Learning Bayesian Networks with Mixed Variables
Greedy search
deal internal functions
Graphical interface for editing networks
From a network family, generate LaTeX output
Insert/remove an arrow in network
Calculates the joint prior distribution
Estimation of parameters in the local probability distributions
Make a suggestion for simulation probabilities
Creates the full trylist
Bayesian network data structure
Generates and learns all networks for a set of variables.
Tools for manipulating networks
Representation of nodes
The number of possible networks
Sorts a list of networks
Makes a network family unique.
Perturbs a network
Local probability distributions
Weightloss of rats
Reads/saves .net file
Simulation of data sets with a given dependency structure
Network score
Bayesian networks with continuous and/or discrete variables can be learned and compared from data. The method is described in Boettcher and Dethlefsen (2003), <doi:10.18637/jss.v008.i20>.