Update app.py

app.py

@@ -139,6 +139,8 @@ st.markdown("""
 """, unsafe_allow_html=True)
 
 # 3. DYNAMIC GEOCODING ENGINE WITH PERSISTENT JSON
+
+
 @st.cache_data(show_spinner=False)
 def fetch_coordinates_batch(unique_locations):
     """
@@ -161,7 +163,7 @@ def fetch_coordinates_batch(unique_locations):
                         d, s = k.split("|")
                         coords_map[(d, s)] = tuple(v)
         except json.JSONDecodeError:
-            pass # File corrupted, start fresh
+            pass  # File corrupted, start fresh
 
     # 2. Add Hardcoded Pre-fills (High Priority Redundancy)
     # These override if missing, but usually JSON is preferred source if present
@@ -188,70 +190,77 @@ def fetch_coordinates_batch(unique_locations):
     for k, v in prefills.items():
         if k not in coords_map:
             coords_map[k] = v
-            
+
     # 3. Identify missing locations
     missing_locs = [loc for loc in unique_locations if loc not in coords_map]
-    
+
     if not missing_locs:
         return coords_map
 
     # 4. Dynamic Fetching for missing
     progress_text = "📡 New locations found. Fetching coordinates..."
     my_bar = st.progress(0, text=progress_text)
-    
-    headers = {'User-Agent': 'StarkDashboard/1.0 (Government Research Project)'}
+
+    headers = {
+        'User-Agent': 'StarkDashboard/1.0 (Government Research Project)'}
     updated = False
-    
+
     for i, (district, state) in enumerate(missing_locs):
         try:
             # Update Progress
-            my_bar.progress((i + 1) / len(missing_locs), text=f"📍 Locating: {district}, {state}")
-            
+            my_bar.progress((i + 1) / len(missing_locs),
+                            text=f"📍 Locating: {district}, {state}")
+
             # API Call
             query = f"{district}, {state}, India"
             url = "https://nominatim.openstreetmap.org/search"
             params = {'q': query, 'format': 'json', 'limit': 1}
-            
-            response = requests.get(url, params=params, headers=headers, timeout=5)
-            
+
+            response = requests.get(
+                url, params=params, headers=headers, timeout=5)
+
             if response.status_code == 200 and response.json():
                 data = response.json()[0]
-                coords_map[(district, state)] = (float(data['lat']), float(data['lon']))
+                coords_map[(district, state)] = (
+                    float(data['lat']), float(data['lon']))
                 updated = True
             else:
-                pass # Fail silently, will fall back to state center logic later
-                
+                pass  # Fail silently, will fall back to state center logic later
+
             # Respect Rate Limiting (1 request per second)
-            time.sleep(1.1) 
-            
+            time.sleep(1.1)
+
         except Exception as e:
             continue
-            
+
     my_bar.empty()
-    
+
     # 5. Save back to JSON if new data fetched
     if updated:
         # Convert keys to string "District|State" for JSON compatibility
         save_data = {f"{k[0]}|{k[1]}": v for k, v in coords_map.items()}
         with open(json_file, 'w') as f:
             json.dump(save_data, f)
-            
+
     return coords_map
 
 # 4. MAIN DATA LOADER
+
+
 @st.cache_data(ttl=300)
 def load_data():
     try:
         df = pd.read_csv('analyzed_aadhaar_data.csv')
     except FileNotFoundError:
-        return pd.DataFrame() # Return empty to trigger external error check
+        return pd.DataFrame()  # Return empty to trigger external error check
+
+    if 'date' in df.columns:
+        df['date'] = pd.to_datetime(df['date'])
 
