Fix numerical problems in EMGLLF (R version)

[valse.git] / pkg / R / constructionModelesLassoRank.R

diff --git a/pkg/R/constructionModelesLassoRank.R b/pkg/R/constructionModelesLassoRank.R
index 5da26e3..85685e9 100644 (file)
--- a/pkg/R/constructionModelesLassoRank.R
+++ b/pkg/R/constructionModelesLassoRank.R
@@ -1,7 +1,7 @@
 #' constructionModelesLassoRank
 #'
 #' Construct a collection of models with the Lasso-Rank procedure.
-#' 
+#'
 #' @param S output of selectVariables.R
 #' @param k number of components
 #' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
@@ -14,82 +14,82 @@
 #' @param ncores Number of cores, by default = 3
 #' @param fast TRUE to use compiled C code, FALSE for R code only
 #' @param verbose TRUE to show some execution traces
-#' 
+#'
 #' @return a list with several models, defined by phi, rho, pi, llh
 #'
 #' @export
-constructionModelesLassoRank = function(S, k, mini, maxi, X, Y, eps, rank.min,
-                                        rank.max, ncores, fast=TRUE, verbose=FALSE)
+constructionModelesLassoRank <- function(S, k, mini, maxi, X, Y, eps, rank.min, rank.max, 
+  ncores, fast, verbose)
 {
-  n = dim(X)[1]
-  p = dim(X)[2]
-  m = dim(Y)[2]
-  L = length(S)
-  
+  n <- dim(X)[1]
+  p <- dim(X)[2]
+  m <- dim(Y)[2]
+  L <- length(S)
+
   # Possible interesting ranks
-  deltaRank = rank.max - rank.min + 1
-  Size = deltaRank^k
-  RankLambda = matrix(0, nrow=Size*L, ncol=k+1)
+  deltaRank <- rank.max - rank.min + 1
+  Size <- deltaRank^k
+  RankLambda <- matrix(0, nrow = Size * L, ncol = k + 1)
   for (r in 1:k)
   {
-    # On veut le tableau de toutes les combinaisons de rangs possibles, et des lambdas
-    # Dans la première colonne : on répète (rank.max-rank.min)^(k-1) chaque chiffre :
-    #   ça remplit la colonne
-    # Dans la deuxieme : on répète (rank.max-rank.min)^(k-2) chaque chiffre,
-    #   et on fait ça (rank.max-rank.min)^2 fois
-    # ...
-    # Dans la dernière, on répète chaque chiffre une fois,
-    #   et on fait ça (rank.min-rank.max)^(k-1) fois.
-    RankLambda[,r] = rep(rank.min + rep(0:(deltaRank-1), deltaRank^(r-1), each=deltaRank^(k-r)), each = L)
+    # On veut le tableau de toutes les combinaisons de rangs possibles, et des
+    # lambdas Dans la première colonne : on répète (rank.max-rank.min)^(k-1) chaque
+    # chiffre : ça remplit la colonne Dans la deuxieme : on répète
+    # (rank.max-rank.min)^(k-2) chaque chiffre, et on fait ça (rank.max-rank.min)^2
+    # fois ...  Dans la dernière, on répète chaque chiffre une fois, et on fait ça
+    # (rank.min-rank.max)^(k-1) fois.
+    RankLambda[, r] <- rep(rank.min + rep(0:(deltaRank - 1), deltaRank^(r - 1), 
+      each = deltaRank^(k - r)), each = L)
   }
-  RankLambda[,k+1] = rep(1:L, times = Size)
-  
+  RankLambda[, k + 1] <- rep(1:L, times = Size)
+
   if (ncores > 1)
   {
-    cl = parallel::makeCluster(ncores, outfile='')
-    parallel::clusterExport( cl, envir=environment(),
-                             varlist=c("A1","Size","Pi","Rho","mini","maxi","X","Y","eps",
-                                       "Rank","m","phi","ncores","verbose") )
+    cl <- parallel::makeCluster(ncores, outfile = "")
+    parallel::clusterExport(cl, envir = environment(), varlist = c("A1", "Size", 
+      "Pi", "Rho", "mini", "maxi", "X", "Y", "eps", "Rank", "m", "phi", "ncores", 
+      "verbose"))
   }
-  
+
   computeAtLambda <- function(index)
   {
-    lambdaIndex = RankLambda[index,k+1]
-    rankIndex = RankLambda[index,1:k]
-    if (ncores > 1)
-      require("valse") #workers start with an empty environment
-    
+    lambdaIndex <- RankLambda[index, k + 1]
+    rankIndex <- RankLambda[index, 1:k]
+    if (ncores > 1) 
+      require("valse")  #workers start with an empty environment
+
     # 'relevant' will be the set of relevant columns
-    selected = S[[lambdaIndex]]$selected
-    relevant = c()
-    for (j in 1:p){
-      if (length(selected[[j]])>0){
-        relevant = c(relevant,j)
-      }
+    selected <- S[[lambdaIndex]]$selected
+    relevant <- c()
+    for (j in 1:p)
+    {
+      if (length(selected[[j]]) > 0)
+        relevant <- c(relevant, j)
     }
-    if (max(rankIndex)<length(relevant)){
-      phi = array(0, dim=c(p,m,k))
+    if (max(rankIndex) < length(relevant))
+    {
+      phi <- array(0, dim = c(p, m, k))
       if (length(relevant) > 0)
       {
-        res = EMGrank(S[[lambdaIndex]]$Pi, S[[lambdaIndex]]$Rho, mini, maxi,
-                      X[,relevant], Y, eps, rankIndex, fast)
-        llh = c( res$LLF, sum(rankIndex * (length(relevant)- rankIndex + m)) ) 
-        phi[relevant,,] = res$phi
+        res <- EMGrank(S[[lambdaIndex]]$Pi, S[[lambdaIndex]]$Rho, mini, maxi, 
+          X[, relevant], Y, eps, rankIndex, fast)
+        llh <- c(res$LLF, sum(rankIndex * (length(relevant) - rankIndex + m)))
+        phi[relevant, , ] <- res$phi
       }
-      list("llh"=llh, "phi"=phi, "pi" = S[[lambdaIndex]]$Pi, "rho" = S[[lambdaIndex]]$Rho)
-      
+      list(llh = llh, phi = phi, pi = S[[lambdaIndex]]$Pi, rho = S[[lambdaIndex]]$Rho)
     }
   }
-  
-  #For each lambda in the grid we compute the estimators
-  out =
-    if (ncores > 1)
-      parLapply(cl, seq_len(length(S)*Size), computeAtLambda)
-  else
-    lapply(seq_len(length(S)*Size), computeAtLambda)
-  
-  if (ncores > 1)
+
+  # For each lambda in the grid we compute the estimators
+  out <-
+    if (ncores > 1) {
+      parLapply(cl, seq_len(length(S) * Size), computeAtLambda)
+    } else {
+      lapply(seq_len(length(S) * Size), computeAtLambda)
+    }
+
+  if (ncores > 1) 
     parallel::stopCluster(cl)
-  
+
   out
 }