| 
						
						
						
					 | 
					 | 
					@ -0,0 +1,52 @@
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					import concurrent.futures  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					from collections import Counter  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					import cppy.cp_util as util
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					class WordFrequencyAgent:  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    def __init__(self, words):          
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        self.words = words  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    def compute_word_frequency(self):          
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        self.word_freq = Counter(self.words)  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    def get_word_frequency(self):  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        return self.word_freq
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					# 将文本分割成多个部分,并为每个部分创建一个Agent
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					def create_agents(words, num_agents = 4 ):  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    text_chunks = [ words[i::num_agents] for i in range(num_agents) ]  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    agents = [ WordFrequencyAgent(chunk) for chunk in text_chunks ]
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    return agents    
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					def compute_all_word_frequencies(agents):  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    with concurrent.futures.ThreadPoolExecutor() as executor:  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        # 使用线程池来并行计算词频  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        future_to_agent = {executor.submit(agent.compute_word_frequency): agent for agent in agents}  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        for future in concurrent.futures.as_completed(future_to_agent):  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					            agent = future_to_agent[future]  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					            try:  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					                # 获取计算结果,但不处理异常  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					                data = future.result()  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					            except Exception as exc:  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					                print(f'生成 {agent.text_chunk[:10]}... 的词频时出错: {exc}')  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					            # 词频已经被保存在agent中
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					# 所有Agent计算完成后,合并它们的词频结果
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					def merge_word_frequencies(agents):  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    merged_freq = Counter()  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    for agent in agents:  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        merged_freq.update(agent.get_word_frequency())  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    return merged_freq  
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					if __name__ == '__main__':       
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    words = util.extract_file_words(util.testfilepath) # 从文本抽词
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    agents = create_agents(words)  # 创建代理
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    compute_all_word_frequencies(agents)  # 计算
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    merged_word_freq = merge_word_frequencies(agents)   # 合并结果    
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					    for (w, c) in merged_word_freq.most_common(10):  # 排序输出
 | 
				
			
			
		
	
		
		
			
				
					
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					 | 
					        print(w, '-', c)
 |