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
1.6 KiB
49 lines
1.6 KiB
import jieba # 引入分词模块
|
|
import wordcloud # 引入词云图配置模块
|
|
import imageio # 引入图片模块，改变词云图形状
|
|
|
|
|
|
# 1、对弹幕进行读取
|
|
f = open("全弹幕.txt",encoding="utf-8") # 读取全弹幕
|
|
text = f.read()
|
|
f1 = open("AI弹幕.txt",encoding="utf-8") # 读取AI弹幕
|
|
text1 = f1.read()
|
|
|
|
|
|
# 2、对弹幕数据进行分词操作
|
|
word_list = jieba.lcut(text) #对全弹幕进行分词
|
|
for word in word_list:
|
|
with open('全弹幕分词.xls',mode='a',encoding='utf-8') as f: # 将全弹幕分词保存在xls表中
|
|
if word != '\n': # 防止输入换行字符
|
|
f.write(word)
|
|
f.write('\n')
|
|
|
|
word_list1 = jieba.lcut(text1) #对AI弹幕进行分词
|
|
for word in word_list1:
|
|
with open('AI弹幕分词.xls',mode='a',encoding='utf-8') as f: # 将AI弹幕分词保存在xls表中
|
|
if word != '\n': # 防止输入换行字符
|
|
f.write(word)
|
|
f.write('\n')
|
|
|
|
# 3、将分割出的词连接成字符串
|
|
word_str = ' '.join(word_list) # 全弹幕
|
|
word_str1 = ' '.join(word_list1) # AI弹幕
|
|
|
|
|
|
# 4、进行词云图相关配置
|
|
img = imageio.imread('1.jpg') # 载入图片
|
|
wcdall = wordcloud.WordCloud( # 全弹幕词云图
|
|
mask=img, # 形状
|
|
background_color='white', # 背景颜色
|
|
font_path='msyh.ttc' # 字体文件
|
|
)
|
|
wcdall.generate(word_str)
|
|
wcdall.to_file('全弹幕词云.png')
|
|
|
|
wcdai = wordcloud.WordCloud( # AI弹幕词云图
|
|
mask=img, # 形状
|
|
background_color='white', # 背景颜色
|
|
font_path='msyh.ttc' # 字体文件
|
|
)
|
|
wcdai.generate(word_str1)
|
|
wcdai.to_file('AI弹幕词云.png') |