嘻嘻嘻,简单搞了个关于嘉尔在《福布斯中国》受采访的词云
可以参照一下代码
import jieba
from wordcloud import WordCloud # 从wordcloud库中导入WordCloud类,这个类用来创建词云对象
from PIL import Image # python imaging library PIL
import matplotlib.pyplot as plt
import numpy as np
# 打开文本,进行中文分词
f = open("Forbes-JacksonWang.txt", encoding="utf-8")
s = f.read()
text = ' '.join(jieba.lcut(s))
# 生成对象
img = Image.open("lovelygaga.jpg") # 打开遮罩图片
mask = np.array(img) # 将图片转换为数组
#设置停用词
stopwords = set()
content = [line.strip() for line in
open("stop_words.txt", 'r', encoding="utf-8").readlines()]
stopwords.update(content)
# 创建词云对象
wc = WordCloud(
font_path='C: Windows\Fonts\华康方圆体W7.TTC',
width=825,
height=800,
background_color='white',
max_words=150,
stopwords=stopwords
).generate(text)
# 用p显示图片
p.imshow(wc, interpolation='bilinear')
# 不显示坐标轴
p.axis("off")
# 显示词云图片
p.show()
# 保存到文件
wc.to_file("C:\\Desktop\\JacksonWang_wordcloud.jpg")