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 #' @param ncores_outer Number of cores for the outer loop on k
  18 #' @param ncores_inner Number of cores for the inner loop on lambda
  19 #' @param size_coll_mod (Maximum) size of a collection of models
  20 #' @param fast TRUE to use compiled C code, FALSE for R code only
  21 #' @param verbose TRUE to show some execution traces
  22 #'
  23 #' @return a list with estimators of parameters
  24 #'
  25 #' @examples
  26 #' #TODO: a few examples
  27 #' @export
  28 valse = function(X, Y, procedure='LassoMLE', selecMod='DDSE', gamma=1, mini=10, maxi=50,
  29                  eps=1e-4, kmin=2, kmax=2, rank.min=1, rank.max=10, ncores_outer=1, ncores_inner=1,
  30                  size_coll_mod=10, fast=TRUE, verbose=FALSE, plot = TRUE)
  31 {
  32   p = dim(X)[2]
  33   m = dim(Y)[2]
  34   n = dim(X)[1]
  35
  36   if (verbose)
  37     print("main loop: over all k and all lambda")
  38
  39   if (ncores_outer > 1)
  40   {
  41     cl = parallel::makeCluster(ncores_outer, outfile='')
  42     parallel::clusterExport( cl=cl, envir=environment(), varlist=c("X","Y","procedure",
  43                                                                    "selecMod","gamma","mini","maxi","eps","kmin","kmax","rang.min","rang.max",
  44                                                                    "ncores_outer","ncores_inner","verbose","p","m") )
  45   }
  46
  47   # Compute models with k components
  48   computeModels <- function(k)
  49   {
  50     if (ncores_outer > 1)
  51       require("valse") #nodes start with an empty environment
  52
  53     if (verbose)
  54       print(paste("Parameters initialization for k =",k))
  55     #smallEM initializes parameters by k-means and regression model in each component,
  56     #doing this 20 times, and keeping the values maximizing the likelihood after 10
  57     #iterations of the EM algorithm.
  58     P = initSmallEM(k, X, Y)
  59     grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, X, Y,
  60                                      gamma, mini, maxi, eps, fast)
  61     if (length(grid_lambda)>size_coll_mod)
  62       grid_lambda = grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
  63
  64     if (verbose)
  65       print("Compute relevant parameters")
  66     #select variables according to each regularization parameter
  67     #from the grid: S$selected corresponding to selected variables
  68     S = selectVariables(P$phiInit, P$rhoInit, P$piInit, P$gamInit, mini, maxi, gamma,
  69                         grid_lambda, X, Y, 1e-8, eps, ncores_inner, fast) #TODO: 1e-8 as arg?! eps?
  70
  71     if (procedure == 'LassoMLE')
  72     {
  73       if (verbose)
  74         print('run the procedure Lasso-MLE')
  75       #compute parameter estimations, with the Maximum Likelihood
  76       #Estimator, restricted on selected variables.
  77       models <- constructionModelesLassoMLE(P$phiInit, P$rhoInit, P$piInit, P$gamInit,
  78                                             mini, maxi, gamma, X, Y, thresh, eps, S, ncores_inner, fast, verbose)
  79     }
  80     else
  81     {
  82       if (verbose)
  83         print('run the procedure Lasso-Rank')
  84       #compute parameter estimations, with the Low Rank
  85       #Estimator, restricted on selected variables.
  86       models <- constructionModelesLassoRank(S$Pi, S$Rho, mini, maxi, X, Y, eps, S,
  87                                              rank.min, rank.max, ncores_inner, fast, verbose)
  88     }
  89     #warning! Some models are NULL after running selectVariables
  90     models = models[sapply(models, function(cell) !is.null(cell))]
  91     models
  92   }
  93
  94   # List (index k) of lists (index lambda) of models
  95   models_list <-
  96     if (ncores_outer > 1)
  97       parLapply(cl, kmin:kmax, computeModels)
  98   else
  99     lapply(kmin:kmax, computeModels)
 100   if (ncores_outer > 1)
 101     parallel::stopCluster(cl)
 102
 103   if (! requireNamespace("capushe", quietly=TRUE))
 104   {
 105     warning("'capushe' not available: returning all models")
 106     return (models_list)
 107   }
 108
 109   # Get summary "tableauRecap" from models
 110   tableauRecap = do.call( rbind, lapply( seq_along(models_list), function(i) {
 111     models <- models_list[[i]]
 112     #For a collection of models (same k, several lambda):
 113     LLH <- sapply( models, function(model) model$llh[1] )
 114     k = length(models[[1]]$pi)
 115     sumPen = sapply(models, function(model)
 116       k*(dim(model$rho)[1]+sum(model$phi[,,1]!=0)+1)-1)
 117     data.frame(model=paste(i,".",seq_along(models),sep=""),
 118                pen=sumPen/n, complexity=sumPen, contrast=-LLH)
 119   } ) )
 120
 121   print(tableauRecap)
 122   tableauRecap = tableauRecap[which(tableauRecap[,4]!= Inf),]
 123   modSel = capushe::capushe(tableauRecap, n)
 124   indModSel <-
 125     if (selecMod == 'DDSE')
 126       as.numeric(modSel@DDSE@model)
 127   else if (selecMod == 'Djump')
 128     as.numeric(modSel@Djump@model)
 129   else if (selecMod == 'BIC')
 130     modSel@BIC_capushe$model
 131   else if (selecMod == 'AIC')
 132     modSel@AIC_capushe$model
 133
 134   mod = as.character(tableauRecap[indModSel,1])
 135   listMod = as.integer(unlist(strsplit(mod, "[.]")))
 136   modelSel = models_list[[listMod[1]]][[listMod[2]]]
 137
 138   ##Affectations
 139   Gam = matrix(0, ncol = length(modelSel$pi), nrow = n)
 140   for (i in 1:n){
 141     for (r in 1:length(modelSel$pi)){
 142       sqNorm2 = sum( (Y[i,]%*%modelSel$rho[,,r]-X[i,]%*%modelSel$phi[,,r])^2 )
 143       Gam[i,r] = modelSel$pi[r] * exp(-0.5*sqNorm2)* det(modelSel$rho[,,r])
 144     }
 145   }
 146   Gam = Gam/rowSums(Gam)
 147   modelSel$affec = apply(Gam, 1,which.max)
 148   modelSel$proba = Gam
 149
 150   if (plot){
 151     print(plot_valse(modelSel,n))
 152   }
 153
 154   return(modelSel)
 155 }