第一次的博客编程作业

import jieba

txt1='今天是星期天，天气晴，今天晚上我要去看电影'
txt2='今天是周天，天气晴朗，我晚上要去看电影'

all_txt=[]
all_txt.append(txt1)
all_txt.append(txt2)
all_txt_list=[]
for txt in all_txt:
    txt_list=[word for word in jieba.cut(txt)]
    all_txt_list.append(txt_list)
for word in all_txt_list:
    print(word)

def cosine(vector1,vector2):
    dot_product = 0.0
    normA = 0.0
    normB = 0.0
    for a,b in zip(vector1,vector2):
        dot_product += a*b
        normA += a**2
        normB += b**2
    if normA == 0.0 or normB==0.0:
        return None
    else:
        return dot_product / ((normA*normB)**0.5)

def Jaccrad(model, reference): 
# terms_reference为源句子，terms_model为候选句子
    terms_reference = jieba.cut(reference)  # 默认精准模式
    terms_model = jieba.cut(model)
    grams_reference = set(terms_reference)  # 去重；如果不需要就改为list
    grams_model = set(terms_model)
    temp = 0
    for i in grams_reference:
        if i in grams_model:
            temp = temp + 1
    fenmu = len(grams_model) + len(grams_reference) - temp  # 并集
    jaccard_coefficient = float(temp / fenmu)  # 交集
    return jaccard_coefficient

import jieba
import os

path1=os.path.abspath('.')
#读取停用词，创建一个停用词表
stwlist= [line.strip() for line in open(path1+'\\'+'baidu_stopwords.txt',encoding='utf-8').readlines()]

test ={}
test['orig.txt'] = open(path1+'\\'+'orig.txt', 'r', encoding='utf-8').read()
test['orig_0.8_add.txt'] = open(path1+'\\'+'orig_0.8_add.txt', 'r', encoding='utf-8').read()
test['orig_0.8_del.txt'] = open(path1+'\\'+'orig_0.8_del.txt', 'r', encoding='utf-8').read()
test['orig_0.8_dis_1.txt'] = open(path1+'\\'+'orig_0.8_dis_1.txt', 'r', encoding='utf-8').read()
test['orig_0.8_dis_3.txt'] = open(path1+'\\'+'orig_0.8_dis_3.txt', 'r', encoding='utf-8').read()
test['orig_0.8_dis_7.txt'] = open(path1+'\\'+'orig_0.8_dis_7.txt', 'r', encoding='utf-8').read()
test['orig_0.8_dis_10.txt'] = open(path1+'\\'+'orig_0.8_dis_10.txt', 'r', encoding='utf-8').read()
test['orig_0.8_dis_15.txt'] = open(path1+'\\'+'orig_0.8_dis_15.txt', 'r', encoding='utf-8').read()
test['orig_0.8_mix.txt'] = open(path1+'\\'+'orig_0.8_mix.txt', 'r', encoding='utf-8').read()
test['orig_0.8_rep.txt'] = open(path1+'\\'+'orig_0.8_rep.txt', 'r', encoding='utf-8').read()

def jaccard():
#预处理：去分词，去停用词,去符号
    test_word=[]
    i=0
    for key in test.keys():
        test_word.append([])
        words = jieba.cut(test[key],cut_all =False)
        for word in words:
             if word.strip() not in stwlist:
                  if word !='\t':
                     if word !='\r\n':
                         test_word[i].append(word)
        i=i+1
#jaccard系数的计算    
    j=0
    for key in test.keys():
        temp=0
        for word in test_word[0]:
             if word in test_word[j]:
                temp =temp +1
        fenmu = len(test_word[0]) + len(test_word[j]) -temp
        jaccard_coefficient =float(temp/fenmu)
        print('测试样本为:%s,相似度为：%.2f'%(key,jaccard_coefficient))
        print('-----------------------------------')
        j=j+1

if __name__=='__main__':
    jaccard()

try:

except FileNotFoundError:
    print("文件未找到")

except TimeoutError:
    print（"文件读取超时"）

except FileEmpty:
    print("文件为空文件")

else:
    print("无异常出现")