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.
49 lines
1.4 KiB
49 lines
1.4 KiB
2 months ago
|
import pandas as pd
|
||
|
|
import jieba
|
||
|
|
from wordcloud import WordCloud
|
||
|
|
from imageio import imread
|
||
|
|
def GetWordCloud():
|
||
|
|
"""根据弹幕以及词频制作词云图"""
|
||
|
|
# 读取弹幕文件并转为字典类型
|
||
|
|
df = pd.read_csv("danmu.csv")
|
||
|
|
danmus = dict(zip(df["弹幕"], df["数量"]))
|
||
|
|
|
||
|
|
# 读取停用词
|
||
|
|
with open('stopwords.txt', 'r', encoding='utf-8') as f:
|
||
|
|
stopwords = f.readlines()
|
||
|
|
stopwords = [stopword.strip() for stopword in stopwords]
|
||
|
|
|
||
|
|
# 将所有评论合并为一个字符串
|
||
|
|
txt = ''
|
||
|
|
for key, value in danmus.items():
|
||
|
|
for i in range(value):
|
||
|
|
txt += key
|
||
|
|
|
||
|
|
# 获得每个词汇及其数量
|
||
|
|
words = jieba.lcut(txt)
|
||
|
|
words_dict = {}
|
||
|
|
for word in words:
|
||
|
|
if len(word) == 1:
|
||
|
|
continue
|
||
|
|
if word not in stopwords:
|
||
|
|
words_dict[word] = words_dict.get(word, 0) + 1
|
||
|
|
words_list = list(words_dict.items())
|
||
|
|
words_list.sort(key = lambda x:x[1], reverse=True)
|
||
|
|
words_count = dict(words_list)
|
||
|
|
|
||
|
|
# 生成词云图
|
||
|
|
wordcloud = WordCloud(
|
||
|
|
background_color="white",
|
||
|
|
width=1000,
|
||
|
|
height=800,
|
||
|
|
font_path="msyh.ttc",
|
||
|
|
max_words=1000,
|
||
|
|
mask=imread("mask.png"),
|
||
|
|
).generate_from_frequencies(words_count)
|
||
|
|
|
||
|
|
#词云图保存文件
|
||
|
|
wordcloud.to_file("wordcloud.png")
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
GetWordCloud()
|