pkg/R/selectVariables.R

   1 #' selectVariables
   2 #'
   3 #' It is a function which construct, for a given lambda, the sets of relevant variables.
   4 #'
   5 #' @param phiInit an initial estimator for phi (size: p*m*k)
   6 #' @param rhoInit an initial estimator for rho (size: m*m*k)
   7 #' @param piInit\tan initial estimator for pi (size : k)
   8 #' @param gamInit an initial estimator for gamma
   9 #' @param mini\t\tminimum number of iterations in EM algorithm
  10 #' @param maxi\t\tmaximum number of iterations in EM algorithm
  11 #' @param gamma\t power in the penalty
  12 #' @param glambda grid of regularization parameters
  13 #' @param X\t\t\t matrix of regressors
  14 #' @param Y\t\t\t matrix of responses
  15 #' @param thresh real, threshold to say a variable is relevant, by default = 1e-8
  16 #' @param eps\t\t threshold to say that EM algorithm has converged
  17 #' @param ncores Number or cores for parallel execution (1 to disable)
  18 #'
  19 #' @return a list of outputs, for each lambda in grid: selected,Rho,Pi
  20 #'
  21 #' @examples TODO
  22 #'
  23 #' @export
  24 #'
  25 selectVariables <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma,
  26   glambda, X, Y, thresh = 1e-08, eps, ncores = 3, fast = TRUE)
  27 {
  28   if (ncores > 1) {
  29     cl <- parallel::makeCluster(ncores, outfile = "")
  30     parallel::clusterExport(cl = cl, varlist = c("phiInit", "rhoInit", "gamInit",
  31       "mini", "maxi", "glambda", "X", "Y", "thresh", "eps"), envir = environment())
  32   }
  33
  34   # Computation for a fixed lambda
  35   computeCoefs <- function(lambda)
  36   {
  37     params <- EMGLLF(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
  38       X, Y, eps, fast)
  39
  40     p <- dim(phiInit)[1]
  41     m <- dim(phiInit)[2]
  42
  43     # selectedVariables: list where element j contains vector of selected variables
  44     # in [1,m]
  45     selectedVariables <- lapply(1:p, function(j) {
  46       # from boolean matrix mxk of selected variables obtain the corresponding boolean
  47       # m-vector, and finally return the corresponding indices
  48       seq_len(m)[apply(abs(params$phi[j, , ]) > thresh, 1, any)]
  49     })
  50
  51     list(selected = selectedVariables, Rho = params$rho, Pi = params$pi)
  52   }
  53
  54   # For each lambda in the grid, we compute the coefficients
  55   out <- if (ncores > 1)
  56     parLapply(cl, glambda, computeCoefs) else lapply(glambda, computeCoefs)
  57   if (ncores > 1)
  58     parallel::stopCluster(cl)
  59   # Suppress models which are computed twice En fait, ca ca fait la comparaison de
  60   # tous les parametres On veut juste supprimer ceux qui ont les memes variables
  61   # sélectionnées sha1_array <- lapply(out, digest::sha1) out[
  62   # duplicated(sha1_array) ]
  63   selec <- lapply(out, function(model) model$selected)
  64   ind_dup <- duplicated(selec)
  65   ind_uniq <- which(!ind_dup)
  66   out2 <- list()
  67   for (l in 1:length(ind_uniq))
  68     out2[[l]] <- out[[ind_uniq[l]]]
  69   out2
  70 }