X-Git-Url: https://git.auder.net/?p=morpheus.git;a=blobdiff_plain;f=pkg%2FR%2FoptimParams.R;h=039070c5280b847af077056b2cfcc89b6c73b589;hp=ecfae7f5d145e49ddd13244125818fdda22917cd;hb=2591fa8343c69ddb94dec5e55871d34c55eff9a3;hpb=9a6881ed8a16c31a3dbe995e3b1af76c1db6b5a0

diff --git a/pkg/R/optimParams.R b/pkg/R/optimParams.R
index ecfae7f..039070c 100644
--- a/pkg/R/optimParams.R
+++ b/pkg/R/optimParams.R
@@ -31,7 +31,7 @@
 #' o$f( o$linArgs(par0) )
 #' o$f( o$linArgs(par1) )
 #' @export
-optimParams <- function(X, Y, K, link=c("logit","probit"))
+optimParams <- function(X, Y, K, link=c("logit","probit"), M=NULL)
 {
   # Check arguments
   if (!is.matrix(X) || any(is.na(X)))
@@ -42,9 +42,21 @@ optimParams <- function(X, Y, K, link=c("logit","probit"))
   if (!is.numeric(K) || K!=floor(K) || K < 2)
     stop("K: integer >= 2")
 
+  if (is.null(M))
+  {
+    # Precompute empirical moments
+    Mtmp <- computeMoments(X, Y)
+    M1 <- as.double(Mtmp[[1]])
+    M2 <- as.double(Mtmp[[2]])
+    M3 <- as.double(Mtmp[[3]])
+    M <- c(M1, M2, M3)
+  }
+  else
+    M <- c(M[[1]], M[[2]], M[[3]])
+
   # Build and return optimization algorithm object
   methods::new("OptimParams", "li"=link, "X"=X,
-    "Y"=as.integer(Y), "K"=as.integer(K))
+    "Y"=as.integer(Y), "K"=as.integer(K), "Mhat"=as.double(M))
 }
 
 #' Encapsulated optimization for p (proportions), β and b (regression parameters)
@@ -82,19 +94,15 @@ setRefClass(
       "Check args and initialize K, d, W"
 
       callSuper(...)
-      if (!hasArg("X") || !hasArg("Y") || !hasArg("K") || !hasArg("li"))
+      if (!hasArg("X") || !hasArg("Y") || !hasArg("K")
+        || !hasArg("li") || !hasArg("Mhat"))
+      {
         stop("Missing arguments")
-
-      # Precompute empirical moments
-      M <- computeMoments(X, Y)
-      M1 <- as.double(M[[1]])
-      M2 <- as.double(M[[2]])
-      M3 <- as.double(M[[3]])
-      Mhat <<- c(M1, M2, M3)
+      }
 
       n <<- nrow(X)
-      d <<- length(M1)
-      W <<- diag(d+d^2+d^3) #initialize at W = Identity
+      d <<- ncol(X)
+      # W will be initialized when calling run()
     },
 
     expArgs = function(v)
@@ -104,7 +112,7 @@ setRefClass(
       list(
         # p: dimension K-1, need to be completed
         "p" = c(v[1:(K-1)], 1-sum(v[1:(K-1)])),
-        "β" = matrix(v[K:(K+d*K-1)], ncol=K),
+        "β" = t(matrix(v[K:(K+d*K-1)], ncol=d)),
         "b" = v[(K+d*K):(K+(d+1)*K-1)])
     },
 
@@ -112,25 +120,20 @@ setRefClass(
     {
       "Linearize vectors+matrices from list L into a vector"
 
-      c(L$p[1:(K-1)], as.double(L$β), L$b)
+      # β linearized row by row, to match derivatives order
+      c(L$p[1:(K-1)], as.double(t(L$β)), L$b)
     },
 
