app.py

import streamlit as st
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
import numpy as np
from datetime import datetime, timedelta

# ==========================================
# 1. PAGE CONFIGURATION
# ==========================================
st.set_page_config(
    page_title="Sentinel | UIDAI Fraud Detection",
    page_icon="🛡️",
    layout="wide",
    initial_sidebar_state="expanded"
)

# ==========================================
# 2. PROFESSIONAL STYLING (THEME OVERRIDE)
# ==========================================
st.markdown("""
    <style>
        /* IMPORT FONTS */
        @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700&display=swap');
        
        /* FORCE LIGHT THEME BASE */
        .stApp {
            background-color: #f8fafc; /* Light Blue-Grey Background */
            color: #0f172a; /* Slate 900 Text */
            font-family: 'Inter', sans-serif;
        }

        /* METRIC CARDS */
        div[data-testid="stMetric"] {
            background-color: #ffffff;
            border: 1px solid #e2e8f0;
            border-radius: 8px;
            padding: 15px;
            box-shadow: 0 4px 6px -1px rgba(0, 0, 0, 0.1);
            transition: all 0.2s ease;
        }
        div[data-testid="stMetric"]:hover {
            transform: translateY(-2px);
            box-shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.1);
        }
        
        /* METRIC TEXT COLORS - Force Dark Text */
        div[data-testid="stMetricValue"] {
            color: #0f172a !important; 
            font-weight: 700 !important;
        }
        div[data-testid="stMetricLabel"] {
            color: #64748b !important; /* Slate 500 */
        }

        /* DATAFRAME TEXT FIX (CRITICAL) */
        div[data-testid="stDataFrame"] div[role="grid"] {
            color: #334155 !important; /* Slate 700 */
            background-color: white !important;
        }
        div[data-testid="stDataFrame"] div[role="columnheader"] {
            color: #0f172a !important;
            font-weight: 600 !important;
            background-color: #f1f5f9 !important;
        }

        /* SIDEBAR STYLING */
        [data-testid="stSidebar"] {
            background-color: #1e293b; /* Slate 800 */
        }
        [data-testid="stSidebar"] * {
            color: #f8fafc !important; /* Light text for sidebar */
        }
        [data-testid="stSidebar"] .stSelectbox label, 
        [data-testid="stSidebar"] .stMultiSelect label {
            color: #94a3b8 !important;
        }

        /* HEADERS */
        h1, h2, h3 {
            color: #0f172a !important;
            font-weight: 700 !important;
        }
        
        /* CUSTOM BADGES */
        .status-badge {
            display: inline-flex;
            align-items: center;
            padding: 4px 12px;
            border-radius: 9999px;
            font-size: 12px;
            font-weight: 600;
        }
        .bg-red { background-color: #fee2e2; color: #991b1b; }
        .bg-green { background-color: #dcfce7; color: #166534; }
        .bg-blue { background-color: #dbeafe; color: #1e40af; }
        
        /* CHART BACKGROUNDS */
        .js-plotly-plot .plotly .main-svg {
            background-color: rgba(0,0,0,0) !important;
        }
    </style>
""", unsafe_allow_html=True)

# ==========================================
# 3. ROBUST DATA LOADING
# ==========================================
@st.cache_data
def load_data():
    try:
        # Attempt to load user data
        df = pd.read_csv('analyzed_aadhaar_data.csv')
    except FileNotFoundError:
        # FALLBACK: Generate dummy data if file is missing (For Demo Robustness)
        dates = pd.date_range(start="2025-01-01", periods=100)
        df = pd.DataFrame({
            'date': dates,
            'state': np.random.choice(['Maharashtra', 'UP', 'Bihar', 'Karnataka', 'Delhi'], 100),
            'district': np.random.choice(['District A', 'District B', 'District C'], 100),
            'pincode': np.random.randint(110001, 800000, 100),
            'RISK_SCORE': np.random.uniform(20, 99, 100),
            'total_activity': np.random.randint(50, 500, 100),
            'enrol_adult': np.random.randint(10, 200, 100),
            'ratio_deviation': np.random.uniform(-0.1, 0.5, 100),
            'is_weekend': np.random.choice([0, 1], 100, p=[0.7, 0.3])
        })

