Update app.py

app.py

@@ -62,12 +62,12 @@ def process_ner(text: str, pipeline) -> dict:
                 "entity": entity_type,
                 "start": token['start'],
                 "end": token['end'],
-                "score": token['score'],
+                "scores": [token['score']],
                 "tokens": [token['word']]
             }
         else:
             current_entity['end'] = token['end']
-            current_entity['score'] = max(current_entity['score'], token['score'])
+            current_entity['scores'].append(token['score'])
             current_entity['tokens'].append(token['word'])
 
     if current_entity is not None:
@@ -129,9 +129,9 @@ def generate_wordcloud(entities: List[Dict], color_map: Dict[str, str], file_pat
     for entity in entities:
         cleaned_entity = re.sub(r'^\W+', '', ' '.join(entity['tokens']))
         entity_texts.append(cleaned_entity)
-        entity_scores.append(np.mean([token['score'] for token in entity['tokens']]))
+        entity_scores.append(np.mean(entity['scores']))
         entity_types.append(entity['entity'])
-        print(f"{cleaned_entity} ({entity['entity']}): {np.mean([token['score'] for token in entity['tokens']])}")
+        print(f"{cleaned_entity} ({entity['entity']}): {np.mean(entity['scores'])}")
 
     word_freq = {text: score for text, score in zip(entity_texts, entity_scores)}