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
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
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:
verbose=True
查看收敛失败的时间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)