import os

# Generate a larger dataset
large_data = {
    'transaction_id': range(50000),
    'store': ['Downtown', 'Uptown', 'Suburban', 'Airport', 'Mall'] * 10000,
    'product': [f'product_{i % 200}' for i in range(50000)],
    'amount': [round(10 + (i % 500) * 0.5, 2) for i in range(50000)]
}

df_large = pd.DataFrame(large_data)
table_large = pa.Table.from_pandas(df_large)

# Write with different compression codecs
for codec in ['NONE', 'SNAPPY', 'GZIP', 'ZSTD']:
    path = f'transactions_{codec.lower()}.parquet'
    pq.write_table(table_large, path, compression=codec)
    size = os.path.getsize(path)
    print(f"{codec:<8}: {size:>10,} bytes")