X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2Fmain.R;h=701a2c93e78262950eec17d3013ee97f2a86ac3d;hp=8ce5117498b58c33b2cda93b80c814fce8b443af;hb=0e0fb59a6ea0a975d1a9059153aa27f54458bf95;hpb=2279a641f2bee1db586e7ab1e13726d111d5daaf

diff --git a/pkg/R/main.R b/pkg/R/main.R
index 8ce5117..701a2c9 100644
--- a/pkg/R/main.R
+++ b/pkg/R/main.R
@@ -14,6 +14,11 @@
 #' @param kmax integer, maximum number of clusters, by default = 10
 #' @param rang.min integer, minimum rank in the low rank procedure, by default = 1
 #' @param rang.max integer, maximum rank in the
+#' @param ncores_outer Number of cores for the outer loop on k
+#' @param ncores_inner Number of cores for the inner loop on lambda
+#' @param size_coll_mod (Maximum) size of a collection of models
+#' @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 estimators of parameters
 #'
@@ -21,60 +26,56 @@
 #' #TODO: a few examples
 #' @export
 valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, maxi=50,
-	eps=1e-4, kmin=2, kmax=2, rang.min=1, rang.max=10, ncores_outer=1, ncores_inner=3,
-	verbose=FALSE)
+	eps=1e-4, kmin=2, kmax=4, rang.min=1, rang.max=10, ncores_outer=1, ncores_inner=1,
+	size_coll_mod=50, fast=TRUE, verbose=FALSE, plot = TRUE)
 {
   p = dim(X)[2]
   m = dim(Y)[2]
   n = dim(X)[1]
 
-  tableauRecap = list()
   if (verbose)
 		print("main loop: over all k and all lambda")
 
 	if (ncores_outer > 1)
 	{
-		cl = parallel::makeCluster(ncores_outer)
+		cl = parallel::makeCluster(ncores_outer, outfile='')
 		parallel::clusterExport( cl=cl, envir=environment(), varlist=c("X","Y","procedure",
 			"selecMod","gamma","mini","maxi","eps","kmin","kmax","rang.min","rang.max",
-			"ncores_outer","ncores_inner","verbose","p","m","k","tableauRecap") )
+			"ncores_outer","ncores_inner","verbose","p","m") )
 	}
 
-	# Compute model with k components
-	computeModel <- function(k)
+	# Compute models with k components
+	computeModels <- function(k)
 	{
 		if (ncores_outer > 1)
 			require("valse") #nodes start with an empty environment
 
 		if (verbose)
 			print(paste("Parameters initialization for k =",k))
-    #smallEM initializes parameters by k-means and regression model in each component,
+		#smallEM initializes parameters by k-means and regression model in each component,
     #doing this 20 times, and keeping the values maximizing the likelihood after 10
     #iterations of the EM algorithm.
     P = initSmallEM(k, X, Y)
     grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, X, Y,
-			gamma, mini, maxi, eps)
-
-		# TODO: 100 = magic number
-    if (length(grid_lambda)>100)
-      grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = 100)]
+			gamma, mini, maxi, eps, fast)
+    if (length(grid_lambda)>size_coll_mod)
+      grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
 