-    if 'date' in df.columns: df['date'] = pd.to_datetime(df['date'])
-    
     # Clean Data
     df['district'] = df['district'].astype(str).str.strip()
     df['state'] = df['state'].astype(str).str.strip()
-    
+
     # --- FIX DUPLICATE STATES ---
     # Standardize State Names to remove variations (e.g., J&K)
     state_mapping = {
@@ -263,13 +272,14 @@ def load_data():
         'Pondicherry': 'Puducherry'
     }
     df['state'] = df['state'].replace(state_mapping)
-    
+
     # Get Unique Locations
-    unique_locs = list(df[['district', 'state']].drop_duplicates().itertuples(index=False, name=None))
-    
+    unique_locs = list(
+        df[['district', 'state']].drop_duplicates().itertuples(index=False, name=None))
+
     # Fetch Coordinates (Cached + Persistent JSON)
     coords_db = fetch_coordinates_batch(unique_locs)
-    
+
     # Fallback Centers (State Capitals)
     state_centers = {
         'Andaman and Nicobar Islands': (11.7401, 92.6586), 'Andhra Pradesh': (15.9129, 79.7400),
@@ -285,31 +295,33 @@ def load_data():
         'Telangana': (18.1124, 79.0193), 'Tripura': (23.9408, 91.9882), 'Uttar Pradesh': (26.8467, 80.9462),
         'Uttarakhand': (30.0668, 79.0193), 'West Bengal': (22.9868, 87.8550)
     }
-    
+
     def get_lat_lon(row):
         key = (row['district'], row['state'])
-        
+
         # 1. Check Exact Match from API/Cache
         if key in coords_db:
             lat, lon = coords_db[key]
             # Tiny jitter to separate stacked points
             return pd.Series({'lat': lat + np.random.normal(0, 0.002), 'lon': lon + np.random.normal(0, 0.002)})
-            
+
         # 2. Fallback to State Center
         center = state_centers.get(row['state'], (20.5937, 78.9629))
         np.random.seed(hash(key) % 2**32)
         return pd.Series({
-            'lat': center[0] + np.random.uniform(-0.5, 0.5), 
+            'lat': center[0] + np.random.uniform(-0.5, 0.5),
             'lon': center[1] + np.random.uniform(-0.5, 0.5)
         })
 
     coords = df.apply(get_lat_lon, axis=1)
     df['lat'] = coords['lat']
     df['lon'] = coords['lon']
-    
-    df['risk_category'] = pd.cut(df['RISK_SCORE'], bins=[-1, 50, 75, 85, 100], labels=['Low', 'Medium', 'High', 'Critical'])
+
+    df['risk_category'] = pd.cut(
+        df['RISK_SCORE'], bins=[-1, 50, 75, 85, 100], labels=['Low', 'Medium', 'High', 'Critical'])
     return df
 
+
 with st.spinner('Initializing S.T.A.R.K AI & Geocoding...'):
     df = load_data()
 
@@ -317,30 +329,40 @@ with st.spinner('Initializing S.T.A.R.K AI & Geocoding...'):
 with st.sidebar:
     st.markdown("### 🛡️ S.T.A.R.K AI Control")
     st.markdown("---")
-    
+
     if not df.empty:
         if 'date' in df.columns:
             min_d, max_d = df['date'].min().date(), df['date'].max().date()
-            dr = st.date_input("Date Range", value=(min_d, max_d), min_value=min_d, max_value=max_d)
-            if len(dr) == 2: df = df[(df['date'].dt.date >= dr[0]) & (df['date'].dt.date <= dr[1])]
-        
+            dr = st.date_input("Date Range", value=(
+                min_d, max_d), min_value=min_d, max_value=max_d)
+            if len(dr) == 2:
+                df = df[(df['date'].dt.date >= dr[0]) &
+                        (df['date'].dt.date <= dr[1])]
+
         state_list = ['All'] + sorted(df['state'].unique().tolist())
         sel_state = st.selectbox("State", state_list)
-        filtered_df = df[df['state'] == sel_state] if sel_state != 'All' else df.copy()
-        
+        filtered_df = df[df['state'] ==
+                         sel_state] if sel_state != 'All' else df.copy()
+
         dist_list = ['All'] + sorted(filtered_df['district'].unique().tolist())
         sel_dist = st.selectbox("District", dist_list)
-        if sel_dist != 'All': filtered_df = filtered_df[filtered_df['district'] == sel_dist]
-        
+        if sel_dist != 'All':
+            filtered_df = filtered_df[filtered_df['district'] == sel_dist]
+
         st.markdown("---")
-        risk_filter = st.multiselect("Risk Level", ['Low', 'Medium', 'High', 'Critical'], default=['High', 'Critical'])
-        if risk_filter: filtered_df = filtered_df[filtered_df['risk_category'].isin(risk_filter)]
+        risk_filter = st.multiselect(
+            "Risk Level", ['Low', 'Medium', 'High', 'Critical'], default=['High', 'Critical'])
+        if risk_filter:
+            filtered_df = filtered_df[filtered_df['risk_category'].isin(
+                risk_filter)]
     else:
         filtered_df = pd.DataFrame()
-        
+
     st.markdown("---")
-    st.link_button("📓 Open Analysis Notebook", "https://colab.research.google.com/drive/1YAQ4nfxltvG_cts3fmGc_zi2JQc4oPOT?usp=sharing", use_container_width=True)
-    st.info(f"**User:** UIDAI_Officer\n\n**Team:** UIDAI_4571\n\n**Update:** {datetime.now().strftime('%H:%M:%S')}")
+    st.link_button("📓 Open Analysis Notebook",
+                   "https://colab.research.google.com/drive/1YAQ4nfxltvG_cts3fmGc_zi2JQc4oPOT?usp=sharing", use_container_width=True)
+    st.info(
+        f"**User:** UIDAI_Officer\n\n**Team:** UIDAI_4571\n\n**Update:** {datetime.now().strftime('%H:%M:%S')}")
 
