Code Editor for app.py

import streamlit as st
import pandas as pd
import plotly.express as px
from sklearn.preprocessing import LabelEncoder

# Configure page
st.set_page_config(
    page_title="SecPen Cybersecurity Threat Classifier",
    page_icon="🛡️",
    layout="wide"
)

# Custom CSS
st.markdown("""
    <style>
    .main {
        padding: 2rem;
    }
    .stTitle {
        color: #ffffff;
        font-size: 2.5rem !important;
        padding-bottom: 2rem;
    }
    .upload-section {
        background-color: #1E2130;
        padding: 2rem;
        border-radius: 10px;
        margin-bottom: 2rem;
    }
    .results-section {
        background-color: #1E2130;
        padding: 2rem;
        border-radius: 10px;
    }
    </style>
""", unsafe_allow_html=True)

# Title and description
st.title("🛡️ SecPen Cybersecurity Threat Classifier")
st.markdown("Upload a CSV of network flows to predict threat type and analyze patterns.")

# File upload section
with st.container():
    st.markdown('<div class="upload-section">', unsafe_allow_html=True)
    uploaded_file = st.file_uploader(
        "Upload CSV file", 
        type=['csv'],
        help="Upload a CSV file containing network flow features"
    )
    st.markdown('</div>', unsafe_allow_html=True)

if uploaded_file is not None:
    try:
        # Load and process data
        df = pd.read_csv(uploaded_file)
        
        # Display results in tabs
        with st.container():
            st.markdown('<div class="results-section">', unsafe_allow_html=True)
            tabs = st.tabs(["📊 Data Overview", "📈 Visualizations", "🔍 Detailed Analysis"])
            
            with tabs[0]:
                col1, col2 = st.columns(2)
                with col1:
                    st.subheader("Dataset Summary")
                    st.dataframe(df.describe(), use_container_width=True)
                with col2:
                    st.subheader("Sample Data")
                    st.dataframe(df.head(), use_container_width=True)

            with tabs[1]:
                if len(df.select_dtypes(include=['float64', 'int64']).columns) > 0:
                    numeric_col = st.selectbox(
                        "Select feature for distribution plot",
                        df.select_dtypes(include=['float64', 'int64']).columns
                    )
                    fig = px.histogram(df, x=numeric_col, title=f'Distribution of {numeric_col}')
                    st.plotly_chart(fig, use_container_width=True)

            with tabs[2]:
                st.subheader("Correlation Analysis")
                numeric_df = df.select_dtypes(include=['float64', 'int64'])
                if not numeric_df.empty:
                    corr = numeric_df.corr()
                    fig = px.imshow(
                        corr,
                        title="Feature Correlation Matrix",
                        color_continuous_scale='RdBu'
                    )
                    st.plotly_chart(fig, use_container_width=True)
            
            st.markdown('</div>', unsafe_allow_html=True)

    except Exception as e:
        st.error(f"Error processing file: {str(e)}")
else:
    # Show placeholder when no file is uploaded
    st.info("Please upload a CSV file containing the network flow features used for prediction.")