jieba库的分词和词云

Posted 2020-11-29 gtxy

1.分词

#DreaminRedMansions.py
import jieba   #调用jieba库

txt = open("D:Downloadlianxiipassageone.txt","r",encoding="UTF-8").read()  #打开txt文件阅读

words = jieba.lcut(txt)    #分词
counts = {}   #建立一个空字典
for word in words:
    if len(word)==1:
        continue
    else:
        counts[word]=counts.get(word,0) + 1    #遍历每个中文单词，通过字典来计数
items = list(counts.items())    #将字典counts转换为列表类型
items.sort(key=lambda x:x[1],reverse = True)   #对列表进行排序
for i in range(20):
    word,count = items[i]
    print("{0:<10}{1:>5}".format(word,count))     #打印出前20个词

自选一篇文章，结果如下

 

2.词云

from wordcloud import WordCloud
import jieba
def create_word_cloud():
    path_txt = ‘D:Downloadlianxiipassageone.txt‘
    
    text = open(path_txt,"r",encoding="UTF-8").read()
    
    wordlist = jieba.lcut(text) # jieba分词
    wl = " ".join(wordlist)
 
    # 设置词云
    w = WordCloud(
        # 设置背景颜色为白色
        background_color="white",
        # 设置最大显示的词云数为200
        max_words=200,
        # 字体的一般路径--宋体
        font_path=‘simsun.ttc‘,
        height=1200,
        width=1600,
        # 设置字体最大的字体大小
        max_font_size=100,
        # 设置配色方案
        random_state=100,
    )


    w.generate(wl)  # 生成词云
    w.to_file(‘img_book1.png‘)  # 把词云保存下
 
 
if __name__ == ‘__main__‘:
    create_word_cloud()