X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FEMGLLF.R;h=2aeea537b9d6656c04032c2697d407f6c4d1d823;hp=0a279f0bf56f92b84acbbddfab6bc8de1c07dd1a;hb=17b9fa5f6004bb55e915d8916f1c9a1f128a65ce;hpb=1b698c1619dbcf5b3a0608dc894d249945d2bce3

diff --git a/pkg/R/EMGLLF.R b/pkg/R/EMGLLF.R
index 0a279f0..2aeea53 100644
--- a/pkg/R/EMGLLF.R
+++ b/pkg/R/EMGLLF.R
@@ -19,11 +19,12 @@
 #'   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 : ...
+#'   S : ...
+#'   affec : ...
 #'
 #' @export
 EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda, 
-  X, Y, eps, fast = TRUE)
+  X, Y, eps, fast)
 {
   if (!fast)
   {
@@ -41,29 +42,27 @@ EMGLLF <- function(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, 
     PACKAGE = "valse")
+	list(phi = phi, rho = rho, pi = pi, llh = llh, S = S, affec=affec)
 }
 
 # R version - slow but easy to read
 .EMGLLF_R <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda, 
-  X2, Y, eps)
+  X, Y, eps)
 {
   # Matrix dimensions
-  n <- dim(Y)[1]
-  if (length(dim(phiInit)) == 2) {
-    p <- 1
-    m <- dim(phiInit)[1]
-    k <- dim(phiInit)[2]
-  } else {
-    p <- dim(phiInit)[1]
-    m <- dim(phiInit)[2]
-    k <- dim(phiInit)[3]
-  }
-  X <- matrix(nrow = n, ncol = p)
-  X[1:n, 1:p] <- X2
+  n <- nrow(X)
+  p <- ncol(X)
+  m <- ncol(Y)
+  k <- length(piInit)
+
+  # Adjustments required when p==1 or m==1 (var.sel. or output dim 1)
+  if (p==1 || m==1)
+    phiInit <- array(phiInit, dim=c(p,m,k))
+  if (m==1)
+    rhoInit <- array(rhoInit, dim=c(m,m,k))
 
   # Outputs
-  phi <- array(NA, dim = c(p, m, k))
-  phi[1:p, , ] <- phiInit
+  phi <- phiInit
   rho <- rhoInit
   pi <- piInit
   llh <- -Inf
@@ -119,7 +118,8 @@ EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
 
     # t(m) is the largest value in the grid O.1^k such that it is nonincreasing
     while (kk < 1000 && -a/n + lambda * sum(pi^gamma * b) <
-      -sum(gam2 * log(pi2))/n + lambda * sum(pi2^gamma * b))
+      # na.rm=TRUE to handle 0*log(0)
+      -sum(gam2 * log(pi2), na.rm=TRUE)/n + lambda * sum(pi2^gamma * b))
     {
       pi2 <- pi + 0.1^kk * (1/n * gam2 - pi)
       kk <- kk + 1
@@ -146,8 +146,8 @@ EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
       {
         for (mm in 1:m)
         {
-          S[j, mm, r] <- -rho[mm, mm, r] * ps2[j, mm, r]
-            + sum(phi[-j, mm, r] * Gram2[j, -j, r])
+          S[j, mm, r] <- -rho[mm, mm, r] * ps2[j, mm, r] +
+            sum(phi[-j, mm, r] * Gram2[j, -j, r])
           if (abs(S[j, mm, r]) <= n * lambda * (pi[r]^gamma)) {
             phi[j, mm, r] <- 0
           } else if (S[j, mm, r] > n * lambda * (pi[r]^gamma)) {
@@ -159,34 +159,39 @@ EMGLLF <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
       }
     }
 
-    ######## E step#
+    ## E step
 
     # Precompute det(rho[,,r]) for r in 1...k
-    detRho <- sapply(1:k, function(r) det(rho[, , r]))
-    gam1 <- matrix(0, nrow = n, ncol = k)
+    detRho <- sapply(1:k, function(r) gdet(rho[, , r]))
+    sumLogLLH <- 0
     for (i in 1:n)
     {
-      # Update gam[,]
-      for (r in 1:k)
-      {
-        gam1[i, r] <- pi[r] * exp(-0.5
-          * sum((Y[i, ] %*% rho[, , r] - X[i, ] %*% phi[, , r])^2)) * detRho[r]
-      }
+      # Update gam[,]; use log to avoid numerical problems
+      logGam <- sapply(1:k, function(r) {
+        log(pi[r]) + log(detRho[r]) - 0.5 *
+          sum((Y[i, ] %*% rho[, , r] - X[i, ] %*% phi[, , r])^2)
+      })
+
+      logGam <- logGam - max(logGam) #adjust without changing proportions
+      gam[i, ] <- exp(logGam)
+      norm_fact <- sum(gam[i, ])
+      gam[i, ] <- gam[i, ] / norm_fact
+      sumLogLLH <- sumLogLLH + log(norm_fact) - log((2 * base::pi)^(m/2))
     }
-    gam <- gam1 / rowSums(gam1)
-    sumLogLLH <- sum(log(rowSums(gam)) - log((2 * base::pi)^(m/2)))
+
     sumPen <- sum(pi^gamma * b)
     last_llh <- llh
-    llh <- -sumLogLLH/n + lambda * sumPen
+    llh <- -sumLogLLH/n #+ lambda * sumPen
     dist <- ifelse(ite == 1, llh, (llh - last_llh)/(1 + abs(llh)))
     Dist1 <- max((abs(phi - Phi))/(1 + abs(phi)))
     Dist2 <- max((abs(rho - Rho))/(1 + abs(rho)))
     Dist3 <- max((abs(pi - Pi))/(1 + abs(Pi)))
     dist2 <- max(Dist1, Dist2, Dist3)
 
-    if (ite >= mini && (dist >= eps || dist2 >= sqrt(eps))) 
+    if (ite >= mini && (dist >= eps || dist2 >= sqrt(eps)))
       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)
 }