 # 6. HEADER & METRICS
 col1, col2 = st.columns([3, 1])
@@ -348,62 +370,81 @@ with col1:
     st.title("🛡️ S.T.A.R.K AI Dashboard")
     st.markdown("**Context-Aware Fraud Detection & Prevention System**")
 with col2:
-    st.markdown(f"""<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: 8px;">{datetime.now().strftime('%d %b %Y')}</div></div>""", unsafe_allow_html=True)
+    st.markdown(
+        f"""<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: 8px;">{datetime.now().strftime('%d %b %Y')}</div></div>""", unsafe_allow_html=True)
 
 st.markdown("---")
 
 if not filtered_df.empty:
     m1, m2, m3, m4, m5 = st.columns(5)
-    total, high, crit = len(filtered_df), len(filtered_df[filtered_df['RISK_SCORE'] > 75]), len(filtered_df[filtered_df['RISK_SCORE'] > 85])
+    total, high, crit = len(filtered_df), len(filtered_df[filtered_df['RISK_SCORE'] > 75]), len(
+        filtered_df[filtered_df['RISK_SCORE'] > 85])
     m1.metric("Total Centers", f"{total:,}", border=True)
-    m2.metric("High Risk", f"{high}", delta="Review", delta_color="inverse", border=True)
-    m3.metric("Critical", f"{crit}", delta="Urgent", delta_color="inverse", border=True)
-    m4.metric("Avg Risk", f"{filtered_df['RISK_SCORE'].mean():.1f}/100" if not filtered_df.empty else "0", border=True)
-    m5.metric("Weekend Spikes", f"{len(filtered_df[(filtered_df['is_weekend'] == 1) & (filtered_df['RISK_SCORE'] > 70)])}", delta="Suspicious", delta_color="off", border=True)
+    m2.metric("High Risk", f"{high}", delta="Review",
+              delta_color="inverse", border=True)
+    m3.metric("Critical", f"{crit}", delta="Urgent",
+              delta_color="inverse", border=True)
+    m4.metric(
+        "Avg Risk", f"{filtered_df['RISK_SCORE'].mean():.1f}/100" if not filtered_df.empty else "0", border=True)
+    m5.metric("Weekend Spikes", f"{len(filtered_df[(filtered_df['is_weekend'] == 1) & (filtered_df['RISK_SCORE'] > 70)])}",
+              delta="Suspicious", delta_color="off", border=True)
 else:
-    st.error("❌ Critical Error: 'analyzed_aadhaar_data.csv' not found. Please upload the data file.")
+    st.error(
+        "❌ Critical Error: 'analyzed_aadhaar_data.csv' not found. Please upload the data file.")
 
 st.markdown("##")
 
 # 7. TABS
-tab_map, tab_list, tab_charts, tab_insights = st.tabs(["🗺️ Geographic Risk", "📋 Priority List", "📊 Patterns", "🔍 AI Insights"])
+tab_map, tab_list, tab_charts, tab_insights = st.tabs(
+    ["🗺️ Geographic Risk", "📋 Priority List", "📊 Patterns", "🔍 AI Insights"])
 
