from pathlib import Path

import pandas as pd


path = Path("orders.parquet")

orders = pd.DataFrame(
    {
        "order_id": ["A100", "A101", "A102"],
        "customer": ["Ada", "Lin", "Maya"],
        "region": ["EMEA", "APAC", "AMER"],
        "total_usd": [149.50, 88.00, 212.25],
    }
)

orders.to_parquet(
    path,
    engine="pyarrow",
    compression="snappy",
    index=False,
)

round_trip = pd.read_parquet(path, engine="pyarrow")
selected = pd.read_parquet(
    path,
    engine="pyarrow",
    columns=["order_id", "total_usd"],
)

print(round_trip.to_string(index=False))
print()
print(round_trip.dtypes)
print()
print(f"rows match: {len(round_trip) == len(orders)}")
print(f"columns: {', '.join(round_trip.columns)}")
print(f"selected columns: {', '.join(selected.columns)}")
print(f"order IDs match: {round_trip['order_id'].tolist() == orders['order_id'].tolist()}")