# Profile: Data · NumPy and pandas. Predict each mask before running.
import pandas as pd
raw = pd.DataFrame({"order_id": ["A01", "A01", " A01 ", "B01"],
                    "units": ["2", "2", "3", "4"]}, dtype="string")
print("Source rows:\n" + raw.to_string())
extra = raw.duplicated(keep="first")
print("Exact-copy extras:", extra.tolist())
duplicates = raw.loc[extra].copy()
work = raw.loc[~extra].copy()
work["order_id"] = work["order_id"].str.strip()
conflicts = work["order_id"].duplicated(keep=False)
print("Remaining labels:", work.index.tolist())
print("Conflict decisions:", conflicts.to_dict())
print("Duplicate labels:", duplicates.index.tolist())
print("Conflict source rows:\n" + raw.loc[work.index[conflicts]].to_string())
print("Still eligible for acceptance:", work.loc[~conflicts].index.tolist())

# All remaining rows still receive field checks, including conflicting IDs.