sklearn调整后的大集互信息得分

Question

from sklearn.metrics import adjusted_mutual_info_score
import numpy as np

a = np.random.randint(0,2,30000000)
b = np.random.randint(0,2,30000000)

print(a.shape)
print(b.shape)

c = adjusted_mutual_info_score(a,b)

print(c)

如果运行以下代码，您将退出：

RuntimeWarning: invalid value encountered in log
  log_outer = -np.log(outer) + log(pi.sum()) + log(pj.sum())
nan

我不明白为什么会这样，但是如果您制作1000个值的较小集合，则一切运行正常。谁能告诉我发生了什么事以及如何解决这个问题？我会很感激的。