vicky428的博客

# -*- coding: utf-8 -*- """ Created on Thu Aug 30 11:46:33 2018 @author: wenyun.wxw """ import time import re import os import sys import codecs import shutil import numpy as ...

#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Tue Jul 3 17:43:53 2018 @author: vicky """ # 导入第三方包 import pandas as pd import numpy as np import statsmodels.formula.api as smf from ...

# -*- coding: utf-8 -*- """ Created on Tue Jul 17 21:00:19 2018 @author: wenyun.wxw """ #特征提取 #- Tf-idf # 词频矩阵：矩阵元素a[i][j] 表示j词在i类文本下的词频 from sklearn.feature_extraction.text import CountVectorize...

# -*- coding: utf-8 -*- """ Created on Wed Jul 18 09:35:01 2018 @author: wenyun.wxw """ import jieba from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.cluster import KMeans...

# -*- coding: utf-8 -*- """ Created on Fri Jul 13 20:00:33 2018 @author: wenyun.wxw """ import jieba import re ratecontent2=ratecontent for i in range(len(ratecontent)): if ratecontent[i]=='此...

# -*- coding: utf-8 -*- """ Created on Thu Jul 12 15:08:33 2018 @author: wenyun.wxw """ import requests import re #https://rate.tmall.com/list_detail_rate.htm? #itemId=567925396518 #商品id #&spu...

# -*- coding: utf-8 -*- """ Created on Thu Jul 26 10:51:30 2018 @author: wenyun.wxw """ #计算行数 count = -1 for count,line in enumerate(open('data.txt','r',encoding='utf-8')): pass count=count+1 ...

# -*- coding: utf-8 -*- """ Created on Fri Jul 27 11:42:16 2018 @author: wenyun.wxw """ import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.cluster import KMeans i...

#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Sun Jul 29 22:37:01 2018 @author: vicky """ import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.clust...

# -*- coding: utf-8 -*- """ Created on Wed Jul 18 11:01:41 2018 @author: wenyun.wxw """ # coding=utf-8 """ Created on 2016-01-06 @author: Eastmount """ import time import re ...

#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Fri Aug 3 16:46:12 2018 @author: vicky """ import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.clust...

# -*- coding: utf-8 -*- """ Created on Mon Aug 27 14:42:09 2018 @author: wenyun.wxw """ import requests import re #创建循环链接 urls = [] #替换页面数为i，取前100页评论 for i in list(range(1,99)): urls.append('h...

# -*- coding: utf-8 -*- """ Created on Tue Aug 28 11:02:24 2018 @author: wenyun.wxw """ import requests import re def xiaodu(score): #score=0为全部，1为差评，2为中评，3为好评, 4配图评论 urls = [] #替换页面数为i，...

# -*- coding: utf-8 -*- """ Created on Tue Aug 28 15:09:32 2018 @author: wenyun.wxw """ data=ratecontent_less+ratecontent_jd_less #合并天猫评论和京东评论 num=len(data) for i in range(num-1): if data[i]==...

# -*- coding: utf-8 -*- """ Created on Tue Aug 28 14:38:16 2018 @author: wenyun.wxw """ import jieba import re from wordcloud import WordCloud import matplotlib.pyplot as plt data=ratecontent_less...

#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Tue Jul 3 17:43:53 2018 @author: vicky """ # 导入第三方包 import pandas as pd import numpy as np import statsmodels.formula.api as smf from ...