sdnet-package: sdnet: Soft Discretization-based Bayesian Network Inference

In sdnet: Soft-Discretization-Based Bayesian Network Inference

Description

sdnet Fitting discrete Bayesian networks using marginal mixture distributions. A Bayesian network is defined by a graphical structure in form of directed acyclic graph and a probability model given as a set of conditional distributions, one for each node in the network. Considered in the package are only categorical Bayesian networks - networks which nodes represent discrete random variables. The searching functions implemented in sdnet output sets of networks with increasing complexity that fit the data according to the MLE criterion. These optimal networks is believed to explain and represent the relations between the node-variables. The final network selection is left to the user.

Before starting to use the package, we suggest the user to take a look at some of the main objects used in sdnet such as catNetwork and catNetworkEvaluate and then familiarize with the main search functions cnSearchOrder and cnSearchSA. More details and examples can be found in the manual pages and the vignettes accompanying the package.

Since sdnet does not have its own plotting abilities, the user needs to setup some external tools in order to visualize networks, or more precisely, catNetwork objects. There are two options: first one is to use igraph package and second, and better one, is to use Graphviz library. Graphviz is not a R-package but a platform independent library that the user have to install in advance on its machine in order to use this option.

If the user choose the first option, igraph, the only thing he/she has to do is to install the library in R and set the environment variable R_SDNET_USE_IGRAPH to TRUE. A convenient place to do this is in the R .First function

.First <- function() {

......................

Sys.setenv(R_SDNET_USE_IGRAPH=TRUE)

}

In order to use Graphviz, in addition to installing the library, the user has to register a environmental variable with name R_DOTVIEWER with the path to the Dot executable file of Graphviz. The Dot routine generates a postscript or pdf-file from a text dot-file. Also, the user needs a postscript and pdf-viewer. The full path to it has to be given in another variable with name R_PDFVIEWER. Note that R_PDFVIEWER variable might be already setup. To check this call Sys.getenv("R_PDFVIEWER") in R.

The variables R_DOTVIEWER and eventually R_PDFVIEWER can be registered in the .First function residing in the .Rprofile initializing file.

Below we give two examples. On UNIX platform the user may use code like this one

.First <- function() {

......................

Sys.setenv(R_DOTVIEWER="/usr/bin/dot")

}

On Windows platform the user may have the following two lines in its .First function

.First <- function() {

......................

Sys.setenv(R_PDFVIEWER="\"C:/Program Files (x86)/Adobe/Reader 9.0/Reader/AcroRd32\"")

Sys.setenv(R_DOTVIEWER="\"C:/Program Files (x86)/Graphviz 2.26.3/bin/Dot\"")

}

Note that all paths in Windows should be embraced by comment marks, "\"".

Author(s)

N. Balov

sdnet documentation built on May 2, 2019, 12:43 a.m.