​
 # 导入相关库
 import pandas as pd
 import jieba
 ​
 # 读取数据
 data = pd.read_csv('meidi_jd.csv', encoding='gb18030')
 ​
 # 查看数据
 data.head()

 # 生成分词
 data['cut'] = data['comment'].apply(lambda x : list(jieba.cut(x)))
 ​
 data.head()

 data['cut'] = data['comment'].apply(lambda x : list(set(jieba.cut(x))))
 ['很', '好', '很', '好', '很', '好', '很', '好', '很', '好', '很', '好', '很', '好', '很', '好', '很', '好', '很', '好', '很', '好']

 data['cut'] = data['comment'].apply(lambda x : list(jieba.cut(x)))
 ​
 data.head()
 ​
 print(data['cut'].loc[14])
 ['很好', '很好', '很好', '很好', '很好', '很好', '很好', '很好', '很好', '很好', '很好']

 # 读取停用词数据
 stopwords = pd.read_csv('StopwordsCN.txt', encoding='utf8', names=['stopword'], index_col=False)
 ​
 stopwords.head()

 # 将所有的分词合并
 words = []
 ​
 for content in data['cut']:
     words.extend(content)

# 创建分词数据框
 corpus = pd.DataFrame(words, columns=['word'])
 corpus['cnt'] = 1
 ​
 # 分组统计
 g = corpus.groupby(['word']).agg({'cnt': 'count'}).sort_values('cnt', ascending=False)
 ​
 g.head(10)

 # 导入相关库
 from collections import Counter
 from pprint import pprint
 ​
 ​
 counter = Counter(words)
 ​
 # 打印前十高频词
 pprint(counter.most_common(10))
 [('不错', 3913),
 ('安装', 3055),
 ('好', 2045),
 ('很好', 1824),
 ('买', 1634),
 ('热水器', 1182),
 ('挺', 1051),
 ('师傅', 923),
 ('美', 894),
 ('送货', 821)]

 import jieba
 import jieba.analyse
 import codecs
 import re
 from collections import Counter
 from wordcloud import WordCloud
 import matplotlib.pyplot as plt
 import wordcloud
 ​
 str = "我在河南大学上学，今年22岁了"
 ​
 seg_list = jieba.cut(str,cut_all=True)
 print("全模式："+"/".join(seg_list))
 ​
 seg_list = jieba.cut(str,cut_all=False)
 print("默认(精确模式)："+"/".join(seg_list))
 ​
 # 搜索引擎模式
 seg_list = jieba.cut_for_search(str)
 print("搜索引擎模式："+"/".join(seg_list))
 ​
 # 添加用户自定义词典
 str = "大连圣亚在大连"
 seg_list = jieba.cut(str,cut_all=False)
 print("默认(精确模式)："+"/".join(seg_list))
 ​
 # 添加自定义词典后
 jieba.load_userdict(r"./user_dict.txt")
 seg_list = jieba.cut(str,cut_all=False)
 print("默认(精确模式)："+"/".join(seg_list))
 ​
 str = "我家在河南省驻马店市汝南县东官庄镇"
 seg_list = jieba.cut(str) #默认是精确模式
 print("精确模式："+"/".join(seg_list))
 ​
 # 动态调整词典
 jieba.add_word("东官庄镇")
 seg_list = jieba.cut(str)
 print("精确模式："+"/".join(seg_list))
 ​
 ​
 # 加载停用词
 # 创建停用词列表
 def stopwordlist():
     stopwords = [line.strip() for line in open('./hit_stopwords.txt',encoding='UTF-8').readlines()]
     return stopwords
 ​
 ​
 # 对句子进行中文分词
 def seg_depart(sentence):
     print('正在分词')
     sentence_depart = jieba.cut(sentence.strip())
     # 创建一个停用词列表
     stopwords = stopwordlist()
     # 输出结果为 outstr
     outstr = ''
 #     去停用词
     for word in sentence_depart:
         if word not in stopwords:
             if word != '\t':
                 outstr += word
                 outstr += " "
     return outstr
 ​
 ​
 # 给出文档路径
 filename = "./text.txt"
 outfilename = "./out.txt"
 inputs = open(filename,'r',encoding='UTF-8')
 outputs = open(outfilename,'w',encoding='UTF-8')
 ​
 ​
 jieba.add_word("停用词")
 # 将输出结果写到out.txt中
 for line in inputs:
     line_seg = seg_depart(line)
 ​
     outputs.write(line_seg + '\n')
     print("-------------------------正在分词和去停用词--------------------------")
     print("原文："+line)
     print("去停用词："+line_seg)
 ​
 outputs.close()
 inputs.close()
 print("删除停用词和分词成功！！！")
 ​
 ​
 # class WordCounter(object):
 def count_from_file(file,top_limit=0):
     with codecs.open(file,'r','UTF-8') as f:
         content = f.read()
         # 将多个空格替换为一个空格
         content =re.sub(r'\s+',r' ',content)
         content = re.sub(r'\.+',r' ',content)
 ​
         # 去停用词
         content = seg_depart(content)
 ​
 ​
         return count_from_str(content,top_limit=top_limit)
 ​
 ​
 def count_from_str(content,top_limit=0):
     if top_limit <= 0:
         top_limit = 100
     #     提取文章的关键词
     tags = jieba.analyse.extract_tags(content,topK=100)
 ​
     words = jieba.cut(content)
 ​
     counter = Counter()
 ​
     for word in words:
         if word in tags:
             counter[word] += 1
 ​
     return counter.most_common(top_limit)
 ​
 ​
 # if __name__ == '__main__':
 #     counter = WordCounter()
 #     retult = counter.count_from_file(r'./text.txt',top_limit=10)
 ​
     # print(retult)
 ​
 print("打印词频==============")
 retult = count_from_file(r'./text.txt',top_limit=10)
 print(retult)
 ​
 ​
 print("*"*100)
 ​
 # 例子
 # sentence = 'Ilikeyou '
 # wc = wordcloud.WordCloud()
 # pic = wc.generate(sentence)
 # plt.imshow(pic)
 # plt.axis("off")
 # plt.show()
 ​
 # wc.to_file('test.png')
 ​
 print("分词并生成词云图")
 ​ 
def create_word_cloud(file): 
​ 
    content = codecs.open(file,'r','UTF-8').read() 
#     结巴分词 
    wordlist = jieba.cut(content) 
    wl = " ".join(wordlist) 
​ 
    print(wl) 
​ 
#     设置词云图 
    wc = wordcloud.WordCloud( 
    #     设置背景颜色 
        background_color='pink', 
    #     设置最大显示的词数 
        max_words=100, 
    #     设置字体路径 
        font_path = 'C:\Windows\Fonts\msyh.ttc', 
        height = 1200, 
        width=1600, 
    #     设置字体最大值 
        max_font_size=300, 
    #     设置有多少种配色方案，即多少种随机生成状态 
        random_state=30, 
    ) 
​ 
    # 生成词云图 
    myword = wc.generate(wl) 
​ 
    # 展示词云图 
    plt.imshow(myword) 
    plt.axis("off") 
    plt.show() 
    wc.to_file('py_pic.png') 
​ 
# content = codecs.open("./text.txt",'r','UTF-8').read() 
create_word_cloud("text.txt") 
​ 
​