Python自然语言处理笔记（四）wordnet可视化

networkx

书中代码实现

书中p165，networkx和matplotlib结合使用可视化wordnet的网络结构（语义网络）

import networkx as nx
import matplotlib
from nltk.corpus import wordnet as wn
 
def traverse(graph, start, node):
    graph.depth[node.name] = node.shortest_path_distance(start)
    for child in node.hyponyms():
        graph.add_edge(node.name, child.name) 
        traverse(graph, start, child) 
def hyponym_graph(start):
    G = nx.Graph() 
    G.depth = {}
    traverse(G, start, start)
    return G
def graph_draw(graph):
    nx.draw_graphviz(graph,
        node_size = [16 * graph.degree(n) for n in graph],
        node_color = [graph.depth[n] for n in graph],
        with_labels = False)
    matplotlib.pyplot.show()
 
if __name__=='__main__':
    dog=wn.synset('dog.n.01')
    graph=hyponym_graph(dog)
    graph_draw(graph)

报错：AttributeError: module ‘networkx’ has no attribute ‘draw_graphviz’
解决方法：
Python3.6版本
nx.draw(graph,node_size=[16 * graph.degree(n) for n in graph], node_color=[graph.depth[n] for n in graph], with_labels=False) 就可以运行了

拓展：wordnet层次图

from nltk.corpus import wordnet as wn
import matplotlib
import networkx as nx

def travers(graph, start, node):
    graph.depth[node.name] = node.shortest_path_distance(start)
    for child in node.hyponyms():
        graph.add_edge(node.name, child.name)
        #graph.add_node(child.name, desc=[child])
        travers(graph, start, child)
def hyponym_graph(start):
    G = nx.Graph()
    G.depth = {}
    travers(G, start, start)
    return G
def graph_draw(graph):
    nx.draw(graph, node_size=[5 * graph.degree(n) for n in graph], node_color=[graph.depth[n] for n in graph],
            with_labels=True)

    matplotlib.pyplot.show()


if __name__=='__main__':
    computer = wn.synset('computer.n.01')
    graph = hyponym_graph(computer)
    graph_draw(graph)

实验结果：

可以显示节点的标签，但是不知道怎么把内容提取出来。待解决。
解决方法

#node.name改为node.name()
from nltk.corpus import wordnet as wn
import matplotlib
import networkx as nx

def travers(graph, start, node):
    graph.depth[node.name()] = node.shortest_path_distance(start)

    for child in node.hyponyms():
        graph.add_edge(node.name(), child.name())
        travers(graph, start, child)
def hyponym_graph(start):
    G = nx.Graph()
    G.depth = {}
    travers(G, start, start)
    return G
def graph_draw(graph):
    nx.draw(graph, node_size=[5 * graph.degree(n) for n in graph], node_color=[graph.depth[n] for n in graph],
            with_labels=True)

    matplotlib.pyplot.show()


if __name__=='__main__':
    computer = wn.synset('computer.n.01')
    graph = hyponym_graph(computer)
    graph_draw(graph)

书中用函数都没有加（），所以显示出来的都有问题。
例如：

>>> computer.name
<bound method Synset.name of Synset('computer.n.01')>
>>> computer.name()
'computer.n.01'

开心~~~