Upload 5 files

app.py

@@ -0,0 +1,63 @@
+import streamlit as st
+import pandas as pd
+import joblib
+import pickle
+import numpy as np
+
+# Load model and preprocessing artifacts
+model = joblib.load("ensemble_model.pkl")
+with open("features_to_drop.pkl", "rb") as f:
+    features_to_drop = pickle.load(f)
+
+# Column names from the raw 49-column dataset (before feature engineering)
+raw_columns = [
+    'srcip', 'sport', 'dstip', 'dsport', 'proto', 'state', 'dur', 'sbytes', 'dbytes',
+    'sttl', 'dttl', 'sloss', 'dloss', 'service', 'Sload', 'Dload', 'Spkts', 'Dpkts',
+    'swin', 'dwin', 'stcpb', 'dtcpb', 'smeansz', 'dmeansz', 'trans_depth', 'res_bdy_len',
+    'Sjit', 'Djit', 'Stime', 'Ltime', 'Sintpkt', 'Dintpkt', 'tcprtt', 'synack', 'ackdat',
+    'is_sm_ips_ports', 'ct_state_ttl', 'ct_flw_http_mthd', 'is_ftp_login', 'ct_ftp_cmd',
+    'ct_srv_src', 'ct_srv_dst', 'ct_dst_ltm', 'ct_src_ ltm', 'ct_src_dport_ltm',
+    'ct_dst_sport_ltm', 'ct_dst_src_ltm', 'attack_cat', 'Label'
+]
+
+# Function to preprocess a single input row
+def preprocess_input(row_values):
+    if len(row_values) != 49:
+        raise ValueError(f"❌ Expected 49 values, but got {len(row_values)}.")
+    
+    # Create DataFrame from input
+    input_df = pd.DataFrame([row_values], columns=raw_columns)
+
+    # Convert all columns to numeric
+    input_df = input_df.apply(pd.to_numeric, errors='coerce')
+
+    # Feature engineering
+    input_df['duration'] = input_df['Ltime'] - input_df['Stime']
+    input_df['byte_ratio'] = input_df['sbytes'] / (input_df['dbytes'] + 1)
+    input_df['pkt_ratio'] = input_df['Spkts'] / (input_df['Dpkts'] + 1)
+
+    # ✅ Fix: convert features_to_drop to list before adding with another list
+    input_df = input_df.drop(columns=list(features_to_drop) + ['attack_cat', 'Label'], errors='ignore')
+
+    return input_df
+
+# Streamlit UI
+st.title("🔍 Anomaly Detection In Network Traffic")
+st.markdown("Paste a **single row** of raw features from the dataset (49 values, tab-separated):")
+
+user_input = st.text_area("Input Row", height=150)
+
+if st.button("Predict"):
+    try:
+        # Parse the input
+        values = user_input.strip().split("\t")
+
+        # Preprocess the input row
+        processed_df = preprocess_input(values)
+
+        # Predict using the preprocessed data
+        prediction = model.predict(processed_df)[0]
+        st.success(f"✅ Predicted Attack Category: **{prediction}**")
+
+    except Exception as e:
+        st.error(f"❌ Error processing input: {e}")

category_encodings.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d3adee7f8b02aaa7a418edcf40a7323190ff3f341aca38190ae791846556fa
+size 388170

ensemble_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c52325a456b3c3aef4d23e7bdcebe47dbf9fb7a0c8c368df86a7e810b4f0be
+size 3542608

features_to_drop.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b1f550232da8f121220bebf07112cf4a933e24a3b219b0e31557f567903387
+size 314

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+pandas
+numpy
+xgboost==2.1.4
+joblib
+scikit-learn
+gdown