Naive Bayes Models for Probability Estimation: Online Appendix

This page contains additional information meant to supplement
Daniel Lowd and Pedro Domingos (2005). Naive Bayes Models for Probability Estimation. International Conference on Machine Learning.

Details and Results

Experimental Method -- Extended information on the experimental methods we used, to supplement the descriptions in the paper.

Table 2 -- Augmented with dataset and model statistics, as well as standard errors for all log likelihoods.

Graphs -- Supplementary graphs, comparing naive Bayes log likelihoods in all 50 query scenarios.

Models -- All model files produced in our experiments, both NBE and WinMine.

Source Code

For reproducing results or using in other projects, we provide the source code used to obtain the results in this paper. You are welcome to use the code under the terms of the modified BSD license for research or commercial purposes, however please acknowledge its use with a citation:

Lowd, D. and Domingos, P. "Naive Bayes Models for Probability Estimation". ICML, 2005. Bonn, Germany: ACM Press.

If you like, please also drop us a line about what you do with NBE and what results you obtain. See the LICENSE file for official license information.

nbe.tar.gz -- Source code for learning and applying NBE models.

inference.tar.gz -- Source code used in our timed query experiments, including our implementations of Gibbs sampling and belief propagation. Requires that the NBE code above be present, installed in another directory.

scripts.tar.gz -- Perl scripts used for preparing data and running experiments.

[Total NBE downloads: ]

Comments to Daniel Lowd (lowd at cs dot washington dot edu)