#'
#' export
constructionModelesLassoMLE = function(phiInit, rhoInit, piInit, gamInit, mini, maxi,
- gamma, X, Y, seuil, tau, selected, ncores=3, verbose=FALSE)
+ gamma, X, Y, thresh, tau, S, ncores=3, artefact = 1e3, verbose=FALSE)
{
if (ncores > 1)
- {
+ {
cl = parallel::makeCluster(ncores)
parallel::clusterExport( cl, envir=environment(),
- varlist=c("phiInit","rhoInit","gamInit","mini","maxi","gamma","X","Y","seuil",
- "tau","selected","ncores","verbose") )
- }
-
- # Individual model computation
- computeAtLambda <- function(lambda)
- {
- if (ncores > 1)
- require("valse") #// nodes start with an ampty environment
-
+ varlist=c("phiInit","rhoInit","gamInit","mini","maxi","gamma","X","Y","thresh",
+ "tau","S","ncores","verbose") )
+ }
+
+ # Individual model computation
+ computeAtLambda <- function(lambda)
+ {
+ if (ncores > 1)
+ require("valse") #// nodes start with an empty environment
+
if (verbose)
- print(paste("Computations for lambda=",lambda))
-
- n = dim(X)[1]
- p = dim(phiInit)[1]
- m = dim(phiInit)[2]
- k = dim(phiInit)[3]
-
- sel.lambda = selected[[lambda]]
-# col.sel = which(colSums(sel.lambda)!=0) #if boolean matrix
- col.sel <- which( sapply(sel.lambda,length) > 0 ) #if list of selected vars
-
- if (length(col.sel) == 0)
- return (NULL)
-
- # lambda == 0 because we compute the EMV: no penalization here
- res = EMGLLF(phiInit[col.sel,,],rhoInit,piInit,gamInit,mini,maxi,gamma,0,
- X[,col.sel],Y,tau)
-
- # Eval dimension from the result + selected
- phiLambda2 = res_EM$phi
- rhoLambda = res_EM$rho
- piLambda = res_EM$pi
- phiLambda = array(0, dim = c(p,m,k))
- for (j in seq_along(col.sel))
- phiLambda[col.sel[j],,] = phiLambda2[j,,]
-
- dimension = 0
- for (j in 1:p)
- {
- b = setdiff(1:m, sel.lambda[,j])
- if (length(b) > 0)
- phiLambda[j,b,] = 0.0
- dimension = dimension + sum(sel.lambda[,j]!=0)
- }
-
- # on veut calculer la vraisemblance avec toutes nos estimations
- densite = vector("double",n)
- for (r in 1:k)
- {
- delta = Y%*%rhoLambda[,,r] - (X[, col.sel]%*%phiLambda[col.sel,,r])
- densite = densite + piLambda[r] *
- det(rhoLambda[,,r])/(sqrt(2*base::pi))^m * exp(-tcrossprod(delta)/2.0)
- }
- llhLambda = c( sum(log(densite)), (dimension+m+1)*k-1 )
- list("phi"= phiLambda, "rho"= rhoLambda, "pi"= piLambda, "llh" = llhLambda)
- }
-
- #Pour chaque lambda de la grille, on calcule les coefficients
+ print(paste("Computations for lambda=",lambda))
+
+ n = dim(X)[1]
+ p = dim(phiInit)[1]
+ m = dim(phiInit)[2]
+ k = dim(phiInit)[3]
+
+ sel.lambda = S[[lambda]]$selected
+ # col.sel = which(colSums(sel.lambda)!=0) #if boolean matrix
+ col.sel <- which( sapply(sel.lambda,length) > 0 ) #if list of selected vars
+
+ if (length(col.sel) == 0)
+ {return (NULL)} else {
+
+ # lambda == 0 because we compute the EMV: no penalization here
+ res_EM = EMGLLF(phiInit[col.sel,,],rhoInit,piInit,gamInit,mini,maxi,gamma,0,
+ X[,col.sel],Y,tau)
+
+ # Eval dimension from the result + selected
+ phiLambda2 = res_EM$phi
+ rhoLambda = res_EM$rho
+ piLambda = res_EM$pi
+ phiLambda = array(0, dim = c(p,m,k))
+ for (j in seq_along(col.sel))
+ phiLambda[col.sel[j],,] = phiLambda2[j,,]
+
+ dimension = 0
+ for (j in 1:p)
+ {
+ b = setdiff(1:m, sel.lambda[[j]])## je confonds un peu ligne et colonne : est-ce dans le bon sens ?
