v.1.09

app.py

@@ -116,9 +116,84 @@ def create_visualizations(df):
         logger.error(f"Visualization error: {e}")
         return None, None
 
+def process_file(file_obj):
+    try:
+        # Debug print
+        logger.info("Starting to read Excel file...")
+        
+        # Read Excel with error details
+        try:
+            df = pd.read_excel(file_obj, sheet_name='Публикации')
+            logger.info(f"Successfully read Excel file. Shape: {df.shape}")
+            logger.info(f"Columns: {df.columns.tolist()}")
+        except Exception as e:
+            logger.error(f"Failed to read Excel file: {str(e)}")
+            raise
+
+        detector = EventDetector()
+        processed_rows = []
+        total = len(df)
+        current_status = "0%"
+        
+        # Create progress counter
+        progress_text = gr.Textbox.update(
+            value=f"Обработано 0 из {total} строк (0%)"
+        )
+        
+        for idx, row in df.iterrows():
+            try:
+                # Get text and entity with validation
+                text = str(row.get('Выдержки из текста', ''))
+                if not text.strip():
+                    logger.warning(f"Empty text at row {idx}")
+                    continue
+                    
+                entity = str(row.get('Объект', ''))
+                if not entity.strip():
+                    logger.warning(f"Empty entity at row {idx}")
+                    continue
+                
+                # Process the row
+                event_type, event_summary = detector.detect_events(text, entity)
+                sentiment = detector.analyze_sentiment(text)
+                
+                processed_rows.append({
+                    'Объект': entity,
+                    'Заголовок': str(row.get('Заголовок', '')),
+                    'Sentiment': sentiment,
+                    'Event_Type': event_type,
+                    'Event_Summary': event_summary,
+                    'Текст': text
+                })
+                
+                # Update progress every 5 rows
+                if idx % 5 == 0 or idx == total - 1:
+                    percentage = round((idx + 1) / total * 100)
+                    if percentage != current_status:
+                        current_status = percentage
+                        logger.info(f"Processed {idx + 1}/{total} rows ({percentage}%)")
+                
+            except Exception as e:
+                logger.error(f"Error processing row {idx}: {str(e)}")
+                continue
+        
+        # Create final DataFrame
+        result_df = pd.DataFrame(processed_rows)
+        logger.info(f"Processing complete. Final DataFrame shape: {result_df.shape}")
+        
+        if result_df.empty:
+            logger.error("No rows were processed successfully")
+            raise ValueError("No data was processed successfully")
+            
+        return result_df
+        
+    except Exception as e:
+        logger.error(f"File processing error: {str(e)}")
+        raise
+
 def create_interface():
     with gr.Blocks(theme=gr.themes.Soft()) as app:
-        gr.Markdown("# AI-анализ мониторинга новостей v.1.08+")
+        gr.Markdown("# AI-анализ мониторинга новостей v.1.09")
         
         with gr.Row():
             file_input = gr.File(
@@ -135,7 +210,7 @@ def create_interface():
             
         with gr.Row():
             progress = gr.Textbox(
-                label="Статус",
+                label="Статус обработки",
                 interactive=False,
                 value="Ожидание файла..."
             )
@@ -157,21 +232,38 @@ def create_interface():
             if file_bytes is None:
                 gr.Warning("Пожалуйста, загрузите файл")
                 return None, None, None, "Ожидание файла..."
+                
             try:
-                # Convert bytes to BytesIO for pandas to read
+                # Create BytesIO object and debug print its content
                 file_obj = io.BytesIO(file_bytes)
+                logger.info("File loaded into BytesIO successfully")
+                
+                # Process file with progress updates
+                progress_status = "Начинаем обработку файла..."
+                yield None, None, None, progress_status
+                
                 df = process_file(file_obj)
                 
                 if df.empty:
                     return None, None, None, "Нет данных для обработки"
-                    
+                
+                progress_status = f"Создание визуализаций..."
+                yield None, None, None, progress_status
+                
                 fig_sentiment, fig_events = create_visualizations(df)
-                return df, fig_sentiment, fig_events, "Обработка завершена успешно!"
+                
+                return (
+                    df, 
+                    fig_sentiment, 
+                    fig_events, 
+                    f"Обработка завершена успешно! Обработано {len(df)} строк"
+                )
                 
             except Exception as e:
-                logger.error(f"Analysis error: {e}")
-                gr.Error(f"Ошибка анализа: {str(e)}")
-                return None, None, None, f"Ошибка: {str(e)}"
+                error_msg = f"Ошибка анализа: {str(e)}"
+                logger.error(error_msg)
+                gr.Error(error_msg)
+                return None, None, None, error_msg
             
         analyze_btn.click(
             fn=analyze,
@@ -181,42 +273,6 @@ def create_interface():
         
     return app
 
-def process_file(file_obj):
-    try:
-        # Read Excel directly from BytesIO object
-        df = pd.read_excel(file_obj, sheet_name='Публикации')
-        detector = EventDetector()
-        processed_rows = []
-        total = len(df)
-        
-        for idx, row in df.iterrows():
-            text = str(row.get('Выдержки из текста', ''))
-            entity = str(row.get('Объект', ''))
-            
-            event_type, event_summary = detector.detect_events(text, entity)
-            sentiment = detector.analyze_sentiment(text)
-            
-            processed_rows.append({
-                'Объект': entity,
-                'Заголовок': str(row.get('Заголовок', '')),
-                'Sentiment': sentiment,
-                'Event_Type': event_type,
-                'Event_Summary': event_summary,
-                'Текст': text
-            })
-            
-            if idx % 10 == 0:
-                logger.info(f"Processed {idx}/{total} rows")
-        
-        result_df = pd.DataFrame(processed_rows)
-        logger.info("File processing complete!")
-        return result_df
-        
-    except Exception as e:
-        logger.error(f"File processing error: {e}")
-        gr.Error(f"Error processing file: {str(e)}")
-        return pd.DataFrame(columns=['Объект', 'Заголовок', 'Sentiment', 'Event_Type', 'Event_Summary', 'Текст'])
-
 if __name__ == "__main__":
     app = create_interface()
     app.launch(share=True)