Learn R Programming

mimiSBM

A mixture of multilayer Stochastic Block Models (SBM) to group co-membership matrices with similar information into components and to partition observations into different clusters.

Installation

This package can be installed from GitHub with :

# install.packages("remotes")
remotes::install_github("Kdesantiago/mimiSBM")

Copy Link

Version

Install

install.packages('mimiSBM')

Monthly Downloads

149

Version

0.0.1.3

License

GPL-3

Maintainer

Kylliann De Santiago

Last Published

January 9th, 2024

Functions in mimiSBM (0.0.1.3)

fit_SBM_per_layer

SBM on each layer
Mat_lien_alpha

Create probality-component list for clustering per view component.
fit_SBM_per_layer_parallel

SBM on each layer - parallelized
Loss_BayesianMSBM

mimiSBM Evidence Lower BOund
CEM

Clustering Matrix : One hot encoding
initialisation_params_bayesian

Initialization of mimiSBM parameters
VBEM_step

Variational Bayes Expectation Maximization
diag_nulle

Diagonal coefficient to 0 on each slice given the 3rd dimension.
log_Softmax

log softmax of matrices (by row)
lab_switching

Label Switching
BayesianMixture_SBM_model

mimiSBM model for fixed K and Q
sort_Z

Sort the clustering matrix
transpo

Transposition of an array
mimiSBM

Mixture of Multilayer Integrator SBM (mimiSBM)
plot_adjacency

Plot adjacency matrices
update_u_bayesian

Update of bayesian parameter u
partition_K_barre

Create a link between final clustering and clustering per view component.
update_eta_bayesian

Update of bayesian parameter eta
update_tau_bayesian

Update of bayesian parameter tau
trig_sup

Upper triangular Matrix/Array
update_xi_bayesian

Update of bayesian parameter xi
update_theta_bayesian

Update of bayesian parameter theta
one_hot_errormachine

One Hot Encoding with Error machine
update_beta_bayesian

Update of bayesian parameter beta
multinomial_lbeta_function

Calculation of Log multinomial Beta value.
rSMB_partition

Simulation of mixture multilayer Stochastick block model
rMSBM

Simulate data from the mimiSBM generative model.