巴黎
此笔记本说明了通过 巴黎算法 对图进行层次聚类。
[1]:
from IPython.display import SVG
[2]:
import numpy as np
[3]:
from sknetwork.data import karate_club, painters, movie_actor
from sknetwork.hierarchy import Paris, cut_straight, dasgupta_score, tree_sampling_divergence
from sknetwork.visualization import visualize_graph, visualize_bigraph, visualize_dendrogram
图
[4]:
graph = karate_club(metadata=True)
adjacency = graph.adjacency
position = graph.position
[5]:
# hierarchical clustering
paris = Paris()
dendrogram = paris.fit_predict(adjacency)
[6]:
image = visualize_dendrogram(dendrogram)
SVG(image)
[6]:
[7]:
# cuts of the dendrogram
labels = cut_straight(dendrogram)
print(labels)
[1 1 1 1 1 1 1 1 0 1 1 1 1 1 0 0 1 1 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0 0]
[8]:
n_clusters = 4
labels, dendrogram_aggregate = cut_straight(dendrogram, n_clusters, return_dendrogram=True)
print(labels)
[0 0 0 0 3 3 3 0 1 0 3 0 0 0 1 1 3 0 1 0 1 0 1 2 2 2 2 2 2 2 1 2 1 1]
[9]:
_, counts = np.unique(labels, return_counts=True)
[10]:
# aggregate dendrogram
image = visualize_dendrogram(dendrogram_aggregate, names=counts, rotate_names=False)
SVG(image)
[10]:
[11]:
# corresponding clustering
image = visualize_graph(adjacency, position, labels=labels)
SVG(image)
[11]:
[12]:
# metrics
dasgupta_score(adjacency, dendrogram)
[12]:
0.6655354449472097
有向图
[13]:
graph = painters(metadata=True)
adjacency = graph.adjacency
position = graph.position
names = graph.names
[14]:
# hierarchical clustering
paris = Paris()
dendrogram = paris.fit_predict(adjacency)
[15]:
image = visualize_dendrogram(dendrogram, names, n_clusters=3, rotate=True)
SVG(image)
[15]:
[16]:
# cut with 3 clusters
labels = cut_straight(dendrogram, n_clusters = 3)
print(labels)
[0 0 1 0 1 1 2 0 0 1 0 0 0 2]
[17]:
image = visualize_graph(adjacency, position, names=names, labels=labels)
SVG(image)
[17]:
[18]:
# metrics
dasgupta_score(adjacency, dendrogram)
[18]:
0.5842857142857143
二部图
[19]:
graph = movie_actor(metadata=True)
biadjacency = graph.biadjacency
names_row = graph.names_row
names_col = graph.names_col
[20]:
# hierarchical clustering
paris = Paris()
paris.fit(biadjacency)
dendrogram_row = paris.dendrogram_row_
dendrogram_col = paris.dendrogram_col_
dendrogram_full = paris.dendrogram_full_
[21]:
image = visualize_dendrogram(dendrogram_row, names_row, n_clusters=4, rotate=True)
SVG(image)
[21]:
[22]:
image = visualize_dendrogram(dendrogram_col, names_col, n_clusters=4, rotate=True)
SVG(image)
[22]:
[23]:
# cuts
labels = cut_straight(dendrogram_full, n_clusters = 4)
n_row = biadjacency.shape[0]
labels_row = labels[:n_row]
labels_col = labels[n_row:]
[24]:
image = visualize_bigraph(biadjacency, names_row, names_col, labels_row, labels_col)
SVG(image)
[24]:
