From: emilie <emilie@devijver.org>
Date: Mon, 6 Mar 2017 12:27:35 +0000 (+0100)
Subject: upadate valse.R
X-Git-Url: https://git.auder.net/images/doc/html/current/pieces/img/cross.svg?a=commitdiff_plain;h=c7dab9ff8b95a7630c7dafdcf40d60c659290ef2;p=valse.git

upadate valse.R
---

diff --git a/.Rbuildignore b/.Rbuildignore
new file mode 100644
index 0000000..91114bf
--- /dev/null
+++ b/.Rbuildignore
@@ -0,0 +1,2 @@
+^.*\.Rproj$
+^\.Rproj\.user$
diff --git a/NAMESPACE b/NAMESPACE
new file mode 100644
index 0000000..d3bb83f
--- /dev/null
+++ b/NAMESPACE
@@ -0,0 +1,17 @@
+# Generated by roxygen2: do not edit by hand
+
+export(basicInitParameters)
+export(discardSimilarModels_EMGLLF)
+export(discardSimilarModels_EMGrank)
+export(generateXY)
+export(generateXYdefault)
+export(gridLambda)
+export(initSmallEM)
+export(modelSelection)
+export(selectVariables)
+importFrom(methods,new)
+importFrom(stats,cutree)
+importFrom(stats,dist)
+importFrom(stats,hclust)
+importFrom(stats,runif)
+useDynLib(valse)
diff --git a/R/valse.R b/R/valse.R
new file mode 100644
index 0000000..e5205a5
--- /dev/null
+++ b/R/valse.R
@@ -0,0 +1,121 @@
+#' Main function
+#'
+#' @param X matrix of covariates (of size n*p)
+#' @param Y matrix of responses (of size n*m)
+#' @param procedure among 'LassoMLE' or 'LassoRank'
+#' @param selecMod method to select a model among 'SlopeHeuristic', 'BIC', 'AIC'
+#' @param gamma integer for the power in the penaly, by default = 1
+#' @param mini integer, minimum number of iterations in the EM algorithm, by default = 10
+#' @param maxi integer, maximum number of iterations in the EM algorithm, by default = 100
+#' @param eps real, threshold to say the EM algorithm converges, by default = 1e-4
+#' @param kmin integer, minimum number of clusters, by default = 2
+#' @param kmax integer, maximum number of clusters, by default = 10
+#' @param rang.min integer, minimum rank in the low rank procedure, by default = 1
+#' @param rang.max integer, maximum rank in the
+#' @return a list with estimators of parameters
+#' @export
+#-----------------------------------------------------------------------
+valse = function(X,Y,procedure,selecMod,gamma = 1,mini = 10,
+                 maxi = 100,eps = 1e-4,kmin = 2,kmax = 10,
+                 rang.min = 1,rang.max = 10) {
+  ##################################
+  #core workflow: compute all models
+  ##################################
+  
+  p = dim(phiInit)[1]
+  m = dim(phiInit)[2]
+  
+  print("main loop: over all k and all lambda")
+  for (k in kmin:kmax)
+  {
+    print(k)
+    
+    print("Parameters initialization")
+    #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.
+    init = initSmallEM(k, X, Y)
+    phiInit <<- init$phiInit
+    rhoInit <<- init$rhoInit
+    piInit	<<- init$piInit
+    gamInit <<- init$gamInit
+    
+    gridLambda <<- gridLambda(phiInit, rhoInit, piInit, tauInit, X, Y, gamma, mini, maxi, eps)
+    
+    print("Compute relevant parameters")
+    #select variables according to each regularization parameter
+    #from the grid: A1 corresponding to selected variables, and
+    #A2 corresponding to unselected variables.
+    params = selectiontotale(phiInit,rhoInit,piInit,tauInit,
+                             mini,maxi,gamma,gridLambda,
+                             X,Y,thresh,eps)
+    A1 <<- params$A1
+    A2 <<- params$A2
+    Rho <<- params$Rho
+    Pi <<- params$Pi
+    
+    if (procedure == 'LassoMLE') {
+      print('run the procedure Lasso-MLE')
+      #compute parameter estimations, with the Maximum Likelihood
+      #Estimator, restricted on selected variables.
