KCenters

此笔记本演示了使用 KCenters 算法进行图聚类。

[1]:

from IPython.display import SVG

[2]:

import numpy as np

[3]:

from sknetwork.data import karate_club, painters, movie_actor
from sknetwork.clustering import get_modularity
from sknetwork.clustering import KCenters
from sknetwork.visualization import svg_graph, svg_bigraph

图

[4]:

graph = karate_club(metadata=True)
adjacency = graph.adjacency
position = graph.position

[5]:

kcenters = KCenters(n_clusters=2)
kcenters.fit(adjacency)
labels = kcenters.fit_predict(adjacency)

[6]:

# cluster centers
kcenters.centers_

[6]:

array([19, 15])

[7]:

labels_unique, counts = np.unique(labels, return_counts=True)
print(labels_unique, counts)

[0 1] [16 18]

[8]:

image = svg_graph(adjacency, position, labels=labels)
SVG(image)

[8]:

../../_images/tutorials_clustering_kcenters_10_0.svg

[9]:

# metric
get_modularity(adjacency, labels)

[9]:

0.37146614069690986

有向图

[10]:

graph = painters(metadata=True)
adjacency = graph.adjacency
names = graph.names
position = graph.position

[11]:

# clustering
kcenters = KCenters(n_clusters=3, directed=True)
labels = kcenters.fit_predict(adjacency)

[12]:

labels_unique, counts = np.unique(labels, return_counts=True)
print(labels_unique, counts)

[0 1 2] [5 5 4]

[13]:

# cluster centers
names[kcenters.centers_]

[13]:

array(['Pablo Picasso', 'Edouard Manet', 'Leonardo da Vinci'],
      dtype='<U21')

[14]:

image = svg_graph(adjacency, position, names=names, labels=labels)
SVG(image)

[14]:

../../_images/tutorials_clustering_kcenters_17_0.svg

[15]:

get_modularity(adjacency, labels)

[15]:

0.32480000000000003

二部图

[16]:

graph = movie_actor(metadata=True)
biadjacency = graph.biadjacency
names_row = graph.names_row
names_col = graph.names_col

[17]:

# clustering
kcenters = KCenters(n_clusters=3, center_position="both")
kcenters.fit(biadjacency)
labels_row = kcenters.labels_row_
labels_col = kcenters.labels_col_

[18]:

# cluster centers
centers_row = kcenters.centers_row_
centers_col = kcenters.centers_col_

print("centers row:", names_row[centers_row])
print("centers col:", names_col[centers_col])

centers row: ["Pirates of the Caribbean: At World's End" 'La La Land']
centers col: ['Marion Cotillard']

[19]:

image = svg_bigraph(biadjacency, names_row, names_col, labels_row, labels_col)
SVG(image)

[19]:

../../_images/tutorials_clustering_kcenters_23_0.svg

[20]:

# metric
get_modularity(biadjacency, labels_row, labels_col)

[20]:

0.3861546782044349