You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
python/part2

49 lines
1.1 KiB

from wordcloud import WordCloud, STOPWORDS
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import jieba
# 打开文件
text = open("xinglang.txt", encoding="utf-8").read()
# 中文分词
text = ' '.join(jieba.cut(text))
print(text[:100])
# 停用词
stopwords = STOPWORDS
STOPWORDS.add("的")
STOPWORDS.add("了")
STOPWORDS.add("这")
STOPWORDS.add("和")
STOPWORDS.add("是")
STOPWORDS.add("上")
STOPWORDS.add("让")
STOPWORDS.add("为")
STOPWORDS.add("中")
STOPWORDS.add("个")
STOPWORDS.add("能")
STOPWORDS.add("年")
STOPWORDS.add("到")
STOPWORDS.add("在")
STOPWORDS.add("我")
STOPWORDS.add("也")
STOPWORDS.add("到")
STOPWORDS.add("有")
STOPWORDS.add("就")
STOPWORDS.add("寻亲")
# 生成对象
# 使用蒙版图片
mask = np.array(Image.open("zhihu.png")) # 使用蒙版图片
wc = WordCloud(
mask=mask,
font_path="STKAITI.TTF",
mode="RGBA",
background_color=None,
stopwords=STOPWORDS
).generate(text)
# 显示词云
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
plt.show()
# 保存文件
wc.to_file("xinglang_wordcloud.png")