Merge branch 'dev'

.Rbuildignore

@@ -1,3 +1,6 @@
-^.*\.Rproj$
+### For some reason Hadley's regex's from http://r-pkgs.had.co.nz/package.html are being ignored, so do this manually
+^cran-comments\.md$
+^README\.Rmd$
+^sparsebn\.Rproj$
 ^\.Rproj\.user$
 ^\.travis\.yml$

.travis.yml

@@ -4,6 +4,15 @@ language: R
 sudo: false
 cache: packages
 
+#r_build_args: --no-build-vignettes --no-manual --no-resave-data
+#r_check_args: --no-build-vignettes --no-manual
+
+# Test master and dev branches
+branches:
+    only:
+        - master
+        - dev
+
 # Test on release, old, and development versions of R
 r:
  - oldrel

DESCRIPTION

@@ -1,10 +1,10 @@
 Package: sparsebn
 Title: Learning Sparse Bayesian Networks from High-Dimensional Data
-Version: 0.0.0.9000
-Date: 2016-04-05
+Version: 0.0.1
+Date: 2016-08-12
 Authors@R: person("Bryon", "Aragam", email = "sparsebn@gmail.com", role = c("aut", "cre"))
 Maintainer: Bryon Aragam <sparsebn@gmail.com>
-Description: Methods and tools for learning sparse Bayesian networks from high-dimensional data using sparse regularization.
+Description: Fast methods for learning sparse Bayesian networks from high-dimensional data using sparse regularization. Designed to incorporate mixed experimental and observational data with thousands of variables with either continuous or discrete observations.
 Depends:
     R (>= 3.2.3),
     sparsebnUtils,
@@ -15,6 +15,7 @@ Suggests:
     rmarkdown,
     mvtnorm,
     igraph,
+    graph,
     testthat
 URL: https://github.com/itsrainingdata/sparsebn
 BugReports: https://github.com/itsrainingdata/sparsebn/issues

R/data.R

@@ -1,18 +1,49 @@
 #' The pathfinder network
 #'
-#' The pathfinder network from the \href{http://www.bnlearn.com/bnrepository/#pathfinder}{Bayesian network repository}.
-#' Pathfinder is an expert system developed in 1992 by Heckerman et. al
+#' Simulated data and network for the pathfinder network from the \href{http://www.bnlearn.com/bnrepository/#pathfinder}{Bayesian network repository}.
+#' Pathfinder is an expert system developed by Heckerman et. al (1992)
 #' to assist with the diagnosis of lymph-node diseases.
 #'
+#' The data is simulated from a Gaussian SEM assuming unit edge weights and
+#' unit variances for all nodes.
+#'
+#' @format A \code{\link{list}} with four components:
+#'
+#' \itemize{
+#' \item \code{dag} An \code{\link[sparsebnUtils]{edgeList}} containing the pathfinder network (109 nodes, 195 edges).
+#' \item \code{data} A \code{\link{data.frame}} with 109 variables and 1000 observations.
+#' \item \code{ivn} A \code{\link{list}} specifying which nodes are under intervention in each observation; since this dataset
+#' is purely observational, this is just \code{NULL}. Compatible with the input to \code{\link[sparsebnUtils]{sparsebnData}}.
+#' \item \code{cov} Covariance matrix used to generate the data.
+#' }
+#'
 #' @format An \code{\link{edgeList}} object with 109 nodes and 195 edges.
 #'
+#' @usage
+#' data(pathfinder)
+#'
+#' @examples
+#' \dontrun{
+#' # Create a valid sparsebnData object from the simulated pathfinder data
+#' data(pathfinder)
+#' dat <- sparsebnData(pathfinder$data, type = "c")
+#'
+#' # If desired, change the edge weights to be randomly generated
+#' coefs <- get.adjacency.matrix(pathfinder$dag)
+#' coefs[coefs != 0] <- runif(n = num.edges(pathfinderDAG), min = 0.5, max = 2)
+#' vars <- Matrix::Diagonal(n = num.nodes(pathfinderDAG), x = rep(1, num.nodes(pathfinderDAG)))
+#' id <- vars
+#' covMat <- t(solve(id - coefs)) %*% vars %*% solve(id - coefs)
+#' pathfinder.data <- rmvnorm(n = 1000, sigma = as.matrix(covMat))
+#' }
+#'
 "pathfinder"
 
-#' The cytometry network
+#' The discrete cytometry network
 #'
 #' Data and network for analyzing the flow cytometry experiment
 #' from \href{http://science.sciencemag.org/content/308/5721/523.long}{Sachs et al. (2005)}.
-#' The data is a cleaned and discretized version of the raw data from these experiments.
+#' The data is a cleaned and discretized version of the raw data (see \code{\link{cytometryContinuous}}) from these experiments.
 #'
 #' @format A \code{\link{list}} with three components:
 #'
@@ -23,4 +54,37 @@
 #' Compatible with the input to \code{\link[sparsebnUtils]{sparsebnData}}.
 #' }
 #'
+#' @usage
+#' data(cytometryDiscrete)
+#'
+#' @examples
+#' # Create a valid sparsebnData object from the cytometry data
+#' data(cytometryDiscrete)
+#' dat <- sparsebnData(cytometryDiscrete$data, type = "d", ivn = cytometryDiscrete$ivn)
+#'
 "cytometryDiscrete"
+
+#' The continuous cytometry network
+#'
+#' Data and network for analyzing the flow cytometry experiment
+#' from \href{http://science.sciencemag.org/content/308/5721/523.long}{Sachs et al. (2005)}.
+#' This dataset contains the raw measurements from these experiments.
+#'
+#' @format A \code{\link{list}} with three components:
+#'
+#' \itemize{
+#' \item \code{dag} An \code{\link[sparsebnUtils]{edgeList}} containing the consensus network (11 nodes, 17 edges).
+#' \item \code{data} A \code{\link{data.frame}} with 11 variables and 7466 observations.
+#' \item \code{ivn} A \code{\link{list}} specifying which nodes are under intervention in each observation.
+#' Compatible with the input to \code{\link[sparsebnUtils]{sparsebnData}}.
+#' }
+#'
+#' @usage
+#' data(cytometryContinuous)
+#'
+#' @examples
+#' # Create a valid sparsebnData object from the cytometry data
+#' data(cytometryContinuous)
+#' dat <- sparsebnData(cytometryContinuous$data, type = "c", ivn = cytometryContinuous$ivn)
+#'
+"cytometryContinuous"

