Dupe-check logging

dupe_checking_paradigm.py

import datetime

# Filename function for logging
def dt_filename(
        filename: str,
        extension: str,
        path: str = "",
        date: str = str(datetime.datetime.now()),
) -> str:
    filename = "_".join([filename, date])
    return "/".join([path, filename]) + extension

# Write dupes to output files suffixed by datetime
# THIS IS AN EXAMPLE
dupes_idx = [df.duplicated(keep=False), 
             df['client_id'].duplicated(keep=False)]

dupes_filenames = ['row_dupes', 
                   'client_dupes']

for idx, filename in zip(dupes_idx, dupes_filenames):
    if not idx.any():
        print(f"No duplicates for {filename}!")
    else:
        df[idx].to_csv(dt_filename(filename, '.csv', 'outputs'))
        print(filename)
        display(df[idx])