Magnitude on a local model — the real artifacts

import pandas as pd

file_path = './sales-h1-2026.csv'

try:
    df = pd.read_csv(file_path)

    # Ensure necessary columns exist and are numeric
    if 'units' not in df.columns or 'unit_price' not in df.columns or 'client' not in df.columns or 'region' not in df.columns:
        print('Error: The CSV file is missing one or more required columns (\'units\', \'unit_price\', \'client\', \'region\').')
    else:
        # Calculate total revenue per line item
        df['revenue'] = df['units'] * df['unit_price']

        # Calculate total revenue per client
        client_revenue = df.groupby('client')['revenue'].sum().sort_values(ascending=False).reset_index()
        client_revenue.rename(columns={'revenue': 'total_revenue'}, inplace=True)

        # Identify most frequent region
        region_counts = df['region'].value_counts()
        most_frequent_region = region_counts.idxmax()

        print('--- Total Revenue Per Client (Top Clients) ---\n')
        print(client_revenue.to_markdown(index=False))
        print(f'\n--- Most Frequent Region ---\n')
        print(f'The region that appears most is: {most_frequent_region} with {region_counts.max()} entries.')

except FileNotFoundError:
    print(f'Error: The file {file_path} was not found.')
except Exception as e:
    print(f'An error occurred during processing: {e}')