วิธีแก้ Notebook ในงาน Data Science 'ตาย': 6 นิสัยสร้างโค้ดที่รันได้ยาวนาน

from pathlib import Path
import pandas as pd
 
DATA_PATH = Path("olympics_athletes_events.csv")
RANDOM_SEED = 42
 
NATURAL_KEY = ["id", "games", "event"]
SENTINEL_ID_FLOOR = 900_000   # real athlete ids in this extract stop at 134205
VALID_SEXES = {"M", "F"}
VALID_MEDALS = {"Gold", "Silver", "Bronze"}
AGE_RANGE = (10, 75)
HEIGHT_RANGE_CM = (120, 230)
WEIGHT_RANGE_KG = (25, 220)
MIN_ATHLETES_PER_SPORT = 5

def load_raw(path: Path) -> pd.DataFrame:
    """Read the Olympics CSV with no cleaning applied."""
    return pd.read_csv(path)
 
def clean(df: pd.DataFrame) -> pd.DataFrame:
    """Drop test rows and duplicate entries, then encode 'no medal' explicitly."""
    out = df[df["id"] < SENTINEL_ID_FLOOR].copy()
    out = out.drop_duplicates(subset=NATURAL_KEY, keep="first")
    out["medal"] = out["medal"].fillna("None")
    out["sex"] = out["sex"].astype("category")
    out["season"] = out["season"].astype("category")
    return out.reset_index(drop=True)
 
def add_features(df: pd.DataFrame) -> pd.DataFrame:
    """Add decade, is_medalist and bmi. Never mutates the input frame."""
    out = df.copy()
    out["decade"] = (out["year"] // 10) * 10
    out["is_medalist"] = out["medal"].ne("None")
    out["bmi"] = bmi(out["weight"], out["height"])
    return out

def validate_raw(df: pd.DataFrame) -> list[str]:
    """Return a list of contract violations. An empty list means the data is usable."""
    problems = []
 
expected = {"id", "sex", "age", "height", "weight", "year", "sport", "event",
                "medal", "games", "team"}
    missing = expected - set(df.columns)
    if missing:
        problems.append(f"missing columns: {sorted(missing)}")
        return problems
 
dupes = df.duplicated(subset=NATURAL_KEY).sum()
    if dupes:
        problems.append(f"{dupes} duplicate rows on {NATURAL_KEY}")
 
sentinels = df.loc[df["id"] >= SENTINEL_ID_FLOOR, "id"]
    if len(sentinels):
        found = sorted(int(i) for i in sentinels.unique())
        problems.append(f"{len(sentinels)} sentinel ids: {found}")
 
bad_sex = set(df["sex"].dropna().unique()) - VALID_SEXES
    if bad_sex:
        problems.append(f"unexpected sex values: {bad_sex}")
 
bad_medal = set(df["medal"].dropna().unique()) - VALID_MEDALS
    if bad_medal:
        problems.append(f"unexpected medal values: {bad_medal}")
 
for col, (lo, hi) in [("age", AGE_RANGE),
                          ("height", HEIGHT_RANGE_CM),
                          ("weight", WEIGHT_RANGE_KG)]:
        out = df[col].dropna()
        n = ((out < lo) | (out > hi)).sum()
        if n:
            problems.append(f"{n} {col} values outside {lo}-{hi}")
 
return problems

def _fixture() -> pd.DataFrame:
    return pd.DataFrame({
        "id": [1, 1, 2],
        "games": ["1924 Summer"] * 3,
        "event": ["Rings", "Rings", "Rings"],
        "sex": ["M", "M", "F"],
        "age": [24.0, 24.0, None],
        "height": [180.0, 180.0, 165.0],
        "weight": [81.0, 81.0, 55.0],
        "year": [1924, 1924, 1924],
        "season": ["Summer"] * 3,
        "sport": ["Gymnastics"] * 3,
        "medal": ["Gold", "Gold", None],
        "team": ["Denmark"] * 3,
    })
 
def run_tests() -> None:
    fx = _fixture()
 
assert len(clean(fx)) == 2, "clean() must drop the duplicate entry"
    assert clean(fx)["medal"].tolist() == ["Gold", "None"], "missing medal becomes 'None'"
 
before = fx.copy()
    add_features(fx)
    pd.testing.assert_frame_equal(fx, before)   # add_features must not mutate
 
feat = add_features(clean(fx))
    assert feat["is_medalist"].tolist() == [True, False]
    assert round(feat.loc[0, "bmi"], 1) == 25.0
    assert feat["decade"].unique().tolist() == [1920]
 
assert validate_raw(fx) == [f"1 duplicate rows on {NATURAL_KEY}"]
    assert "missing columns" in validate_raw(pd.DataFrame({"id": [1]}))[0]
 
planted = pd.concat([fx, fx.iloc[[2]].assign(id=999999)], ignore_index=True)
    assert any("sentinel" in p for p in validate_raw(planted))
    assert 999999 not in clean(planted)["id"].values
 
print("all 10 checks passed")

def bmi(weight_kg: float, height_cm: float) -> float:
    """Body mass index in kg/m2.
 
>>> round(bmi(81.0, 180.0), 1)
    25.0
    >>> round(bmi(55.0, 165.0), 1)
    20.2
    """
    return weight_kg / (height_cm / 100) ** 2
 
import doctest
doctest.run_docstring_examples(bmi, globals(), name="bmi", verbose=True)

def main() -> pd.DataFrame:
    raw = load_raw(DATA_PATH)
    problems = validate_raw(raw)
    df = add_features(clean(raw))
 
print("\nspot check:")
    print(df.sample(3, random_state=RANDOM_SEED)[["name", "year", "sport", "medal", "bmi"]])
 
report = medal_rate_by_sport(df)
    return report
 
if __name__ == "__main__":
    run_tests()
    doctest.run_docstring_examples(bmi, globals(), name="bmi", verbose=True)
    main()