fix

app.py

@@ -22,8 +22,8 @@ def parse_args(args):
     parser = argparse.ArgumentParser(description="CBD Classification")
     parser.add_argument('--data_dir', type=str, default="./")
     parser.add_argument('--excel_file', type=str, default="dumc_1223_case3_duct_correct.csv")
-    parser.add_argument('--modality', type=str, default="tabular")
-    parser.add_argument('--phase', type=str, default="combine")
+    parser.add_argument('--mode', type=str, default="train")
+    parser.add_argument('--scale', type=bool, default=True)
     parser.add_argument('--smote', type=bool, default=True)
     parser.add_argument('--model_name_or_path', type=str, default="./ensemble_1", choices=[])
     parser.add_argument('--top_p', type=float, default=None)
@@ -33,12 +33,12 @@ def parse_args(args):
     return parser.parse_args(args)
 
 
-def load_data_and_prepare(data_dir, excel_file, modality, phase, smote):
+def load_data_and_prepare(data_dir, excel_file, mode, scale, smote):
     # Load train, validation, and test data
-    train_df,val_df = load_data(data_dir, excel_file, 'train', modality, phase, smote)
+    train_df,val_df = load_data(data_dir, excel_file, mode, scale, smote)
     
-    train_df.drop(columns=['patient_id'],inplace = True)
-    val_df.drop(columns=['patient_id'],inplace = True)
+    train_df.drop(columns=['patient_id','target'],inplace = True)
+    val_df.drop(columns=['patient_id','target'],inplace = True)
     
     train = pd.concat([train_df,val_df],axis=0)
     
@@ -47,15 +47,6 @@ def load_data_and_prepare(data_dir, excel_file, modality, phase, smote):
 
 # Inference function
 def classify(tabular_data):
-    """
-    Perform classification on tabular data using a PyCaret pre-trained model.
-
-    Args:
-        tabular_data (list or array-like): Input data points (e.g., a single row of features)
-
-    Returns:
-        str: Classification result and probabilities
-    """
     try:
         # Ensure tabular_data is a 2D list and extract the first row
         if isinstance(tabular_data, list) and isinstance(tabular_data[0], list):