Create app.py

create download function according to timestamp

app.py

@@ -0,0 +1,270 @@
+import gradio as gr
+import pandas as pd
+from datetime import datetime, timedelta
+import io
+import os
+from huggingface_hub import HfApi, hf_hub_download
+from typing import List, Tuple, Optional
+import tempfile
+import zipfile
+
+class DataManager:
+    def __init__(self):
+        self.repo_id = "CIV3283/Data_Storage"
+        self.branch = "data_branch"
+        self.api = HfApi()
+        
+    def get_available_files(self) -> Tuple[List[str], List[str]]:
+        """获取所有可用的feedback和query文件"""
+        try:
+            # 获取仓库中的所有文件
+            repo_files = self.api.list_repo_files(
+                repo_id=self.repo_id,
+                revision=self.branch
+            )
+            
+            feedback_files = []
+            query_files = []
+            
+            for file in repo_files:
+                if file.endswith('_feedback_log.csv') and 'CIV3283_Student_' in file:
+                    feedback_files.append(file)
+                elif file.endswith('_query_log.csv') and 'CIV3283_Student_' in file:
+                    query_files.append(file)
+            
+            return sorted(feedback_files), sorted(query_files)
+            
+        except Exception as e:
+            print(f"Error getting files: {e}")
+            return [], []
+    
+    def download_and_read_csv(self, filename: str) -> pd.DataFrame:
+        """下载并读取CSV文件"""
+        try:
+            # 下载文件到临时位置
+            local_file = hf_hub_download(
+                repo_id=self.repo_id,
+                filename=filename,
+                revision=self.branch,
+                cache_dir=tempfile.gettempdir()
+            )
+            
+            # 读取CSV
+            df = pd.read_csv(local_file)
+            
+            # 确保timestamp列存在并转换为datetime
+            if 'timestamp' in df.columns:
+                df['timestamp'] = pd.to_datetime(df['timestamp'])
+            
+            return df
+            
+        except Exception as e:
+            print(f"Error reading {filename}: {e}")
+            return pd.DataFrame()
+    
+    def filter_data_by_date(self, df: pd.DataFrame, start_date: str, end_date: str) -> pd.DataFrame:
+        """根据日期范围筛选数据"""
+        if df.empty or 'timestamp' not in df.columns:
+            return df
+        
+        try:
+            # 转换输入的日期字符串
+            start_dt = pd.to_datetime(start_date)
+            
+            if end_date == "现在":
+                end_dt = pd.Timestamp.now()
+            else:
+                end_dt = pd.to_datetime(end_date) + timedelta(days=1) - timedelta(seconds=1)  # 包含整天
+            
+            # 筛选数据
+            mask = (df['timestamp'] >= start_dt) & (df['timestamp'] <= end_dt)
+            return df[mask]
+            
+        except Exception as e:
+            print(f"Error filtering data: {e}")
+            return df
+    
+    def process_files(self, file_type: str, start_date: str, end_date: str) -> Tuple[str, str, str]:
+        """处理文件并生成下载内容"""
+        feedback_files, query_files = self.get_available_files()
+        
+        result_data = []
+        file_info = []
+        total_records = 0
+        
+        # 根据选择的文件类型确定要处理的文件
+        files_to_process = []
+        if file_type in ["反馈文件", "两者都要"]:
+            files_to_process.extend([(f, "feedback") for f in feedback_files])
+        if file_type in ["查询文件", "两者都要"]:
+            files_to_process.extend([(f, "query") for f in query_files])
+        
+        # 处理每个文件
+        for filename, ftype in files_to_process:
+            df = self.download_and_read_csv(filename)
+            if not df.empty:
+                original_count = len(df)
+                filtered_df = self.filter_data_by_date(df, start_date, end_date)
+                filtered_count = len(filtered_df)
+                
+                if filtered_count > 0:
+                    result_data.append(filtered_df)
+                    total_records += filtered_count
+                
+                file_info.append(f"{filename}: {original_count}条记录 → {filtered_count}条符合条件")
+        
+        # 合并所有数据
+        if result_data:
+            combined_df = pd.concat(result_data, ignore_index=True)
+            
+            # 生成CSV内容
+            csv_buffer = io.StringIO()
+            combined_df.to_csv(csv_buffer, index=False, encoding='utf-8')
+            csv_content = csv_buffer.getvalue()
+            
+            # 生成文件名
+            end_date_str = "现在" if end_date == "现在" else end_date
+            filename = f"CIV3283_数据导出_{file_type}_{start_date}_to_{end_date_str}.csv"
