sciencehub-team/keeling-curvePublic

def load_co2(path: str = DATA) -> pd.DataFrame:
    """Monthly mean CO₂ in the air at Mauna Loa, Hawaii, in ppm, from March 1958.

    Columns: year, month, decimal_date, average, deseasonalized, ndays, sdev,
    unc. NOAA fills months without measurements by interpolation and marks
    them with a negative ndays.
    """
    co2 = pd.read_csv(path, comment="#")
    return co2.rename(columns={"decimal date": "decimal_date"})

def yearly_mean(path: str = DATA) -> pd.Series:
    """The deseasonalized concentration averaged over each complete year, in ppm, by year."""
    co2 = load_co2(path)
    complete = co2.groupby("year").filter(lambda year: len(year) == 12)
    return complete.groupby("year")["deseasonalized"].mean()

def growth_rate(start_year: int, end_year: int, path: str = DATA) -> float:
    """Average growth of CO₂ between two complete years, in ppm a year.

    >>> round(growth_rate(1960, 1970), 2)
    0.88
    """
    yearly = yearly_mean(path)
    if start_year not in yearly.index or end_year not in yearly.index:
        raise ValueError(f"Both years need twelve months of data; there are {yearly.index.min()} to {yearly.index.max()}.")
    return float((yearly[end_year] - yearly[start_year]) / (end_year - start_year))

def seasonal_cycle(path: str = DATA) -> pd.Series:
    """Each month's mean departure from the deseasonalized trend, in ppm: the breath of the northern forests."""
    co2 = load_co2(path)
    return (co2["average"] - co2["deseasonalized"]).groupby(co2["month"]).mean()