-#' valse
+#' runValse
#'
#' Main function
#'
#' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
#' @param kmin integer, minimum number of clusters, by default = 2
#' @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 rank.min integer, minimum rank in the low rank procedure, by default = 1
+#' @param rank.max integer, maximum rank in the low rank procedure, by default = 5
+#' @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 thresh real, threshold to say a variable is relevant, by default = 1e-8
+#' @param grid_lambda, a vector with regularization parameters if known, by default numeric(0)
+#' @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
+#' @param plot TRUE to plot the selected models after run
#'
-#' @return a list with estimators of parameters
+#' @return
+#' The selected model if enough data are available to estimate it,
+#' or a list of models otherwise.
#'
#' @examples
-#' #TODO: a few examples
+#' n = 50; m = 10; p = 5
+#' beta = array(0, dim=c(p,m,2))
+#' beta[,,1] = 1
+#' beta[,,2] = 2
+#' data = generateXY(n, c(0.4,0.6), rep(0,p), beta, diag(0.5, p), diag(0.5, m))
+#' X = data$X
+#' Y = data$Y
+#' res = runValse(X, Y)
+#' X <- matrix(runif(100), nrow=50)
+#' Y <- matrix(runif(100), nrow=50)
+#' res = runValse(X, Y)
+#'
#' @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)
+runValse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mini = 10,
+ maxi = 50, eps = 1e-04, kmin = 2, kmax = 3, rank.min = 1, rank.max = 5, ncores_outer = 1,
+ ncores_inner = 1, thresh = 1e-08, grid_lambda = numeric(0), size_coll_mod = 10,
+ fast = TRUE, verbose = FALSE, plot = TRUE)
{
- p = dim(X)[2]
- m = dim(Y)[2]
- n = dim(X)[1]
+ n <- nrow(X)
+ p <- ncol(X)
+ m <- ncol(Y)
- tableauRecap = list()
if (verbose)
- print("main loop: over all k and all lambda")
-
- if (ncores_k > 1)
- {
- cl = parallel::makeCluster(ncores_k)
- 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") )
- }
+ print("main loop: over all k and all lambda")
- # Compute model with k components
- computeModel <- function(k)
- {
- if (ncores_k > 1)
- require("valse") #nodes start with an empty environment
+ 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", "rank.min", "rank.max", "ncores_outer", "ncores_inner", "thresh",
+ "size_coll_mod", "verbose", "p", "m"))
+ }
- 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)
+ # Compute models with k components
+ computeModels <- function(k)
+ {
+ if (ncores_outer > 1)
+ require("valse") #nodes start with an empty environment
- # TODO: 100 = magic number
- if (length(grid_lambda)>100)
- grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = 100)]
+ 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, fast)
+ if (length(grid_lambda) == 0)
+ {
+ grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
+ X, Y, 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: 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)
+ 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$gamInit, mini, maxi,
+ gamma, grid_lambda, X, Y, thresh, eps, ncores_inner, fast)
- if (procedure == 'LassoMLE')
- {
+ if (procedure == "LassoMLE") {
if (verbose)
- print('run the procedure Lasso-MLE')
- #compute parameter estimations, with the Maximum Likelihood
- #Estimator, restricted on selected variables.
- model = constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
- maxi, gamma, X, Y, thresh, eps, S$selected)
- llh = matrix(ncol = 2)
- for (l in seq_along(model[[k]]))
- llh = rbind(llh, model[[k]][[l]]$llh)
- LLH = llh[-1,1]
- D = llh[-1,2]
- }
- else
- {
+ print("run the procedure Lasso-MLE")
+ # compute parameter estimations, with the Maximum Likelihood Estimator,
+ # restricted on selected variables.
+ models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit,
+ P$gamInit, mini, maxi, gamma, X, Y, eps, S, ncores_inner, fast, verbose)
+ } else {
if (verbose)
- print('run the procedure Lasso-Rank')
- #compute parameter estimations, with the Low Rank
- #Estimator, restricted on selected variables.
- model = constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
- rank.min, rank.max)
+ print("run the procedure Lasso-Rank")
+ # compute parameter estimations, with the Low Rank Estimator, restricted on
+ # selected variables.
+ models <- constructionModelesLassoRank(S, k, mini, maxi, X, Y, eps, rank.min,
+ rank.max, ncores_inner, fast, verbose)
+ }
+ # warning! Some models are NULL after running selectVariables
+ models <- models[sapply(models, function(cell) !is.null(cell))]
+ models
+ }
- ################################################
- ### Regarder la SUITE
- phi = runProcedure2()$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
- }
+ # 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)
}
- tableauRecap[[k]] = matrix(c(LLH, D, rep(k, length(model[[k]])), 1:length(model[[k]])), ncol = 4))
+ if (ncores_outer > 1)
+ parallel::stopCluster(cl)
+
+ if (!requireNamespace("capushe", quietly = TRUE))
+ {
+ warning("'capushe' not available: returning all models")
+ return(models_list)
}
- model <-
- if (ncores_k > 1)
- parLapply(cl, kmin:kmax, computeModel)
- else
- lapply(kmin:kmax, computeModel)
- if (ncores_k > 1)
- parallel::stopCluster(cl)
+ # 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)
+ }))
+ tableauRecap <- tableauRecap[which(tableauRecap[, 4] != Inf), ]
+ if (verbose)
+ print(tableauRecap)
- if (verbose)
- print('Model selection')
- tableauRecap = do.call( rbind, tableaurecap ) #stack list cells into a matrix
- tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
- tableauRecap = tableauRecap[(tableauRecap[,1])!=Inf,]
- data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])
+ if (nrow(tableauRecap) > 10) {
+ 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
+ }
+ listMod <- as.integer(unlist(strsplit(as.character(indModSel), "[.]")))
+ modelSel <- models_list[[listMod[1]]][[listMod[2]]]
+ modelSel$models <- tableauRecap
- require(capushe)
- modSel = capushe(data, n)
- indModSel <-
- if (selecMod == 'DDSE')
- as.numeric(modSel@DDSE@model)
- else if (selecMod == 'Djump')
- as.numeric(modSel@Djump@model)
- else if (selecMod == 'BIC')
- modSel@BIC_capushe$model
- else if (selecMod == 'AIC')
- modSel@AIC_capushe$model
- model[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
+ if (plot)
+ print(plot_valse(X, Y, modelSel))
+ return(modelSel)
+ }
+ tableauRecap
}