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, maxi=50,
  24     eps=1e-4, kmin=2, kmax=4, rang.min=1, rang.max=10, ncores_outer=1, ncores_inner=1, size_coll_mod = 50,
  25     verbose=FALSE)
  26 {
  27   p = dim(X)[2]
  28   m = dim(Y)[2]
  29   n = dim(X)[1]
  30
  31   if (verbose)
  32         print("main loop: over all k and all lambda")
  33
  34     if (ncores_outer > 1)
  35     {
  36         cl = parallel::makeCluster(ncores_outer, outfile='')
  37         parallel::clusterExport( cl=cl, envir=environment(), varlist=c("X","Y","procedure",
  38             "selecMod","gamma","mini","maxi","eps","kmin","kmax","rang.min","rang.max",
  39             "ncores_outer","ncores_inner","verbose","p","m") )
  40     }
  41
  42     # Compute models with k components
  43     computeModels <- function(k)
  44     {
  45         if (ncores_outer > 1)
  46             require("valse") #nodes start with an empty environment
  47
  48         if (verbose)
  49             print(paste("Parameters initialization for k =",k))
  50         #smallEM initializes parameters by k-means and regression model in each component,
  51     #doing this 20 times, and keeping the values maximizing the likelihood after 10
  52     #iterations of the EM algorithm.
  53     P = initSmallEM(k, X, Y)
  54     grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, X, Y,
  55             gamma, mini, maxi, eps)
  56     if (length(grid_lambda)>size_coll_mod)
  57       grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
  58
  59         if (verbose)
  60             print("Compute relevant parameters")
  61     #select variables according to each regularization parameter
  62     #from the grid: S$selected corresponding to selected variables
  63     S = selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma,
  64             grid_lambda, X, Y, 1e-8, eps, ncores_inner) #TODO: 1e-8 as arg?! eps?
  65
  66     if (procedure == 'LassoMLE')
  67         {
  68       if (verbose)
  69                 print('run the procedure Lasso-MLE')
  70       #compute parameter estimations, with the Maximum Likelihood
  71       #Estimator, restricted on selected variables.
  72       models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
  73                 mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, artefact = 1e3, verbose)
  74     }
  75         else
  76         {
  77       if (verbose)
  78                 print('run the procedure Lasso-Rank')
  79       #compute parameter estimations, with the Low Rank
  80       #Estimator, restricted on selected variables.
  81       models <- constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, A1,
  82                 rank.min, rank.max, ncores_inner, verbose)
  83     }
  84         #attention certains modeles sont NULL après selectVariables
  85         models = models[sapply(models, function(cell) !is.null(cell))]
  86     models
  87   }
  88
  89     # List (index k) of lists (index lambda) of models
  90     models_list <-
  91       if (ncores_outer > 1)
  92             parLapply(cl, kmin:kmax, computeModels)
  93         else
  94             lapply(kmin:kmax, computeModels)
  95     if (ncores_outer > 1)
  96         parallel::stopCluster(cl)
  97
  98     if (! requireNamespace("capushe", quietly=TRUE))
  99     {
 100         warning("'capushe' not available: returning all models")
 101         return (models_list)
 102     }
 103
 104     # Get summary "tableauRecap" from models
 105     tableauRecap = do.call( rbind, lapply( models_list, function(models) {
 106         #Pour un groupe de modeles (même k, différents lambda):
 107         llh = matrix(ncol = 2)
 108         for (l in seq_along(models))
 109             llh = rbind(llh, models[[l]]$llh) #TODO: LLF? harmonize between EMGLLF and EMGrank?
 110         LLH = llh[-1,1]
 111         D = llh[-1,2]
 112         k = length(models[[1]]$pi)
 113         cbind(LLH, D, rep(k, length(models)), 1:length(models))
 114     } ) )
 115     tableauRecap = tableauRecap[rowSums(tableauRecap[, 2:4])!=0,]
 116   tableauRecap = tableauRecap[(tableauRecap[,1])!=Inf,]
 117   data = cbind(1:dim(tableauRecap)[1], tableauRecap[,2], tableauRecap[,2], tableauRecap[,1])
 118 browser()
 119   modSel = capushe::capushe(data, n)
 120   indModSel <-
 121         if (selecMod == 'DDSE')
 122             as.numeric(modSel@DDSE@model)
 123         else if (selecMod == 'Djump')
 124             as.numeric(modSel@Djump@model)
 125         else if (selecMod == 'BIC')
 126             modSel@BIC_capushe$model
 127         else if (selecMod == 'AIC')
 128             modSel@AIC_capushe$model
 129   models_list[[tableauRecap[indModSel,3]]][[tableauRecap[indModSel,4]]]
 130 }