Python 聊天機器人 - 使用 Excel

Question

我有以下聊天機器人，它讀取文本文件並使用 NLTK，然后相應地從該文本文件中輸出文本。 但我想使用具有多列和數百行的 excel 文件。 每一行都應該有一個問題、它的答案和它的答案來源。

如何在其中實現 Excel 以便聊天機器人在 excel 文件中搜索類似於用戶輸入聊天機器人的問題的問題？

#Meet Robo: your friend

#import necessary libraries
import io
import random
import string # to process standard python strings
import warnings
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import warnings
warnings.filterwarnings('ignore')

import nltk
from nltk.stem import WordNetLemmatizer
nltk.download('popular', quiet=True) # for downloading packages

# uncomment the following only the first time
#nltk.download('punkt') # first-time use only
#nltk.download('wordnet') # first-time use only


#Reading in the corpus
with open('chatbot.txt','r', encoding='utf8', errors ='ignore') as fin:
    raw = fin.read().lower()

#TOkenisation
sent_tokens = nltk.sent_tokenize(raw)# converts to list of sentences 
word_tokens = nltk.word_tokenize(raw)# converts to list of words

# Preprocessing
lemmer = 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)))


# Keyword Matching
GREETING_INPUTS = ("hello", "hi", "greetings", "sup", "what's up","hey",)
GREETING_RESPONSES = ["hi", "hey", "*nods*", "hi there", "hello", "I am glad! You are talking to me"]

def greeting(sentence):
    """If user's input is a greeting, return a greeting response"""
    for word in sentence.split():
        if word.lower() in GREETING_INPUTS:
            return random.choice(GREETING_RESPONSES)


# Generating response
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..") 

Answer 1

您是否嘗試使用 pandas.read_excel() 打開 excel 文件？

例如：

import pandas
qanda = pandas.read_excel('chatbot_qa.xlsx',sheet_name='QuestionsAndAnswers')

它工作正常，您可以迭代行並按列查找問題和答案。

for row in qanda:
   chatbot.echo(row.question)

你也可以使用 pyexcel-xlsx[1] 來做類似的事情。

[1] https://pythonhosted.org/pyexcel-xlsx/

Answer 2

更新代碼以使用 Excel 輸入文件。 （這里 Excel 有 2 列“問題”和“答案”）該算法搜索用戶在“問題”列中輸入的內容，並在“答案”列的前面給出答案：

#Meet Robo: your friend

#import necessary libraries
import io
import random
import string # to process standard python strings
import warnings
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import warnings
import pandas as pd
warnings.filterwarnings('ignore')

import nltk
from nltk.stem import WordNetLemmatizer
nltk.download('popular', quiet=True) # for downloading packages

# uncomment the following only the first time
#nltk.download('punkt') # first-time use only
#nltk.download('wordnet') # first-time use only

#Reading in the corpus
xls = pd.read_excel(r"FAQ.xlsx") #use r before absolute file path

xls = xls.applymap(str)

#TOkenisation

QuestionTokenS = []

# Iterate over each row
for index, rows in xls.iterrows():
    # Create list for the current row
    my_list = [rows.Question]
    # append the list to the final list
    QuestionTokenS.append(my_list)

Question_tokens = [item for l in QuestionTokenS for item in l]

AnswerTokenS = []

# Iterate over each row
for index, rows in xls.iterrows():
    # Create list for the current row
    my_list = [rows.Answer]
    # append the list to the final list
    AnswerTokenS.append(my_list)

Answer_tokens = [item for l in AnswerTokenS for item in l]

# Preprocessing
lemmer = 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)))

# Keyword Matching
GREETING_INPUTS = ("hello", "hi", "greetings", "sup", "what's up","hey",)
GREETING_RESPONSES = ["hi", "hey", "*nods*", "hi there", "hello", "I am glad! You are talking to me"]

def greeting(sentence):
    """If user's input is a greeting, return a greeting response"""
    for word in sentence.split():
        if word.lower() in GREETING_INPUTS:
            return random.choice(GREETING_RESPONSES)

# Generating response
def response(user_response):
    robo_response=''
    Question_tokens.append(user_response)
    TfidfVec = TfidfVectorizer(tokenizer=LemNormalize,stop_words='english')
    tfidf = TfidfVec.fit_transform(Question_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+Answer_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))
                xls.drop(xls.tail(1).index, inplace=True)
    else:
        flag=False
        print("ROBO: Bye! take care..")