Let's start by pulling the model into Python and transforming it into a form that we can use. To do this, we will need two additional libraries. We will use Pandas to read from our generated CSV and statsmodel to run our statistical procedures. Both libraries are pretty powerful and full of features, and we will only be touching on a few of them so feel free to explore them further later.

To start off, let's make a test that will run a simple regression over one of the variables and show us the output. That should give us a good place to start. I'm keeping this in a unit testing structure because I know I want to test this code and just want to explore a bit to know exactly what to test for. This first step you could do in a one-off file, but I'm choosing to start with it so I can build from it:

import pandas
import statsmodels.formula.api as sm
import nose.tools as nt

def vanilla_model_test():
  df = pandas.read_csv('./generated_data.csv')
  model_fit...