Reattribute GitHub EMU Account Post Migration

reattribute_github_emu.py

import pandas as pd
import argparse

def merge_data(mannequin_df, users_df, slug):
    # Merge the dataframes on 'mannequin-user' and 'login'
    merged_df = pd.merge(mannequin_df, users_df, left_on='mannequin-user', right_on='login', how='inner')

    # Ensure that we only apply the transformation on non-null 'name' values
    merged_df['name'] = merged_df['name'].apply(lambda x: f"{x.replace(' ', '-').lower()}_{slug}" if isinstance(x, str) else '')

    # Select and reorder the columns to match the desired output
    output_df = merged_df[['mannequin-user', 'mannequin-id', 'target-user', 'name']]

    # Save the result to a new CSV
    output_df.to_csv('merged_output.csv', index=False)
    print("CSV file has been created successfully.")

if __name__ == '__main__':
    # Set up argument parsing
    parser = argparse.ArgumentParser(
        description='This script merges mannequin user data with user data based on the mannequin-user and login fields. '
                    'It outputs a CSV file with the merged data, including a transformed name column.'
    )
    parser.add_argument('mannequin_df', type=str, help='Path to the mannequin CSV file')
    parser.add_argument('users_df', type=str, help='Path to the users CSV file')
    parser.add_argument('slug', type=str, help='Suffix to append to the name column')

    # Parse the arguments
    args = parser.parse_args()

    # Load the CSV files
    mannequin_df = pd.read_csv(args.mannequin_df)
    users_df = pd.read_csv(args.users_df)

    # Call the merge function with arguments
    merge_data(mannequin_df, users_df, f"_{args.slug}")