#' constructionModelesLassoMLE
#'
-#' TODO: description
+#' Construct a collection of models with the Lasso-MLE procedure.
#'
-#' @param ...
+#' @param phiInit an initialization for phi, get by initSmallEM.R
+#' @param rhoInit an initialization for rho, get by initSmallEM.R
+#' @param piInit an initialization for pi, get by initSmallEM.R
+#' @param gamInit an initialization for gam, get by initSmallEM.R
+#' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
+#' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
+#' @param gamma integer for the power in the penaly, by default = 1
+#' @param X matrix of covariates (of size n*p)
+#' @param Y matrix of responses (of size n*m)
+#' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
+#' @param S output of selectVariables.R
+#' @param ncores Number of cores, by default = 3
+#' @param fast TRUE to use compiled C code, FALSE for R code only
+#' @param verbose TRUE to show some execution traces
#'
-#' @return ...
+#' @return a list with several models, defined by phi, rho, pi, llh
#'
-#' export
-constructionModelesLassoMLE = function(phiInit, rhoInit, piInit, gamInit, mini, maxi,
- gamma, X, Y, seuil, tau, selected, ncores=3, verbose=FALSE)
+#' @export
+constructionModelesLassoMLE <- function(phiInit, rhoInit, piInit, gamInit, mini,
+ maxi, gamma, X, Y, eps, S, ncores = 3, fast, verbose)
{
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") )
- }
+ {
+ cl <- parallel::makeCluster(ncores, outfile = "")
+ parallel::clusterExport(cl, envir = environment(), varlist = c("phiInit",
+ "rhoInit", "gamInit", "mini", "maxi", "gamma", "X", "Y", "eps", "S",
+ "ncores", "fast", "verbose"))
+ }
- # Individual model computation
- computeAtLambda <- function(lambda)
- {
- if (ncores > 1)
- require("valse") #// nodes start with an ampty environment
+ # 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))
+ print(paste("Computations for lambda=", lambda))
- n = dim(X)[1]
- p = dim(phiInit)[1]
- m = dim(phiInit)[2]
- k = dim(phiInit)[3]
+ n <- nrow(X)
+ p <- ncol(X)
+ m <- ncol(Y)
+ k <- length(piInit)
+ sel.lambda <- S[[lambda]]$selected
+ # col.sel = which(colSums(sel.lambda)!=0) #if boolean matrix
+ col.sel <- which(sapply(sel.lambda, length) > 0) #if list of selected vars
+ if (length(col.sel) == 0)
+ return(NULL)
- sel.lambda = selected[[lambda]]
-# col.sel = which(colSums(sel.lambda)!=0) #if boolean matrix
- col.sel <- which( sapply(sel.lambda,length) > 0 ) #if list of selected vars
+ # lambda == 0 because we compute the EMV: no penalization here
+ res <- EMGLLF(array(phiInit,dim=c(p,m,k))[col.sel, , ], rhoInit, piInit, gamInit,
+ mini, maxi, gamma, 0, as.matrix(X[, col.sel]), Y, eps, fast)
- if (length(col.sel) == 0)
- return (NULL)
+ # Eval dimension from the result + selected
+ phiLambda2 <- res$phi
+ rhoLambda <- res$rho
+ piLambda <- res$pi
+ phiLambda <- array(0, dim = c(p, m, k))
+ for (j in seq_along(col.sel))
+ phiLambda[col.sel[j], sel.lambda[[j]], ] <- phiLambda2[j, sel.lambda[[j]], ]
+ dimension <- length(unlist(sel.lambda))
- # 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,,]
+ ## Affectations
+ Gam <- matrix(0, ncol = length(piLambda), nrow = n)
+ for (i in 1:n)
+ {
+ for (r in 1:length(piLambda))
+ {
+ sqNorm2 <- sum((Y[i, ] %*% rhoLambda[, , r] - X[i, ] %*% phiLambda[, , r])^2)
+ Gam[i, r] <- piLambda[r] * exp(-0.5 * sqNorm2) * det(rhoLambda[, , r])
+ }
+ }
+ Gam2 <- Gam/rowSums(Gam)
+ affec <- apply(Gam2, 1, which.max)
+ proba <- Gam2
+ LLH <- c(sum(log(apply(Gam,1,sum))), (dimension + m + 1) * k - 1)
+ # ## Computation of the loglikelihood
+ # # Precompute det(rhoLambda[,,r]) for r in 1...k
+ # detRho <- sapply(1:k, function(r) gdet(rhoLambda[, , r]))
+ # sumLogLLH <- 0
+ # for (i in 1:n)
+ # {
+ # # Update gam[,]; use log to avoid numerical problems
+ # logGam <- sapply(1:k, function(r) {
+ # log(piLambda[r]) + log(detRho[r]) - 0.5 *
+ # sum((Y[i, ] %*% rhoLambda[, , r] - X[i, ] %*% phiLambda[, , r])^2)
+ # })
+ #
+ # #logGam <- logGam - max(logGam) #adjust without changing proportions -> change the LLH
+ # gam <- exp(logGam)
+ # norm_fact <- sum(gam)
+ # sumLogLLH <- sumLogLLH + log(norm_fact) - m/2* log(2 * base::pi)
+ # }
+ #llhLambda <- c(-sumLogLLH/n, (dimension + m + 1) * k - 1)
+ list(phi = phiLambda, rho = rhoLambda, pi = piLambda, llh = LLH, affec = affec, proba = proba)
+ }
- 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)
- }
+ # For each lambda, computation of the parameters
+ out <-
+ if (ncores > 1) {
+ parLapply(cl, 1:length(S), computeAtLambda)
+ } else {
+ lapply(1:length(S), computeAtLambda)
+ }
- # 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
- out =
- if (ncores > 1)
- parLapply(cl, seq_along(glambda), computeAtLambda)
- else
- lapply(seq_along(glambda), computeAtLambda)
-
- if (ncores > 1)
+ if (ncores > 1)
parallel::stopCluster(cl)
- out
+ out
}