-    #TODO: compare with R version?
-    #D <- diag(d) #matrix of ej vectors
-    #Y * X
-    #Y * ( t( apply(X, 1, function(row) row %o% row) ) - Reduce('+', lapply(1:d, function(j) as.double(D[j,] %o% D[j,])), rep(0, d*d)))
-    #Y * ( t( apply(X, 1, function(row) row %o% row %*% row) ) - Reduce('+', lapply(1:d, function(j) ), rep(0, d*d*d)))
     computeW = function(θ)
     {
-      #require(MASS)
+      require(MASS)
       dd <- d + d^2 + d^3
       M <- Moments(θ)
       Omega <- matrix( .C("Compute_Omega",
-        X=as.double(X), Y=as.double(Y), M=as.double(M),
+        X=as.double(X), Y=as.integer(Y), M=as.double(M),
         pn=as.integer(n), pd=as.integer(d),
         W=as.double(W), PACKAGE="morpheus")$W, nrow=dd, ncol=dd )
-      W <<- MASS::ginv(Omega, tol=1e-4)
-      NULL #avoid returning W
+      MASS::ginv(Omega)
     },
 
     Moments = function(θ)
@@ -166,7 +169,7 @@ setRefClass(
       "Gradient of f, dimension (K-1) + d*K + K = (d+2)*K - 1"
 
       L <- expArgs(θ)
-      -2 * t(grad_M(L)) %*% W %*% as.matrix((Mhat - Moments(L)))
+      -2 * t(grad_M(L)) %*% W %*% as.matrix(Mhat - Moments(L))
     },
 
     grad_M = function(θ)
@@ -245,31 +248,40 @@ setRefClass(
         stop("θ0: list")
       if (is.null(θ0$β))
         stop("At least θ0$β must be provided")
-      if (!is.matrix(θ0$β) || any(is.na(θ0$β)) || ncol(θ0$β) != K)
-        stop("θ0$β: matrix, no NA, ncol == K")
+      if (!is.matrix(θ0$β) || any(is.na(θ0$β))
+        || nrow(θ0$β) != d || ncol(θ0$β) != K)
+      {
+        stop("θ0$β: matrix, no NA, nrow = d, ncol = K")
+      }
       if (is.null(θ0$p))
         θ0$p = rep(1/K, K-1)
-      else if (length(θ0$p) != K-1 || sum(θ0$p) > 1)
-        stop("θ0$p should contain positive integers and sum to < 1")
-      # Next test = heuristic to detect missing b (when matrix is called "beta")
-      if (is.null(θ0$b) || all(θ0$b == θ0$β))
+      else if (!is.numeric(θ0$p) || length(θ0$p) != K-1
+        || any(is.na(θ0$p)) || sum(θ0$p) > 1)
+      {
+        stop("θ0$p: length K-1, no NA, positive integers, sum to <= 1")
+      }
+      if (is.null(θ0$b))
         θ0$b = rep(0, K)
-      else if (any(is.na(θ0$b)))
-        stop("θ0$b cannot have missing values")
-      # TODO: stopping condition? N iterations? Delta <= epsilon ?
-      for (loop in 1:10)
+      else if (!is.numeric(θ0$b) || length(θ0$b) != K || any(is.na(θ0$b)))
+        stop("θ0$b: length K, no NA")
+
+      # (Re)Set W to identity, to allow several run from the same object
+      W <<- diag(d+d^2+d^3)
+
+      loopMax <- 2 #TODO: loopMax = 3 ? Seems not improving...
+      x_init <- linArgs(θ0)
+      for (loop in 1:loopMax)
       {
-        op_res = constrOptim( linArgs(θ0), .self$f, .self$grad_f,
+        op_res = constrOptim( x_init, .self$f, .self$grad_f,
           ui=cbind(
             rbind( rep(-1,K-1), diag(K-1) ),
             matrix(0, nrow=K, ncol=(d+1)*K) ),
           ci=c(-1,rep(0,K-1)) )
-
-        computeW(expArgs(op_res$par))
-        # debug:
-        #print(W)
-        print(op_res$value)
-        print(expArgs(op_res$par))
+        if (loop < loopMax) #avoid computing an extra W
+          W <<- computeW(expArgs(op_res$par))
+        x_init <- op_res$par
+        #print(op_res$value) #debug
+        #print(expArgs(op_res$par)) #debug
       }
 
       expArgs(op_res$par)