The R Journal: article published in 2018, volume 10:2

bnclassify: Learning Bayesian Network Classifiers PDF download
Bojan Mihaljević, Concha Bielza and Pedro Larrañaga , The R Journal (2018) 10:2, pages 455-468.

Abstract The bnclassify package provides state-of-the art algorithms for learning Bayesian network classifiers from data. For structure learning it provides variants of the greedy hill-climbing search, a well-known adaptation of the Chow-Liu algorithm and averaged one-dependence estimators. It provides Bayesian and maximum likelihood parameter estimation, as well as three naive-Bayes specific methods based on discriminative score optimization and Bayesian model averaging. The implementation is efficient enough to allow for time-consuming discriminative scores on medium sized data sets. The bnclassify package provides utilities for model evaluation, such as cross-validated accuracy and penalized log-likelihood scores, and analysis of the underlying networks, including network plotting via the Rgraphviz package. It is extensively tested, with over 200 automated tests that give a code coverage of 94%. Here we present the main functionalities, illustrate them with a number of data sets, and comment on related software.

Received: 2018-05-29; online 2018-12-11, supplementary material, (833 bytes)
CRAN packages: bnlearn, bnclassify, caret, mlr, gRain, deal
CRAN Task Views implied by cited CRAN packages: Bayesian, gR, HighPerformanceComputing, MachineLearning, Multivariate
Bioconductor packages: Rgraphviz

CC BY 4.0
This article and supplementary materials are licensed under a Creative Commons Attribution 4.0 International license.

  author = {Bojan Mihaljević and Concha Bielza and Pedro Larrañaga},
  title = {{bnclassify: Learning Bayesian Network Classifiers}},
  year = {2018},
  journal = {{The R Journal}},
  doi = {10.32614/RJ-2018-073},
  url = {},
  pages = {455--468},
  volume = {10},
  number = {2}