Analyze data frames that contain mainly categorical (string) data

describe_population.py

import pandas as pd

def describe_population(df: pd.DataFrame) -> pd.DataFrame:
    """
    Report the populated and uniqueness counts for each column of the input.
    
    The ratio columns are given as percents.
    """

    N = len(df)

    dtypes = df.dtypes

    distincts = df.nunique()
    nas = df.isnull().sum()
    pop = N - nas

    out = pd.DataFrame()

    out['dtype'] = dtypes

    out['na'] = nas
    out['populated'] = pop
    out['distinct'] = distincts

    out['pop/N'] = 100 * pop / N
    out['dist/pop'] = 100 * distincts / pop

    out.columns.name = "N = {:,}".format(N)

    return out

Thank you! I will modify it to reveal data values since I don't have to worry about revealing secrets in my use case.