import time

df = pd.read_csv('large_sales_data.csv')

start = time.time()

# Row-wise revenue calculation
df['gross_revenue'] = df.apply(
    lambda row: row['sales'] * row['quantity'], axis=1
)
df['tax'] = df.apply(
    lambda row: row['gross_revenue'] * 0.075, axis=1
)
df['net_revenue'] = df.apply(
    lambda row: row['gross_revenue'] - row['tax'], axis=1
)

# Row-wise flagging
df['order_flag'] = df.apply(
    lambda row: 'high' if row['net_revenue'] > 50000 else 'low', axis=1
)

# Final aggregation
result = df.groupby('region')['net_revenue'].sum()

end = time.time()
print(f"Total runtime: {end - start:.2f} seconds")