import jieba excludes = {"将军","却说","荆州","二人","不可","不能","如此"} txt = open("sg.txt", "r", encoding='utf-8').read() words = jieba.lcut(txt) counts = {} for word in words: if len(word) == 1: continue if word == "诸葛亮" or word == "孔明曰": rword = "孔明" elif word == "关公" or word == "云长": rword = "关羽" elif word == "玄德" or word == "玄德曰": rword = "刘备" elif word == "孟德" or word == "丞相": rword = "曹操" else: rword = word counts[rword] = counts.get(rword,0) + 1 for word in excludes: del(counts[word]) items = list(counts.items()) items.sort(key=lambda x:x[1], reverse=True) for i in range(5): word, count = items[i] print ("{0:<10}{1:>5}".format(word, count)) from wordcloud import WordCloud import matplotlib.pyplot as plt import numpy as np from PIL import Image def create_word_cloud(filename): text = open("{}.txt".format(filename)).read() wordlist = jieba.cut(text, cut_all=True) wl = " ".join(wordlist) cloud_mask = np.array(Image.open("bg.png")) wc = WordCloud( background_color="black", mask=cloud_mask, max_words=2000, font_path='simsun.ttf', height=1200, width=1600, max_font_size=100, random_state=100, ) myword = wc.generate(wl) plt.imshow(myword) plt.axis("off") plt.show() wc.to_file('py_book.png') if __name__ == '__main__': create_word_cloud('sg')
jieba分词词云
猜你喜欢
转载自www.cnblogs.com/chenzhijie/p/12702633.html
今日推荐
周排行