+ ## moi pour la dimension, j'aurai juste mis length(unlist(sel.lambda)) mais je sais pas si c'est rapide
+ if (length(b) > 0)
+ phiLambda[j,b,] = 0.0
+ dimension = dimension + sum(sel.lambda[[j]]!=0)
+ }
+
+ # Computation of the loglikelihood
+ densite = vector("double",n)
+ for (r in 1:k)
+ {
+ delta = (Y%*%rhoLambda[,,r] - (X[, col.sel]%*%phiLambda[col.sel,,r]))/artefact
+ print(max(delta))
+ densite = densite + piLambda[r] *
+ det(rhoLambda[,,r])/(sqrt(2*base::pi))^m * exp(-tcrossprod(delta)/2.0)
+ }
+ llhLambda = c( sum(artefact^2 * log(densite)), (dimension+m+1)*k-1 )
+ list("phi"= phiLambda, "rho"= rhoLambda, "pi"= piLambda, "llh" = llhLambda)
+ }
+ }
+
+ # For each lambda, computation of the parameters
out =
- if (ncores > 1)
- parLapply(cl, glambda, computeAtLambda)
- else
- lapply(glambda, computeAtLambda)
-
- if (ncores > 1)
+ if (ncores > 1)
+ parLapply(cl, 1:length(S), computeAtLambda)
+ else
+ lapply(1:length(S), computeAtLambda)
+
+ if (ncores > 1)
parallel::stopCluster(cl)
-
- out
+
+ out
}
#' #TODO: a few examples
#' @export
valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, maxi=50,
- eps=1e-4, kmin=2, kmax=2, rang.min=1, rang.max=10, ncores_outer=1, ncores_inner=3,
+ eps=1e-4, kmin=2, kmax=4, rang.min=1, rang.max=10, ncores_outer=1, ncores_inner=1, size_coll_mod = 50,
verbose=FALSE)
{
p = dim(X)[2]
grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, X, Y,
gamma, mini, maxi, eps)
# TODO: 100 = magic number
- if (length(grid_lambda)>100)
- grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = 100)]
+ if (length(grid_lambda)>size_coll_mod)
+ grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
if (verbose)
print("Compute relevant parameters")
#from the grid: S$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?
-
+
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$gamInit, mini,
+ maxi, gamma, X, Y, thresh, eps, S, ncores_inner, artefact = 1e3, verbose)
}
else
{
# List (index k) of lists (index lambda) of models
models_list <-
- #if (ncores_k > 1)
if (ncores_outer > 1)
parLapply(cl, kmin:kmax, computeModels)
else
lapply(kmin:kmax, computeModels)
- #if (ncores_k > 1)
if (ncores_outer > 1)
parallel::stopCluster(cl)
}
# Get summary "tableauRecap" from models ; TODO: jusqu'à ligne 114 à mon avis là c'est faux :/
- tableauRecap = t( sapply( models_list, function(models) {
+ tableauRecap = sapply( models_list, function(models) {
llh = do.call(rbind, lapply(models, function(model) model$llh))
LLH = llh[-1,1]
D = llh[-1,2]
- c(LLH, D, rep(k, length(model)), 1:length(model))
- } ))
+ c(LLH, D, rep(k, length(LLH)), 1:length(LLH))
+ })
+ tableauRecap
if (verbose)
print('Model selection')
tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
modSel@BIC_capushe$model
else if (selecMod == 'AIC')
modSel@AIC_capushe$model
- model[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
+ models_list[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
}
projects / valse.git / commitdiff