X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2Fmain.R;h=72ee724481544b9e9922f57a3c2669a1d5532024;hp=89c4bcdd17004b6165042910a0ddbf2cbfb43a57;hb=fb6e49cb85308c3f99cc98fe955aa7c36839c819;hpb=9fadef2bff80d4b0371962dea4b6de24086f230b diff --git a/pkg/R/main.R b/pkg/R/main.R index 89c4bcd..72ee724 100644 --- a/pkg/R/main.R +++ b/pkg/R/main.R @@ -26,109 +26,111 @@ #' #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=4, rank.min=1, rank.max=10, ncores_outer=1, ncores_inner=1, - size_coll_mod=50, fast=TRUE, verbose=FALSE, plot = TRUE) + eps=1e-4, kmin=2, kmax=2, rank.min=1, rank.max=10, ncores_outer=1, ncores_inner=1, + 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, 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") ) - } - - # 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","rang.min","rang.max", + "ncores_outer","ncores_inner","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, fast) + 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") + + 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$gamInit, mini, maxi, gamma, - grid_lambda, X, Y, 1e-8, eps, ncores_inner, fast) #TODO: 1e-8 as arg?! eps? + grid_lambda, X, Y, 1e-8, eps, ncores_inner, fast) #TODO: 1e-8 as arg?! eps? if (procedure == 'LassoMLE') - { + { if (verbose) - print('run the procedure Lasso-MLE') + print('run the procedure Lasso-MLE') #compute parameter estimations, with the Maximum Likelihood #Estimator, restricted on selected variables. models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit, - mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, fast, verbose) + mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, fast, verbose) } - else - { + else + { if (verbose) - print('run the procedure Lasso-Rank') + print('run the procedure Lasso-Rank') #compute parameter estimations, with the Low Rank #Estimator, restricted on selected variables. models <- constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, S, - rank.min, rank.max, ncores_inner, fast, verbose) + rank.min, rank.max, ncores_inner, fast, verbose) } - #attention certains modeles sont NULL après selectVariables - models = models[sapply(models, function(cell) !is.null(cell))] + #warning! Some models are NULL after running selectVariables + models = models[sapply(models, function(cell) !is.null(cell))] models } - - # List (index k) of lists (index lambda) of models - models_list <- - if (ncores_outer > 1) - parLapply(cl, kmin:kmax, computeModels) - else - lapply(kmin:kmax, computeModels) - if (ncores_outer > 1) - parallel::stopCluster(cl) - - if (! requireNamespace("capushe", quietly=TRUE)) - { - warning("'capushe' not available: returning all models") - return (models_list) - } - - # Get summary "tableauRecap" from models - tableauRecap = do.call( rbind, lapply( seq_along(models_list), function(i) { - models <- models_list[[i]] - #Pour un groupe de modeles (même k, différents lambda): - LLH <- sapply( models, function(model) model$llh[1] ) - k = length(models[[1]]$pi) - sumPen = sapply(models, function(model) - k*(dim(model$rho)[1]+sum(model$phi[,,1]!=0)+1)-1) - data.frame(model=paste(i,".",seq_along(models),sep=""), - pen=sumPen/n, complexity=sumPen, contrast=-LLH) - } ) ) -print(tableauRecap) + + # List (index k) of lists (index lambda) of models + models_list <- + if (ncores_outer > 1) + parLapply(cl, kmin:kmax, computeModels) + else + lapply(kmin:kmax, computeModels) + if (ncores_outer > 1) + parallel::stopCluster(cl) + + if (! requireNamespace("capushe", quietly=TRUE)) + { + warning("'capushe' not available: returning all models") + return (models_list) + } + + # Get summary "tableauRecap" from models + tableauRecap = do.call( rbind, lapply( seq_along(models_list), function(i) { + models <- models_list[[i]] + #For a collection of models (same k, several lambda): + LLH <- sapply( models, function(model) model$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$model - + if (selecMod == 'DDSE') + as.numeric(modSel@DDSE@model) + else if (selecMod == 'Djump') + as.numeric(modSel@Djump@model) + else if (selecMod == 'BIC') + modSel@BIC_capushe$model + else if (selecMod == 'AIC') + modSel@AIC_capushe$model + mod = as.character(tableauRecap[indModSel,1]) listMod = as.integer(unlist(strsplit(mod, "[.]"))) modelSel = models_list[[listMod[1]]][[listMod[2]]] @@ -144,8 +146,8 @@ print(tableauRecap) Gam = Gam/rowSums(Gam) modelSel$affec = apply(Gam, 1,which.max) modelSel$proba = Gam - - if (plot){ + + if (plot){ print(plot_valse(modelSel,n)) }