# Profile: Data · NumPy and pandas. Keep source labels while adding reasons.
import pandas as pd
raw = pd.DataFrame({"code": ["R1", "R1", "R2", "R3"],
"date": ["2026-04-01", "2026-04-01", "not-a-date", "2026-04-03"],
"units": ["2", "2", "unknown", "4"]}, dtype="string")
work = raw.loc[[0, 2, 3]].copy() # label 1 was an exact duplicate in this toy case
work["units"] = pd.to_numeric(work["units"], errors="coerce")
work["date"] = pd.to_datetime(work["date"], format="%Y-%m-%d", errors="coerce")
checks = {"invalid_units": work["units"].isna(),
"invalid_date": work["date"].isna()}
reasons = pd.Series("", index=work.index, dtype="string")
for name, mask in checks.items():
reasons.loc[mask] = reasons.loc[mask] + name + ";"
reasons = reasons.str.rstrip(";")
valid = reasons.eq("")
rejected = raw.loc[work.index[~valid]].copy()
rejected["reason"] = reasons.loc[~valid]
print("Working labels:", work.index.tolist())
print("Reason labels:", reasons.index.tolist())
print("Reasons:", reasons.to_dict())
print("Untouched source row 2:", raw.loc[2].to_dict())
print("Rejected evidence:\n" + rejected.to_string(index=False))
