X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FEMGrank.R;h=fa66b3de581be86ea610a01cfd42cc6163e99bcd;hp=b85a0faf4fd9b1b2cea2c4f7b11ccf5c9371a08d;hb=1196a43d961a95abc18d3c8e777e9a4e8233e562;hpb=ea5860f1b4fc91f06e371a0b26915198474a849d

diff --git a/pkg/R/EMGrank.R b/pkg/R/EMGrank.R
index b85a0fa..fa66b3d 100644
--- a/pkg/R/EMGrank.R
+++ b/pkg/R/EMGrank.R
@@ -1,36 +1,35 @@
 #' EMGrank
 #'
-#' Description de EMGrank
+#' Run an generalized EM algorithm developped for mixture of Gaussian regression 
+#' models with variable selection by an extension of the low rank estimator.
+#' Reparametrization is done to ensure invariance by homothetic transformation.
+#' It returns a collection of models, varying the number of clusters and the rank of the regression mean.
 #'
-#' @param Pi Parametre de proportion
-#' @param Rho Parametre initial de variance renormalisé
-#' @param mini Nombre minimal d'itérations dans l'algorithme EM
-#' @param maxi Nombre maximal d'itérations dans l'algorithme EM
-#' @param X Régresseurs
-#' @param Y Réponse
-#' @param tau Seuil pour accepter la convergence
-#' @param rank Vecteur des rangs possibles
+#' @param Pi An initialization for pi
+#' @param Rho An initialization for rho, the variance parameter
+#' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
+#' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
+#' @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 rank vector of possible ranks
+#' @param fast boolean to enable or not the C function call
 #'
-#' @return A list ...
-#'   phi : parametre de moyenne renormalisé, calculé par l'EM
-#'   LLF : log vraisemblance associé à cet échantillon, pour les valeurs estimées des paramètres
+#' @return A list (corresponding to the model collection) defined by (phi,LLF):
+#'   phi : regression mean for each cluster
+#'   LLF : log likelihood with respect to the training set
 #'
 #' @export
-EMGrank <- function(Pi, Rho, mini, maxi, X, Y, tau, rank, fast = TRUE)
+EMGrank <- function(Pi, Rho, mini, maxi, X, Y, eps, rank, fast)
 {
   if (!fast)
   {
     # Function in R
-    return(.EMGrank_R(Pi, Rho, mini, maxi, X, Y, tau, rank))
+    return(.EMGrank_R(Pi, Rho, mini, maxi, X, Y, eps, rank))
   }
 
   # Function in C
-  n <- nrow(X)  #nombre d'echantillons
-  p <- ncol(X)  #nombre de covariables
-  m <- ncol(Y)  #taille de Y (multivarié)
-  k <- length(Pi)  #nombre de composantes dans le mélange
-  .Call("EMGrank", Pi, Rho, mini, maxi, X, Y, tau, rank, phi = double(p * m * k), 
-    LLF = double(1), n, p, m, k, PACKAGE = "valse")
+  .Call("EMGrank", Pi, Rho, mini, maxi, X, Y, eps, as.integer(rank), PACKAGE = "valse")
 }
 
 # helper to always have matrices as arg (TODO: put this elsewhere? improve?)  -->
@@ -43,7 +42,7 @@ matricize <- function(X)
 }
 
 # R version - slow but easy to read
-.EMGrank_R <- function(Pi, Rho, mini, maxi, X, Y, tau, rank)
+.EMGrank_R <- function(Pi, Rho, mini, maxi, X, Y, eps, rank)
 {
   # matrix dimensions
   n <- nrow(X)
@@ -64,7 +63,7 @@ matricize <- function(X)
   
   # main loop
   ite <- 1
-  while (ite <= mini || (ite <= maxi && sumDeltaPhi > tau))
+  while (ite <= mini || (ite <= maxi && sumDeltaPhi > eps))
   {
     # M step: update for Beta ( and then phi)
     for (r in 1:k)