import jieba
from wordcloud import WordCloud
import numpy as np
import PIL .Image as image
import matplotlib.pyplot as plt
#导入数据,形成列表
text = open(r"aaa.txt",encoding="utf-8")
mylist = list(text)
#逐行分词
word_list = [" ".join(jieba.cut(row)) for row in mylist]
#各行的结果合并成一个列表
new_list = " ".join(word_list)
#导入找到的图片
mask = np.array(image.open(r"tupian.jpg"))
#绘制词语,图使用刚设置的变量mask
wordcloud = WordCloud(font_path = "simhei.ttf",background_color = "white",mask = mask).generate(new_list)
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
import jieba
from wordcloud import WordCloud
import numpy as np
import PIL .Image as image
import matplotlib.pyplot as plt
#导入数据,形成列表
text = open(r"aaa.txt",encoding="utf-8")
mylist = list(text)
#逐行分词
word_list = [" ".join(jieba.cut(row)) for row in mylist]
#各行的结果合并成一个列表
new_list = " ".join(word_list)
#导入找到的图片
mask = np.array(image.open(r"tupian.jpg"))
#绘制词语,图使用刚设置的变量mask
wordcloud = WordCloud(font_path = "simhei.ttf",background_color = "white",mask = mask).generate(new_list)
plt.imshow(wordcloud)
plt.axis("off")
plt.show()
本文展示了如何使用Python中的jieba库进行中文文本分词,并利用wordcloud库结合图片生成词云图,以可视化文本数据特征。
1万+

被折叠的 条评论
为什么被折叠?



