Port barmpy to PyMC

[dvbuntu]

PyMC is a python library that tries to fit bayesian models with Markov Chain Monte Carlo. BARN essentially fits that mold, so it would be instructive and potentially useful to port barmpy to that ecosystem. PyMC is a different approach from sklearn, however, so there may be a bit of learning curve. Some good first steps:

1. Understand PyMC-BART
2. Port BARN to PyMC, using PyMC-BART as a starting point
3. Extract only needed MCMC components from PyMC to be used in BARN, keeping sklearn compatibility.

[dvbuntu]

Related but possibly distinct would be using PyMC or another backend to handle all the MCMC stepping. This requires having sufficient control over the process to do the neural network proposal, training, and acceptance. But it may simplify future development and take advantage of available improvements. It was previously important to implement and fully understand myself, but as barmpy matures, it's likely more valuable to use the best possible tools where possible.