Update app.py

app.py

@@ -3,6 +3,8 @@ import pandas as pd
 import plotly.express as px
 import plotly.graph_objects as go
 import numpy as np
+import requests
+import time
 from datetime import datetime, timedelta
 
 # 1. PAGE CONFIGURATION
@@ -60,10 +62,79 @@ st.markdown("""
     </style>
 """, unsafe_allow_html=True)
 
-# 3. ENHANCED DATA LOADING
+# 3. DYNAMIC GEOCODING ENGINE
+@st.cache_data(show_spinner=False)
+def fetch_coordinates_batch(unique_locations):
+    """
+    Fetches coordinates from OpenStreetMap Nominatim API.
+    unique_locations: List of tuples (District, State)
+    Returns: Dictionary {(District, State): (lat, lon)}
+    """
+    # 1. Pre-filled Cache (For speed & redundancy)
+    coords_map = {
+        ('Gautam Buddha Nagar', 'Uttar Pradesh'): (28.39, 77.65),
+        ('West Jaintia Hills', 'Meghalaya'): (25.55, 92.38),
+        ('West Khasi Hills', 'Meghalaya'): (25.56, 91.29),
+        ('Bijapur', 'Chhattisgarh'): (18.80, 80.82),
+        ('Dhule', 'Maharashtra'): (20.90, 74.77),
+        ('Dhamtari', 'Chhattisgarh'): (20.71, 81.55),
+        ('Udupi', 'Karnataka'): (13.34, 74.75),
+        ('Supaul', 'Bihar'): (26.29, 86.82),
+        ('Puruliya', 'West Bengal'): (23.25, 86.50),
+        ('Mumbai', 'Maharashtra'): (19.0760, 72.8777),
+        ('Pune', 'Maharashtra'): (18.5204, 73.8567),
+        ('Bangalore', 'Karnataka'): (12.9716, 77.5946),
+        ('Bengaluru', 'Karnataka'): (12.9716, 77.5946),
+        ('Chennai', 'Tamil Nadu'): (13.0827, 80.2707),
+        ('Hyderabad', 'Telangana'): (17.3850, 78.4867),
+        ('Kolkata', 'West Bengal'): (22.5726, 88.3639),
+        ('Delhi', 'Delhi'): (28.7041, 77.1025),
+        ('Shimla', 'Himachal Pradesh'): (31.1048, 77.1734)
+    }
+    
+    # 2. Identify missing locations
+    missing_locs = [loc for loc in unique_locations if loc not in coords_map]
+    
+    if not missing_locs:
+        return coords_map
+
+    # 3. Dynamic Fetching for missing
+    progress_text = "📡 Connecting to Satellite Geocoding API..."
+    my_bar = st.progress(0, text=progress_text)
+    
+    headers = {'User-Agent': 'StarkDashboard/1.0 (Government Research Project)'}
+    
+    for i, (district, state) in enumerate(missing_locs):
+        try:
+            # Update Progress
+            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)
+            
+            if response.status_code == 200 and response.json():
+                data = response.json()[0]
+                coords_map[(district, state)] = (float(data['lat']), float(data['lon']))
+            else:
+                # Fallback if API fails: Keep existing State Centers logic inside main loop later
+                pass
+                
+            # Respect Rate Limiting (1 request per second)
+            time.sleep(1.1) 
+            
+        except Exception as e:
+            continue
+            
+    my_bar.empty()
+    return coords_map
+
+# 4. MAIN DATA LOADER
 @st.cache_data(ttl=300)
 def load_data():
-    # Strictly load data from CSV - NO RANDOM GENERATION
     try:
         df = pd.read_csv('analyzed_aadhaar_data.csv')
     except FileNotFoundError:
@@ -72,87 +143,17 @@ def load_data():
 
     if 'date' in df.columns: df['date'] = pd.to_datetime(df['date'])
     
