Update app.py

download file name

app.py

@@ -13,28 +13,28 @@ class DataManager:
         self.repo_id = "CIV3283/Data_Storage"
         self.branch = "data_branch"
         
-        # 优先使用传入的token，否则从环境变量获取
+        # Use provided token first, otherwise get from environment variable
         self.token = token or os.getenv('CIV3283_access')
         
-        # 如果有token，进行认证
+        # Authenticate if token is available
         if self.token:
             try:
                 login(token=self.token)
-                print("✅ 认证成功")
+                print("✅ Authentication successful")
             except Exception as e:
-                print(f"❌ 认证失败: {e}")
+                print(f"❌ Authentication failed: {e}")
         
         self.api = HfApi(token=self.token)
         
     def get_available_files(self) -> Tuple[List[str], List[str]]:
-        """获取所有可用的feedback和query文件"""
+        """Get all available feedback and query files"""
         try:
-            # 尝试获取仓库中的所有文件
+            # Try to get all files from repository
             repo_files = self.api.list_repo_files(
                 repo_id=self.repo_id,
                 revision=self.branch,
                 token=self.token,
-                repo_type="space"  # 明确指定这是一个space
+                repo_type="space"  # Explicitly specify this is a space
             )
             
             feedback_files = []
@@ -49,18 +49,18 @@ class DataManager:
             return sorted(feedback_files), sorted(query_files)
             
         except Exception as e:
-            print(f"❌ 获取文件列表错误: {e}")
-            # 如果API调用失败，尝试手动生成可能的文件名列表
+            print(f"❌ Error getting file list: {e}")
+            # If API call fails, try to generate possible filename list
             return self._generate_possible_filenames()
     
     def _generate_possible_filenames(self) -> Tuple[List[str], List[str]]:
-        """生成可能的文件名列表作为后备方案"""
+        """Generate possible filename list as backup"""
         feedback_files = []
         query_files = []
         
-        # 生成01到95的所有可能文件名
+        # Generate all possible filenames from 01 to 95
         for i in range(1, 96):
-            student_id = f"{i:02d}"  # 格式化为两位数
+            student_id = f"{i:02d}"  # Format as two digits
             feedback_file = f"CIV3283_Student_{student_id}_feedback_log.csv"
             query_file = f"CIV3283_Student_{student_id}_query_log.csv"
             feedback_files.append(feedback_file)
@@ -69,9 +69,9 @@ class DataManager:
         return feedback_files, query_files
     
     def download_and_read_csv(self, filename: str) -> pd.DataFrame:
-        """下载并读取CSV文件"""
+        """Download and read CSV file"""
         try:
-            # 下载文件到临时位置
+            # Download file to temporary location
             local_file = hf_hub_download(
                 repo_id=self.repo_id,
                 filename=filename,
@@ -81,35 +81,35 @@ class DataManager:
                 cache_dir=tempfile.gettempdir()
             )
             
-            # 读取CSV
+            # Read CSV
             df = pd.read_csv(local_file)
             
-            # 确保timestamp列存在并转换为datetime
+            # Ensure timestamp column exists and convert to datetime
             if 'timestamp' in df.columns:
                 df['timestamp'] = pd.to_datetime(df['timestamp'])
             
             return df
             
         except Exception as e:
-            print(f"❌ 读取文件 {filename} 失败: {e}")
-            # 返回空DataFrame而不是完全失败
+            print(f"❌ Failed to read file {filename}: {e}")
+            # Return empty DataFrame rather than complete failure
             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"""
+        """Filter data by date range"""
         if df.empty or 'timestamp' not in df.columns:
             return df
         
         try:
-            # 转换输入的日期字符串
+            # Convert input date strings
             start_dt = pd.to_datetime(start_date)
             
-            if end_date == "现在":
+            if end_date == "now":
                 end_dt = pd.Timestamp.now()
             else:
-                end_dt = pd.to_datetime(end_date) + timedelta(days=1) - timedelta(seconds=1)  # 包含整天
+                end_dt = pd.to_datetime(end_date) + timedelta(days=1) - timedelta(seconds=1)  # Include full day
             
-            # 筛选数据
+            # Filter data
             mask = (df['timestamp'] >= start_dt) & (df['timestamp'] <= end_dt)
             return df[mask]
             
