RuntimeWarning , RuntimeError (Discord 服务器上的 Python Al Chat Bot)

Posted 2023-02-15

【中文标题】RuntimeWarning , RuntimeError (Discord 服务器上的 Python Al Chat Bot)

【英文标题】：RuntimeWarning , RuntimeError (Python Al Chat Bot on Discord Server)

【发布时间】：2022-01-16 08:15:44

【问题描述】：

我的目标：能够整合 Al Chatbot 和 Discord

import nltk

nltk.download('punkt')

from nltk.stem.lancaster import LancasterStemmer
stemmer=LancasterStemmer()
import numpy
import tflearn
import tensorflow
import random
import json
import pickle
import nest_asyncio
import asyncio
#---------------------------------------------------------------------------
import discord 
import os





with open("intents.json") as file:
     data=json.load(file)
     print(data['intents'])
     
try:
    with open("data.pickle","rb") as f:
        words,labels,training,output=pickle.load(f)
except: 
    words=[]
    labels=[]
    docs_x=[]
    docs_y=[]
    
    for intent in data['intents']:
        for pattern in intent['patterns']:
            wrds=nltk.word_tokenize(pattern)
            words.extend(wrds)
            docs_x.append(wrds)
            docs_y.append(intent["tag"])
             
            
            if intent["tag"] not in labels:
               labels.append(intent["tag"])
               
               
    #remove duplicate          
    words=[stemmer.stem(w.lower()) for w in words if w != "?"]
    
    words=sorted(list(set(words)))
    
    labels=sorted(labels)
     
    
    training=[] 
    output=[]
    
    out_empty=[0 for _ in range(len(labels))]
    
    for x, doc in enumerate(docs_x):
        bag=[]
        wrds=[stemmer.stem(w) for w in doc]
        
        for w in words:
          if w in wrds:
             bag.append(1)
          else:
             bag.append(0)
             
        output_row=out_empty[:]
             
        output_row[labels.index(docs_y[x])]=1
        
        training.append(bag)     
        output.append(output_row)
        
    training=numpy.array(training)
    output=numpy.array(output)
    
    with open("data.pickle","wb") as f:
        pickle.dump((words,labels,training,output),f)

tensorflow.compat.v1.reset_default_graph()

net=tflearn.input_data(shape=[None,len(training[0])])
net=tflearn.fully_connected(net,16) 
net=tflearn.fully_connected(net,16)
net=tflearn.fully_connected(net,len(output[0]),activation="softmax")
net=tflearn.regression(net)

model=tflearn.DNN(net)

model.fit(training, output,n_epoch=10000,batch_size=16,show_metric=True )    

model.save('C:/Users/Desktop/chatbot/model/model.tflearn')
model.load('C:/Users/Desktop/chatbot/model/model.tflearn')

    





def bag_of_words(s,words):

   bag=[0 for _ in range(len(words))]
   s_words=nltk.word_tokenize(s)
   s_words=[stemmer.stem(word.lower()) for word in s_words]

 
   for se in s_words:
       for i,w in enumerate(words):
           if w==se:
              bag[i]=1

   return numpy.array(bag)



def chat():
    print("start talking with the bot (type quit to stop!")
    while True:
        inp=input("You:")
        if inp.lower()=="quit":
           break
       
        results= model.predict([bag_of_words(inp,words)])[0]
        # print("results:",results)
       
        results_index=numpy.argmax(results)
        
        if results[results_index]>0.7:
            
                
            tag=labels[results_index]
            print("tag:", tag)
        
            for tg in data["intents"]:
                if tg["tag"]==tag:
                   responses=tg['responses']
            
            client=discord.Client()             #FOR DISCORD--------------------------------------
            async def on_message(message):
                if inp.author == client.user:
                   return
               
                if inp.content.startswith("$M-bot"):
                    response=responses.request(inp.content[7:])
                    await asyncio.sleep(5) 
                    await inp.channel.send(response) 
                    
            
            on_message(inp)    
            client.run("API KEY TAKEN FROM DISCORD for BOT")
            print("Bot:",random.choice(responses))
         
        else:
          print("I didn't get that. Please try again")  
          
chat()  

警告和错误（Pyconsole）：

start talking with the bot (type quit to stop!

You:hello
tag: greeting
C:/Users/Desktop/chatbot/chatbot.py:154: RuntimeWarning: coroutine 'chat.<locals>.on_message' was never awaited
  on_message(inp)
RuntimeWarning: Enable tracemalloc to get the object allocation traceback
Traceback (most recent call last):

  File "F:\Anaconda\lib\site-packages\discord\client.py", line 713, in run
    loop.run_forever()

  File "F:\Anaconda\lib\asyncio\base_events.py", line 560, in run_forever
    self._check_running()

  File "F:\Anaconda\lib\asyncio\base_events.py", line 552, in _check_running
    raise RuntimeError('This event loop is already running')

RuntimeError: This event loop is already running


During handling of the above exception, another exception occurred:

Traceback (most recent call last):

  File "F:\Anaconda\lib\site-packages\discord\client.py", line 90, in _cleanup_loop
    _cancel_tasks(loop)

  File "F:\Anaconda\lib\site-packages\discord\client.py", line 75, in _cancel_tasks
    loop.run_until_complete(asyncio.gather(*tasks, return_exceptions=True))

  File "F:\Anaconda\lib\asyncio\base_events.py", line 592, in run_until_complete
    self._check_running()

  File "F:\Anaconda\lib\asyncio\base_events.py", line 552, in _check_running
    raise RuntimeError('This event loop is already running')

