X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2Fmain.R;h=634c27396507901537f72d3238c075c187677157;hp=ab25daf5fa210933b5516a0fa875e06b935f2808;hb=43d76c49d2f98490abc782c7e8a8b94baee40247;hpb=0eb161e3f3d018bce7d98fc85622d14910f89d43

diff --git a/pkg/R/main.R b/pkg/R/main.R
index ab25daf..634c273 100644
--- a/pkg/R/main.R
+++ b/pkg/R/main.R
@@ -12,8 +12,14 @@
 #' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
 #' @param kmin integer, minimum number of clusters, by default = 2
 #' @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 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_outer Number of cores for the outer loop on k
+#' @param ncores_inner Number of cores for the inner loop on lambda
+#' @param thresh real, threshold to say a variable is relevant, by default = 1e-8
+#' @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
 #'
@@ -21,107 +27,132 @@
 #' #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=3, rank.min=1, rank.max=5, ncores_outer=1, ncores_inner=1,
+                 thresh=1e-8,
+                 size_coll_mod=10, fast=TRUE, verbose=FALSE, plot = TRUE)
 {
   p = dim(X)[2]
   m = dim(Y)[2]
   n = dim(X)[1]
-
+  
   if (verbose)
-		print("main loop: over all k and all lambda")
-
-	if (ncores_outer > 1)
-	{
-		cl = parallel::makeCluster(ncores_outer)
-		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") )
-	}
-
-	# 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,
+    print("main loop: over all k and all lambda")
+  
+  if (ncores_outer > 1)
+  {
+    cl = parallel::makeCluster(ncores_outer, outfile='')
+    parallel::clusterExport( cl=cl, envir=environment(), varlist=c("X","Y","procedure",
+                                                                   "selecMod","gamma","mini","maxi","eps","kmin","kmax","rank.min","rank.max",
+                                                                   "ncores_outer","ncores_inner","thresh","size_coll_mod","verbose","p","m") )
+  }
+  
+  # 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,
     #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)]
-
-		if (verbose)
-			print("Compute relevant parameters")
+                                     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: S$selected corresponding to selected variables
     S = selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma,
-			grid_lambda, X, Y, 1e-8, eps, ncores_inner) #TODO: 1e-8 as arg?! eps?
-
+                        grid_lambda, X, Y, thresh, eps, ncores_inner, fast) 
+    
     if (procedure == 'LassoMLE')
-		{
+    {
       if (verbose)
-				print('run the procedure Lasso-MLE')
+        print('run the procedure Lasso-MLE')
       #compute parameter estimations, with the Maximum Likelihood
       #Estimator, restricted on selected variables.
-      models <- constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
-				maxi, gamma, X, Y, thresh, eps, S$selected, ncores_inner, verbose)
+      models <- constructionModelesLassoMLE( P$phiInit, P$rhoInit, P$piInit, P$gamInit, 
+                                            mini, maxi, gamma, X, Y, eps, S, ncores_inner, fast, verbose)
+      
     }
-		else
-		{
+    else
+    {
       if (verbose)
-				print('run the procedure Lasso-Rank')
+        print('run the procedure Lasso-Rank')
       #compute parameter estimations, with the Low Rank
       #Estimator, restricted on selected variables.
