Remove duplicate records from CSV

remove_duplicates.py

import pandas as pd

# Read the data from the exported CSV file
df = pd.read_csv('exported_data.csv')

# Remove duplicates based on user_id, mail_id, and send_date
df_cleaned = df.drop_duplicates(subset=['user_id', 'mail_id', 'send_date'])

# Write the cleaned data to a new file
df_cleaned.to_csv('cleaned_data.csv', index=False)