pkg/R/selectVariables.R

   1 #' selectVariables
   2 #'
   3 #' It is a function which constructs, for a given lambda, the sets for each cluster 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 an initial estimator for pi (size : k)
   8 #' @param gamInit an initial estimator for gamma
   9 #' @param mini  minimum number of iterations in EM algorithm
  10 #' @param maxi  maximum number of iterations in EM algorithm
  11 #' @param gamma  power in the penalty
  12 #' @param glambda grid of regularization parameters
  13 #' @param X    matrix of regressors
  14 #' @param Y    matrix of responses
  15 #' @param thresh real, threshold to say a variable is relevant, by default = 1e-8
  16 #' @param eps   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 #' @export
  22 selectVariables <- function(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma,
  23   glambda, X, Y, thresh = 1e-08, eps, ncores = 3, fast)
  24 {
  25   if (ncores > 1) {
  26     cl <- parallel::makeCluster(ncores, outfile = "")
  27     parallel::clusterExport(cl = cl, varlist = c("phiInit", "rhoInit", "gamInit",
  28       "mini", "maxi", "glambda", "X", "Y", "thresh", "eps"), envir = environment())
  29   }
  30
  31   # Computation for a fixed lambda
  32   computeCoefs <- function(lambda)
  33   {
  34     params <- EMGLLF(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, lambda,
  35       X, Y, eps, fast)
  36
  37     p <- ncol(X)
  38     m <- ncol(Y)
  39
  40     # selectedVariables: list where element j contains vector of selected variables
  41     # in [1,m]
  42     selectedVariables <- lapply(1:p, function(j) {
  43       # from boolean matrix mxk of selected variables obtain the corresponding boolean
  44       # m-vector, and finally return the corresponding indices
  45       if (m>1) {
  46         seq_len(m)[apply(abs(params$phi[j, , ]) > thresh, 1, any)]
  47       } else {
  48         if (any(params$phi[j, , ] > thresh))
  49           1
  50         else
  51           numeric(0)
  52       }
  53     })
  54
  55     list(selected = selectedVariables, Rho = params$rho, Pi = params$pi)
  56   }
  57
  58   # For each lambda in the grid, we compute the coefficients
  59   out <-
  60     if (ncores > 1) {
  61       parLapply(cl, glambda, computeCoefs)
  62     } else {
  63       lapply(glambda, computeCoefs)
  64     }
  65   if (ncores > 1)
  66     parallel::stopCluster(cl)
  67
  68   print(out)
  69   # Suppress models which are computed twice
  70   # sha1_array <- lapply(out, digest::sha1) out[ duplicated(sha1_array) ]
  71   selec <- lapply(out, function(model) model$selected)
  72   ind_dup <- duplicated(selec)
  73   ind_uniq <- which(!ind_dup)
  74   out2 <- list()
  75   for (l in 1:length(ind_uniq))
  76     out2[[l]] <- out[[ind_uniq[l]]]
  77   out2
  78 }