adjusted rand index和adjusted mutual information score

最新推荐文章于 2023-02-23 14:54:25 发布

ASD991936157

最新推荐文章于 2023-02-23 14:54:25 发布

阅读量2.1k

点赞数

本文链接：https://blog.csdn.net/ASD991936157/article/details/52206875

版权

这段代码演示了如何使用`sklearn.metrics`中的`adjusted_rand_score`和`adjusted_mutual_info_score`来评估随机生成的标签分配。通过对不同数量的聚类（2到100）进行多次运行，计算平均得分和标准差，展示两者在随机标签情况下的性能差异。

摘要由CSDN通过智能技术生成

import matplotlib.pyplot as plt
import numpy as np
from sklearn import metrics


def uniform_labelings_scores(score_func, n_samples, n_clusters_range, fixed_n_classes=None, n_runs=5, seed=42):
    random_labels = np.random.RandomState(seed).random_integers
    scores = np.zeros((len(n_clusters_range), n_runs))
    for i, k in enumerate(n_clusters_range):
        for j in range(n_runs):
            if fixed_n_classes is None:
                labels_a = random_labels(low=1, high=k, size=n_samples)
            else:
                labels_a = random_labels(low=1, high=fixed_n_classes, size=n_samples)
            labels_b = random_labels(low=1, high=k, size=n_samples)
            scores[i, j] = score_func(labels_a, labels_b)
    return scores


score_funcs = [metrics.adjusted_rand_score, metrics.adjusted_mutual_info_score]
n_samples = 100
n_clusters_range = map(int, np.lin