X-Git-Url: https://git.auder.net/?p=valse.git;a=blobdiff_plain;f=pkg%2FR%2Fmain.R;h=0a3487b0cb430097425ddeb9f563df8dfc9febd0;hp=64e058629859e8b1442e5a1110a2eb8670b554bf;hb=9cb34faffaa6fcb78eb8ae3bdb70fb5147d73466;hpb=1b698c1619dbcf5b3a0608dc894d249945d2bce3

diff --git a/pkg/R/main.R b/pkg/R/main.R
index 64e0586..0a3487b 100644
--- a/pkg/R/main.R
+++ b/pkg/R/main.R
@@ -17,6 +17,7 @@
 #' @param ncores_outer Number of cores for the outer loop on k
 #' @param ncores_inner Number of cores for the inner loop on lambda
 #' @param thresh real, threshold to say a variable is relevant, by default = 1e-8
+#' @param grid_lambda, a vector with regularization parameters if known, by default numeric(0)
 #' @param size_coll_mod (Maximum) size of a collection of models
 #' @param fast TRUE to use compiled C code, FALSE for R code only
 #' @param verbose TRUE to show some execution traces
@@ -28,12 +29,12 @@
 #' @export
 valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mini = 10, 
   maxi = 50, eps = 1e-04, kmin = 2, kmax = 3, rank.min = 1, rank.max = 5, ncores_outer = 1, 
-  ncores_inner = 1, thresh = 1e-08, size_coll_mod = 10, fast = TRUE, verbose = FALSE, 
-  plot = TRUE)
+  ncores_inner = 1, thresh = 1e-08, grid_lambda = numeric(0), size_coll_mod = 10,
+  fast = TRUE, verbose = FALSE, plot = TRUE)
 {
-  p <- dim(X)[2]
-  m <- dim(Y)[2]
-  n <- dim(X)[1]
+  n <- nrow(X)
+  p <- ncol(X)
+  m <- ncol(Y)
 
   if (verbose) 
     print("main loop: over all k and all lambda")
@@ -57,9 +58,12 @@ valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mi
     # smallEM initializes parameters by k-means and regression model in each
     # component, doing this 20 times, and keeping the values maximizing the
     # likelihood after 10 iterations of the EM algorithm.
-    P <- initSmallEM(k, X, Y)
-    grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, 
-      X, Y, gamma, mini, maxi, eps, fast)
+    P <- initSmallEM(k, X, Y, fast)
+    if (length(grid_lambda) == 0)
+    {
+      grid_lambda <- computeGridLambda(P$phiInit, P$rhoInit, P$piInit, P$gamInit, 
+                                       X, Y, gamma, mini, maxi, eps, fast)
+    }
     if (length(grid_lambda) > size_coll_mod) 
       grid_lambda <- grid_lambda[seq(1, length(grid_lambda), length.out = size_coll_mod)]
 
@@ -119,7 +123,8 @@ valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mi
       complexity = sumPen, contrast = -LLH)
   }))
   tableauRecap <- tableauRecap[which(tableauRecap[, 4] != Inf), ]
-
+  if (verbose == TRUE)
+    print(tableauRecap)
   modSel <- capushe::capushe(tableauRecap, n)
   indModSel <- if (selecMod == "DDSE") 
     as.numeric(modSel@DDSE@model) else if (selecMod == "Djump") 
@@ -138,12 +143,13 @@ valse <- function(X, Y, procedure = "LassoMLE", selecMod = "DDSE", gamma = 1, mi
     for (r in 1:length(modelSel$pi))
     {
       sqNorm2 <- sum((Y[i, ] %*% modelSel$rho[, , r] - X[i, ] %*% modelSel$phi[, , r])^2)
-      Gam[i, r] <- modelSel$pi[r] * exp(-0.5 * sqNorm2) * det(modelSel$rho[, , r])
+      Gam[i, r] <- modelSel$pi[r] * exp(-0.5 * sqNorm2) * gdet(modelSel$rho[, , r])
     }
   }
   Gam <- Gam/rowSums(Gam)
   modelSel$affec <- apply(Gam, 1, which.max)
   modelSel$proba <- Gam
+  modelSel$tableau <- tableauRecap
 
   if (plot)
     print(plot_valse(X, Y, modelSel, n))