Delete app.py

app.py

@@ -1,207 +0,0 @@
-# ============================
-# AI-Based Network Intrusion Detection System (NIDS)
-# VOIS Internship – Final Project
-# ============================
-
-import streamlit as st
-import pandas as pd
-import numpy as np
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score, confusion_matrix
-import matplotlib.pyplot as plt
-import seaborn as sns
-from groq import Groq
-
-# ============================
-# PAGE CONFIG
-# ============================
-st.set_page_config(page_title="AI-Based NIDS", layout="wide")
-
-st.title("AI-Based Network Intrusion Detection System")
-st.markdown("""
-This project implements a **Random Forest–based Network Intrusion Detection System (NIDS)**.  
-It supports:
-- Simulated traffic
-- Real CIC-style CSV datasets
-- Live packet analysis
-- AI-based explanation using Groq
-""")
-
-# ============================
-# SESSION STATE INIT
-# ============================
-for key in ["model", "accuracy", "conf_matrix", "features", "X_test", "y_test"]:
-    if key not in st.session_state:
-        st.session_state[key] = None
-
-# ============================
-# SIDEBAR – SETTINGS
-# ============================
-st.sidebar.header("1. Settings")
-groq_api_key = st.sidebar.text_input("Groq API Key", type="password")
-
-st.sidebar.header("2. Data Mode")
-data_mode = st.sidebar.radio(
-    "Select Data Source",
-    ("Simulation Mode", "CSV Upload Mode")
-)
-
-# ============================
-# DATA LOADING FUNCTIONS
-# ============================
-def load_simulated_data(samples=2000):
-    np.random.seed(42)
-    df = pd.DataFrame({
-        "packet_size": np.random.randint(20, 1500, samples),
-        "duration": np.random.uniform(0, 60, samples),
-        "src_bytes": np.random.randint(0, 10000, samples),
-        "dst_bytes": np.random.randint(0, 10000, samples),
-        "failed_logins": np.random.randint(0, 5, samples),
-    })
-    df["label"] = np.where(
-        (df["failed_logins"] > 2) | (df["src_bytes"] > 8000),
-        1, 0
-    )
-    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)
-
-    df = df.rename(columns={
-        "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]
-
-# ============================
-# MODEL TRAINING
-# ============================
-def train_model(df):
-    X = df.drop("label", axis=1)
-    y = df["label"]
-
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.3, random_state=42
-    )
-
-    model = RandomForestClassifier(
-        n_estimators=100,
-        max_depth=12,
-        random_state=42
-    )
-    model.fit(X_train, y_train)
-
-    acc = accuracy_score(y_test, model.predict(X_test))
-    cm = confusion_matrix(y_test, model.predict(X_test))
-
-    return model, acc, cm, X_test, y_test
-
-def plot_confusion_matrix(cm):
-    fig, ax = plt.subplots()
-    sns.heatmap(
-        cm, annot=True, fmt="d",
-        xticklabels=["Normal", "Intrusion"],
-        yticklabels=["Normal", "Intrusion"],
-        cmap="Blues", ax=ax
-    )
-    ax.set_xlabel("Predicted")
-    ax.set_ylabel("Actual")
-    ax.set_title("Confusion Matrix")
-    return fig
-
-# ============================
-# TRAIN MODEL BUTTON
-# ============================
-st.sidebar.header("3. Model Training")
-
-uploaded_file = None
-if data_mode == "CSV Upload Mode":
-    uploaded_file = st.sidebar.file_uploader("Upload CSV Dataset", type=["csv"])
-
-if st.sidebar.button("Train Model"):
-    with st.spinner("Training model..."):
-        if data_mode == "Simulation Mode":
-            df = load_simulated_data()
-        else:
-            if uploaded_file is None:
-                st.sidebar.error("Please upload a CSV file first.")
-                st.stop()
-            raw_df = pd.read_csv(uploaded_file)
-            df = preprocess_csv(raw_df)
-
-        model, acc, cm, X_test, y_test = train_model(df)
-
-        st.session_state.model = model
-        st.session_state.accuracy = acc
-        st.session_state.conf_matrix = cm
-        st.session_state.X_test = X_test
-        st.session_state.y_test = y_test
-
-        st.sidebar.success(f"Training completed (Accuracy: {acc:.2%})")
-
-# ============================
-# DASHBOARD
-# ============================
-st.header("Threat Analysis Dashboard")
-
-if st.session_state.model is not None:
-    st.metric("Model Accuracy", f"{st.session_state.accuracy:.2%}")
-    st.pyplot(plot_confusion_matrix(st.session_state.conf_matrix))
-
-    st.markdown("---")
-    st.subheader("Live Packet Simulation")
-
-    if st.button("Capture Random Packet"):
-        idx = np.random.randint(0, len(st.session_state.X_test))
-        st.session_state.packet = st.session_state.X_test.iloc[idx]
-        st.session_state.actual = st.session_state.y_test.iloc[idx]
-
-    if "packet" in st.session_state:
-        packet = st.session_state.packet
-        pred = st.session_state.model.predict([packet])[0]
-
-        st.write("Packet Data")
-        st.dataframe(packet.to_frame().T)
-
-        if pred == 1:
-            st.error("Prediction: Intrusion Detected")
-        else:
-            st.success("Prediction: Normal Traffic")
-
-        st.caption(f"Ground Truth: {st.session_state.actual}")
-
-        st.markdown("---")
-        st.subheader("AI Explanation (Groq)")
-
-        if st.button("Generate Explanation"):
-            if not groq_api_key:
-                st.warning("Enter Groq API key first.")
-            else:
-                client = Groq(api_key=groq_api_key)
-                prompt = f"""
-                You are a cybersecurity analyst.
-                The following packet was classified as {'Intrusion' if pred == 1 else 'Normal'}.
-
-                Packet details:
-                {packet.to_string()}
-
-                Explain briefly in simple terms.
-                """
-                response = client.chat.completions.create(
-                    model="llama-3.3-70b-versatile",
-                    messages=[{"role": "user", "content": prompt}],
-                    temperature=0.6
-                )
-                st.info(response.choices[0].message.content)
-else:
-    st.info("Train the model to begin analysis.")