#' @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
#'
#' #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]
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 models with k components
#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: S$selected corresponding to selected variables
S = selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma,
- grid_lambda, X, Y, 1e-8, eps, ncores_inner) #TODO: 1e-8 as arg?! eps?
-
+ grid_lambda, X, Y, 1e-8, eps, ncores_inner, fast) #TODO: 1e-8 as arg?! eps?
+
if (procedure == 'LassoMLE')
{
if (verbose)
print('run the procedure Lasso-MLE')
#compute parameter estimations, with the Maximum Likelihood
#Estimator, restricted on selected variables.
- models <- constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
- maxi, gamma, X, Y, thresh, eps, S$selected, ncores_inner, verbose)
+ models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
+ mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, artefact=1e3, fast, verbose)
}
else
{
#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)
+ rank.min, rank.max, ncores_inner, fast, verbose)
}
+ #attention certains modeles sont NULL après 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)
if (ncores_outer > 1)
parLapply(cl, kmin:kmax, computeModels)
else
lapply(kmin:kmax, computeModels)
- #if (ncores_k > 1)
if (ncores_outer > 1)
parallel::stopCluster(cl)
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$llh))
- LLH = llh[-1,1]
- D = llh[-1,2]
- c(LLH, D, rep(k, length(model)), 1:length(model))
- } ))
- if (verbose)
- print('Model selection')
- tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
- tableauRecap = tableauRecap[!is.infinite(tableauRecap[,1]),]
- data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])
+ # Get summary "tableauRecap" from models
+ tableauRecap = do.call( rbind, lapply( seq_along(models_list), function(i) {
+ models <- models_list[[i]]
+ #Pour un groupe de modeles (même k, différents lambda):
+ LLH <- sapply( models, function(model) model$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$phi[,,1]!=0)+1)-1)
+ data.frame(model=paste(i,".",seq_along(models),sep=""),
+ pen=sumPen/n, complexity=sumPen, contrast=LLH)
+ } ) )
- modSel = capushe::capushe(data, n)
+ modSel = capushe::capushe(tableauRecap, n)
indModSel <-
if (selecMod == 'DDSE')
as.numeric(modSel@DDSE@model)
modSel@BIC_capushe$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]]]
+
}
projects / valse.git / blobdiff