import pandas as pd


orders = pd.DataFrame(
    {
        "order_id": ["A100", "A101", "A102", "A103", "A104"],
        "customer": [
            " Ada Lovelace ",
            "LIN   CHEN",
            "Maya Patel",
            "  n/a ",
            None,
        ],
        "status": [" Paid ", "PAID", " pending", "", pd.NA],
    }
)
cleaned = orders.copy()

cleaned["customer"] = (
    cleaned["customer"]
    .astype("string")
    .str.strip()
    .str.replace(r"\s+", " ", regex=True)
    .replace({"n/a": pd.NA})
)

cleaned["status"] = (
    cleaned["status"]
    .astype("string")
    .str.strip()
    .str.casefold()
    .replace({"": pd.NA, "n/a": pd.NA})
)

expected_customer = pd.Series(
    ["Ada Lovelace", "LIN CHEN", "Maya Patel", pd.NA, pd.NA],
    name="customer",
    dtype="string",
)
expected_status = pd.Series(
    ["paid", "paid", "pending", pd.NA, pd.NA],
    name="status",
    dtype="string",
)

assert len(cleaned) == len(orders)
pd.testing.assert_series_equal(cleaned["customer"], expected_customer)
pd.testing.assert_series_equal(cleaned["status"], expected_status)

print(cleaned.to_string(index=False))
print()
print(f"rows retained: {len(cleaned)}")
print(f"missing customers: {cleaned['customer'].isna().sum()}")
print(f"missing statuses: {cleaned['status'].isna().sum()}")