X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2Fmain.R;h=de473f7943e2098f0a48fd3e77e97c026af004e5;hp=ab25daf5fa210933b5516a0fa875e06b935f2808;hb=aa480ac1fef50618978307a4df2cf9da1e285abc;hpb=0eb161e3f3d018bce7d98fc85622d14910f89d43 diff --git a/pkg/R/main.R b/pkg/R/main.R index ab25daf..de473f7 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 #' @@ -21,8 +26,8 @@ #' #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) { p = dim(X)[2] m = dim(Y)[2] @@ -33,10 +38,10 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, 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 @@ -52,26 +57,25 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=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: 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 { @@ -80,18 +84,20 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, #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) if (! requireNamespace("capushe", quietly=TRUE)) @@ -100,18 +106,19 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, 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 ) + k == length(models[[1]]$pi) + # TODO: chuis pas sûr du tout des lignes suivantes... + # J'ai l'impression qu'il manque des infos + sumPen = sapply( models, function(model) + sum( model$pi^gamma * sapply(1:k, function(r) sum(abs(model$phi[,,r]))) ) ) + data.frame(model=paste(i,".",seq_along(models),sep=""), + pen=sumPen/1000, complexity=sumPen, contrast=LLH) + } ) ) modSel = capushe::capushe(data, n) indModSel <- @@ -123,5 +130,6 @@ valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, modSel@BIC_capushe$model else if (selecMod == 'AIC') modSel@AIC_capushe$model - model[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]] + + models_list[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]] }