v.1.34

app.py

@@ -645,7 +645,7 @@ def create_interface():
     control = ProcessControl()
     
     with gr.Blocks(theme=gr.themes.Soft()) as app:
-        gr.Markdown("# AI-анализ мониторинга новостей v.1.33")
+        gr.Markdown("# AI-анализ мониторинга новостей v.1.34")
         
         with gr.Row():
             file_input = gr.File(
@@ -704,130 +704,130 @@ def create_interface():
             control.request_stop()
             return "Остановка обработки..."
                 
-@spaces.GPU(duration=300)
-def analyze(file_bytes):
-    if file_bytes is None:
-        gr.Warning("Пожалуйста, загрузите файл")
-        return None, None, None, False, None, "Ожидание файла...", ""
-        
-    try:
-        # Reset stop flag
-        control.reset()
-        
-        file_obj = io.BytesIO(file_bytes)
-        logger.info("File loaded into BytesIO successfully")
-        
-        detector = EventDetector()
-        
-        # Read and deduplicate data
-        df = pd.read_excel(file_obj, sheet_name='Публикации')
-        original_count = len(df)
-        df = fuzzy_deduplicate(df, 'Выдержки из текста', threshold=55)
-        removed_count = original_count - len(df)
-        dedup_message = f"Удалено {removed_count} дубликатов из {original_count} записей"
-        logger.info(f"Removed {removed_count} duplicate entries")
-        
-        processed_rows = []
-        total = len(df)
-        batch_size = 3
-        
-        for batch_start in range(0, total, batch_size):
-            if control.should_stop():
+        @spaces.GPU(duration=300)
+        def analyze(file_bytes):
+            if file_bytes is None:
+                gr.Warning("Пожалуйста, загрузите файл")
+                return None, None, None, False, None, "Ожидание файла...", ""
+                
+            try:
+                # Reset stop flag
+                control.reset()
+                
+                file_obj = io.BytesIO(file_bytes)
+                logger.info("File loaded into BytesIO successfully")
+                
+                detector = EventDetector()
+                
+                # Read and deduplicate data
+                df = pd.read_excel(file_obj, sheet_name='Публикации')
+                original_count = len(df)
+                df = fuzzy_deduplicate(df, 'Выдержки из текста', threshold=55)
+                removed_count = original_count - len(df)
+                dedup_message = f"Удалено {removed_count} дубликатов из {original_count} записей"
+                logger.info(f"Removed {removed_count} duplicate entries")
+                
+                processed_rows = []
+                total = len(df)
+                batch_size = 3
+                
+                for batch_start in range(0, total, batch_size):
+                    if control.should_stop():
+                        if processed_rows:
+                            result_df = pd.DataFrame(processed_rows)
+                            output_bytes_io = create_output_file(result_df, file_obj)
+                            if output_bytes_io:
+                                output_bytes = output_bytes_io.getvalue()  # Convert BytesIO to bytes
+                                fig_sentiment, fig_events = create_visualizations(result_df)
+                                return (
+                                    result_df,
+                                    fig_sentiment,
+                                    fig_events,
+                                    True,
+                                    output_bytes,  # Return bytes instead of BytesIO
+                                    f"Обработка остановлена. Обработано {len(processed_rows)}/{total} строк",
+                                    dedup_message
+                                )
+                        break
+                    
+                    batch_end = min(batch_start + batch_size, total)
+                    batch = df.iloc[batch_start:batch_end]
+                    
+                    for idx, row in batch.iterrows():
+                        try:
+                            text = str(row.get('Выдержки из текста', '')).strip()
+                            entity = str(row.get('Объект', '')).strip()
+                            
+                            if not text or not entity:
+                                continue
+                            
+                            # Process with GPU
+                            results = detector.process_text(text, entity)
+                            
+                            processed_rows.append({
+                                'Объект': entity,
+                                'Заголовок': str(row.get('Заголовок', '')),
+                                'Translated': results['translated_text'],
+                                'Sentiment': results['sentiment'],
+                                'Impact': results['impact'],
+                                'Reasoning': results['reasoning'],
+                                'Event_Type': results['event_type'],
+                                'Event_Summary': results['event_summary'],
+                                'Выдержки из текста': text[:1000]
+                            })
+                            
+                        except Exception as e:
+                            logger.error(f"Error processing row {idx}: {str(e)}")
+                            continue
+                    
+                    # Create intermediate results
+                    if processed_rows:
+                        result_df = pd.DataFrame(processed_rows)
+                        output_bytes_io = create_output_file(result_df, file_obj)
+                        if output_bytes_io:
+                            output_bytes = output_bytes_io.getvalue()  # Convert BytesIO to bytes
+                            fig_sentiment, fig_events = create_visualizations(result_df)
+                            yield (
+                                result_df,
+                                fig_sentiment,
+                                fig_events,
+                                True,
+                                output_bytes,  # Return bytes instead of BytesIO
+                                f"Обработано {len(processed_rows)}/{total} строк",
+                                dedup_message
+                            )
+                    
+                    # Cleanup GPU resources after batch
+                    torch.cuda.empty_cache()
+                    time.sleep(2)
+                
+                # Create final results
                 if processed_rows:
-                    result_df = pd.DataFrame(processed_rows)
-                    output_bytes_io = create_output_file(result_df, file_obj)
+                    final_df = pd.DataFrame(processed_rows)
+                    output_bytes_io = create_output_file(final_df, file_obj)
                     if output_bytes_io:
                         output_bytes = output_bytes_io.getvalue()  # Convert BytesIO to bytes
-                        fig_sentiment, fig_events = create_visualizations(result_df)
+                        fig_sentiment, fig_events = create_visualizations(final_df)
                         return (
-                            result_df,
+                            final_df,
                             fig_sentiment,
                             fig_events,
                             True,
                             output_bytes,  # Return bytes instead of BytesIO
-                            f"Обработка остановлена. Обработано {len(processed_rows)}/{total} строк",
+                            "Обработка завершена!",
                             dedup_message
                         )
-                break
-            
-            batch_end = min(batch_start + batch_size, total)
-            batch = df.iloc[batch_start:batch_end]
-            
-            for idx, row in batch.iterrows():
-                try:
-                    text = str(row.get('Выдержки из текста', '')).strip()
-                    entity = str(row.get('Объект', '')).strip()
-                    
-                    if not text or not entity:
-                        continue
-                    
-                    # Process with GPU
-                    results = detector.process_text(text, entity)
-                    
-                    processed_rows.append({
-                        'Объект': entity,
-                        'Заголовок': str(row.get('Заголовок', '')),
-                        'Translated': results['translated_text'],
-                        'Sentiment': results['sentiment'],
-                        'Impact': results['impact'],
-                        'Reasoning': results['reasoning'],
-                        'Event_Type': results['event_type'],
-                        'Event_Summary': results['event_summary'],
-                        'Выдержки из текста': text[:1000]
-                    })
+                else:
+                    return None, None, None, False, None, "Нет обработанных данных", ""
                     
