运用jieba库统计词频及制作词云

一、对中国十九大报告做词频分析

 import jieba
 txt = open("中国十九大报告.txt.txt","r",encoding="utf-8").read()
 words = jieba.lcut(txt)
 counts = {}
 for word in words:
     if len(word)==1:
         continue
     else:
         counts[word] = counts.get(word,0)+1
 items = list(counts.items())
 items.sort(key=lambda x:x[1],reverse=True)
 for i in range(15):
     word,count = items[i]
     print("{0:<10}{1:>5}".format(word,count))
     

二、根据词频制作词云

 import jieba
 import wordcloud
 from imageio import imread
 mask = imread("wujiaoxing.png")
 f = open("中共十九大报告词频.txt","r",encoding="utf-8")
 t = f.read()
 f.close()
 ls = jieba.lcut(t)
 txt = " ".join(ls)
 w = wordcloud.WordCloud(font_path="msyh.ttc",mask = mask,width = 1000,height=800,background_color="black")
 w.generate(txt)
 w.to_file("grwordcloud.png")