+      model = constructionModelesLassoMLE(
+        phiInit, rhoInit,piInit,tauInit,mini,maxi,
+        gamma,gridLambda,X,Y,thresh,eps,A1,A2)
+      ################################################
+      ### Regarder la SUITE
+      r1 = runProcedure1()
+      Phi2 = Phi
+      Rho2 = Rho
+      Pi2 = Pi
+      
+      if (is.null(dim(Phi2)))
+        #test was: size(Phi2) == 0
+      {
+        Phi[, , 1:k] <<- r1$phi
+        Rho[, , 1:k] <<- r1$rho
+        Pi[1:k,] <<- r1$pi
+      } else
+      {
+        Phi <<-
+          array(0., dim = c(p, m, kmax, dim(Phi2)[4] + dim(r1$phi)[4]))
+        Phi[, , 1:(dim(Phi2)[3]), 1:(dim(Phi2)[4])] <<- Phi2
+        Phi[, , 1:k, dim(Phi2)[4] + 1] <<- r1$phi
+        Rho <<-
+          array(0., dim = c(m, m, kmax, dim(Rho2)[4] + dim(r1$rho)[4]))
+        Rho[, , 1:(dim(Rho2)[3]), 1:(dim(Rho2)[4])] <<- Rho2
+        Rho[, , 1:k, dim(Rho2)[4] + 1] <<- r1$rho
+        Pi <<- array(0., dim = c(kmax, dim(Pi2)[2] + dim(r1$pi)[2]))
+        Pi[1:nrow(Pi2), 1:ncol(Pi2)] <<- Pi2
+        Pi[1:k, ncol(Pi2) + 1] <<- r1$pi
+      }
+    } else {
+      print('run the procedure Lasso-Rank')
+      #compute parameter estimations, with the Low Rank
+      #Estimator, restricted on selected variables.
+      model = constructionModelesLassoRank(Pi, Rho, mini, maxi, X, Y, eps,
+                                           A1, rank.min, rank.max)
+      
+      ################################################
+      ### Regarder la SUITE  
+      phi = runProcedure2()$phi
+      Phi2 = Phi
+      if (dim(Phi2)[1] == 0)
+      {
+        Phi[, , 1:k,] <<- phi
+      } else
+      {
+        Phi <<- array(0, dim = c(p, m, kmax, dim(Phi2)[4] + dim(phi)[4]))
+        Phi[, , 1:(dim(Phi2)[3]), 1:(dim(Phi2)[4])] <<- Phi2
+        Phi[, , 1:k,-(1:(dim(Phi2)[4]))] <<- phi
+      }
+    }
+  }
+  print('Model selection')
+  if (selecMod == 'SlopeHeuristic') {
+    
+  } else if (selecMod == 'BIC') {
+    
+  } else if (selecMod == 'AIC') {
+    
+  }
+}
diff --git a/man/basicInitParameters.Rd b/man/basicInitParameters.Rd
new file mode 100644
index 0000000..6ed8547
--- /dev/null
+++ b/man/basicInitParameters.Rd
@@ -0,0 +1,26 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/generateSampleInputs.R
+\name{basicInitParameters}
+\alias{basicInitParameters}
+\title{Initialize the parameters in a basic way (zero for the conditional mean, uniform for weights,
+identity for covariance matrices, and uniformly distributed for the clustering)}
+\usage{
+basicInitParameters(n, p, m, k)
+}
+\arguments{
+\item{n}{sample size}
+
+\item{p}{number of covariates}
+
+\item{m}{size of the response}
+
+\item{k}{number of clusters}
+}
+\value{
+list with phiInit, rhoInit,piInit,gamInit
+}
+\description{
+Initialize the parameters in a basic way (zero for the conditional mean, uniform for weights,
+identity for covariance matrices, and uniformly distributed for the clustering)
+}
+
diff --git a/man/discardSimilarModels_EMGLLF.Rd b/man/discardSimilarModels_EMGLLF.Rd
new file mode 100644
index 0000000..20ac957
--- /dev/null
+++ b/man/discardSimilarModels_EMGLLF.Rd
@@ -0,0 +1,27 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/discardSimilarModels.R
+\name{discardSimilarModels_EMGLLF}
+\alias{discardSimilarModels_EMGLLF}
+\title{Discard models which have the same relevant variables - for EMGLLF}
+\usage{
+discardSimilarModels_EMGLLF(B1, B2, glambda, rho, pi)
+}
+\arguments{
+\item{B1}{array of relevant coefficients (of size p*m*length(gridlambda))}
+
+\item{B2}{array of irrelevant coefficients (of size p*m*length(gridlambda))}
+
+\item{glambda}{grid of regularization parameters (vector)}
+
+\item{rho}{covariance matrix (of size m*m*K*size(gridLambda))}
+
+\item{pi}{weight parameters (of size K*size(gridLambda))}
+}
+\value{
+a list with update B1, B2, glambda, rho and pi, and ind the vector of indices
+of selected models.
