GSVD

此笔记本说明了通过广义奇异值分解邻接矩阵来嵌入图。

[1]:

from IPython.display import SVG

[2]:

import numpy as np

[3]:

from sknetwork.data import karate_club, painters, movie_actor
from sknetwork.embedding import GSVD
from sknetwork.visualization import visualize_graph, visualize_bigraph

图

[4]:

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

[5]:

gsvd = GSVD(2, normalized=False)
embedding = gsvd.fit_transform(adjacency)

[6]:

image = visualize_graph(adjacency, embedding, labels=labels)
SVG(image)

[6]:

../../_images/tutorials_embedding_gsvd_8_0.svg

有向图

[7]:

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

[8]:

gsvd = GSVD(2, normalized=False)
embedding = gsvd.fit_transform(adjacency)

[9]:

image = visualize_graph(adjacency, embedding, names=names)
SVG(image)

[9]:

../../_images/tutorials_embedding_gsvd_12_0.svg

二部图

[10]:

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

[11]:

gsvd = GSVD(2, normalized=False)
gsvd.fit(biadjacency)

[11]:

GSVD(n_components=2, regularization=None, factor_row=0.5, factor_col=0.5, factor_singular=0.0, normalized=False, solver=LanczosSVD(n_iter=None, tol=0.0))

[12]:

embedding_row = gsvd.embedding_row_
embedding_col = gsvd.embedding_col_

[13]:

image = visualize_bigraph(biadjacency, names_row, names_col,
                    position_row=embedding_row, position_col=embedding_col,
                    color_row='blue', color_col='red')
SVG(image)

[13]:

../../_images/tutorials_embedding_gsvd_17_0.svg