#' @examples
#' #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_k=1, ncores_lambda=3, verbose=FALSE)
+valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, maxi=50,
+ 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]
m = dim(Y)[2]
n = dim(X)[1]
- tableauRecap = list()
if (verbose)
print("main loop: over all k and all lambda")
- if (ncores_k > 1)
+ if (ncores_outer > 1)
{
- cl = parallel::makeCluster(ncores_k)
+ 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_k","ncores_lambda","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_k > 1)
+ 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)]
+ 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_lambda)
-
+ #from the grid: S$selected corresponding to selected variables
+ S = selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma,
+ grid_lambda, X, Y, 1e-8, eps, ncores_inner) #TODO: 1e-8 as arg?! eps?
+
if (procedure == 'LassoMLE')
{
if (verbose)
print('run the procedure Lasso-MLE')
#compute parameter estimations, with the Maximum Likelihood
#Estimator, restricted on selected variables.
- model = constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
- maxi, gamma, X, Y, thresh, eps, S$selected)
- llh = matrix(ncol = 2)
- for (l in seq_along(model[[k]]))
- llh = rbind(llh, model[[k]][[l]]$llh)
- LLH = llh[-1,1]
- D = llh[-1,2]
+ models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
+ mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, artefact = 1e3, verbose)
}
else
{
print('run the procedure Lasso-Rank')
#compute parameter estimations, with the Low Rank
#Estimator, restricted on selected variables.
- model = constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
- rank.min, rank.max)
-
- ################################################
- ### Regarder la SUITE
- phi = runProcedure2()$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, verbose)
}
- tableauRecap[[k]] = matrix(c(LLH, D, rep(k, length(model[[k]])), 1:length(model[[k]])), ncol = 4))
+ #attention certains modeles sont NULL après selectVariables
+ models = models[sapply(models, function(cell) !is.null(cell))]
+ models
}
- model <-
- 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 (verbose)
- print('Model selection')
- tableauRecap = do.call( rbind, tableaurecap ) #stack list cells into a matrix
- tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
+ 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( models_list, function(models) {
+ #Pour un groupe de modeles (même k, différents lambda):
+ llh = matrix(ncol = 2)
+ for (l in seq_along(models))
+ llh = rbind(llh, models[[l]]$llh)
+ LLH = llh[-1,1]
+ D = llh[-1,2]
+ k = length(models[[1]]$pi)
+ cbind(LLH, D, rep(k, length(models)), 1:length(models))
+ } ) )
+ 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(data, 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]]]
+ models_list[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
}
projects / valse.git / blobdiff