X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FEMGLLF.R;h=93012fb163100e8d2d4952ffb156ac94286fc1a3;hb=859c30ec72871f923da0498c14a94e67b0219875;hp=bf4476b63d839fc1f260ff7b005309f32e80d4af;hpb=228ee602a972fcac6177db0d539bf9d0c5fa477f;p=valse.git

diff --git a/pkg/R/EMGLLF.R b/pkg/R/EMGLLF.R
index bf4476b..93012fb 100644
--- a/pkg/R/EMGLLF.R
+++ b/pkg/R/EMGLLF.R
@@ -1,6 +1,9 @@
-#' EMGLLF 
+#' 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
@@ -14,37 +17,38 @@
 #' @param Y matrix of responses (of size n*m)
 #' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
 #'
-#' @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,LLF,S,affec):
+#'   phi : regression mean for each cluster
+#'   rho : variance (homothetic) for each cluster
+#'   pi : proportion for each cluster
+#'   LLF : log likelihood with respect to the training set
+#'   S : selected variables indexes
+#'   affec : cluster affectation for each observation (of the training set)
 #'
 #' @export
-EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda, 
+EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
   X, Y, eps, fast)
 {
   if (!fast)
   {
     # Function in R
-    return(.EMGLLF_R(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda, 
+    return(.EMGLLF_R(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
       X, Y, eps))
   }
 
   # 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), 
-    LLF = double(maxi), S = double(p * m * k), affec = integer(n), n, p, m, k, 
+  m <- ncol(Y)  #taille de Y (multivarie)
+  k <- length(piInit)  #nombre de composantes dans le melange
+  .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")
 }
 
 # R version - slow but easy to read
-.EMGLLF_R <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda, 
+.EMGLLF_R <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
   X, Y, eps)
 {
   # Matrix dimensions
@@ -72,7 +76,6 @@ EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
   ps2 <- array(0, dim = c(p, m, k))
   X2 <- array(0, dim = c(n, p, k))
   Y2 <- array(0, dim = c(n, m, k))
-  EPS <- 1e-15
 
   for (ite in 1:maxi)
   {
@@ -190,5 +193,6 @@ EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
       break
   }
 
-  list(phi = phi, rho = rho, pi = pi, llh = llh, S = S)
+	affec = apply(gam, 1, which.max)
+  list(phi = phi, rho = rho, pi = pi, llh = llh, S = S, affec=affec)
 }