SelvarClustLasso: Regularization for variable selection in model-based...

In SelvarMix: Regularization for Variable Selection in Model-Based Clustering and Discriminant Analysis

Description

This function implements the variable selection in model-based clustering using a lasso ranking on the variables as described in Sedki et al (2014). The variable ranking step uses the penalized EM algorithm of Zhou et al (2009).

Usage

SelvarClustLasso(x, nbcluster, lambda, rho, type, rank, hsize, criterion, 
                 models, rmodel, imodel, nbcores)

Arguments

x	matrix or data frame containing quantitative data. Rows correspond to observations and columns correspond to variables
nbcluster	numeric listing of the number of clusters (must be positive integers)
lambda	numeric listing of the tuning parameters for \ell_1 mean penalty
rho	numeric listing of the tuning parameters for \ell_1 precision matrix penalty
type	character defining the type of ranking procedure, must be "lasso" or "likelihood". Default is "lasso"
rank	integer listing the rank of variables with (the length this vector must be equal to the number of variables in the dataset)
hsize	optional parameter make less strength the forward and backward algorithms to select S and W sets
criterion	list of character defining the criterion to select the best model. The best model is the one with the highest criterion value. Possible values: "BIC", "ICL", c("BIC", "ICL"). Default is "BIC"
models	a Rmixmod [Model] object defining the list of models to run. The models Gaussian_pk_L_C, Gaussian_pk_Lk_C, Gaussian_pk_L_Ck, and Gaussian_pk_Lk_Ck are called by default (see mixmodGaussianModel() in Rmixmod package to specify other models)
rmodel	list of character defining the covariance matrix form for the linear regression of U on the R set of variables. Possible values: "LI" for spherical form, "LB" for diagonal form and "LC" for general form. Possible values: "LI", "LB", "LC", c("LI", "LB"), c("LI", "LC"), c("LB", "LC") and c("LI", "LB", "LC"). Default is c("LI", "LB", "LC")
imodel	list of character defining the covariance matrix form for independent variables W. Possible values: "LI" for spherical form and "LB" for diagonal form. Possible values: "LI", "LB", c("LI", "LB"). Default is c("LI", LB")
nbcores	number of CPUs to be used when parallel computing is used (default is 2)

Value

for each criterion BIC or ICL

S	The selected set of relevant clustering variables
R	The selected subset of regressors
U	The selected set of redundant variables
W	The selected set of independent variables
criterionValue	The criterion value for the selected model
nbcluster	The selected number of clusters
model	The selected Gaussian mixture form

rmodel	The selected covariance form for the regression
imodel	The selected covariance form for the independent Gaussian distribution
parameters	Rmixmod [Parameter] object containing all mixture parameters
regparameters	Matrix containing all regression coefficients, each column is the regression coefficients of one redundant variable on the selected R set
proba	Matrix containing the conditional probabilities of belonging to each cluster for all observations
partition	Vector of length n containing the cluster assignments of the n observations according to the Maximum-a-Posteriori rule

Author(s)

Mohammed Sedki <[e-mail]>

References

Zhou, H., Pan, W., and Shen, X., 2009. "Penalized model-based clustering with unconstrained covariance matrices". Electronic Journal of Statistics, vol. 3, pp.1473-1496.

Maugis, C., Celeux, G., and Martin-Magniette, M. L., 2009. "Variable selection in model-based clustering: A general variable role modeling". Computational Statistics and Data Analysis, vol. 53/11, pp. 3872-3882.

Sedki, M., Celeux, G., Maugis-Rabusseau, C., 2014. "SelvarMix: A R package for variable selection in model-based clustering and discriminant analysis with a regularization approach". Inria Research Report available at http://hal.inria.fr/hal-01053784

See Also

SelvarLearnLasso SortvarClust SortvarLearn wine

Examples

## Not run: 
## wine data set 
## n = 178 observations, p = 27 variables 
data(wine)
set.seed(123)
obj <- SelvarClustLasso(x=wine[,1:27], nbcluster=1:5, nbcores=4)
summary(obj)
print(obj)

## End(Not run) 

SelvarMix documentation built on May 31, 2017, 3:31 a.m.