From e64d0e8bab4bf68ba24508f67f6539caa0f706bb Mon Sep 17 00:00:00 2001
From: poxf2i6c4 <2437587625@qq.com>
Date: Mon, 20 Jan 2025 19:27:07 +0800
Subject: [PATCH] ADD file via upload

---
 src | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)
 create mode 100644 src

diff --git a/src b/src
new file mode 100644
index 0000000..060f4cf
--- /dev/null
+++ b/src
@@ -0,0 +1,44 @@
+import json
+import pandas as pd
+from datetime import timedelta,datetime
+
+# 从 JSON 文件中加载数据
+ with open('commits_data_large.json', 'r') as f:
+    commits = json.load(f)
+             
+ # 将数据转换为 DataFrame
+ df = pd.DataFrame(commits)
+
+# 1.处理缺失值
+df = df.dropna()
+
+# 2. 转换日期时间格式
+df['author_date'] = pd.to_datetime(df['author_date'])
+
+
+
+
+# 特征工程
+ 
+  # 1. 提取时间相关特征
+ df['year'] = df['author_date'].dt.year
+ df['month'] = df['author_date'].dt.month
+df['day'] = df['author_date'].dt.day
+df['day_of_week'] = df['author_date'].dt.dayofweek
+df['hour'] = df['author_date'].dt.hour
+
+# 2. 计算开发者提交频率
+commit_counts = df.groupby('author_email').size().reset_index(name='commit_count')
+
+# 3. 计算开发者的活跃周期
+df['first_commit_date'] = df.groupby('author_email')['author_date'].transform('min')
+df['last_commit_date'] = df.groupby('author_email')['author_date'].transform('max')
+df['active_days'] = (df['last_commit_date'] - df['first_commit_date']).dt.days
+
+# 4. 合并特征
+df_features = pd.merge(commit_counts, avg_interval, on='author_email')
+df_features = pd.merge(df_features, df[['author_email', 'active_days']].drop_duplicates(), on='author_email')
+
+output_path = 'Dataset.csv'
+df_features.to_csv(output_path, index=False)
+print("数据预处理完成。")
\ No newline at end of file