【Python自然语言处理+tkinter图形化界面】实现智能医疗客服问答机器人实战（附源码、数据集、演示 超详细）

# -*- coding:utf-8 -*-
from fuzzywuzzy import fuzz
import sys
import jieba
import csv
import pickle
print(sys.getdefaultencoding())
import logging
from fuzzywuzzy import fuzz
import math
from scipy import sparse
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from scipy.sparse import lil_matrix
from sklearn.naive_bayes import MultinomialNB
import warnings
from tkinter import *
import time
import difflib
from collections import Counter
import numpy as np
filename = 'label.csv'
def tokenization(filename):
    corpus = []
    label = []
    question = []
    answer = []
    with open(filename, 'r', encoding="utf-8") as f:
        data_corpus = csv.reader(f)
        next(data_corpus)
        for words in data_corpus:
            word = jieba.cut(words[1])
            tmp = ''
            for x in word:
                tmp += x
            corpus.append(tmp)
            question.append(words[1])
            label.append(words[0])
            answer.append(words[2])
    with open('corpus.h5','wb') as f:
        pickle.dump(corpus,f)
    with open('label.h5','wb') as f:
        pickle.dump(label,f)
    with open('question.h5', 'wb') as f:
        pickle.dump(question, f)
    with open('answer.h5', 'wb') as f:
        pickle.dump(answer, f)
    return corpus,label,question,answer
def train_model():
    with open('corpus.h5','rb') as f_corpus:
        corpus = pickle.load(f_corpus)
    with open('label.h5','rb') as f_label:
        label = pickle.load(f_label,encoding='bytes')
    vectorizer = CountVectorizer(min_df=1)
    transformer = TfidfTransformer()
    tfidf = transformer.fit_transform(vectorizer.fit_transform(corpus))
    words_frequency = vectorizer.fit_transform(corpus)
    word = vectorizer.get_feature_names()
    saved = tfidf_calculate(vectorizer.vocabulary_,sparse.csc_matrix(words_frequency),len(corpus))
    model = MultinomialNB()
    model.fit(tfidf,label)
    with open('model.h5','wb') as f_model:
        pickle.dump(model,f_model)
    with open('idf.h5','wb') as f_idf:
        pickle.dump(saved,f_idf)
    return model,tfidf,label
class tfidf_calculate(object):
    def __init__(self,feature_index,frequency,docs):
        self.feature_index = feature_index
        self.frequency = frequency
        self.docs = docs
        self.len = len(feature_index)
    def key_count(self,input_words):
        keys = jieba.cut(input_words)
        count = {}
        for key in keys:
            num = count.get(key, 0)
            count[key] = num + 1
        return count
    def getTfidf(self,input_words):
        count = self.key_count(input_words)
        result = lil_matrix((1, self.len))
        frequency = sparse.csc_matrix(self.frequency)
        for x in count:
            word = self.feature_index.get(x)
            if word != None and word>=0:
                word_frequency = frequency.getcol(word)
                feature_docs = word_frequency.sum()
                tfidf = count.get(x) * (math.log((self.docs+1) / (feature_docs+1))+1)
                result[0, word] = tfidf
        return result    
if __name__=="__main__":
    tokenization(filename)
    train_model()