-    # --- PRECISE DISTRICT GEOLOCATION DATABASE ---
-    # Manually curated high-precision coordinates for known districts in the dataset
-    district_coords = {
-        # High Priority Districts from Snippet
-        'Gautam Buddha Nagar': (28.39, 77.65), # Uttar Pradesh
-        'West Jaintia Hills': (25.55, 92.38),  # Meghalaya
-        'West Khasi Hills': (25.56, 91.29),    # Meghalaya
-        'Bijapur': (18.80, 80.82),             # Chhattisgarh
-        'Dhule': (20.90, 74.77),               # Maharashtra
-        'Dhamtari': (20.71, 81.55),            # Chhattisgarh
-        'Udupi': (13.34, 74.75),               # Karnataka
-        'Supaul': (26.29, 86.82),              # Bihar
-        'Puruliya': (23.25, 86.50),            # West Bengal
-        
-        # Major Metros & Hubs (Commonly appear)
-        'Mumbai': (19.0760, 72.8777),
-        'Pune': (18.5204, 73.8567),
-        'Nagpur': (21.1458, 79.0882),
-        'Thane': (19.2183, 72.9781),
-        'Nashik': (19.9975, 73.7898),
-        'Lucknow': (26.8467, 80.9462),
-        'Kanpur': (26.4499, 80.3319),
-        'Ghaziabad': (28.6692, 77.4538),
-        'Agra': (27.1767, 78.0081),
-        'Varanasi': (25.3176, 82.9739),
-        'Patna': (25.5941, 85.1376),
-        'Gaya': (24.7914, 85.0002),
-        'Muzaffarpur': (26.1197, 85.3910),
-        'Bangalore': (12.9716, 77.5946), 'Bengaluru': (12.9716, 77.5946),
-        'Mysore': (12.2958, 76.6394),
-        'Hubli': (15.3647, 75.1240),
-        'Mangalore': (12.9141, 74.8560),
-        'Belgaum': (15.8497, 74.4977),
-        'Chennai': (13.0827, 80.2707),
-        'Coimbatore': (11.0168, 76.9558),
-        'Madurai': (9.9252, 78.1198),
-        'Kolkata': (22.5726, 88.3639),
-        'Howrah': (22.5958, 88.2636),
-        'Darjeeling': (27.0410, 88.2663),
-        'Ahmedabad': (23.0225, 72.5714),
-        'Surat': (21.1702, 72.8311),
-        'Vadodara': (22.3072, 73.1812),
-        'Rajkot': (22.3039, 70.8022),
-        'Jaipur': (26.9124, 75.7873),
-        'Jodhpur': (26.2389, 73.0243),
-        'Udaipur': (24.5854, 73.7125),
-        'Hyderabad': (17.3850, 78.4867),
-        'Warangal': (17.9689, 79.5941),
-        'Bhopal': (23.2599, 77.4126),
-        'Indore': (22.7196, 75.8577),
-        'Raipur': (21.2514, 81.6296),
-        'Bilaspur': (22.0797, 82.1409),
-        'Guwahati': (26.1445, 91.7362),
-        'Visakhapatnam': (17.6868, 83.2185),
-        'Vijayawada': (16.5062, 80.6480),
-        'Thiruvananthapuram': (8.5241, 76.9366),
-        'Kochi': (9.9312, 76.2673),
-        'Kozhikode': (11.2588, 75.7804),
-        'Shimla': (31.1048, 77.1734),
-        'Dehradun': (30.3165, 78.0322),
-        'Ranchi': (23.3441, 85.3096),
-        'Bhubaneswar': (20.2961, 85.8245),
-        'Chandigarh': (30.7333, 76.7794),
-        'Gandhinagar': (23.2156, 72.6369),
-        'Panaji': (15.4909, 73.8278),
-        'Srinagar': (34.0837, 74.7973),
-        'Jammu': (32.7266, 74.8570),
-        'Imphal': (24.8170, 93.9368),
-        'Shillong': (25.5788, 91.8933),
-        'Aizawl': (23.7271, 92.7176),
-        'Kohima': (25.6751, 94.1086),
-        'Gangtok': (27.3389, 88.6065),
-        'Agartala': (23.8315, 91.2868),
-        'Port Blair': (11.6234, 92.7265),
-        'Kavaratti': (10.5667, 72.6417),
-        'Puducherry': (11.9416, 79.8083),
-        'Silvassa': (20.2763, 73.0083),
-        'Daman': (20.3974, 72.8328)
-    }
-
-    # Fallback State Centers (Only used if District is NOT in above list)
+    # Clean Data
+    df['district'] = df['district'].astype(str).str.strip()
+    df['state'] = df['state'].astype(str).str.strip()
+    
+    # Get Unique Locations
+    unique_locs = list(df[['district', 'state']].drop_duplicates().itertuples(index=False, name=None))
+    
+    # Fetch Coordinates (Cached)
+    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),
         'Arunachal Pradesh': (28.2180, 94.7278), 'Assam': (26.2006, 92.9376), 'Bihar': (25.0961, 85.3131),
@@ -168,35 +169,34 @@ def load_data():
         'Uttarakhand': (30.0668, 79.0193), 'West Bengal': (22.9868, 87.8550)
     }
     
-    def get_coords(row):
-        district = str(row.get('district', '')).strip()
-        state = row.get('state', '')
+    def get_lat_lon(row):
+        key = (row['district'], row['state'])
         
-        # 1. Try Exact District Match
-        if district in district_coords:
-            base_lat, base_lon = district_coords[district]
-            # Tiny jitter just to separate overlapping dots from same district
-            return pd.Series({'lat': base_lat + np.random.normal(0, 0.005), 'lon': base_lon + np.random.normal(0, 0.005)})
+        # 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 with Randomized Jitter (Only if district unknown)
-        center = state_centers.get(state, (20.5937, 78.9629))
-        np.random.seed(hash(state + district) % 2**32) 
+        # 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']
     
-    coords = df.apply(get_coords, axis=1)
-    df['lat'], df['lon'] = coords['lat'], coords['lon']
-    
-    # Recalculate Risk Category based on real data
     df['risk_category'] = pd.cut(df['RISK_SCORE'], bins=[-1, 50, 75, 85, 100], labels=['Low', 'Medium', 'High', 'Critical'])
     return df
 
-with st.spinner('Loading S.T.A.R.K AI System...'): 
+with st.spinner('Initializing S.T.A.R.K AI & Geocoding...'):
     df = load_data()
 
-# 4. SIDEBAR & FILTERS
+# 5. SIDEBAR & FILTERS
 with st.sidebar:
     st.markdown("### 🛡️ S.T.A.R.K AI Control")
     st.markdown("---")
@@ -225,7 +225,7 @@ with st.sidebar:
     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')}")
 
-# 5. HEADER & METRICS
+# 6. HEADER & METRICS
 col1, col2 = st.columns([3, 1])
 with col1:
     st.title("🛡️ S.T.A.R.K AI Dashboard")
@@ -248,16 +248,24 @@ else:
 
 st.markdown("##")
 
-# 6. TABS
+# 7. TABS
 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
+
             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=3.8 if sel_state == 'All' else 5.5,
-                center={"lat": 22.0, "lon": 80.0}, hover_name="district", hover_data={"state":True, "pincode":True}, mapbox_style="carto-positron", height=650, title="<b>Live Fraud Risk Heatmap</b>")
+                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.warning("No data found to map.")