Update app.py

app.py

@@ -23,7 +23,7 @@ warnings.filterwarnings("ignore")
 MODEL_NAME = "microsoft/codebert-base"
 MAX_LENGTH = 512
 DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-DATASET_PATH = "ijadataset2-1.zip"  # Update this path if needed
+DATASET_PATH = "archive (1).zip"  # Update this path if needed
 
 # Initialize models with caching
 @st.cache_resource
@@ -40,13 +40,13 @@ def load_models():
 def load_dataset():
     try:
         # Extract dataset if needed
-        if not os.path.exists("Diverse_100K_Dataset"):
+        if not os.path.exists("Subject_CloneTypes_Directories"):
             with zipfile.ZipFile(DATASET_PATH, 'r') as zip_ref:
                 zip_ref.extractall(".")
         
         # Load sample pairs (modify this based on your dataset structure)
         clone_pairs = []
-        base_path = "Diverse_100K_Dataset/Subject_CloneTypes_Directories"
+        base_path = "Subject_CloneTypes_Directories"
         
         # Example: Load one pair from each clone type
         for clone_type in ["Clone_Type1", "Clone_Type2", "Clone_Type3 - ST"]: