update

demo/binary_classifier_demo.py

@@ -101,30 +101,89 @@ def run_binary_classifier(text, show_analysis=False):
         
         # Basic statistics
         analysis_md += "### Основная статистика\n"
-        analysis_md += f"- Всего токенов: {text_analysis['basic_stats']['total_tokens']}\n"
-        analysis_md += f"- Всего слов: {text_analysis['basic_stats']['total_words']}\n"
-        analysis_md += f"- Уникальных слов: {text_analysis['basic_stats']['unique_words']}\n"
-        analysis_md += f"- Стоп-слов: {text_analysis['basic_stats']['stop_words']}\n"
-        analysis_md += f"- Средняя длина слова: {text_analysis['basic_stats']['avg_word_length']:.2f} символов\n\n"
+        for key, value in text_analysis.get('basic_stats', {}).items():
+            if isinstance(value, float):
+                analysis_md += f"- {key}: {value:.2f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
+        analysis_md += "\n"
+        
+        # Morphological analysis
+        analysis_md += "### Морфологический анализ\n"
+        morph_analysis = text_analysis.get('morphological_analysis', {})
+        for key, value in morph_analysis.items():
+            if key == 'pos_distribution':
+                analysis_md += "- Распределение частей речи:\n"
+                for pos, count in value.items():
+                    analysis_md += f"  - {pos}: {count}\n"
+            elif isinstance(value, float):
+                analysis_md += f"- {key}: {value:.3f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
+        analysis_md += "\n"
+        
+        # Syntactic analysis
+        analysis_md += "### Синтаксический анализ\n"
+        synt_analysis = text_analysis.get('syntactic_analysis', {})
+        for key, value in synt_analysis.items():
+            if key == 'dependencies':
+                analysis_md += "- Зависимости:\n"
+                for dep, count in value.items():
+                    analysis_md += f"  - {dep}: {count}\n"
+            elif isinstance(value, float):
+                analysis_md += f"- {key}: {value:.3f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
+        analysis_md += "\n"
+        
+        # Named entities
+        analysis_md += "### Именованные сущности\n"
+        entities = text_analysis.get('named_entities', {})
+        for key, value in entities.items():
+            if key == 'entity_types':
+                analysis_md += "- Типы сущностей:\n"
+                for ent, count in value.items():
+                    analysis_md += f"  - {ent}: {count}\n"
+            elif isinstance(value, float):
+                analysis_md += f"- {key}: {value:.3f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
+        analysis_md += "\n"
         
         # Lexical diversity
         analysis_md += "### Лексическое разнообразие\n"
-        analysis_md += f"- TTR (Type-Token Ratio): {text_analysis['lexical_diversity']['ttr']:.3f}\n"
-        analysis_md += f"- MTLD (упрощенный): {text_analysis['lexical_diversity']['mtld']:.2f}\n\n"
+        for key, value in text_analysis.get('lexical_diversity', {}).items():
+            if isinstance(value, float):
+                analysis_md += f"- {key}: {value:.3f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
+        analysis_md += "\n"
         
         # Text structure
         analysis_md += "### Структура текста\n"
-        analysis_md += f"- Количество предложений: {text_analysis['text_structure']['sentence_count']}\n"
-        analysis_md += f"- Средняя длина предложения: {text_analysis['text_structure']['avg_sentence_length']:.2f} токенов\n\n"
+        for key, value in text_analysis.get('text_structure', {}).items():
+            if isinstance(value, float):
+                analysis_md += f"- {key}: {value:.2f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
+        analysis_md += "\n"
         
         # Readability
         analysis_md += "### Читабельность\n"
-        analysis_md += f"- Flesch-Kincaid score: {text_analysis['readability']['flesh_kincaid_score']:.2f}\n"
-        analysis_md += f"- Процент длинных слов: {text_analysis['readability']['long_words_percent']:.2f}%\n\n"
+        for key, value in text_analysis.get('readability', {}).items():
+            if isinstance(value, float):
+                analysis_md += f"- {key}: {value:.2f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
+        analysis_md += "\n"
         
         # Semantic coherence
         analysis_md += "### Семантическая связность\n"
-        analysis_md += f"- Средняя связность между предложениями: {text_analysis['semantic_coherence']['avg_coherence_score']:.3f}\n"
+        for key, value in text_analysis.get('semantic_coherence', {}).items():
+            if isinstance(value, float):
+                analysis_md += f"- {key}: {value:.3f}\n"
+            else:
+                analysis_md += f"- {key}: {value}\n"
     
     return gr.Markdown(result_md), gr.Markdown(analysis_md) if analysis_md else None, text