@@ -118,21 +118,21 @@ class DataManager:
             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"""
+        """Process files and generate download content"""
         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
+        # Determine files to process based on selected file type
         files_to_process = []
-        if file_type in ["反馈文件", "两者都要"]:
+        if file_type in ["Feedback Files", "Both"]:
             files_to_process.extend([(f, "feedback") for f in feedback_files])
-        if file_type in ["查询文件", "两者都要"]:
+        if file_type in ["Query Files", "Both"]:
             files_to_process.extend([(f, "query") for f in query_files])
         
-        # 处理每个文件
+        # Process each file
         for filename, ftype in files_to_process:
             df = self.download_and_read_csv(filename)
             if not df.empty:
@@ -144,44 +144,45 @@ class DataManager:
                     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")
+                file_info.append(f"{filename}: {original_count} records → {filtered_count} matching criteria")
         
-        # 合并所有数据
+        # Combine all data
         if result_data:
             combined_df = pd.concat(result_data, ignore_index=True)
             
-            # 生成CSV内容
+            # Generate CSV content
             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"
+            # Generate filename with type and date info
+            end_date_str = "now" if end_date == "now" else end_date
+            type_str = file_type.lower().replace(" ", "_")
+            filename = f"CIV3283_data_export_{type_str}_{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)
+            # Generate status info
+            status = f"✅ Successfully processed {len(files_to_process)} files\n"
+            status += f"📊 Total records found: {total_records}\n"
+            status += f"📅 Date range: {start_date} to {end_date_str}\n\n"
+            status += "File details:\n" + "\n".join(file_info)
             
             return csv_content, filename, status
         else:
-            return "", "", "❌ 没有找到符合条件的数据"
+            return "", "", "❌ No matching data found"
 
-# 全局变量存储数据管理器
+# Global variable to store data manager
 data_manager = None
 
 def initialize_data_manager(hf_token=None):
-    """初始化数据管理器"""
+    """Initialize data manager"""
     global data_manager
     data_manager = DataManager(token=hf_token)
     return data_manager
 
 def process_and_download(file_type, start_date, end_date, hf_token):
-    """处理请求并返回下载文件"""
+    """Process request and return download file"""
     try:
-        # 确保数据管理器已初始化
+        # Ensure data manager is initialized
         global data_manager
         env_token = os.getenv('CIV3283_access')
         current_token = hf_token or env_token
@@ -192,7 +193,7 @@ def process_and_download(file_type, start_date, end_date, hf_token):
         csv_content, filename, status = data_manager.process_files(file_type, start_date, end_date)
         
         if csv_content:
-            # 创建临时文件
+            # Create temporary file
             temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False, encoding='utf-8')
             temp_file.write(csv_content)
             temp_file.close()
@@ -202,12 +203,12 @@ def process_and_download(file_type, start_date, end_date, hf_token):
             return status, None, None
             
     except Exception as e:
-        return f"❌ 处理过程中出现错误: {str(e)}", None, None
+        return f"❌ Error occurred during processing: {str(e)}", None, None
 
 def get_file_summary(hf_token=None):
-    """获取文件概览"""
+    """Get file overview"""
     try:
-        # 如果还没有初始化或token发生变化，重新初始化
+        # If not initialized or token changed, reinitialize
         global data_manager
         env_token = os.getenv('CIV3283_access')
         current_token = hf_token or env_token
@@ -216,21 +217,21 @@ def get_file_summary(hf_token=None):
             data_manager = initialize_data_manager(current_token)
         
         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"
+        summary = f"📁 Currently available files:\n"
+        summary += f"   Feedback files: {len(feedback_files)}\n"
+        summary += f"   Query files: {len(query_files)}\n"
+        summary += f"   Total: {len(feedback_files) + len(query_files)} files"
         
         if env_token:
-            summary += f"\n✅ 使用环境变量 CIV3283_access 认证"
+            summary += f"\n✅ Authenticated using environment variable CIV3283_access"
         elif hf_token:
-            summary += f"\n✅ 使用手动输入的token认证"
+            summary += f"\n✅ Authenticated using manual token input"
         else:
-            summary += f"\n⚠️  未找到认证token（可能无法访问私有仓库）"
+            summary += f"\n⚠️  No authentication token found (may not access private repositories)"
             
         return summary
     except Exception as e:
-        return f"❌ 获取文件列表失败: {str(e)}"
+        return f"❌ Failed to get file list: {str(e)}"
 
 # 创建Gradio界面
 def create_interface():
@@ -352,8 +353,9 @@ def create_interface():
     
     return demo
 
-# 启动应用
+# Launch application
 if __name__ == "__main__":
     demo = create_interface()
     demo.launch(
+
     )