X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FEMGrank.R;h=f2bf58e05b50a04e6a9c341dbc78978186cdf0bd;hp=436b28982eb093c3c4eda822399ff50b850ffa29;hb=6279ba8656582370e7242ff9e77d22c23fe8ca04;hpb=ffdf94474d96cdd3e9d304ce809df7e62aa957ed

diff --git a/pkg/R/EMGrank.R b/pkg/R/EMGrank.R
index 436b289..f2bf58e 100644
--- a/pkg/R/EMGrank.R
+++ b/pkg/R/EMGrank.R
@@ -1,4 +1,4 @@
-#' EMGrank 
+#' EMGrank
 #'
 #' Description de EMGrank
 #'
@@ -8,7 +8,7 @@
 #' @param maxi Nombre maximal d'itérations dans l'algorithme EM
 #' @param X Régresseurs
 #' @param Y Réponse
-#' @param tau Seuil pour accepter la convergence
+#' @param eps Seuil pour accepter la convergence
 #' @param rank Vecteur des rangs possibles
 #'
 #' @return A list ...
@@ -16,20 +16,20 @@
 #'   LLF : log vraisemblance associé à cet échantillon, pour les valeurs estimées des paramètres
 #'
 #' @export
-EMGrank <- function(Pi, Rho, mini, maxi, X, Y, tau, rank, fast = TRUE)
+EMGrank <- function(Pi, Rho, mini, maxi, X, Y, eps, rank, fast = TRUE)
 {
   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), 
+  .Call("EMGrank", Pi, Rho, mini, maxi, X, Y, eps, rank, phi = double(p * m * k), 
     LLF = double(1), n, p, m, k, PACKAGE = "valse")
 }
 
@@ -43,19 +43,19 @@ 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 <- dim(X)[1]
-  p <- dim(X)[2]
-  m <- dim(Rho)[2]
-  k <- dim(Rho)[3]
-  
+  n <- nrow(X)
+  p <- ncol(X)
+  m <- ncol(Y)
+  k <- length(Pi)
+
   # init outputs
   phi <- array(0, dim = c(p, m, k))
   Z <- rep(1, n)
   LLF <- 0
-  
+
   # local variables
   Phi <- array(0, dim = c(p, m, k))
   deltaPhi <- c()
@@ -64,17 +64,17 @@ 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
+      Z_indice <- seq_len(n)[Z == r] #indices where Z == r
       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$d
       # Set m-rank(r) singular values to zero, and recompose best rank(r) approximation
       # of the initial product
@@ -82,7 +82,7 @@ matricize <- function(X)
         S[(rank[r] + 1):length(S)] <- 0
       phi[, , r] <- s$u %*% diag(S) %*% t(s$v) %*% Rho[, , r]
     }
-    
+
     # Step E and computation of the loglikelihood
     sumLogLLF2 <- 0
     for (i in seq_len(n))
@@ -91,9 +91,8 @@ matricize <- function(X)
       maxLogGamIR <- -Inf
       for (r in seq_len(k))
       {
-        dotProduct <- tcrossprod(Y[i, ] %*% Rho[, , r] - X[i, ] %*% phi[, 
-          , r])
-        logGamIR <- log(Pi[r]) + log(det(Rho[, , r])) - 0.5 * dotProduct
+        dotProduct <- tcrossprod(Y[i, ] %*% Rho[, , r] - X[i, ] %*% phi[, , r])
+        logGamIR <- log(Pi[r]) + log(gdet(Rho[, , r])) - 0.5 * dotProduct
         # Z[i] = index of max (gam[i,])
         if (logGamIR > maxLogGamIR)
         {
@@ -104,15 +103,15 @@ matricize <- function(X)
       }
       sumLogLLF2 <- sumLogLLF2 + log(sumLLF1)
     }
-    
+
     LLF <- -1/n * sumLogLLF2
-    
+
     # update distance parameter to check algorithm convergence (delta(phi, Phi))
-    deltaPhi <- c(deltaPhi, max((abs(phi - Phi))/(1 + abs(phi))))  #TODO: explain?
+    deltaPhi <- c(deltaPhi, max((abs(phi - Phi))/(1 + abs(phi)))) #TODO: explain?
     if (length(deltaPhi) > deltaPhiBufferSize) 
       deltaPhi <- deltaPhi[2:length(deltaPhi)]
     sumDeltaPhi <- sum(abs(deltaPhi))
-    
+
     # update other local variables
     Phi <- phi
     ite <- ite + 1