alpha
)

Arguments

Value

EM object