pkg/R/main.R

   1 #' valse
   2 #'
   3 #' Main function
   4 #'
   5 #' @param X matrix of covariates (of size n*p)
   6 #' @param Y matrix of responses (of size n*m)
   7 #' @param procedure among 'LassoMLE' or 'LassoRank'
   8 #' @param selecMod method to select a model among 'DDSE', 'DJump', 'BIC' or 'AIC'
   9 #' @param gamma integer for the power in the penaly, by default = 1
  10 #' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
  11 #' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
  12 #' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
  13 #' @param kmin integer, minimum number of clusters, by default = 2
  14 #' @param kmax integer, maximum number of clusters, by default = 10
  15 #' @param rang.min integer, minimum rank in the low rank procedure, by default = 1
  16 #' @param rang.max integer, maximum rank in the
  17 #'
  18 #' @return a list with estimators of parameters
  19 #'
  20 #' @examples
  21 #' #TODO: a few examples
  22 #' @export
  23 valse = function(X,Y,procedure = 'LassoMLE',selecMod = 'DDSE',gamma = 1,mini = 10,
  24                  maxi = 50,eps = 1e-4,kmin = 2,kmax = 2,
  25                  rang.min = 1,rang.max = 10, ncores_k=1, ncores_lambda=3, verbose=FALSE)
  26 {
  27   p = dim(X)[2]
  28   m = dim(Y)[2]
  29   n = dim(X)[1]
  30
  31   tableauRecap = list()
  32   if (verbose)
  33         print("main loop: over all k and all lambda")
  34
  35     if (ncores_k > 1)
  36     {
  37         cl = parallel::makeCluster(ncores_k)
  38         parallel::clusterExport( cl=cl, envir=environment(), varlist=c("X","Y","procedure",
  39             "selecMod","gamma","mini","maxi","eps","kmin","kmax","rang.min","rang.max",
  40             "ncores_k","ncores_lambda","verbose","p","m","k","tableauRecap") )
  41     }
  42
  43     # Compute model with k components
  44     computeModel <- function(k)
  45     {
  46         if (ncores_k > 1)
  47             require("valse") #nodes start with an empty environment
  48
  49         if (verbose)
  50             print(paste("Parameters initialization for k =",k))
  51     #smallEM initializes parameters by k-means and regression model in each component,
  52     #doing this 20 times, and keeping the values maximizing the likelihood after 10
  53     #iterations of the EM algorithm.
  54     P = initSmallEM(k, X, Y)
  55     grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, X, Y,
  56             gamma, mini, maxi, eps)
  57
  58         # TODO: 100 = magic number
  59     if (length(grid_lambda)>100)
  60       grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = 100)]
  61
  62         if (verbose)
  63             print("Compute relevant parameters")
  64     #select variables according to each regularization parameter
  65     #from the grid: A1 corresponding to selected variables, and
  66     #A2 corresponding to unselected variables.
  67     S = selectVariables(P$phiInit,P$rhoInit,P$piInit,P$gamInit,mini,maxi,gamma,
  68             grid_lambda,X,Y,1e-8,eps,ncores_lambda)
  69
  70     if (procedure == 'LassoMLE')
  71         {
  72       if (verbose)
  73                 print('run the procedure Lasso-MLE')
  74       #compute parameter estimations, with the Maximum Likelihood
  75       #Estimator, restricted on selected variables.
  76       model = constructionModelesLassoMLE(phiInit, rhoInit, piInit, gamInit, mini,
  77                 maxi, gamma, X, Y, thresh, eps, S$selected)
  78       llh = matrix(ncol = 2)
  79       for (l in seq_along(model[[k]]))
  80         llh = rbind(llh, model[[k]][[l]]$llh)
  81       LLH = llh[-1,1]
  82       D = llh[-1,2]
  83     }
  84         else
  85         {
  86       if (verbose)
  87                 print('run the procedure Lasso-Rank')
  88       #compute parameter estimations, with the Low Rank
  89       #Estimator, restricted on selected variables.
  90       model = constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
  91                 rank.min, rank.max)
  92
  93       ################################################
  94       ### Regarder la SUITE
  95       phi = runProcedure2()$phi
  96       Phi2 = Phi
  97       if (dim(Phi2)[1] == 0)
  98         Phi[, , 1:k,] <- phi
  99       else
 100       {
 101         Phi <- array(0, dim = c(p, m, kmax, dim(Phi2)[4] + dim(phi)[4]))
 102         Phi[, , 1:(dim(Phi2)[3]), 1:(dim(Phi2)[4])] <<- Phi2
 103         Phi[, , 1:k,-(1:(dim(Phi2)[4]))] <<- phi
 104       }
 105     }
 106     tableauRecap[[k]] = matrix(c(LLH, D, rep(k, length(model[[k]])), 1:length(model[[k]])), ncol = 4))
 107   }
 108
 109     model <-
 110         if (ncores_k > 1)
 111             parLapply(cl, kmin:kmax, computeModel)
 112         else
 113             lapply(kmin:kmax, computeModel)
 114     if (ncores_k > 1)
 115         parallel::stopCluster(cl)
 116
 117     if (verbose)
 118         print('Model selection')
 119     tableauRecap = do.call( rbind, tableaurecap ) #stack list cells into a matrix
 120   tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
 121   tableauRecap = tableauRecap[(tableauRecap[,1])!=Inf,]
 122   data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])
 123
 124     require(capushe)
 125   modSel = capushe(data, n)
 126   indModSel <-
 127         if (selecMod == 'DDSE')
 128             as.numeric(modSel@DDSE@model)
 129         else if (selecMod == 'Djump')
 130             as.numeric(modSel@Djump@model)
 131         else if (selecMod == 'BIC')
 132             modSel@BIC_capushe$model
 133         else if (selecMod == 'AIC')
 134             modSel@AIC_capushe$model
 135   model[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
 136 }