 with tab_map:
     c_map, c_det = st.columns([3, 1])
     with c_map:
         if not filtered_df.empty:
             # Dynamic Zoom based on selection
-            if sel_dist != 'All': zoom_lvl = 10
-            elif sel_state != 'All': zoom_lvl = 6
-            else: zoom_lvl = 3.8
+            if sel_dist != 'All':
+                zoom_lvl = 10
+            elif sel_state != 'All':
+                zoom_lvl = 6
+            else:
+                zoom_lvl = 3.8
 
             fig = px.scatter_mapbox(filtered_df, lat="lat", lon="lon", color="RISK_SCORE", size="total_activity",
-                color_continuous_scale=["#22c55e", "#fbbf24", "#f97316", "#ef4444"], size_max=25, zoom=zoom_lvl,
-                center=None if sel_state == 'All' else {"lat": filtered_df['lat'].mean(), "lon": filtered_df['lon'].mean()},
-                hover_name="district", hover_data={"state":True, "pincode":True, "lat":False, "lon":False}, 
-                mapbox_style="carto-positron", height=650, title="<b>Live Fraud Risk Heatmap</b>")
-            
-            fig.update_layout(margin={"r":0,"t":40,"l":0,"b":0})
+                                    color_continuous_scale=["#22c55e", "#fbbf24", "#f97316", "#ef4444"], size_max=25, zoom=zoom_lvl,
+                                    center=None if sel_state == 'All' else {
+                                        "lat": filtered_df['lat'].mean(), "lon": filtered_df['lon'].mean()},
+                                    hover_name="district", hover_data={"state": True, "pincode": True, "lat": False, "lon": False},
+                                    mapbox_style="carto-positron", height=650, title="<b>Live Fraud Risk Heatmap</b>")
+
+            fig.update_layout(margin={"r": 0, "t": 40, "l": 0, "b": 0})
             st.plotly_chart(fig, use_container_width=True)
-        else: st.info("Waiting for data...")
-    
+        else:
+            st.info("Waiting for data...")
+
     with c_det:
         st.subheader("🔥 Top Hotspots")
         if not filtered_df.empty:
-            top = filtered_df.groupby('district').agg({'RISK_SCORE': 'mean', 'total_activity': 'sum'}).sort_values('RISK_SCORE', ascending=False).head(5)
+            top = filtered_df.groupby('district').agg(
+                {'RISK_SCORE': 'mean', 'total_activity': 'sum'}).sort_values('RISK_SCORE', ascending=False).head(5)
             for i, (d, r) in enumerate(top.iterrows(), 1):
-                clr, bdg = ("#ef4444", "CRITICAL") if r['RISK_SCORE'] > 85 else ("#f97316", "HIGH")
-                st.markdown(f"""<div class="hotspot-card" style="border-left-color: {clr};"><b>#{i} {d}</b><br><span style="font-size:12px;color:#64748b">Risk: <b style="color:{clr}">{r['RISK_SCORE']:.1f}</b> | Act: {int(r['total_activity'])}</span></div>""", unsafe_allow_html=True)
+                clr, bdg = ("#ef4444", "CRITICAL") if r['RISK_SCORE'] > 85 else (
+                    "#f97316", "HIGH")
+                st.markdown(
+                    f"""<div class="hotspot-card" style="border-left-color: {clr};"><b>#{i} {d}</b><br><span style="font-size:12px;color:#64748b">Risk: <b style="color:{clr}">{r['RISK_SCORE']:.1f}</b> | Act: {int(r['total_activity'])}</span></div>""", unsafe_allow_html=True)
 
 with tab_list:
     st.subheader("🎯 Priority Investigation")
     if not filtered_df.empty:
-        targets = filtered_df[filtered_df['RISK_SCORE'] > 75].sort_values('RISK_SCORE', ascending=False)
+        targets = filtered_df[filtered_df['RISK_SCORE'] >
+                              75].sort_values('RISK_SCORE', ascending=False)
         csv = targets.to_csv(index=False).encode('utf-8')
-        st.download_button("📥 Export CSV", data=csv, file_name="stark_priority.csv", mime="text/csv", type="primary")
-        st.dataframe(targets[['date', 'state', 'district', 'pincode', 'enrol_adult', 'total_activity', 'RISK_SCORE']], 
-            column_config={"RISK_SCORE": st.column_config.ProgressColumn("Risk", format="%.1f%%", min_value=0, max_value=100)}, use_container_width=True, hide_index=True)
-    else: st.info("Waiting for data...")
+        st.download_button("📥 Export CSV", data=csv,
+                           file_name="stark_priority.csv", mime="text/csv", type="primary")
+        st.dataframe(targets[['date', 'state', 'district', 'pincode', 'enrol_adult', 'total_activity', 'RISK_SCORE']],
+                     column_config={"RISK_SCORE": st.column_config.ProgressColumn("Risk", format="%.1f%%", min_value=0, max_value=100)}, use_container_width=True, hide_index=True)
+    else:
+        st.info("Waiting for data...")
 
