import pandas as pd

orders = pd.DataFrame(
    {
        "order_id": [1001, 1002, 1003, 1004],
        "customer_id": ["C001", "C002", "C001", "C004"],
        "total_usd": [125.0, 240.0, 90.0, 410.0],
    }
)

customers = pd.DataFrame(
    {
        "customer_id": ["C001", "C002", "C003"],
        "segment": ["SMB", "Enterprise", "SMB"],
        "region": ["EMEA", "APAC", "AMER"],
    }
)

left_join = orders.merge(
    customers,
    on="customer_id",
    how="left",
    validate="many_to_one",
    indicator=True,
)

unmatched_orders = left_join.loc[
    left_join["_merge"] == "left_only",
    ["order_id", "customer_id"],
]

inner_join = orders.merge(
    customers,
    on="customer_id",
    how="inner",
    validate="many_to_one",
)

print(f"pandas {pd.__version__}")
print()

print("LEFT_MERGE")
print(left_join.to_string(index=False))
print()

print("UNMATCHED_ORDERS")
print(unmatched_orders.to_string(index=False))
print()

print("LEFT_VERIFY")
print(f"rows={len(left_join)}")
print(f"unmatched_orders={len(unmatched_orders)}")
print(left_join["_merge"].value_counts())
print()

print("INNER_MERGE")
print(inner_join.to_string(index=False))
print()

print("INNER_VERIFY")
print(f"rows={len(inner_join)}")
print(f"all_segments_present={inner_join['segment'].notna().all()}")
print()

print("SOURCE_VERIFY")
print(f"orders rows unchanged={len(orders)}")
print(f"customer keys unique={customers['customer_id'].is_unique}")