+}
+\description{
+Discard models which have the same relevant variables - for EMGLLF
+}
+
diff --git a/man/discardSimilarModels_EMGrank.Rd b/man/discardSimilarModels_EMGrank.Rd
new file mode 100644
index 0000000..932c4ff
--- /dev/null
+++ b/man/discardSimilarModels_EMGrank.Rd
@@ -0,0 +1,24 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/discardSimilarModels.R
+\name{discardSimilarModels_EMGrank}
+\alias{discardSimilarModels_EMGrank}
+\title{Discard models which have the same relevant variables
+  - for Lasso-rank procedure (focus on columns)}
+\usage{
+discardSimilarModels_EMGrank(B1, rho, pi)
+}
+\arguments{
+\item{B1}{array of relevant coefficients (of size p*m*length(gridlambda))}
+
+\item{rho}{covariance matrix}
+
+\item{pi}{weight parameters}
+}
+\value{
+a list with B1, in, rho, pi
+}
+\description{
+Discard models which have the same relevant variables
+  - for Lasso-rank procedure (focus on columns)
+}
+
diff --git a/man/generateXY.Rd b/man/generateXY.Rd
new file mode 100644
index 0000000..ef76d82
--- /dev/null
+++ b/man/generateXY.Rd
@@ -0,0 +1,28 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/generateSampleInputs.R
+\name{generateXY}
+\alias{generateXY}
+\title{Generate a sample of (X,Y) of size n}
+\usage{
+generateXY(meanX, covX, covY, pi, beta, n)
+}
+\arguments{
+\item{meanX}{matrix of group means for covariates (of size p*K)}
+
+\item{covX}{covariance for covariates (of size p*p*K)}
+
+\item{covY}{covariance for the response vector (of size m*m*K)}
+
+\item{pi}{proportion for each cluster}
+
+\item{beta}{regression matrix}
+
+\item{n}{sample size}
+}
+\value{
+list with X and Y
+}
+\description{
+Generate a sample of (X,Y) of size n
+}
+
diff --git a/man/generateXYdefault.Rd b/man/generateXYdefault.Rd
new file mode 100644
index 0000000..3f80c08
--- /dev/null
+++ b/man/generateXYdefault.Rd
@@ -0,0 +1,24 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/generateSampleInputs.R
+\name{generateXYdefault}
+\alias{generateXYdefault}
+\title{Generate a sample of (X,Y) of size n with default values}
+\usage{
+generateXYdefault(n, p, m, k)
+}
+\arguments{
+\item{n}{sample size}
+
+\item{p}{number of covariates}
+
+\item{m}{size of the response}
+
+\item{k}{number of clusters}
+}
+\value{
+list with X and Y
+}
+\description{
+Generate a sample of (X,Y) of size n with default values
+}
+
diff --git a/man/gridLambda.Rd b/man/gridLambda.Rd
new file mode 100644
index 0000000..cc203a7
--- /dev/null
+++ b/man/gridLambda.Rd
@@ -0,0 +1,36 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/gridLambda.R
+\name{gridLambda}
+\alias{gridLambda}
+\title{Construct the data-driven grid for the regularization parameters used for the Lasso estimator}
+\usage{
+gridLambda(phiInit, rhoInit, piInit, gamInit, X, Y, gamma, mini, maxi, tau)
+}
+\arguments{
+\item{phiInit}{value for phi}
+
+\item{rhoInit}{value for rho}
+
+\item{piInit}{value for pi}
+
+\item{gamInit}{value for gamma}
+
+\item{X}{matrix of covariates (of size n*p)}
+
+\item{Y}{matrix of responses (of size n*m)}
+
+\item{gamma}{power of weights in the penalty}
+
+\item{mini}{minimum number of iterations in EM algorithm}
+
+\item{maxi}{maximum number of iterations in EM algorithm}
+
+\item{tau}{threshold to stop EM algorithm}
+}
+\value{
+the grid of regularization parameters
+}
+\description{
