fix/improve selectVariables.R
[valse.git] / 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 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 thres threshold to consider a coefficient to be equal to 0
16 #' @param tau threshold to say that EM algorithm has converged
17 #'
18 #' @return a list of outputs, for each lambda in grid: selected,Rho,Pi
19 #'
20 #' @examples TODO
21 #'
22 #' @export
23 #'
24 selectVariables = function(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,glambda,
25 X,Y,thresh,tau, ncores=1) #ncores==1 ==> no //
26 {
27 if (ncores > 1)
28 {
29 cl = parallel::makeCluster(ncores)
30 parallel::clusterExport(cl=cl,
31 varlist=c("phiInit","rhoInit","gamInit","mini","maxi","glambda","X","Y","thresh","tau"),
32 envir=environment())
33 }
34
35 # Calcul pour un lambda
36 computeCoefs <-function(lambda)
37 {
38 params = EMGLLF(phiInit,rhoInit,piInit,gamInit,mini,maxi,gamma,lambda,X,Y,tau)
39
40 p = dim(phiInit)[1]
41 m = dim(phiInit)[2]
42
43 #selectedVariables: list where element j contains vector of selected variables in [1,m]
44 selectedVariables = lapply(1:p, function(j) {
45 #from boolean matrix mxk of selected variables obtain the corresponding boolean m-vector,
46 #and finally return the corresponding indices
47 seq_len(m)[ apply( abs(params$phi[j,,]) > thresh, 1, any ) ]
48 })
49
50 list("selected"=selectedVariables,"Rho"=params$rho,"Pi"=params$pi)
51 }
52
53 # Pour chaque lambda de la grille, on calcule les coefficients
54 out <-
55 if (ncores > 1)
56 parLapply(cl, glambda, computeCoefs)
57 else lapply(glambda, computeCoefs)
58 if (ncores > 1)
59 parallel::stopCluster(cl)
60
61 # Suppression doublons
62 sha1_array <- lapply(out, digest::sha1)
63 out[ !duplicated(sha1_array) ]
64
65 out
66 }