bayesian-testing VS bbai

I created this notebook with "real world" like example: https://github.com/Matt52/bayesian-testing/blob/main/examples/bayesian_ab_testing.ipynb Of course in this case, the data is just generated as I do not have any real data for public sharing. But you can imagine how it would work. You could even use probabilities in time for traffic distribution among variants (as Thompson sampling).

> In fact, polynomial interpolants in Chebyshev points are problem-free when evaluated by the barycentric interpolation formula. They have teh same behavior as discrete Fourier series for period functions, whose reliability nobody worries about. The introduction of splines is a red herring: the true advantage of splines is not that they converge where polynomials fail to do so, but that they are more easility adapted to irregular point distributions and more localized.

You can see also the software package https://www.chebfun.org/ for Chebyshev interpolations with Matlap and https://github.com/rnburn/bbai for interpolation Chebyshev interpolations of arbitrary dimension functions with sparse grids for Python.

Code: https://github.com/rnburn/bbai

https://github.com/rnburn/bbai/blob/master/example/11-meuse-...

References

I’ve been working on a Python project to fit logistic regression models with Jeffreys prior https://github.com/rnburn/bbai.

The github repository https://github.com/rnburn/bbai provides an implementation, a small example demonstrating usage is available at https://github.com/rnburn/bbai/blob/master/example/03-bayesian.py, and here's a comparison to more traditional conjugate prior algorithms for Bayesian linear regression: https://buildingblock.ai/bayesian-ridge-regression#appendix-a-comparison-with-other-bayesian-algorithms