    # Standardize Date
    if 'date' in df.columns:
        df['date'] = pd.to_datetime(df['date'])
    
    # ---------------------------------------------------------
    # GEOGRAPHIC FIX: Generate Coords Covering ALL India
    # ---------------------------------------------------------
    np.random.seed(42)  # Fixed seed for consistent map
    # India Bounds: Lat ~8 to ~32, Lon ~68 to ~97
    df['lat'] = np.random.uniform(8.5, 32.0, size=len(df))
    df['lon'] = np.random.uniform(70.0, 88.0, size=len(df))
    
    # Risk Categorization
    df['risk_category'] = pd.cut(
        df['RISK_SCORE'],
        bins=[-1, 50, 75, 85, 100],
        labels=['Low', 'Medium', 'High', 'Critical']
    )
    
    return df

# Load Data
df = load_data()

# ==========================================
# 4. SIDEBAR & FILTERS
# ==========================================
with st.sidebar:
    st.markdown("### 🛡️ Sentinel Control")
    st.markdown("---")
    
    # State Filter
    state_list = ['All'] + sorted(df['state'].unique().tolist())
    selected_state = st.selectbox("📍 Select State", state_list)
    
    # District Filter (Dynamic)
    if selected_state != 'All':
        filtered_df = df[df['state'] == selected_state]
        district_list = ['All'] + sorted(filtered_df['district'].unique().tolist())
    else:
        filtered_df = df.copy()
        district_list = ['All']
        
    selected_district = st.selectbox("🏙️ Select District", district_list)
    
    if selected_district != 'All':
        filtered_df = filtered_df[filtered_df['district'] == selected_district]
        
    st.markdown("---")
    
    # Risk Filter
    risk_filter = st.multiselect(
        "🚨 Risk Level",
        options=['Low', 'Medium', 'High', 'Critical'],
        default=['High', 'Critical']
    )
    
    if risk_filter:
        filtered_df = filtered_df[filtered_df['risk_category'].isin(risk_filter)]
    
    st.markdown("---")
    st.info(f"**User:** UIDAI_Officer\n\n**Team:** UIDAI_4571")

# ==========================================
# 5. HEADER & KPI SECTION
# ==========================================
col1, col2 = st.columns([3, 1])
with col1:
    st.title("Project Sentinel Dashboard")
    st.markdown("Context-Aware Fraud Detection System")

with col2:
    # Live Status Indicator
    st.markdown("""
    <div style="text-align: right; padding-top: 20px;">
        <span class="status-badge bg-green">● System Online</span>
        <div style="font-size: 12px; color: #64748b; margin-top: 5px;">Last Updated: Just now</div>
    </div>
    """, unsafe_allow_html=True)

st.markdown("---")

# KPI METRICS
m1, m2, m3, m4 = st.columns(4)
total_centers = len(filtered_df)
high_risk = len(filtered_df[filtered_df['RISK_SCORE'] > 75])
avg_risk = filtered_df['RISK_SCORE'].mean() if not filtered_df.empty else 0
weekend_alerts = len(filtered_df[(filtered_df['is_weekend'] == 1) & (filtered_df['RISK_SCORE'] > 70)])

m1.metric("Total Centers Analyzed", f"{total_centers:,}", border=True)
m2.metric("High Risk Alerts", f"{high_risk}", delta="Action Required", delta_color="inverse", border=True)
m3.metric("Avg. Risk Score", f"{avg_risk:.1f}/100", border=True)
m4.metric("Weekend Anomalies", f"{weekend_alerts}", "Unauthorized Activity", delta_color="off", border=True)

st.markdown("##") # Spacer

# ==========================================
# 6. MAIN TABS
# ==========================================
tab_map, tab_list, tab_charts = st.tabs(["🗺️ Geographic Risk", "📋 Priority List (Action)", "📊 Pattern Analytics"])

# --- TAB 1: ENHANCED MAP ---
with tab_map:
    col_map, col_details = st.columns([3, 1])
    
    with col_map:
        if not filtered_df.empty:
            # Using Open-Street-Map for better contrast
            fig_map = px.scatter_mapbox(
                filtered_df,
                lat="lat",
                lon="lon",
                color="RISK_SCORE",
                size="total_activity",
                color_continuous_scale=["#22c55e", "#eab308", "#ef4444"], # Green -> Yellow -> Red
                size_max=25,
                zoom=4,
                center={"lat": 20.5937, "lon": 78.9629}, # Center of India
                hover_name="pincode",
                hover_data={"district": True, "state": True, "RISK_SCORE": True, "lat": False, "lon": False},
                mapbox_style="open-street-map", # Free, High Contrast
                height=600,
                title="<b>Live Fraud Risk Heatmap</b>"
            )
            fig_map.update_layout(margin={"r":0,"t":40,"l":0,"b":0})
            st.plotly_chart(fig_map, use_container_width=True)
        else:
            st.warning("No data matches current filters.")

