sparsebn: sparsebn: Learning Sparse Bayesian Networks from...

In sparsebn: Learning Sparse Bayesian Networks from High-Dimensional Data

Description

Methods for learning sparse Bayesian networks and other graphical models from observational and experimental data via sparse regularization. Includes algorithms for both continuous and discrete data.

Details

The main methods for learning graphical models in sparsebn are:

• estimate.dag for directed acyclic graphs.

• estimate.precision for undirected graphs.

• estimate.covariance for covariance matrices.

The workhorse behind sparsebn is the sparsebnUtils package, which provides various S3 classes and methods for representing and manipulating graphs. For more details on this package and the functionality it provides, see ?sparsebnUtils.

sparsebn documentation built on Sept. 13, 2020, 5:10 p.m.