Adjustments for CRAN upload

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

diff --git a/pkg/R/constructionModelesLassoRank.R b/pkg/R/constructionModelesLassoRank.R
index c219d75..a37a7a6 100644 (file)
--- a/pkg/R/constructionModelesLassoRank.R
+++ b/pkg/R/constructionModelesLassoRank.R
@@ -1,61 +1,99 @@
 #' constructionModelesLassoRank
 #'
 #' constructionModelesLassoRank
 #'

-#' TODO: description
+#' Construct a collection of models with the Lasso-Rank procedure.

 #'
 #'

-#' @param ...
+#' @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
+#' @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.min integer, minimum rank in the low rank procedure, by default = 1
+#' @param rank.max integer, maximum rank in the low rank procedure, by default = 5
+#' @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 ...
+#' @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(pi, rho, mini, maxi, X, Y, tau, A1, rangmin,
-       rangmax, ncores, verbose=FALSE)
+#' @export
+constructionModelesLassoRank <- function(S, k, mini, maxi, X, Y, eps, rank.min, rank.max,
+  ncores, fast, verbose)

 {
 {

-  #get matrix sizes
-  n = dim(X)[1]
-  p = dim(X)[2]
-  m = dim(rho)[2]
-  k = dim(rho)[3]
-  L = dim(A1)[2]
+  n <- nrow(X)
+  p <- ncol(X)
+  m <- ncol(Y)
+  L <- length(S)

 
 

-       # On cherche les rangs possiblement intéressants
-  deltaRank = rangmax - rangmin + 1
-  Size = deltaRank^k
-  Rank = matrix(0, nrow=Size, ncol=k)
-  for(r in 1:k)
-       {
-               # On veut le tableau de toutes les combinaisons de rangs possibles
-               # Dans la première colonne : on répète (rangmax-rangmin)^(k-1) chaque chiffre :
-               #   ça remplit la colonne
-               # Dans la deuxieme : on répète (rangmax-rangmin)^(k-2) chaque chiffre,
-               #   et on fait ça (rangmax-rangmin)^2 fois
-               # ...
-               # Dans la dernière, on répète chaque chiffre une fois,
-               #   et on fait ça (rangmin-rangmax)^(k-1) fois.
-    Rank[,r] = rangmin + rep(0:(deltaRank-1), deltaRank^(r-1), each=deltaRank^(k-r))
+  # Possible interesting ranks
+  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 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),
+      each = deltaRank^(k - r)), each = L)

   }
   }

+  RankLambda[, k + 1] <- rep(1:L, times = Size)

 
 

-       # output parameters
-  phi = array(0, dim=c(p,m,k,L*Size))
-  llh = matrix(0, L*Size, 2) #log-likelihood
+  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"))
+  }
+
+  computeAtLambda <- function(index)
+  {
+    lambdaIndex <- RankLambda[index, k + 1]
+    rankIndex <- RankLambda[index, 1:k]
+    if (ncores > 1)
+      require("valse")  #workers start with an empty environment

 
 

-       # TODO: // loop
-       for(lambdaIndex in 1:L)
-       {
-    # on ne garde que les colonnes actives
-    # 'active' sera l'ensemble des variables informatives
-    active = A1[,lambdaIndex]
-    active = active[-(active==0)]
-    if (length(active) > 0)
-               {
-      for (j in 1:Size)
-                       {
-        res = EMGrank(Pi[,lambdaIndex], Rho[,,,lambdaIndex], mini, maxi,
-                                       X[,active], Y, tau, Rank[j,])
-        llh[(lambdaIndex-1)*Size+j,] =
-                                       c( res$LLF, sum(Rank[j,] * (length(active)- Rank[j,] + m)) )
-        phi[active,,,(lambdaIndex-1)*Size+j] = res$phi
+    # '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]]$Rho, mini, maxi,
+          X[, relevant], Y, eps, rankIndex, fast)
+        llh <- c(res$LLF, sum(rankIndex * (length(relevant) - rankIndex + m)))
+        phi[relevant, , ] <- res$phi

       }
       }

+      list(llh = llh, phi = phi, pi = S[[lambdaIndex]]$Pi, rho = S[[lambdaIndex]]$Rho)

     }
   }
     }
   }

-  return (list("phi"=phi, "llh" = llh))
+
+  # For each lambda in the grid we compute the estimators
+  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

 }
 }