lifetimes

load_dataset.py

import pandas as pd
from lifetimes.datasets import load_dataset

transactions = load_dataset(
    filename='CDNOW_sample.txt', 
    header=None, 
    delim_whitespace=True, 
    names=['customer_id', 'customer_index', 'date', 'quantity', 'amount'],
    converters={'date': lambda x: pd.to_datetime(x, format="%Y%m%d")}
)

transactions.head(3)