from datetime import datetime, timedelta
import random

# Simulate 30 days of sales data
regions = ['North', 'South', 'East', 'West']
products = ['Laptop', 'Tablet', 'Headphones', 'Charger', 'Case']

records = []
start = datetime(2025, 1, 1)

for day in range(30):
    date = start + timedelta(days=day)
    for _ in range(200):
        records.append({
            'date': date.strftime('%Y-%m-%d'),
            'region': random.choice(regions),
            'product': random.choice(products),
            'units_sold': random.randint(1, 20),
            'revenue': round(random.uniform(50, 2000), 2)
        })

df_sales = pd.DataFrame(records)
table_sales = pa.Table.from_pandas(df_sales)

# Save as compressed Parquet
pq.write_table(table_sales, 'sales_jan2025.parquet', compression='ZSTD')
print(f"Saved {len(df_sales):,} records to Parquet")

# Query: total revenue by region for the first two weeks
dataset = ds.dataset('sales_jan2025.parquet', format='parquet')

first_two_weeks = dataset.to_table(
    columns=['region', 'revenue', 'date'],
    filter=ds.field('date') <= '2025-01-14'
).to_pandas()

summary = first_two_weeks.groupby('region')['revenue'].sum().sort_values(ascending=False)
print(f"\nRevenue by region (Jan 1–14):")
print(summary.round(2))