Update app.py

app.py

@@ -66,22 +66,45 @@ def load_simulated_data(samples=2000):
     return df
 
 def preprocess_csv(df):
-    df = df.replace([np.inf, -np.inf], np.nan).dropna()
-
-    # Normalize CIC-like labels
-    if "Label" in df.columns:
-        df["Label"] = df["Label"].apply(lambda x: 0 if x == "BENIGN" else 1)
+    # Clean data
+    df = df.replace([np.inf, -np.inf], np.nan)
+    df = df.dropna()
+
+    # Required CIC columns
+    required_cic_columns = [
+        "Flow Duration",
+        "Total Fwd Packets",
+        "Total Backward Packets",
+        "Packet Length Mean",
+        "Label"
+    ]
+
+    # Check if CSV is CIC-style
+    if not all(col in df.columns for col in required_cic_columns):
+        st.error("Uploaded CSV is not compatible with CIC-IDS feature format.")
+        st.stop()
+
+    # Convert labels
+    df["Label"] = df["Label"].apply(
+        lambda x: 0 if x == "BENIGN" else 1
+    )
 
+    # Rename CIC columns → internal standard names
     df = df.rename(columns={
+        "Packet Length Mean": "packet_size",
         "Flow Duration": "duration",
         "Total Fwd Packets": "src_bytes",
         "Total Backward Packets": "dst_bytes",
-        "Packet Length Mean": "packet_size",
         "Label": "label"
     })
 
-    required = ["packet_size", "duration", "src_bytes", "dst_bytes", "label"]
-    return df[required]
+    # Select only required columns
+    df = df[
+        ["packet_size", "duration", "src_bytes", "dst_bytes", "label"]
+    ]
+
+    return df
+
 
 # ============================
 # MODEL TRAINING