计算两个聚类结果的聚类准确性

使用兰德指数：

import numpy as np
from scipy.special import comb

def rand_index_score(clusters, classes):

    tp_plus_fp = comb(np.bincount(clusters), 2).sum()
    tp_plus_fn = comb(np.bincount(classes), 2).sum()
    A = np.c_[(clusters, classes)]
    tp = sum(comb(np.bincount(A[A[:, 0] == i, 1]), 2).sum()
             for i in set(clusters))
    fp = tp_plus_fp - tp
    fn = tp_plus_fn - tp
    tn = comb(len(A), 2) - tp - fp - fn
    return (tp + tn) / (tp + fp + fn + tn)

clusters = [0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2]

classes = [0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 2, 1, 0, 2, 2, 2, 0]

rand_index_score(clusters, classes)
0.6764705882352942