tools.py 文件源码

def generalized_esd(x, r, alpha=0.05, method='mean'):
    """Generalized ESD test for outliers
       (http://www.itl.nist.gov/div898/handbook/eda/section3/eda35h3.htm).

    Args:
        x (numpy.ndarray): the data
        r (int): max number of outliers
        alpha (float): the signifiance level
        method (str): 'median' or 'mean'

    Returns:
        list[int]: list of the index of outliers
    """
    x = np.asarray(x, dtype=np.float64)
    fn = __get_pd_median if method == 'median' else __get_pd_mean
    NaN = float('nan')
    outliers = []
    N = len(x)
    for i in range(1, r + 1):
        if np.any(~np.isnan(x)):
            m, e = fn(x)
            if e != 0.:
                y = np.abs(x - m)
                j = np.nanargmax(y)
                R = y[j]
                lam = __get_lambda_critical(N, i, alpha)
                if R > lam * e:
                    outliers.append(j)
                    x[j] = NaN
                else:
                    break
            else:
                break
        else:
            break
    return outliers