 		if (verbose)
 			print("Compute relevant parameters")
     #select variables according to each regularization parameter
-    #from the grid: A1 corresponding to selected variables, and
-    #A2 corresponding to unselected variables.
-    S = selectVariables(P$phiInit,P$rhoInit,P$piInit,P$gamInit,mini,maxi,gamma,
-			grid_lambda,X,Y,1e-8,eps,ncores_inner)
-
+    #from the grid: S$selected corresponding to selected variables
+    S = selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma,
+			grid_lambda, X, Y, 1e-8, eps, ncores_inner, fast) #TODO: 1e-8 as arg?! eps?
+    
     if (procedure == 'LassoMLE')
 		{
       if (verbose)
 				print('run the procedure Lasso-MLE')
       #compute parameter estimations, with the Maximum Likelihood
       #Estimator, restricted on selected variables.
-      model = constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
-				maxi, gamma, X, Y, thresh, eps, S$selected, ncores_inner, verbose)
+      models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
+				mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, artefact=1e3, fast, verbose)
     }
 		else
 		{
@@ -82,52 +83,48 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10,
 				print('run the procedure Lasso-Rank')
       #compute parameter estimations, with the Low Rank
       #Estimator, restricted on selected variables.
-      model = constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
-				rank.min, rank.max, ncores_inner, verbose)
-
-      ################################################
-      ### Regarder la SUITE  
-#      phi = runProcedure2()$phi
-#      Phi2 = Phi
-#      if (dim(Phi2)[1] == 0)
-#        Phi[, , 1:k,] <- phi
-#      else
-#      {
-#        Phi <- array(0, dim = c(p, m, kmax, dim(Phi2)[4] + dim(phi)[4]))
-#        Phi[, , 1:(dim(Phi2)[3]), 1:(dim(Phi2)[4])] <<- Phi2
-#        Phi[, , 1:k,-(1:(dim(Phi2)[4]))] <<- phi
-#      }
+      models <- constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
+				rank.min, rank.max, ncores_inner, fast, verbose)
     }
-    model
+		#attention certains modeles sont NULL après selectVariables
+		models = models[sapply(models, function(cell) !is.null(cell))]
+    models
   }
 
-	model_list <-
-		if (ncores_k > 1)
-			parLapply(cl, kmin:kmax, computeModel)
+	# List (index k) of lists (index lambda) of models
+	models_list <-
+	  if (ncores_outer > 1)
+			parLapply(cl, kmin:kmax, computeModels)
 		else
-			lapply(kmin:kmax, computeModel)
-	if (ncores_k > 1)
+			lapply(kmin:kmax, computeModels)
+	if (ncores_outer > 1)
 		parallel::stopCluster(cl)
 
+	if (! requireNamespace("capushe", quietly=TRUE))
+	{
+		warning("'capushe' not available: returning all models")
+		return (models_list)
+	}
+
 	# Get summary "tableauRecap" from models
-	tableauRecap = t( sapply( seq_along(model_list), function(model) {
-		llh = matrix(ncol = 2)
-    for (l in seq_along(model))
-      llh = rbind(llh, model[[l]]$llh)
-    LLH = llh[-1,1]
-    D = llh[-1,2]
-		c(LLH, D, rep(k, length(model)), 1:length(model))
+	tableauRecap = do.call( rbind, lapply( seq_along(models_list), function(i) {
+		models <- models_list[[i]]
+		#Pour un groupe de modeles (même k, différents lambda):
+		LLH <- sapply( models, function(model) model$llh[1] )
+		k = length(models[[1]]$pi)
+		# TODO: chuis pas sûr du tout des lignes suivantes...
+		#       J'ai l'impression qu'il manque des infos 
+		## C'est surtout que la pénalité est la mauvaise, la c'est celle du Lasso, nous on veut ici
+		##celle de l'heuristique de pentes
+		#sumPen = sapply( models, function(model)
+		#	sum( model$pi^gamma * sapply(1:k, function(r) sum(abs(model$phi[,,r]))) ) )
+		sumPen = sapply(models, function(model)
+		  k*(dim(model$rho)[1]+sum(model$phi[,,1]!=0)+1)-1)
+		data.frame(model=paste(i,".",seq_along(models),sep=""),
+			pen=sumPen/n, complexity=sumPen, contrast=LLH)
 	} ) )
 
-	if (verbose)
-		print('Model selection')
-	tableauRecap = do.call( rbind, tableauRecap ) #stack list cells into a matrix
-  tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
-  tableauRecap = tableauRecap[(tableauRecap[,1])!=Inf,]
-  data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])
-
-	require(capushe)
-  modSel = capushe(data, n)
+  modSel = capushe::capushe(tableauRecap, n)
   indModSel <-
 		if (selecMod == 'DDSE')
 			as.numeric(modSel@DDSE@model)
@@ -137,5 +134,12 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10,
 			modSel@BIC_capushe$model
 		else if (selecMod == 'AIC')
 			modSel@AIC_capushe$model
-  model[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
+
+  mod = as.character(tableauRecap[indModSel,1])
+  listMod = as.integer(unlist(strsplit(mod, "[.]")))
+  if (plot){
+    print(plot_valse())
+  }
+  models_list[[listMod[1]]][[listMod[2]]]
+  
 }