X-Git-Url: https://git.auder.net/?p=morpheus.git;a=blobdiff_plain;f=pkg%2FR%2FoptimParams.R;h=c050e630ae7f381e1765d17c3bc530083251d6a5;hp=505b6651b76ebfcf94d441e6864a136ecbf109dd;hb=ab35f6102896a49e86e853262c0650faa2931638;hpb=6dd5c2acccd10635449230faa824b7e8906911bf

diff --git a/pkg/R/optimParams.R b/pkg/R/optimParams.R
index 505b665..c050e63 100644
--- a/pkg/R/optimParams.R
+++ b/pkg/R/optimParams.R
@@ -1,37 +1,47 @@
+#' optimParams
+#'
 #' Wrapper function for OptimParams class
 #'
-#' @param K Number of populations.
-#' @param link The link type, 'logit' or 'probit'.
+#' @name optimParams
+#'
 #' @param X Data matrix of covariables
 #' @param Y Output as a binary vector
+#' @param K Number of populations.
+#' @param link The link type, 'logit' or 'probit'.
+#' @param M the empirical cross-moments between X and Y (optional)
+#' @param nc Number of cores (default: 0 to use all)
 #'
-#' @return An object 'op' of class OptimParams, initialized so that \code{op$run(x0)}
-#'   outputs the list of optimized parameters
+#' @return An object 'op' of class OptimParams, initialized so that
+#'   \code{op$run(θ0)} outputs the list of optimized parameters
 #'   \itemize{
 #'     \item p: proportions, size K
 #'     \item β: regression matrix, size dxK
 #'     \item b: intercepts, size K
 #'   }
-#'   θ0 is a vector containing respectively the K-1 first elements of p, then β by
-#'   columns, and finally b: \code{θ0 = c(p[1:(K-1)],as.double(β),b)}.
+#'   θ0 is a list containing the initial parameters. Only β is required
+#'   (p would be set to (1/K,...,1/K) and b to (0,...0)).
 #'
 #' @seealso \code{multiRun} to estimate statistics based on β, and
 #'   \code{generateSampleIO} for I/O random generation.
 #'
 #' @examples
 #' # Optimize parameters from estimated μ
-#' io = generateSampleIO(10000, 1/2, matrix(c(1,-2,3,1),ncol=2), c(0,0), "logit")
-#' μ = computeMu(io$X, io$Y, list(K=2))
+#' io <- generateSampleIO(100,
+#'   1/2, matrix(c(1,-2,3,1),ncol=2), c(0,0), "logit")
+#' μ <- computeMu(io$X, io$Y, list(K=2))
 #' o <- optimParams(io$X, io$Y, 2, "logit")
+#' \donttest{
 #' θ0 <- list(p=1/2, β=μ, b=c(0,0))
 #' par0 <- o$run(θ0)
 #' # Compare with another starting point
 #' θ1 <- list(p=1/2, β=2*μ, b=c(0,0))
 #' par1 <- o$run(θ1)
+#' # Look at the function values at par0 and par1:
 #' o$f( o$linArgs(par0) )
-#' o$f( o$linArgs(par1) )
+#' 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, nc=0)
 {
   # Check arguments
   if (!is.matrix(X) || any(is.na(X)))
@@ -39,26 +49,41 @@ optimParams <- function(X, Y, K, link=c("logit","probit"))
   if (!is.numeric(Y) || any(is.na(Y)) || any(Y!=0 & Y!=1))
     stop("Y: binary vector with 0 and 1 only")
   link <- match.arg(link)
-  if (!is.numeric(K) || K!=floor(K) || K < 2)
-    stop("K: integer >= 2")
+  if (!is.numeric(K) || K!=floor(K) || K < 2 || K > ncol(X))
+    stop("K: integer >= 2, <= d")
+
+  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), "nc"=as.integer(nc))
 }
 
