X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FEMGrank.R;h=8890e18d162467bebbc0e1ac557074fa0dc6009e;hp=b85a0faf4fd9b1b2cea2c4f7b11ccf5c9371a08d;hb=6af1d4897dbab92a7be05068e0e15823378965d9;hpb=ea5860f1b4fc91f06e371a0b26915198474a849d

diff --git a/pkg/R/EMGrank.R b/pkg/R/EMGrank.R
index b85a0fa..8890e18 100644
--- a/pkg/R/EMGrank.R
+++ b/pkg/R/EMGrank.R
@@ -1,49 +1,48 @@
 #' 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, an array of size p*m*k
+#'   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?)  -->
 # Yes, we should use by-columns storage everywhere... [later!]
 matricize <- function(X)
 {
-  if (!is.matrix(X)) 
+  if (!is.matrix(X))
     return(t(as.matrix(X)))
-  return(X)
+  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)
@@ -64,21 +63,21 @@ 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)
     {
       Z_indice <- seq_len(n)[Z == r] #indices where Z == r
-      if (length(Z_indice) == 0) 
+      if (length(Z_indice) == 0)
         next
       # U,S,V = SVD of (t(Xr)Xr)^{-1} * t(Xr) * Yr
-      s <- svd(MASS::ginv(crossprod(matricize(X[Z_indice, ]))) %*% 
-                 crossprod(matricize(X[Z_indice, ]), matricize(Y[Z_indice, ])))
+      s <- svd(MASS::ginv(crossprod(matricize(X[Z_indice, ]))) %*%
+               crossprod(matricize(X[Z_indice, ]), matricize(Y[Z_indice, ])))
       S <- s$d
       # Set m-rank(r) singular values to zero, and recompose best rank(r) approximation
       # of the initial product
-      if (rank[r] < length(S)) 
+      if (rank[r] < length(S))
         S[(rank[r] + 1):length(S)] <- 0
       phi[, , r] <- s$u %*% diag(S) %*% t(s$v) %*% Rho[, , r]
     }
@@ -108,7 +107,7 @@ matricize <- function(X)
 
     # update distance parameter to check algorithm convergence (delta(phi, Phi))
     deltaPhi <- c(deltaPhi, max((abs(phi - Phi))/(1 + abs(phi)))) #TODO: explain?
-    if (length(deltaPhi) > deltaPhiBufferSize) 
+    if (length(deltaPhi) > deltaPhiBufferSize)
       deltaPhi <- deltaPhi[2:length(deltaPhi)]
     sumDeltaPhi <- sum(abs(deltaPhi))
 
@@ -116,5 +115,5 @@ matricize <- function(X)
     Phi <- phi
     ite <- ite + 1
   }
-  return(list(phi = phi, LLF = LLF))
+  list(phi = phi, LLF = LLF)
 }