-                except Exception as e:
-                    logger.error(f"Error processing row {idx}: {str(e)}")
-                    continue
-            
-            # Create intermediate results
-            if processed_rows:
-                result_df = pd.DataFrame(processed_rows)
-                output_bytes_io = create_output_file(result_df, file_obj)
-                if output_bytes_io:
-                    output_bytes = output_bytes_io.getvalue()  # Convert BytesIO to bytes
-                    fig_sentiment, fig_events = create_visualizations(result_df)
-                    yield (
-                        result_df,
-                        fig_sentiment,
-                        fig_events,
-                        True,
-                        output_bytes,  # Return bytes instead of BytesIO
-                        f"Обработано {len(processed_rows)}/{total} строк",
-                        dedup_message
-                    )
-            
-            # Cleanup GPU resources after batch
-            torch.cuda.empty_cache()
-            time.sleep(2)
-        
-        # Create final results
-        if processed_rows:
-            final_df = pd.DataFrame(processed_rows)
-            output_bytes_io = create_output_file(final_df, file_obj)
-            if output_bytes_io:
-                output_bytes = output_bytes_io.getvalue()  # Convert BytesIO to bytes
-                fig_sentiment, fig_events = create_visualizations(final_df)
-                return (
-                    final_df,
-                    fig_sentiment,
-                    fig_events,
-                    True,
-                    output_bytes,  # Return bytes instead of BytesIO
-                    "Обработка завершена!",
-                    dedup_message
-                )
-        else:
-            return None, None, None, False, None, "Нет обработанных данных", ""
-            
-    except Exception as e:
-        error_msg = f"Ошибка анализа: {str(e)}"
-        logger.error(error_msg)
-        gr.Error(error_msg)
-        return None, None, None, False, None, error_msg, ""
-    finally:
-        if detector:
-            detector.cleanup()
+            except Exception as e:
+                error_msg = f"Ошибка анализа: {str(e)}"
+                logger.error(error_msg)
+                gr.Error(error_msg)
+                return None, None, None, False, None, error_msg, ""
+            finally:
+                if detector:
+                    detector.cleanup()
                     
         def trigger_download(show_button, file_content):
             """Handle download button visibility and file content"""