From 685ee40a1e403143159b9f304f66c6cd6ce83146 Mon Sep 17 00:00:00 2001
From: pbk4qcfyv <1678854362@qq.com>
Date: Wed, 18 Sep 2024 04:37:05 +0800
Subject: [PATCH] ADD file via upload

---
 ai前8.py | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 ai前8.py

diff --git a/ai前8.py b/ai前8.py
new file mode 100644
index 0000000..b19da59
--- /dev/null
+++ b/ai前8.py
@@ -0,0 +1,35 @@
+import pandas as pd
+from openpyxl import Workbook
+import re
+
+def normalize_bullet_comment(commet):
+    #归一化类似的弹幕
+    if re.search(r'哈{2,}',commet):
+        return '哈哈哈'
+    return commet
+
+def is_airelated(comment):
+    ai_keywords = ['ai','神经网络','机器学习','AI','人工智能','深度学习']
+    return any(keyword in comment for keyword in ai_keywords)
+
+#读取弹幕
+with open('弹幕.txt','r',encoding='utf-8') as file:
+    bullet_comments = file.readlines()
+
+#处理弹幕
+bullet_comments = [normalize_bullet_comment(line.strip()) for line in bullet_comments]
+
+#统计包含关键词的弹幕
+ai_related_comments = [comment for comment in bullet_comments if is_airelated(comment)]
+count_series = pd.Series(ai_related_comments).value_counts()
+top_8 = count_series.head(8)
+
+#创建DataFrame并保存到Excel
+df = pd.DataFrame({
+    '弹幕':top_8.index,
+    '数量':top_8.values
+})
+
+df.to_excel('aiTop8.xlsx',index=False,sheet_name='Top 8 Bullet Comments')
+
+