Update app.py

app.py

@@ -12,6 +12,7 @@ import spaces
 import torch
 import os
 import io
+import re
 import colorsys
 
 import numpy as np
@@ -116,7 +117,8 @@ def generate_wordcloud(entities: List[Dict], color_map: Dict[str, str]) -> np.nd
 
     for entity in entities:
         for token in entity['tokens']:
-            cleaned_token = token.lstrip('_')
+            # Remove any leading non-alphanumeric characters
+            cleaned_token = re.sub(r'^\W+', '', token)
             token_texts.append(cleaned_token)
             token_scores.append(entity['score'])
             token_types.append(entity['entity'])