#词云
from wordcloud import WordCloud, STOPWORDS
from imageio import imread
from sklearn.feature_extraction.text import CountVectorizer
import jieba
import csv
# 获取文章内容
with open("mdzs.txt",'r',encoding='UTF-8') as f:
contents = f.read()
print("contents变量的类型:", type(contents))
# 使用jieba分词,获取词的列表
contents_cut = jieba.cut(contents)
print("contents_cut变量的类型:", type(contents_cut))
contents_list = " ".join(contents_cut)
print("contents_list变量的类型:", type(contents_list))
# 制作词云图,collocations避免词云图中词的重复,mask定义词云图的形状,图片要有背景色
wc = WordCloud(stopwords=STOPWORDS.add("一个"), collocations=False,
background_color="white",
font_path=r"C:\Windows\Fonts\simhei.ttf",
width=400, height=300, random_state=42,
mask=imread('cat.png',pilmode="RGB"))
wc.generate(contents_list)
wc.to_file("ciyun.png")
# 使用CountVectorizer统计词频
cv = CountVectorizer()
contents_count = cv.fit_transform([contents_list])
# 词有哪些
list1 = cv.get_feature_names()
# 词的频率
list2 = contents_count.toarray().tolist()[0]
# 将词与频率一一对应
contents_dict = dict(zip(list1, list2))
# 输出csv文件,newline="",解决输出的csv隔行问题
with open("caifu_output.csv", 'w', newline="") as f:
writer = csv.writer(f)
for key, value in contents_dict.items():
writer.writerow([key, value])
Python编程练习:猫猫词云__魔道祖师
最新推荐文章于 2023-06-14 08:00:00 发布