-      models <- constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
-				rank.min, rank.max, ncores_inner, verbose)
+      models <- constructionModelesLassoRank(S, k, mini, maxi, X, Y, eps,
+                                             rank.min, rank.max, ncores_inner, fast, verbose)
     }
+    #warning! Some models are NULL after running selectVariables
+    models = models[sapply(models, function(cell) !is.null(cell))]
     models
   }
-
-	# List (index k) of lists (index lambda) of models
-	models_list <-
-		if (ncores_k > 1)
-			parLapply(cl, kmin:kmax, computeModels)
-		else
-			lapply(kmin:kmax, computeModels)
-	if (ncores_k > 1)
-		parallel::stopCluster(cl)
-
-	if (! requireNamespace("capushe", quietly=TRUE))
-	{
-		warning("'capushe' not available: returning all models")
-		return (models_list)
-	}
-
-	# Get summary "tableauRecap" from models ; TODO: jusqu'à ligne 114 à mon avis là c'est faux :/
-	tableauRecap = t( sapply( models_list, function(models) {
-		llh = do.call(rbind, lapply(models, function(model) model$llh)
-    LLH = llh[-1,1]
-    D = llh[-1,2]
-		c(LLH, D, rep(k, length(model)), 1:length(model))
-	) } ) )
-	if (verbose)
-		print('Model selection')
-  tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
-  tableauRecap = tableauRecap[!is.infinite(tableauRecap[,1]),]
-  data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])
-
-  modSel = capushe::capushe(data, n)
+  
+  # List (index k) of lists (index lambda) of models
+  models_list <-
+    if (ncores_outer > 1)
+      parLapply(cl, kmin:kmax, computeModels)
+  else
+    lapply(kmin:kmax, computeModels)
+  if (ncores_outer > 1)
+    parallel::stopCluster(cl)
+  
+  if (! requireNamespace("capushe", quietly=TRUE))
+  {
+    warning("'capushe' not available: returning all models")
+    return (models_list)
+  }
+  
+  # Get summary "tableauRecap" from models
+  tableauRecap = do.call( rbind, lapply( seq_along(models_list), function(i) {
+    models <- models_list[[i]]
+    #For a collection of models (same k, several lambda):
+    LLH <- sapply( models, function(model) model$llh[1] )
+    k = length(models[[1]]$pi)
+    sumPen = sapply(models, function(model)
+      k*(dim(model$rho)[1]+sum(model$phi[,,1]!=0)+1)-1)
+    data.frame(model=paste(i,".",seq_along(models),sep=""),
+               pen=sumPen/n, complexity=sumPen, contrast=-LLH)
+  } ) )
+  
+  print(tableauRecap)
+  tableauRecap = tableauRecap[which(tableauRecap[,4]!= Inf),]
+  modSel = capushe::capushe(tableauRecap, n)
   indModSel <-
-		if (selecMod == 'DDSE')
-			as.numeric(modSel@DDSE@model)
-		else if (selecMod == 'Djump')
-			as.numeric(modSel@Djump@model)
-		else if (selecMod == 'BIC')
-			modSel@BIC_capushe$model
-		else if (selecMod == 'AIC')
-			modSel@AIC_capushe$model
-  model[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
+    if (selecMod == 'DDSE')
+      as.numeric(modSel@DDSE@model)
+  else if (selecMod == 'Djump')
+    as.numeric(modSel@Djump@model)
+  else if (selecMod == 'BIC')
+    modSel@BIC_capushe$model
+  else if (selecMod == 'AIC')
+    modSel@AIC_capushe$model
+  
+  mod = as.character(tableauRecap[indModSel,1])
+  listMod = as.integer(unlist(strsplit(mod, "[.]")))
+  modelSel = models_list[[listMod[1]]][[listMod[2]]]
+  
+  ##Affectations
+  Gam = matrix(0, ncol = length(modelSel$pi), nrow = n)
+  for (i in 1:n){
+    for (r in 1:length(modelSel$pi)){
+      sqNorm2 = sum( (Y[i,]%*%modelSel$rho[,,r]-X[i,]%*%modelSel$phi[,,r])^2 )
+      Gam[i,r] = modelSel$pi[r] * exp(-0.5*sqNorm2)* det(modelSel$rho[,,r])
+    }
+  }
+  Gam = Gam/rowSums(Gam)
+  modelSel$affec = apply(Gam, 1,which.max)
+  modelSel$proba = Gam
+  
+  if (plot){
+    print(plot_valse(X,Y,modelSel,n))
+  }
+  
+  return(modelSel)
 }