import time

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

start = time.time()

# Fix 1: Correct data types upfront
df['region'] = df['region'].astype('category')
df['category'] = df['category'].astype('category')
df['status'] = df['status'].astype('category')

# Fix 2: Vectorized revenue calculation, no temporary columns
df['net_revenue'] = df['sales'] * df['quantity'] * (1 - 0.075)

# Fix 3: Vectorized flagging with np.where
df['order_flag'] = np.where(df['net_revenue'] > 50000, 'high', 'low')

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

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