Love the book! Ran into this display issue when viewing it on Chrome's PDF viewer:

Description:

We need some easy to follow instructions on how to use the core Stan inside a user-written C++ program. See stan-dev/stan#3085 for example.

The instruction can simply guide through the task of compiling one of the models and running MCMC with the services. The biggest challenges are typically all the dependencies that we need to include in the C++

Feature request

In several places we use multiple dispatch. Right now the types to dispatch on are configured separately. Could we infer the types to dispatch on from Python type hints? That would simplify the code.

Motivation

Instead of:

@dispatch.expectation.register(Gaussian, kernels.Sum, InducingPoints, NoneType, NoneType)
def expectation_gaussian_sum_inducingpoints(
    

trace_to_dataframe() in PyMC3 to save traces is currently implemented in Rethinking_2 notebooks (e.g. Chp_04). But the function is planned for deprecation, with Arviz being the intended package to save traces. As per this comment by @AlexAndorra, Arviz's InferenceData format is a superior replacement to this function as it