Adjustments for CRAN upload

[valse.git] / pkg / R / EMGLLF.R

diff --git a/pkg/R/EMGLLF.R b/pkg/R/EMGLLF.R
index c30b023..4c31bb5 100644 (file)
--- a/pkg/R/EMGLLF.R
+++ b/pkg/R/EMGLLF.R
@@ -1,6 +1,9 @@
 #' EMGLLF
 #'
-#' Description de EMGLLF
+#' Run a generalized EM algorithm developped for mixture of Gaussian regression
+#' models with variable selection by an extension of the Lasso estimator (regularization parameter lambda).
+#' Reparametrization is done to ensure invariance by homothetic transformation.
+#' It returns a collection of models, varying the number of clusters and the sparsity in the regression mean.
 #'
 #' @param phiInit an initialization for phi
 #' @param rhoInit an initialization for rho
@@ -13,14 +16,15 @@
 #' @param X matrix of covariates (of size n*p)
 #' @param Y matrix of responses (of size n*m)
 #' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
+#' @param fast boolean to enable or not the C function call
 #'
-#' @return A list ... phi,rho,pi,LLF,S,affec:
-#'   phi : parametre de moyenne renormalisé, calculé par l'EM
-#'   rho : parametre de variance renormalisé, calculé par l'EM
-#'   pi : parametre des proportions renormalisé, calculé par l'EM
-#'   LLF : log vraisemblance associée à cet échantillon, pour les valeurs estimées des paramètres
-#'   S : ...
-#'   affec : ...
+#' @return A list (corresponding to the model collection) defined by (phi,rho,pi,llh,S,affec):
+#'   phi : regression mean for each cluster, an array of size p*m*k
+#'   rho : variance (homothetic) for each cluster, an array of size m*m*k
+#'   pi : proportion for each cluster, a vector of size k
+#'   llh : log likelihood with respect to the training set
+#'   S : selected variables indexes, an array of size p*m*k
+#'   affec : cluster affectation for each observation (of the training set)
 #'
 #' @export
 EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
@@ -34,14 +38,8 @@ EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
   }
 
   # Function in C
-  n <- nrow(X)  #nombre d'echantillons
-  p <- ncol(X)  #nombre de covariables
-  m <- ncol(Y)  #taille de Y (multivarié)
-  k <- length(piInit)  #nombre de composantes dans le mélange
   .Call("EMGLLF", phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
-    X, Y, eps, phi = double(p * m * k), rho = double(m * m * k), pi = double(k),
-    llh = double(1), S = double(p * m * k), affec = integer(n), n, p, m, k,
-    PACKAGE = "valse")
+    X, Y, eps, PACKAGE = "valse")
 }
 
 # R version - slow but easy to read