python - 在 python 中绘制 sklearn 集群

Question

我使用亲和性传播获得了以下 sklearn 集群。

import sklearn.cluster
import numpy as np

sims =  np.array([[0, 17, 10, 32, 32], [18, 0, 6, 20, 15], [10, 8, 0, 20, 21], [30, 16, 20, 0, 17], [30, 15, 21, 17, 0]])

affprop = sklearn.cluster.AffinityPropagation(affinity="precomputed", damping=0.5)
affprop.fit(sims)

cluster_centers_indices = affprop.cluster_centers_indices_
labels = affprop.labels_
#number of clusters
n_clusters_ = len(cluster_centers_indices)

现在我想绘制集群的输出。我是 sklearn 的新手。请建议我一种合适的方法来在 python 中绘制集群。是否可以使用 pandas 数据框来做到这一点？

编辑:

我使用了code in sklearn直接按照@MohammedKashif 的指示进行操作。

import sklearn.cluster

import numpy as np

sims =  np.array([[0, 17, 10, 32, 32], [18, 0, 6, 20, 15], [10, 8, 0, 20, 21], [30, 16, 20, 0, 17], [30, 15, 21, 17, 0]])

affprop = sklearn.cluster.AffinityPropagation(affinity="precomputed", damping=0.5)
affprop.fit(sims)

cluster_centers_indices = affprop.cluster_centers_indices_
print(cluster_centers_indices)
labels = affprop.labels_
n_clusters_ = len(cluster_centers_indices)
print(n_clusters_)

import matplotlib.pyplot as plt
from itertools import cycle

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

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

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

但是，我得到的输出有点奇怪，如下所示(第二个聚类点(绿色)位于蓝线上。因此，我认为它不应该聚类为一个单独的点，也应该位于蓝色中簇)。如果我在代码中犯了任何错误，请告诉我。

编辑2

正如 σηγ 所指出的，我补充道:

se = SpectralEmbedding(n_components=2, affinity='precomputed')
X = se.fit_transform(sims)
print(X)

但是，对于数组 np.array([[0, 17, 10, 32, 32], [0, 17, 10, 32, 32], [0, 17, 10, 32, 33 ], [0, 17, 10, 32, 32], [0, 17, 10, 32, 32]]) 它给了我 3 分，如下所示。这让我很困惑，因为所有 5 个数组都代表一个点。

请帮助我。

Answer 1

按照前面的例子，我会尝试这样的事情:

import sklearn.cluster
from sklearn.manifold import SpectralEmbedding
import numpy as np
import matplotlib.pyplot as plt
from itertools import cycle

sims =  np.array([[0, 17, 10, 32, 32], [18, 0, 6, 20, 15], [10, 8, 0, 20, 21], [30, 16, 20, 0, 17], [30, 15, 21, 17, 0]])

affprop = sklearn.cluster.AffinityPropagation(affinity="precomputed", damping=0.5)
affprop.fit(sims)

cluster_centers_indices = affprop.cluster_centers_indices_
print(cluster_centers_indices)
labels = affprop.labels_
n_clusters_ = len(cluster_centers_indices)
print(n_clusters_)

se = SpectralEmbedding(n_components=2, affinity='precomputed')
X = se.fit_transform(sims)

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

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

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