Я создаю чат-бота, используя Python. Код:
import nltk
import numpy as np
import random
import string
f=open('/home/hostbooks/ML/stewy/speech/chatbot.txt','r',errors = 'ignore')
raw=f.read()
raw=raw.lower()# converts to lowercase
sent_tokens = nltk.sent_tokenize(raw)# converts to list of sentences
word_tokens = nltk.word_tokenize(raw)# converts to list of words
lemmer = nltk.stem.WordNetLemmatizer()
def LemTokens(tokens):
return [lemmer.lemmatize(token) for token in tokens]
remove_punct_dict = dict((ord(punct), None) for punct in string.punctuation)
def LemNormalize(text):
return LemTokens(nltk.word_tokenize(text.lower().translate(remove_punct_dict)))
GREETING_INPUTS = ("hello", "hi", "greetings", "sup", "what's up","hey","hii")
GREETING_RESPONSES = ["hi", "hey", "*nods*", "hi there", "hello", "I am glad! You are talking to me"]
def greeting(sentence):
for word in sentence.split():
if word.lower() in GREETING_INPUTS:
return random.choice(GREETING_RESPONSES)
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
def response(user_response):
robo_response=''
sent_tokens.append(user_response)
TfidfVec = TfidfVectorizer(tokenizer=LemNormalize, stop_words='english')
tfidf = TfidfVec.fit_transform(sent_tokens)
vals = cosine_similarity(tfidf[-1], tfidf)
idx=vals.argsort()[0][-2]
flat = vals.flatten()
flat.sort()
req_tfidf = flat[-2]
if(req_tfidf==0):
robo_response=robo_response+"I am sorry! I don't understand you"
return robo_response
else:
robo_response = robo_response+sent_tokens[idx]
return robo_response
flag=True
print("ROBO: My name is Robo. I will answer your queries about Chatbots. If you want to exit, type Bye!")
while(flag==True):
user_response = input()
user_response=user_response.lower()
if(user_response!='bye'):
if(user_response=='thanks' or user_response=='thank you' ):
flag=False
print("ROBO: You are welcome..")
else:
if(greeting(user_response)!=None):
print("ROBO: "+greeting(user_response))
else:
print("ROBO: ",end="")
print(response(user_response))
sent_tokens.remove(user_response)
else:
flag=False
print("ROBO: Bye! take care..")
Работает хорошо, но при каждом разговоре выдает эту ошибку:
/home/hostbooks/django1/myproject/lib/python3.6/site-packages/sklearn/feature_extraction/text.py:300: UserWarning: Your stop_words may be inconsistent with your preprocessing.
Tokenizing the stop words generated tokens ['ha', 'le', 'u', 'wa'] not in stop_words.
Вот некоторые разговоры из CMD:
ROBO: чат-бот - это программное обеспечение, которое ведет разговор слуховыми или текстовыми методами.
что такое Индия
/home/hostbooks/django1/myproject/lib/python3.6/site-packages/sklearn/feature_extraction/text.py:300: UserWarning: Your stop_words may be inconsistent with your preprocessing. Tokenizing the stop words generated tokens ['ha', 'le', 'u', 'wa'] not in stop_words. 'stop_words.' % sorted(inconsistent))
ROBO: дикая природа Индии, которая традиционно рассматривается с терпимостью в культуре Индии, поддерживается в этих лесах и в других местах в охраняемых местах обитания.
что такое чатбот
/home/hostbooks/django1/myproject/lib/python3.6/site-packages/sklearn/feature_extraction/text.py:300: UserWarning: Your stop_words may be inconsistent with your preprocessing. Tokenizing the stop words generated tokens ['ha', 'le', 'u', 'wa'] not in stop_words. 'stop_words.' % sorted(inconsistent))
ROBO: чатбот - это программное обеспечение, которое ведет разговор с помощью слуховых или текстовых методов.