+            
+            # 生成状态信息
+            status = f"✅ 成功处理 {len(files_to_process)} 个文件\n"
+            status += f"📊 总共找到 {total_records} 条符合条件的记录\n"
+            status += f"📅 时间范围: {start_date} 到 {end_date_str}\n\n"
+            status += "文件详情:\n" + "\n".join(file_info)
+            
+            return csv_content, filename, status
+        else:
+            return "", "", "❌ 没有找到符合条件的数据"
+
+# 初始化数据管理器
+data_manager = DataManager()
+
+def process_and_download(file_type, start_date, end_date):
+    """处理请求并返回下载文件"""
+    try:
+        csv_content, filename, status = data_manager.process_files(file_type, start_date, end_date)
+        
+        if csv_content:
+            # 创建临时文件
+            temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False, encoding='utf-8')
+            temp_file.write(csv_content)
+            temp_file.close()
+            
+            return status, temp_file.name, filename
+        else:
+            return status, None, None
+            
+    except Exception as e:
+        return f"❌ 处理过程中出现错误: {str(e)}", None, None
+
+def get_file_summary():
+    """获取文件概览"""
+    try:
+        feedback_files, query_files = data_manager.get_available_files()
+        summary = f"📁 当前可用文件:\n"
+        summary += f"   反馈文件: {len(feedback_files)} 个\n"
+        summary += f"   查询文件: {len(query_files)} 个\n"
+        summary += f"   总计: {len(feedback_files) + len(query_files)} 个文件"
+        return summary
+    except Exception as e:
+        return f"❌ 获取文件列表失败: {str(e)}"
+
+# 创建Gradio界面
+def create_interface():
+    with gr.Blocks(title="CIV3283 数据管理器", theme=gr.themes.Soft()) as demo:
+        gr.Markdown("# 🗃️ CIV3283 数据存储管理器")
+        gr.Markdown("从 Hugging Face Space 的 data_branch 分支整理和下载学生数据")
+        
+        # 文件概览
+        with gr.Row():
+            file_summary = gr.Textbox(
+                label="📊 文件概览",
+                value=get_file_summary(),
+                interactive=False,
+                max_lines=5
+            )
+            refresh_btn = gr.Button("🔄 刷新文件列表", variant="secondary")
+        
+        refresh_btn.click(
+            fn=get_file_summary,
+            outputs=file_summary
+        )
+        
+        # 主要控制面板
+        with gr.Row():
+            with gr.Column(scale=1):
+                file_type = gr.Radio(
+                    choices=["查询文件", "反馈文件", "两者都要"],
+                    value="查询文件",
+                    label="📂 选择文件类型"
+                )
+                
+                start_date = gr.Textbox(
+                    label="📅 开始日期",
+                    placeholder="2025-06-16",
+                    value="2025-06-16",
+                    info="格式: YYYY-MM-DD"
+                )
+                
+                end_date = gr.Textbox(
+                    label="📅 结束日期",
+                    placeholder="2025-06-20 或 现在",
+                    value="现在",
+                    info="格式: YYYY-MM-DD 或输入'现在'"
+                )
+                
+                process_btn = gr.Button("🚀 处理并生成下载文件", variant="primary", size="lg")
+            
+            with gr.Column(scale=2):
+                status_box = gr.Textbox(
+                    label="📋 处理状态",
+                    max_lines=15,
+                    interactive=False
+                )
+                
+                download_file = gr.File(
+                    label="📥 下载文件",
+                    interactive=False
+                )
+        
+        # 使用说明
+        with gr.Accordion("📖 使用说明", open=False):
+            gr.Markdown("""
+            ### 功能说明
+            1. **文件类型选择**: 选择要导出的数据类型
+               - 查询文件: 包含搜索信息和查询响应
+               - 反馈文件: 包含学生反馈评论
+               - 两者都要: 合并所有数据
+            
+            2. **日期范围**: 
+               - 开始日期: 必须填写，格式 YYYY-MM-DD
+               - 结束日期: 可以是具体日期或"现在"
+            
+            3. **数据格式**:
+               - Query文件列: student_space, student_id, timestamp, search_info, query_and_response, thumb_feedback
+               - Feedback文件列: student_space, student_id, timestamp, comment
+            
+            ### 注意事项
+            - 系统会自动发现所有可用的学生文件（01-95，跳过缺失的编号）
+            - 时间戳格式: 2025-06-16 08:55:33
+            - 导出的数据保持原始顺序，不进行时间排序
+            - 每次处理会显示详细的文件统计信息
+            """)
+        
+        # 绑定处理函数
+        process_btn.click(
+            fn=process_and_download,
+            inputs=[file_type, start_date, end_date],
+            outputs=[status_box, download_file, gr.State()]
+        )
+    
+    return demo
+
+# 启动应用
+if __name__ == "__main__":
+    demo = create_interface()
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True
+    )