import os import jieba.analyse from textrank4zh import TextRank4Keyword import concurrent.futures import scipy # 定义分块读取函数 def read_in_chunks(file_path, chunk_size=1024 * 1024): with open(file_path, 'r', encoding='utf-8') as f: while True: data = f.read(chunk_size) if not data: break yield data # 定义处理函数 def process_chunk(chunk): # 使用jieba分词提取关键词 jieba_keywords = jieba.analyse.extract_tags(chunk, topK=10, withWeight=True) # 使用textrank4zh提取关键词 tr4w = TextRank4Keyword() tr4w.analyze(chunk, lower=True, window=2) textrank_keywords = tr4w.get_keywords(10, word_min_len=2) # 合并两种方法提取的关键词 keywords = jieba_keywords + textrank_keywords return keywords # 读取文本文件，并按块处理 chunks = [] for chunk in read_in_chunks('cnl_201504.txt'): chunks.append(chunk) # 多线程并行处理 results = [] with concurrent.futures.ThreadPoolExecutor() as executor: futures = [executor.submit(process_chunk, chunk) for chunk in chunks] for future in concurrent.futures.as_completed(futures): results.extend(future.result()) # 合并结果，并按权重降序排序 keywords = {} for keyword, weight in results: if keyword in keywords: keywords[keyword] += weight else: keywords[keyword] = weight keywords = sorted(keywords.items(), key=lambda x: x[1], reverse=True) keywords = [(keyword, weight) for keyword, weight in keywords if len(keyword) > 1][:10] # 输出到txt文件中 with open('output.txt', 'w', encoding='utf-8') as f: for keyword, weight in keywords: f.write(keyword + '\t' + str(weight) + '\n')运行上述代码出现下述问题，请修改代码：AttributeError: module 'networkx' has no attribute 'from_numpy_matrix'

这个错误是因为缺少了 `networkx` 库。你需要在代码开头引入这个库：

import os
import jieba.analyse
from textrank4zh import TextRank4Keyword
import concurrent.futures
import scipy
import networkx as nx

如果你还没有安装这个库，可以通过以下命令安装：

pip install networkx