Update app.py

app.py

@@ -40,18 +40,35 @@ def clean_numeric(val):
     except ValueError:
         return None
 
-
-# ======================
-# PREDICTION FUNCTION
-# ======================
-def predict_malware_csv(file):
+def load_and_clean_csv(file):
     df = pd.read_csv(
         file.name,
-        sep=';',
+        sep=None,
         engine='python',
         dtype=str
     )
 
+    # clean header
+    df.columns = (
+        df.columns
+          .astype(str)
+          .str.strip()
+          .str.replace(r'\s+', '', regex=True)
+    )
+
+    # clean numeric values
+    for col in df.columns:
+        if col not in ['Label', 'file_name']:
+            df[col] = df[col].apply(clean_numeric)
+
+    return df
+
+# ======================
+# PREDICTION FUNCTION
+# ======================
+def predict_malware_csv(file):
+    df = load_and_clean_csv(file)
+
     # Check missing features
     missing = set(feature_names) - set(df.columns)
     if missing:
@@ -107,7 +124,6 @@ app = gr.Interface(
     title="Stacking-based Malware Detection",
     description=(
         "Upload a CSV file.\n\n"
-        f"Required features: {', '.join(feature_names)}"
     )
 )