WARNING: Some of the functions used are now deprecated. It is unlikely I will correct this, due to lack of time.
Here's a notebook and some resources I used at the PyData Munich meetup talk (January 2018).
I know we all love Python and it's great to work and play around with, but if you have a serious project and you're eager to do something with Bayesian networks, then check out the Tetrad project - it's powerful, well documented and open-source.
Readings:
-
https://www.nature.com/articles/nmeth.3550.pdf (A brief open-access tutorial paper from Nature)
-
http://www.cs.technion.ac.il/~dang/books/Learning%20Bayesian%20Networks(Neapolitan,%20Richard).pdf (a classic theory book)
-
https://mitpress.mit.edu/books/probabilistic-graphical-models (A book from the author of a Coursera course on BN; thanks to the anonymous listener for the reference!)
-
https://press.princeton.edu/titles/9991.html (A very good book with probability puzzles you'll solve with a computer)
-
https://www.countbayesie.com/ (One of my favourite blogs - it's also where I got the previous reference from!)