-#' Encapsulated optimization for p (proportions), β and b (regression parameters)
-#'
-#' Optimize the parameters of a mixture of logistic regressions model, possibly using
-#' \code{mu <- computeMu(...)} as a partial starting point.
-#'
-#' @field li Link function, 'logit' or 'probit'
-#' @field X Data matrix of covariables
-#' @field Y Output as a binary vector
-#' @field K Number of populations
-#' @field d Number of dimensions
-#' @field W Weights matrix (iteratively refined)
-#'
+# Encapsulated optimization for p (proportions), β and b (regression parameters)
+#
+# Optimize the parameters of a mixture of logistic regressions model, possibly using
+# \code{mu <- computeMu(...)} as a partial starting point.
+#
+# @field li Link function, 'logit' or 'probit'
+# @field X Data matrix of covariables
+# @field Y Output as a binary vector
+# @field Mhat Vector of empirical moments
+# @field K Number of populations
+# @field n Number of sample points
+# @field d Number of dimensions
+# @field nc Number of cores (OpenMP //)
+# @field W Weights matrix (initialized at identity)
+#
 setRefClass(
   Class = "OptimParams",
 
@@ -72,6 +97,7 @@ setRefClass(
     K = "integer",
     n = "integer",
     d = "integer",
+    nc = "integer",
     # Weights matrix (generalized least square)
     W = "matrix"
   ),
@@ -82,19 +108,15 @@ 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") || !hasArg("nc"))
+      {
         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 +126,7 @@ 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)])
     },
 
@@ -112,22 +134,28 @@ 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: relocate computeW in utils.R
     computeW = function(θ)
     {
-      #require(MASS)
+      "Compute the weights matrix from a parameters list"
+
+      require(MASS)
       dd <- d + d^2 + d^3
-      W <<- MASS::ginv( matrix( .C("Compute_Omega",
-        X=as.double(X), Y=Y, M=Moments(θ), pn=as.integer(n), pd=as.integer(d),
-        W=as.double(W), PACKAGE="morpheus")$W, nrow=dd, ncol=dd ) )
-      NULL #avoid returning W
+      M <- Moments(θ)
+      Omega <- matrix( .C("Compute_Omega",
+        X=as.double(X), Y=as.integer(Y), M=as.double(M),
+        pnc=as.integer(nc), pn=as.integer(n), pd=as.integer(d),
+        W=as.double(W), PACKAGE="morpheus")$W, nrow=dd, ncol=dd )
+      MASS::ginv(Omega)
     },
 
     Moments = function(θ)
     {
-      "Vector of moments, of size d+d^2+d^3"
+      "Compute the vector of theoretical moments (size d+d^2+d^3)"
 
       p <- θ$p
       β <- θ$β
@@ -146,7 +174,7 @@ setRefClass(
 
     f = function(θ)
     {
-      "Product t(hat_Mi - Mi) W (hat_Mi - Mi) with Mi(theta)"
+      "Function to minimize: t(hat_Mi - Mi(θ)) . W . (hat_Mi - Mi(θ))"
 
       L <- expArgs(θ)
       A <- as.matrix(Mhat - Moments(L))
@@ -155,15 +183,15 @@ setRefClass(
 
     grad_f = function(θ)
     {
-      "Gradient of f, dimension (K-1) + d*K + K = (d+2)*K - 1"
+      "Gradient of f: vector of size (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)
     {
-      "Gradient of the vector of moments, size (dim=)d+d^2+d^3 x K-1+K+d*K"
+      "Gradient of the moments vector: matrix of size d+d^2+d^3 x K-1+K+d*K"
 
       p <- θ$p
       β <- θ$β
@@ -229,7 +257,8 @@ setRefClass(
       res
     },
 
-    run = function(θ0)
+    # userW allows to bypass the W optimization by giving a W matrix
+    run = function(θ0, userW=NULL)
     {
       "Run optimization from θ0 with solver..."
 
@@ -237,32 +266,40 @@ 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")
+      }
+      # NOTE: [["b"]] instead of $b because $b would match $beta (in pkg-cran)
+      if (is.null(θ0[["b"]]))
         θ0$b = rep(0, K)
-      else if (any(is.na(θ0$b)))
-        stop("θ0$b cannot have missing values")
+      else if (!is.numeric(θ0$b) || length(θ0$b) != K || any(is.na(θ0$b)))
+        stop("θ0$b: length K, no NA")
 
-      # TODO: stopping condition? N iterations? Delta <= epsilon ?
-      for (loop in 1:10)
+      # (Re)Set W to identity, to allow several run from the same object
+      W <<- if (is.null(userW)) diag(d+d^2+d^3) else userW
+
+      # NOTE: loopMax = 3 seems to not improve the final results.
+      loopMax <- ifelse(is.null(userW), 2, 1)
+      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 #degrades performances (TODO: why?)
       }
 
       expArgs(op_res$par)