R/sparsebn-main.R

@@ -11,6 +11,8 @@
 #
 #   CONTENTS:
 #       estimate.dag
+#       estimate.covariance
+#       estimate.precision
 #
 
 #' Estimate a DAG from data
@@ -42,6 +44,15 @@
 #'
 #' @return A \code{\link[sparsebnUtils]{sparsebnPath}} object.
 #'
+#' @examples
+#'
+#' \dontrun{
+#' # Estimate a DAG from the cytometry data
+#' data(cytometryContinuous)
+#' dat <- sparsebnData(cytometryContinuous$data, type = "d", ivn = cytometryContinuous$ivn)
+#' estimate.dag(dat)
+#' }
+#'
 #' @export
 estimate.dag <- function(data,
                          lambdas = NULL,
@@ -117,6 +128,15 @@ estimate.dag <- function(data,
 #' corresponding to an estimate of the covariance or precision (inverse covariance) matrix for a
 #' given value of lambda.
 #'
+#' @examples
+#'
+#' \dontrun{
+#' data(cytometryContinuous)
+#' dat <- sparsebnData(cytometryContinuous$data, type = "d", ivn = cytometryContinuous$ivn)
+#' estimate.covariance(dat) # estimate covariance
+#' estimate.precision(dat)  # estimate precision
+#' }
+#'
 #' @name estimate.covariance
 #' @rdname estimate.covariance
 NULL

R/zzz.R

@@ -10,9 +10,10 @@
 
 .onAttach <- function(libname, pkgname){
     msg <- paste0("\n",
-                  "sparsebn v0.1, Copyright (c) 2016\n",
+                  "sparsebn v0.0.1, Copyright (c) 2016\n",
                   "\tBryon Aragam, University of California, Los Angeles\n",
                   "\tJiaying Gu, University of California, Los Angeles\n",
+                  "\tDacheng Zhang, University of California, Los Angeles\n",
                   "\tQing Zhou, University of California, Los Angeles\n",
                   "\tFei Fu\n",
                   "\n",

README.Rmd

@@ -16,8 +16,7 @@ knitr::opts_chunk$set(
 
 [![Travis-CI Build Status](https://travis-ci.org/itsrainingdata/sparsebn.svg?branch=master)](https://travis-ci.org/itsrainingdata/sparsebn)
 
-Methods for learning sparse Bayesian networks and other graphical models from
-high-dimensional data via sparse regularization. Designed to handle:
+Methods for learning sparse Bayesian networks and other graphical models from high-dimensional data via sparse regularization. Designed to handle:
 
 - Experimental data with interventions 
 - Mixed observational / experimental data

cran-comments.md

@@ -0,0 +1,33 @@
+## Test environments
+* local OS X install, R 3.3.1
+* ubuntu 12.04 (travis-ci), R 3.3.1
+* win-builder (devel and release)
+
+## R CMD check results
+There were no ERRORs or WARNINGs.
+
+There was 1 NOTE:
+
+* checking CRAN incoming feasibility ... NOTE
+Maintainer: ‘Bryon Aragam <sparsebn@gmail.com>’
+
+New submission
+
+This is the first version of this package that has been submitted to CRAN.
+
+## Re-submission notes
+- I get
+
+Reading CITATION file fails with
+  $ operator is invalid for atomic vectors
+when package is not installed.
+
+Fixed by replacing packageDecription with meta as described in Section 1.9 of R-exts.
+
+## Dependencies
+
+CHECK has been run on all dependencies and passed.
+
+## Reverse dependencies
+
+This is a new release, so there are no reverse dependencies.

inst/CITATION

@@ -0,0 +1,18 @@
+citHeader("To cite sparsebn in publications use:")
+
+year <- sub(".*(2[[:digit:]]{3})-.*", "\\1", meta$Date, perl = TRUE)
+vers <- paste("R package version", meta$Version)
+
+citEntry(entry = "Manual",
+  title        = "sparsebn: Learning Sparse Bayesian Networks from High-Dimensional Data",
+  author       = personList(as.person("Bryon Aragam"), as.person("Jiaying Gu"), as.person("Dacheng Zhang"), as.person("Fei Fu"), as.person("Qing Zhou")),
+  year         = year,
+  note         = vers,
+  url          = "https://github.com/itsrainingdata/sparsebn",
+  textVersion  = paste0("Bryon Aragam, Jiaying Gu, Dacheng Zhang, Fei Fu, and Qing Zhou (", year, "). ",
+        "sparsebn: Learning Sparse Bayesian Networks from High-Dimensional Data. ",
+        vers, ".\n",
+        "https://github.com/itsrainingdata/sparsebn")
+)
+
+citFooter("A lot of effort has gone into building and maintaing the sparsebn package. Please cite it in all papers where it is used.")