From 8202de20a52cb64bcc3525dcea9f5ed25affbc2b Mon Sep 17 00:00:00 2001
From: pzb7h6yxf <1736289433@qq.com>
Date: Tue, 17 Sep 2024 10:02:08 +0800
Subject: [PATCH] =?UTF-8?q?=E5=B0=86=E7=BB=9F=E8=AE=A1=E7=9A=84=E6=95=B0?=
 =?UTF-8?q?=E6=8D=AE=E5=88=A9=E7=94=A8=E7=BC=96=E7=A8=8B=E5=B7=A5=E5=85=B7?=
 =?UTF-8?q?=E8=87=AA=E5=8A=A8=E5=86=99=E5=85=A5Excel=E8=A1=A8=E4=B8=AD?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 2.2.2.py | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 2.2.2.py

diff --git a/2.2.2.py b/2.2.2.py
new file mode 100644
index 0000000..98d80af
--- /dev/null
+++ b/2.2.2.py
@@ -0,0 +1,41 @@
+import jieba
+import wordcloud
+import imageio
+import pandas as pd  # 用于读取Excel文件
+
+# 读取图片作为词云的形状
+img = imageio.imread('四叶草1.png')
+
+# 使用pandas读取Excel文件中的所有列
+df = pd.read_excel('top_ai_danmakus.xlsx')
+
+# 将Excel所有列的数据拼接成一个长字符串
+book = ''
+
+# 遍历每一列并将内容合并成字符串
+for column in df.columns:
+    # 将当前列转换为字符串并拼接到 book 变量
+    book += ' '.join(df[column].astype(str)) + ' '
+
+# 使用jieba进行分词
+book_list = jieba.lcut(book)
+book_str = ' '.join(book_list)
+
+# 打印分词后的字符串
+print(book_str)
+
+# 创建词云
+wc = wordcloud.WordCloud(
+    width=500,
+    height=500,
+    background_color='white',
+    mask=img,
+     stopwords={'main','Taipei','afraid','aiden','Britain'},  # 可添加不需要的停用词
+    font_path='msyh.ttc'  # 设置中文字体路径
+)
+
+# 生成词云
+wc.generate(book_str)
+
+# 保存词云图
+wc.to_file('词云图.png')