Update app.py

app.py

@@ -2,6 +2,7 @@ import joblib
 import pandas as pd
 import gradio as gr
 import numpy as np
+import re
 
 # ======================
 # LOAD MODEL
@@ -12,11 +13,38 @@ base_models = artifact["base_models"]      # list of (name, model)
 meta_model = artifact["meta_model"]
 feature_names = artifact["features"]
 
+# ======================
+# CLEAN FUNCTION (same as training)
+# ======================
+def clean_numeric(val):
+    if pd.isna(val):
+        return None
+
+    val = str(val).strip()
+    val = re.sub(r'\s+', '', val)
+
+    # scientific notation
+    if re.match(r'^-?\d+(\.\d+)?[eE][+-]?\d+$', val):
+        return float(val)
+
+    # remove thousand separators
+    if val.count('.') > 1:
+        val = val.replace('.', '')
+
+    # comma decimal -> dot
+    if ',' in val and '.' not in val:
+        val = val.replace(',', '.')
+
+    try:
+        return float(val)
+    except ValueError:
+        return None
+
+
 # ======================
 # PREDICTION FUNCTION
 # ======================
 def predict_malware_csv(file):
-    # Read CSV
     df = pd.read_csv(file.name)
 
     # Check missing features
@@ -24,7 +52,15 @@ def predict_malware_csv(file):
     if missing:
         return f"❌ Missing features: {list(missing)}", None
 
-    X = df[feature_names]
+    # Keep only needed features
+    X = df[feature_names].copy()
+
+    # 🔥 CLEAN NUMERIC FEATURES
+    for col in feature_names:
+        X[col] = X[col].apply(clean_numeric)
+
+    # Optional: fill NaN if needed
+    # X = X.fillna(0)
 
     # Level-1 predictions
     meta_inputs = []
@@ -65,9 +101,8 @@ app = gr.Interface(
     outputs=outputs,
     title="Stacking-based Malware Detection",
     description=(
-        "Upload a CSV file containing malware features.\n\n"
-        "Model: ExtraTrees + RandomForest + LightGBM + LogisticRegression → XGBoost\n"
-        f"Required features: {', '.join(feature_names)}"
+        "Upload a CSV file.\n\n"
+
     )
 )