attempt to fix ugly code...

[valse.git] / pkg / R / selectVariables.R

#' selectVariables 
#'
#' It is a function which construct, for a given lambda, the sets of relevant variables.
#'
#' @param phiInit an initial estimator for phi (size: p*m*k)
#' @param rhoInit an initial estimator for rho (size: m*m*k)
#' @param piInit\tan initial estimator for pi (size : k)
#' @param gamInit an initial estimator for gamma
#' @param mini\t\tminimum number of iterations in EM algorithm
#' @param maxi\t\tmaximum number of iterations in EM algorithm
#' @param gamma\t power in the penalty
#' @param glambda grid of regularization parameters
#' @param X\t\t\t matrix of regressors
#' @param Y\t\t\t matrix of responses
#' @param thresh real, threshold to say a variable is relevant, by default = 1e-8
#' @param eps\t\t threshold to say that EM algorithm has converged
#' @param ncores Number or cores for parallel execution (1 to disable)
#'
#' @return a list of outputs, for each lambda in grid: selected,Rho,Pi
#'
#' @examples TODO
#'
#' @export
#'
selectVariables <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, 
  glambda, X, Y, thresh = 1e-08, eps, ncores = 3, fast = TRUE)
  {
  if (ncores > 1)
  {
    cl <- parallel::makeCluster(ncores, outfile = "")
    parallel::clusterExport(cl = cl, varlist = c("phiInit", "rhoInit", "gamInit", 
      "mini", "maxi", "glambda", "X", "Y", "thresh", "eps"), envir = environment())
  }
  
  # Computation for a fixed lambda
  computeCoefs <- function(lambda)
  {
    params <- EMGLLF(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda, 
      X, Y, eps, fast)
    
    p <- dim(phiInit)[1]
    m <- dim(phiInit)[2]
    
    # selectedVariables: list where element j contains vector of selected variables
    # in [1,m]
    selectedVariables <- lapply(1:p, function(j)
    {
      # from boolean matrix mxk of selected variables obtain the corresponding boolean
      # m-vector, and finally return the corresponding indices
      seq_len(m)[apply(abs(params$phi[j, , ]) > thresh, 1, any)]
    })
    
    list(selected = selectedVariables, Rho = params$rho, Pi = params$pi)
  }
  
  # For each lambda in the grid, we compute the coefficients
  out <- if (ncores > 1) 
    parLapply(cl, glambda, computeCoefs) else lapply(glambda, computeCoefs)
  if (ncores > 1) 
    parallel::stopCluster(cl)
  # Suppress models which are computed twice En fait, ca ca fait la comparaison de
  # tous les parametres On veut juste supprimer ceux qui ont les memes variables
  # sélectionnées sha1_array <- lapply(out, digest::sha1) out[
  # duplicated(sha1_array) ]
  selec <- lapply(out, function(model) model$selected)
  ind_dup <- duplicated(selec)
  ind_uniq <- which(!ind_dup)
  out2 <- list()
  for (l in 1:length(ind_uniq))
  {
    out2[[l]] <- out[[ind_uniq[l]]]
  }
  out2
}