X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FconstructionModelesLassoRank.R;h=a37a7a6b79ea4d7f6721daedf712774177bad6b6;hp=b9973039172693ca23508eb88c708bc778359f83;hb=6af1d4897dbab92a7be05068e0e15823378965d9;hpb=20d12623f4f395ba126570b3230fc80214191d8e

diff --git a/pkg/R/constructionModelesLassoRank.R b/pkg/R/constructionModelesLassoRank.R
index b997303..a37a7a6 100644
--- a/pkg/R/constructionModelesLassoRank.R
+++ b/pkg/R/constructionModelesLassoRank.R
@@ -15,17 +15,21 @@
 #' @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
+#' @return a list with several models, defined by phi (the regression parameter reparametrized),
+#' rho (the covariance parameter reparametrized), pi (the proportion parameter is the mixture model), llh
+#' (the value of the loglikelihood function for this estimator on the training dataset). The list is given
+#' for several levels of sparsity, given by several regularization parameters computed automatically,
+#' and several ranks (between rank.min and rank.max).
 #'
 #' @export
-constructionModelesLassoRank <- function(S, k, mini, maxi, X, Y, eps, rank.min, rank.max, 
-  ncores, fast = TRUE, verbose = FALSE)
-  {
-  n <- dim(X)[1]
-  p <- dim(X)[2]
-  m <- dim(Y)[2]
+constructionModelesLassoRank <- function(S, k, mini, maxi, X, Y, eps, rank.min, rank.max,
+  ncores, fast, verbose)
+{
+  n <- nrow(X)
+  p <- ncol(X)
+  m <- ncol(Y)
   L <- length(S)
-  
+
   # Possible interesting ranks
   deltaRank <- rank.max - rank.min + 1
   Size <- deltaRank^k
@@ -33,67 +37,63 @@ constructionModelesLassoRank <- function(S, k, mini, maxi, X, Y, eps, rank.min,
   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
+    # lambdas Dans la premiere colonne : on repete (rank.max-rank.min)^(k-1) chaque
+    # chiffre : ca remplit la colonne Dans la deuxieme : on repete
+    # (rank.max-rank.min)^(k-2) chaque chiffre, et on fait ca (rank.max-rank.min)^2
+    # fois ...  Dans la derniere, on repete chaque chiffre une fois, et on fait ca
     # (rank.min-rank.max)^(k-1) fois.
-    RankLambda[, r] <- rep(rank.min + rep(0:(deltaRank - 1), deltaRank^(r - 1), 
+    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)
-  
+
   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", 
+    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) 
+    if (ncores > 1)
       require("valse")  #workers start with an empty environment
-    
+
     # 'relevant' will be the set of relevant columns
     selected <- S[[lambdaIndex]]$selected
     relevant <- c()
     for (j in 1:p)
     {
       if (length(selected[[j]]) > 0)
-      {
         relevant <- c(relevant, j)
-      }
     }
     if (max(rankIndex) < length(relevant))
     {
       phi <- array(0, dim = c(p, m, k))
       if (length(relevant) > 0)
       {
-        res <- EMGrank(S[[lambdaIndex]]$Pi, S[[lambdaIndex]]$Rho, mini, maxi, 
+        res <- EMGrank(S[[lambdaIndex]]$Pi, S[[lambdaIndex]]$Rho, mini, maxi,
           X[, relevant], Y, eps, rankIndex, fast)
-        llh <- c(res$LLF, sum(rankIndex * (length(relevant) - rankIndex + 
-          m)))
+        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)
     }
   }
-  
+
   # 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) 
+  out <-
+    if (ncores > 1) {
+      parallel::parLapply(cl, seq_len(length(S) * Size), computeAtLambda)
+    } else {
+      lapply(seq_len(length(S) * Size), computeAtLambda)
+    }
+
+  if (ncores > 1)
     parallel::stopCluster(cl)
-  
+
   out
 }