偏好值的更改不会影响亲和力传播聚类的结果

时间:2019-05-11 06:23:06

标签: python cluster-analysis

请参阅以下代码

import numpy as np
from sklearn.cluster import AffinityPropagation
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs

##############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=300, centers=centers, cluster_std=0.5)

# Compute similarities
X_norms = np.sum(X ** 2, axis=1)
S = - X_norms[:, np.newaxis] - X_norms[np.newaxis, :] + 2 * np.dot(X, X.T)
p=[10 * np.median(S),np.mean(S,axis=1),np.mean(S,axis=0),100000,-100000]
##############################################################################

# Compute Affinity Propagation
for preference in p:
    af = AffinityPropagation().fit(S, preference)
    cluster_centers_indices = af.cluster_centers_indices_
    labels = af.labels_

    n_clusters_ = len(cluster_centers_indices)

    print('Estimated number of clusters: %d' % n_clusters_)
    print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
    print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
    print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
    print("Adjusted Rand Index: %0.3f" % \
          metrics.adjusted_rand_score(labels_true, labels))
    print("Adjusted Mutual Information: %0.3f" % \
          metrics.adjusted_mutual_info_score(labels_true, labels))
    D = (S / np.min(S))
    print("Silhouette Coefficient: %0.3f" %
          metrics.silhouette_score(D, labels, metric='precomputed'))

    ##############################################################################

    # Plot result
    import pylab as pl
    from itertools import cycle

    pl.close('all')
    pl.figure(1)
    pl.clf()

    colors = cycle('bgrcmykbgrcmykbgrcmykbgrcmyk')
    for k, col in zip(range(n_clusters_), colors):
        class_members = labels == k
        cluster_center = X[cluster_centers_indices[k]]
        pl.plot(X[class_members, 0], X[class_members, 1], col + '.')
        pl.plot(cluster_center[0], cluster_center[1], 'o', markerfacecolor=col,
                markeredgecolor='k', markersize=14)
        for x in X[class_members]:
            pl.plot([cluster_center[0], x[0]], [cluster_center[1], x[1]], col)

    pl.title('Estimated number of clusters: %d' % n_clusters_)
    pl.show()

尽管我在循环中更改了首选项值,但仍然得到相同的集群吗?那么,为什么偏好值的变化不影响聚类结果呢?

更新

当我尝试以下代码时,结果如下

correct

当我尝试使用Agost在构造函数中建议的建议时,我得到了以下输出结果

enter image description here

2 个答案:

答案 0 :(得分:1)

首选项是AffinityPropagation构造函数的参数,而不是fit()方法的参数。您应该将第19行更改为:

af = AffinityPropagation(preference=preference).fit(S)

答案 1 :(得分:1)

AP的sklearn实现似乎非常脆弱。

我的使用建议:

  • 使用verbose=True查看收敛失败的时间
  • 将最大迭代次数增加到至少1000
  • 通过选择0.9而不是0.5来减小阻尼

原因是使用默认参数时,sklearn的AP通常不会收敛...

如@AgostBiro之前所述,首选项不是fit函数(而是构造函数)的参数,因此您的原始代码忽略了该首选项,因为fit(X,y)忽略y(具有无效的y参数是一个愚蠢的API,但是sklearn认为它看起来像分类API)