https://stackoverflow.com/questions/67838850/descriptive-statistics-of-multi-level-categorical-data-in-python

setup.py

#!/usr/bin/python3
import numpy as np
import pandas as pd

df = pd.DataFrame(np.random.randint(1900, 2000, 50), columns=['year'])

df['age_bin'] = pd.cut(pd.Timestamp.today().year - df['year'],
                       bins=[-np.inf,30,40,50,60,70,np.inf],
                       labels=['-30','30-39','40-49','50-59','60-69','70+'])

df['location'] = pd.Series(np.random.randint(1, 6, 50)).map({
    1: 'england',
    2: 'ireland',
    3: 'scotland',
    4: 'wales',
    5: 'jersey',
    6: 'gurnsey',
}).fillna('Other')


df['status'] = pd.Series(np.random.randint(1, 6, 50)).map({
    1: 'married',
    2: 'divorced',
    3: 'single',
    4: 'window',
}).fillna('Other')

print(df)