# Profile: Data · NumPy and pandas. Syntax, conversion and policy are separate.
import pandas as pd
text = pd.Series(["2", "001", "1.0", "1.0000000000000001", "unknown", "1000001"], dtype="string")
digit_spelling = text.str.fullmatch(r"[0-9]+")
number = pd.to_numeric(text, errors="coerce")
valid = digit_spelling & number.notna() & number.gt(0) & number.le(1_000_000)
print("Digit spelling:", digit_spelling.tolist())
print("Valid unit counts:", valid.tolist())
print("Accepted source tokens:", text.loc[valid].tolist())
dates = pd.Series(["2026-02-28", "2026-02-30", "2026-2-3", "2500-04-01"], dtype="string")
shape = dates.str.fullmatch(r"[0-9]{4}-[0-9]{2}-[0-9]{2}")
parsed = pd.to_datetime(dates, format="%Y-%m-%d", errors="coerce")
in_range = parsed.between("2000-01-01", "2099-12-31")
valid_dates = shape & parsed.notna() & in_range
print("Date shape:", shape.tolist())
print("Accepted dates:", dates.loc[valid_dates].tolist())