 with tab_charts:
     c1, c2 = st.columns(2)
@@ -411,32 +452,40 @@ with tab_charts:
         st.markdown("**Ghost ID Detection**")
         if not filtered_df.empty:
             fig = px.scatter(filtered_df, x="total_activity", y="ratio_deviation", color="risk_category", size="RISK_SCORE",
-                color_discrete_map={'Critical': '#ef4444', 'High': '#f97316', 'Medium': '#eab308', 'Low': '#22c55e'}, height=350)
+                             color_discrete_map={'Critical': '#ef4444', 'High': '#f97316', 'Medium': '#eab308', 'Low': '#22c55e'}, height=350)
             fig.add_hline(y=0.2, line_dash="dash", line_color="red")
             st.plotly_chart(fig, use_container_width=True)
     with c2:
         st.markdown("**Weekend Activity Analysis**")
         if not filtered_df.empty:
-            wk_counts = filtered_df.groupby('is_weekend')['total_activity'].sum().reset_index()
-            wk_counts['Type'] = wk_counts['is_weekend'].map({0: 'Weekday', 1: 'Weekend'})
-            fig = px.bar(wk_counts, x='Type', y='total_activity', color='Type', color_discrete_map={'Weekday': '#3b82f6', 'Weekend': '#ef4444'}, height=350)
+            wk_counts = filtered_df.groupby(
+                'is_weekend')['total_activity'].sum().reset_index()
+            wk_counts['Type'] = wk_counts['is_weekend'].map(
+                {0: 'Weekday', 1: 'Weekend'})
+            fig = px.bar(wk_counts, x='Type', y='total_activity', color='Type', color_discrete_map={
+                         'Weekday': '#3b82f6', 'Weekend': '#ef4444'}, height=350)
             st.plotly_chart(fig, use_container_width=True)
 
 with tab_insights:
     st.subheader("🔍 AI Detective Insights")
     if not filtered_df.empty:
         anom = filtered_df[filtered_df['ratio_deviation'] > 0.4]
-        st.info(f"🤖 **AI Analysis:** Detected {len(anom)} centers with statistically significant enrollment deviations (> 2σ from mean).")
-        
+        st.info(
+            f"🤖 **AI Analysis:** Detected {len(anom)} centers with statistically significant enrollment deviations (> 2σ from mean).")
+
         c_i1, c_i2 = st.columns(2)
         with c_i1:
             st.markdown("#### 🚨 Primary Risk Factors")
-            st.markdown("- **High Volume on Weekends:** 28% correlation with fraud")
-            st.markdown("- **Adult Enrollment Spikes:** 45% correlation with ghost IDs")
+            st.markdown(
+                "- **High Volume on Weekends:** 28% correlation with fraud")
+            st.markdown(
+                "- **Adult Enrollment Spikes:** 45% correlation with ghost IDs")
         with c_i2:
             st.markdown("#### 💡 Recommended Actions")
-            st.markdown(f"1. Immediate audit of {len(filtered_df[filtered_df['RISK_SCORE']>90])} centers with >90 Risk Score")
-            st.markdown("2. Deploy biometric re-verification for 'Rural A' cluster")
+            st.markdown(
+                f"1. Immediate audit of {len(filtered_df[filtered_df['RISK_SCORE']>90])} centers with >90 Risk Score")
+            st.markdown(
+                "2. Deploy biometric re-verification for 'Rural A' cluster")
 
 st.markdown("---")
-st.markdown("""<div style="text-align: center; font-size: 13px; color: #94a3b8;"><b>Project S.T.A.R.K AI</b> | UIDAI Hackathon 2026</div>""", unsafe_allow_html=True)
+st.markdown("""<div style="text-align: center; font-size: 13px; color: #94a3b8;"><b>Project S.T.A.R.K AI</b> | UIDAI Hackathon 2026</div>""", unsafe_allow_html=True)