Python制作无向量图

import pandas as pd
import networkx as nx
from sklearn.feature_extraction.text import CountVectorizer
from itertools import combinations

# 读取Excel文件
file_path = 'cleaned_Laos_news.xlsx'
sheet_name = 'Sheet1'  # 修改为实际的工作表名称
data = pd.read_excel(file_path, sheet_name=sheet_name)

# 清除NaN值，将它们替换为一个空字符串
data['cleaned_content'].fillna('', inplace=True)

# 将所有文本内容合并为一个字符串
all_text = ' '.join(data['cleaned_content'])

# 使用CountVectorizer提取词频
vectorizer = CountVectorizer(min_df=1, max_features=30)
X = vectorizer.fit_transform([all_text])
words = vectorizer.get_feature_names_out()

# 创建无向图
G = nx.Graph()

# 添加节点
G.add_nodes_from(words)

# 计算关键词的共现关系并添加边
for i in range(len(data)):
    keywords = [word for word in words if word in data['cleaned_content'][i]]
    for word_pair in combinations(keywords, 2):
        word1, word2 = word_pair
        if G.has_edge(word1, word2):
            G[word1][word2]['weight'] += 1
        else:
            G.add_edge(word1, word2, weight=1)

# 使用 NetworkX 导出 GML 文件
nx.write_gml(G, 'keywords_network.gml')

# 输出提示信息
print("Graph exported as keywords_network.gml")
print("You can import this file into Gephi for visualization.")