update

app.py

@@ -1,6 +1,33 @@
 import gradio as gr
 from ui.dataset_input import create_dataset_input, load_example_dataset
 from ui.analysis_screen import create_analysis_screen, process_analysis_request
+import nltk
+import os
+
+# Download necessary NLTK data packages
+def download_nltk_resources():
+    """Download required NLTK resources if not already downloaded"""
+    try:
+        # Create nltk_data directory in the user's home directory if it doesn't exist
+        nltk_data_path = os.path.expanduser("~/nltk_data")
+        os.makedirs(nltk_data_path, exist_ok=True)
+        
+        # Add this path to NLTK's data path
+        nltk.data.path.append(nltk_data_path)
+        
+        # Download required resources
+        resources = ['punkt', 'wordnet', 'stopwords']
+        for resource in resources:
+            try:
+                nltk.data.find(f'tokenizers/{resource}')
+                print(f"Resource {resource} already downloaded")
+            except LookupError:
+                print(f"Downloading {resource}...")
+                nltk.download(resource, quiet=True)
+        
+        print("NLTK resources check completed")
+    except Exception as e:
+        print(f"Error downloading NLTK resources: {e}")
 
 def create_app():
     """
@@ -81,5 +108,8 @@ def create_app():
     return app
 
 if __name__ == "__main__":
+    # Download required NLTK resources before launching the app
+    download_nltk_resources()
+    
     app = create_app()
     app.launch()