RuntimeError: This event loop is already running


During handling of the above exception, another exception occurred:

Traceback (most recent call last):

  File "C:/Users/Desktop/chatbot/chatbot.py", line 162, in <module>
    chat()

  File "C:/Users/Desktop/chatbot/chatbot.py", line 155, in chat
    client.run("API KEY TAKEN FROM DISCORD for BOT")

  File "F:\Anaconda\lib\site-packages\discord\client.py", line 719, in run
    _cleanup_loop(loop)

  File "F:\Anaconda\lib\site-packages\discord\client.py", line 95, in _cleanup_loop
    loop.close()

  File "F:\Anaconda\lib\asyncio\selector_events.py", line 89, in close
    raise RuntimeError("Cannot close a running event loop")

RuntimeError: Cannot close a running event loop

问题：你好朋友，我正在尝试制作一个可以处理不和谐的聊天机器人，并且可以通过我构建的人工智能模型给出答案，但是我收到了 RuntimeWarning: E​​nable tracemalloc to get the object allocation traceback 和 RuntimeError: This event loop is already running 我该如何解决这些问题？

【参考方案1】：

您的错误是因为您不断重新启动discord.Client。在每个程序中，应该只有一个discord.Client 的实例。如果你想让它吐出最后一个响应，你应该把客户端移出循环。设置机器人对全局变量的响应，并在发送命令时让机器人吐出全局变量

【讨论】：

我添加了一个不会报错的代码，但是我没有达到我想要的。只有当我通过 Discord 向机器人提问时，我才想得到答案，但它允许通过 Pyconsole 提问和回答。你能帮我修一下代码吗？

【参考方案2】：

安排：

    import nltk
    
    nltk.download('punkt')
    
    from nltk.stem.lancaster import LancasterStemmer
    stemmer=LancasterStemmer()
    import numpy
    import tflearn
    import tensorflow
    import random
    import json
    import pickle
    import nest_asyncio
    import asyncio
    #-------------------------------------------------------------------------------
    import discord 
    import os
    
    
    
    with open("intents.json") as file:
         data=json.load(file)
         print(data['intents'])
         
    client=discord.Client() #OUT OF LOOP
    
    @client.event                        #LISTEN EVENTS
    async def on_message(message):
              
              if message.author == client.user:
                 return
             
              if message.content.startswith("$M-bot"):
                  response=responses.request(message.content[7:])
    
                  await message.channel.send(response) 
                 
        
           
       
         
    try:
        with open("data.pickle","rb") as f:
            words,labels,training,output=pickle.load(f)
    except: 
        words=[]
        labels=[]
        docs_x=[]
        docs_y=[]
        
        for intent in data['intents']:
            for pattern in intent['patterns']:
                wrds=nltk.word_tokenize(pattern)
                words.extend(wrds)
                docs_x.append(wrds)
                docs_y.append(intent["tag"])
                 
                
                if intent["tag"] not in labels:
                   labels.append(intent["tag"])
                   
                   
        #remove duplicate          
        words=[stemmer.stem(w.lower()) for w in words if w != "?"]
        
        words=sorted(list(set(words)))
        
        labels=sorted(labels)
         
        
        training=[] 
        output=[]
        
        out_empty=[0 for _ in range(len(labels))]
        
        for x, doc in enumerate(docs_x):
            bag=[]
            wrds=[stemmer.stem(w) for w in doc]
            
            for w in words:
              if w in wrds:
                 bag.append(1)
              else:
                 bag.append(0)
                 
            output_row=out_empty[:]
                 
            output_row[labels.index(docs_y[x])]=1
            
            training.append(bag)     
            output.append(output_row)
            
        training=numpy.array(training)
        output=numpy.array(output)
        
        with open("data.pickle","wb") as f:
            pickle.dump((words,labels,training,output),f)
    
    tensorflow.compat.v1.reset_default_graph()
    
    net=tflearn.input_data(shape=[None,len(training[0])])
    net=tflearn.fully_connected(net,16) 
    net=tflearn.fully_connected(net,16)
    net=tflearn.fully_connected(net,len(output[0]),activation="softmax")
    net=tflearn.regression(net)
    
    model=tflearn.DNN(net)
    
    model.fit(training, output,n_epoch=5000,batch_size=16,show_metric=True )    
    
    model.save('C:/Users/Desktop/chatbot/model/model.tflearn')
    model.load('C:/Users/Desktop/chatbot/model/model.tflearn')
    
        
    
    def bag_of_words(s,words):
    
       bag=[0 for _ in range(len(words))]
       s_words=nltk.word_tokenize(s)
       s_words=[stemmer.stem(word.lower()) for word in s_words]
    
     
       for se in s_words:
           for i,w in enumerate(words):
               if w==se:
                  bag[i]=1
    
       return numpy.array(bag)
    
    
    
    def chat():
        global responses          #GLOBAL VARIABLES
        global inp                #GLOBAL VARIABLES
        print("start talking with the bot (type quit to stop!")
        while True:
            inp=input("You:")
            if inp.lower()=="quit":
               break
           
            results= model.predict([bag_of_words(inp,words)])[0]
            # print("results:",results)
           
            results_index=numpy.argmax(results)
            
            if results[results_index]>0.7:
                
                    
                tag=labels[results_index]
                print("tag:", tag)
            
                for tg in data["intents"]:
                    if tg["tag"]==tag:
                       responses=tg['responses']
                
             
               
                
                print("Bot:",random.choice(responses))
             
            else:
              print("I didn't get that. Please try again")  
              
    
    chat()  
      
    client.run("API KEY")