+Construct the data-driven grid for the regularization parameters used for the Lasso estimator
+}
+
diff --git a/man/initSmallEM.Rd b/man/initSmallEM.Rd
new file mode 100644
index 0000000..86be0cb
--- /dev/null
+++ b/man/initSmallEM.Rd
@@ -0,0 +1,22 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/initSmallEM.R
+\name{initSmallEM}
+\alias{initSmallEM}
+\title{initialization of the EM algorithm}
+\usage{
+initSmallEM(k, X, Y)
+}
+\arguments{
+\item{k}{number of components}
+
+\item{X}{matrix of covariates (of size n*p)}
+
+\item{Y}{matrix of responses (of size n*m)}
+}
+\value{
+a list with phiInit, rhoInit, piInit, gamInit
+}
+\description{
+initialization of the EM algorithm
+}
+
diff --git a/man/modelSelection.Rd b/man/modelSelection.Rd
new file mode 100644
index 0000000..30aeaa5
--- /dev/null
+++ b/man/modelSelection.Rd
@@ -0,0 +1,24 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/modelSelection.R
+\name{modelSelection}
+\alias{modelSelection}
+\title{Among a collection of models, this function constructs a subcollection of models with
+models having strictly different dimensions, keeping the model which minimizes
+the likelihood if there were several with the same dimension}
+\usage{
+modelSelection(LLF)
+}
+\arguments{
+\item{LLF}{a matrix, the first column corresponds to likelihoods for several models
+the second column corresponds to the dimensions of the corresponding models.}
+}
+\value{
+a list with indices, a vector of indices selected models,
+			 and D1, a vector of corresponding dimensions
+}
+\description{
+Among a collection of models, this function constructs a subcollection of models with
+models having strictly different dimensions, keeping the model which minimizes
+the likelihood if there were several with the same dimension
+}
+
diff --git a/man/selectVariables.Rd b/man/selectVariables.Rd
new file mode 100644
index 0000000..09a52f2
--- /dev/null
+++ b/man/selectVariables.Rd
@@ -0,0 +1,49 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/selectVariables.R
+\name{selectVariables}
+\alias{selectVariables}
+\title{selectVaribles
+It is a function which construct, for a given lambda, the sets of
+relevant variables and irrelevant variables.}
+\usage{
+selectVariables(phiInit, rhoInit, piInit, gamInit, mini, maxi, gamma, glambda,
+  X, Y, thres, tau)
+}
+\arguments{
+\item{phiInit}{an initial estimator for phi (size: p*m*k)}
+
+\item{rhoInit}{an initial estimator for rho (size: m*m*k)}
+
+\item{piInit}{an initial estimator for pi (size : k)}
+
+\item{gamInit}{an initial estimator for gamma}
+
+\item{mini}{minimum number of iterations in EM algorithm}
+
+\item{maxi}{maximum number of iterations in EM algorithm}
+
+\item{gamma}{power in the penalty}
+
+\item{glambda}{grid of regularization parameters}
+
+\item{X}{matrix of regressors}
+
+\item{Y}{matrix of responses}
+
+\item{thres}{threshold to consider a coefficient to be equal to 0}
+
+\item{tau}{threshold to say that EM algorithm has converged}
+}
+\value{
+TODO
+}
+\description{
+selectVaribles
+It is a function which construct, for a given lambda, the sets of
+relevant variables and irrelevant variables.
+}
+\examples{
+TODO
+
+}
+
diff --git a/valse.Rproj b/valse.Rproj
new file mode 100644
index 0000000..21a4da0
--- /dev/null
+++ b/valse.Rproj
@@ -0,0 +1,17 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source