Update app.py

app.py

@@ -6,6 +6,18 @@ import os
 import tempfile
 from transformers import AutoModel, AutoTokenizer
 import torch.nn as nn
+import os
+import zipfile
+
+# Check and unzip dataset if not already unzipped
+dataset_folder = "Subject_CloneTypes_Directories"
+
+if not os.path.exists(dataset_folder):
+    with zipfile.ZipFile("Subject_CloneTypes_Directories.zip", 'r') as zip_ref:
+        zip_ref.extractall(dataset_folder)
+    print("✅ Dataset extracted!")
+else:
+    print("✅ Dataset already extracted!")
 
 # Configuration
 MAX_FILE_SIZE = 5000