from pathlib import Path
import sys
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import lapylace as lp
sys.path.append(str(Path.cwd().parent / 'python'))
from data import ros_pathGay
Simple models (linear and discretized age) and attitudes as a function of age. See Chapter 12 in Regression and Other Stories.
Source: Gay/gay_simple.Rmd.
The Python version keeps data handling explicit and uses lapylace for Stan-backed generalized linear models, so the statistical model can be read from a formula rather than from handwritten Stan.
Data
naes04 = pd.read_csv(ros_path('Gay/data', 'naes04.csv'))
naes04.head()| Unnamed: 0 | age | gender | race | gayFavorFederalMarriage | gayFavorStateMarriage | gayKnowSomeone | |
|---|---|---|---|---|---|---|---|
| 0 | 1 | 70.0 | Female | Hispanic | No | NaN | NaN |
| 1 | 2 | 54.0 | Female | White | No | NaN | NaN |
| 2 | 3 | 74.0 | Male | White | No | NaN | NaN |
| 3 | 4 | 73.0 | Female | Other | Yes | No | No |
| 4 | 5 | 48.0 | Female | White | No | Yes | Yes |
Models
The formulas below are the Python counterparts of the model formulas in the source example. Use lapylace for the Stan-backed Bayesian fit with the same formula interface.
# fit = lp.stan_glm('support ~ age', data=naes04, family=lp.gaussian(), chains=4, iter_sampling=1000)
# fit = lp.stan_glm('support ~ factor(age_discrete)', data=naes04, family=lp.gaussian(), chains=4, iter_sampling=1000)Notes
- Source computation blocks represented: 10.
- Data paths are expressed through the shared
ros_path()helper. - Formula-based Bayesian regressions are routed through
lapylace.stan_glm(). - Plotting and simulation work uses NumPy, pandas, matplotlib idioms.