The code used in my article on proxy variables: https://towardsdatascience.com/how-to-use-proxy-variables-in-a-regression-model-539f723ab587

proxy_variables.py

import pandas as pd
import statsmodels.formula.api as smf

#Load the US Census Bureau data into a Dataframe
df = pd.read_csv('us_census_bureau_acs_2015_2019_subset.csv', header=0)

#Construct the model's equation in Patsy syntax. Statsmodels will automatically add the intercept and so we don't explicitly specify it in the model's equation
reg_expr = 'Percent_Households_Below_Poverty_Level ~ Median_Age + Homeowner_Vacancy_Rate + Percent_Pop_25_And_Over_With_College_Or_Higher_Educ'

#Build and train the model and print the training summary
olsr_model = smf.ols(formula=reg_expr, data=df)
olsr_model_results = olsr_model.fit()
print(olsr_model_results.summary())