X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2FselectVariables.R;h=2d1c9b7b71c16d5e7c15453be7d37d65fae501f9;hp=46fb3f33165106d2d4f3a91943b81ac7709b7b74;hb=fb3557f39487d9631ffde30f20b70938d2a6ab0c;hpb=f33f35efc9a01f93bb61959522d90ee6a76b892e

diff --git a/pkg/R/selectVariables.R b/pkg/R/selectVariables.R
index 46fb3f3..2d1c9b7 100644
--- a/pkg/R/selectVariables.R
+++ b/pkg/R/selectVariables.R
@@ -1,48 +1,78 @@
 #' selectVariables
-#' It is a function which construct, for a given lambda, the sets of relevant variables.
+#'
+#' For a given lambda, construct the sets of relevant variables for each cluster.
 #'
 #' @param phiInit an initial estimator for phi (size: p*m*k)
 #' @param rhoInit an initial estimator for rho (size: m*m*k)
-#' @param piInit	an initial estimator for pi (size : k)
+#' @param piInit an initial estimator for pi (size : k)
 #' @param gamInit an initial estimator for gamma
-#' @param mini		minimum number of iterations in EM algorithm
-#' @param maxi		maximum number of iterations in EM algorithm
-#' @param gamma	 power in the penalty
+#' @param mini  minimum number of iterations in EM algorithm
+#' @param maxi  maximum number of iterations in EM algorithm
+#' @param gamma  power in the penalty
 #' @param glambda grid of regularization parameters
-#' @param X			 matrix of regressors
-#' @param Y			 matrix of responses
-#' @param thres	 threshold to consider a coefficient to be equal to 0
-#' @param tau		 threshold to say that EM algorithm has converged
+#' @param X    matrix of regressors
+#' @param Y    matrix of responses
+#' @param thresh real, threshold to say a variable is relevant, by default = 1e-8
+#' @param eps   threshold to say that EM algorithm has converged
+#' @param ncores Number or cores for parallel execution (1 to disable)
+#' @param fast boolean to enable or not the C function call
 #'
 #' @return a list of outputs, for each lambda in grid: selected,Rho,Pi
 #'
-#' @examples TODO
-#'
 #' @export
-selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,X,Y,seuil,tau)
+selectVariables <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma,
+  glambda, X, Y, thresh = 1e-08, eps, ncores = 3, fast)
 {
-	#TODO: parameter ncores (chaque tâche peut aussi demander du parallélisme...)
-	cl = parallel::makeCluster( parallel::detectCores() / 4 )
-	parallel::clusterExport(cl=cl,
-		varlist=c("phiInit","rhoInit","gamInit","mini","maxi","glambda","X","Y","seuil","tau"),
-		envir=environment())
-	#Pour chaque lambda de la grille, on calcule les coefficients
-	out = parLapply( seq_along(glambda), function(lambdaindex)
-	{
-		p = dim(phiInit)[1]
-		m = dim(phiInit)[2]
+  if (ncores > 1) {
+    cl <- parallel::makeCluster(ncores, outfile = "")
+    parallel::clusterExport(cl = cl, varlist = c("phiInit", "rhoInit", "gamInit",
+      "mini", "maxi", "glambda", "X", "Y", "thresh", "eps"), envir = environment())
+  }
+
+  # Computation for a fixed lambda
+  computeCoefs <- function(lambda)
+  {
+    params <- EMGLLF(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
+      X, Y, eps, fast)
+
+    p <- ncol(X)
+    m <- ncol(Y)
+
+    # selectedVariables: list where element j contains vector of selected variables
+    # in [1,m]
+    selectedVariables <- lapply(1:p, function(j) {
+      # from boolean matrix mxk of selected variables obtain the corresponding boolean
+      # m-vector, and finally return the corresponding indices
+      if (m>1) {
+        seq_len(m)[apply(abs(params$phi[j, , ]) > thresh, 1, any)]
+      } else {
+        if (any(params$phi[j, , ] > thresh))
+          1
+        else
+          numeric(0)
+      }
+    })
 
-		params = EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda[lambdaIndex],X,Y,tau)
+    list(selected = selectedVariables, Rho = params$rho, Pi = params$pi)
+  }
 
-		#selectedVariables: list where element j contains vector of selected variables in [1,m]
-		selectedVariables = lapply(1:p, function(j) {
-			#from boolean matrix mxk of selected variables obtain the corresponding boolean m-vector,
-			#and finally return the corresponding indices
-			seq_len(m)[ apply( abs(params$phi[j,,]) > seuil, 1, any ) ]
-		})
+  # For each lambda in the grid, we compute the coefficients
+  out <-
+    if (ncores > 1) {
+      parLapply(cl, glambda, computeCoefs)
+    } else {
+      lapply(glambda, computeCoefs)
+    }
+  if (ncores > 1)
+    parallel::stopCluster(cl)
 
-		list("selected"=selectedVariables,"Rho"=params$Rho,"Pi"=params$Pi)
-	})
-	parallel::stopCluster(cl)
-	out
+  # Suppress models which are computed twice
+  # sha1_array <- lapply(out, digest::sha1) out[ duplicated(sha1_array) ]
+  selec <- lapply(out, function(model) model$selected)
+  ind_dup <- duplicated(selec)
+  ind_uniq <- which(!ind_dup)
+  out2 <- list()
+  for (l in 1:length(ind_uniq))
+    out2[[l]] <- out[[ind_uniq[l]]]
+  out2
 }