univariateselection.py 文件源码

def kolmogorov_smirnov(x_train, x_test):
    r = []
    p = []
    for c in x_train.columns:
        r_, p_ = ks_2samp(x_train[c], x_test[c])
        r.append(r_)
        p.append(p_)
    dfks = pd.DataFrame(index=range(1, 1 + len(x_train.columns)))
    dfks['KS'] = r
    dfks['KS_p'] = p
    return dfks