I have tried to implement the R package ebbr (Empirical Bayes on the Binomial in R, by David Robinson) in Python. Please visit
- http://varianceexplained.org/r/ebbr-package/ to get the idea about what the package does and
- https://github.com/dgrtwo/ebbr for the R implementation
This was to learn more about how packaging works in Python
pip install ebbp
Fit Beta priors from data, compute shrinkage estimates, credible intervals, add those to the dataset
- Mixture of Beta priors
- Extend to Multinomial-dirichlet models?
- Priors other than Beta, fit using MCMC
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.