https://www.notion.so/davidclarance/Stable-and-fast-randomization-using-hash-spaces-ce9357ae742b4e30b67a34fe87fee84e

stable_randomization_duckdb.sql

CREATE TABLE IF NOT EXISTS customers AS
SELECT 'Customer1' AS customer_id UNION ALL
SELECT 'Customer2' AS customer_id UNION ALL
SELECT 'Customer3' AS customer_id UNION ALL
SELECT 'Customer4' AS customer_id;


SELECT 
    c.customer_id,
    ('0x' || md5(c.customer_id)[:10])::int64 % 100 as assigned_bucket
FROM 
    customers c;

You can see the python version here: https://gist.github.com/davidclarance/daeafad5fc3e28e019950a12b0da01f5