问如何检测大数据集中的多元异常值？

EN

from scipy.stats import chi2
import scipy as sp
import numpy as np
def mahalanobis_method(df):
    #M-Distance
    x_minus_mean = df - np.mean(df)
    cov = np.cov(df.values.T)                           #Covariance
    inv_covmat = sp.linalg.inv(cov)                     #Inverse covariance
    left_term = np.dot(x_minus_mean, inv_covmat) 
    mahal = np.dot(left_term, x_minus_mean.T)
    md = np.sqrt(mahal.diagonal())
    
    #Flag as outliers
    outliers = []
    #Cut-off point
    C = np.sqrt(chi2.ppf((1-0.001), df=df.shape[1]))    #degrees of freedom = number of variables
    for i, v in enumerate(md):
        if v > C:
            outliers.append(i)
        else:
            continue
    return outliers, md