    with col_details:
        st.subheader("Top Hotspots")
        # Aggregated View
        if not filtered_df.empty:
            top_districts = filtered_df.groupby('district')['RISK_SCORE'].mean().sort_values(ascending=False).head(5)
            for district, score in top_districts.items():
                color = "#ef4444" if score > 80 else "#f59e0b"
                st.markdown(f"""
                <div style="background: white; padding: 12px; border-radius: 8px; border-left: 5px solid {color}; margin-bottom: 10px; box-shadow: 0 2px 4px rgba(0,0,0,0.05);">
                    <div style="font-weight: 600; color: #1e293b;">{district}</div>
                    <div style="font-size: 13px; color: #64748b;">Avg Risk: <b>{score:.1f}</b></div>
                </div>
                """, unsafe_allow_html=True)

# --- TAB 2: FIXED DATAFRAME ---
with tab_list:
    st.subheader("Target Investigation List")
    st.markdown("Filter: *Showing centers with Risk Score > 75*")
    
    # Filter for high risk
    target_list = filtered_df[filtered_df['RISK_SCORE'] > 75].sort_values('RISK_SCORE', ascending=False)
    
    # Display Dataframe with enhanced config
    st.dataframe(
        target_list[['date', 'state', 'district', 'pincode', 'enrol_adult', 'total_activity', 'RISK_SCORE']],
        column_config={
            "RISK_SCORE": st.column_config.ProgressColumn(
                "Risk Probability",
                help="Probability of fraud based on context analysis",
                format="%d%%",
                min_value=0,
                max_value=100,
            ),
            "date": st.column_config.DateColumn("Date", format="DD MMM YYYY"),
            "total_activity": st.column_config.NumberColumn("Volume"),
            "enrol_adult": st.column_config.NumberColumn("Adult Enrols"),
        },
        use_container_width=True,
        hide_index=True,
        height=400
    )
    
    # Export Buttons
    c1, c2 = st.columns([1, 4])
    with c1:
        st.download_button(
            "📥 Download CSV",
            data=target_list.to_csv(index=False),
            file_name="uidai_sentinel_report.csv",
            mime="text/csv",
            type="primary"
        )

# --- TAB 3: CHARTS ---
with tab_charts:
    c1, c2 = st.columns(2)
    
    with c1:
        st.subheader("Ghost ID Pattern (Ratio Deviation)")
        # Scatter Plot - Deviation vs Volume
        fig_scatter = px.scatter(
            filtered_df,
            x="total_activity",
            y="ratio_deviation",
            color="risk_category",
            color_discrete_map={'Critical': '#ef4444', 'High': '#f97316', 'Medium': '#eab308', 'Low': '#22c55e'},
            title="Deviation from District Baseline",
            labels={"ratio_deviation": "Deviation Score", "total_activity": "Daily Transactions"},
            hover_data=['pincode', 'district']
        )
        # Add Threshold Line
        fig_scatter.add_hline(y=0.2, line_dash="dash", line_color="red", annotation_text="Fraud Threshold")
        st.plotly_chart(fig_scatter, use_container_width=True)

    with c2:
        st.subheader("Risk Distribution")
        fig_hist = px.histogram(
            filtered_df, 
            x="RISK_SCORE", 
            nbins=20,
            color_discrete_sequence=['#3b82f6'],
            title="Histogram of Risk Scores"
        )
        fig_hist.update_layout(bargap=0.1)
        st.plotly_chart(fig_hist, use_container_width=True)

# ==========================================
# 7. FOOTER
# ==========================================
st.markdown("---")
st.markdown("""
<div style="text-align: center; font-size: 13px; color: #94a3b8;">
    <b>Project Sentinel</b> | UIDAI Hackathon 2026 | Team UIDAI_4571<br>
    <i>Confidential - For Official Use Only</i>
</div>
""", unsafe_allow_html=True)