Update app.py

app.py

@@ -9,7 +9,16 @@ import json
 import os
 from datetime import datetime, timedelta
 
+# ==========================================
+# 0. MAPBOX CONFIGURATION (FIX 1)
+# ==========================================
+# Required for stable map rendering. Replace with your own free token if needed.
+# This sample token is a public default often used for demos.
+px.set_mapbox_access_token("pk.eyJ1IjoiZGVtbyIsImEiOiJja2E0Z2QwZjgwMnZ5MnFwdWg1dm80YmQ1In0.SAMPLE")
+
+# ==========================================
 # 1. PAGE CONFIGURATION
+# ==========================================
 st.set_page_config(
     page_title="S.A.T.A.R.K AI | UIDAI Fraud Detection",
     page_icon="🛡️",
@@ -17,13 +26,14 @@ st.set_page_config(
     initial_sidebar_state="expanded"
 )
 
+# ==========================================
 # 2. ROBUST CSS STYLING (Dark Mode Proof)
+# ==========================================
 st.markdown("""
     <style>
         @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;500;600;700;800&display=swap');
         
         /* --- 1. MAIN CONTENT AREA (Light Theme Enforced) --- */
-        /* Target only the main content, NOT the sidebar */
         .stApp > header { background-color: transparent !important; }
         
         div[data-testid="stAppViewContainer"] {
@@ -51,17 +61,16 @@ st.markdown("""
             border-right: 1px solid #334155;
         }
 
-        /* NUCLEAR OPTION: Force ALL text in sidebar to be White */
+        /* Force ALL text in sidebar to be White */
         section[data-testid="stSidebar"] * {
-            color: #f8fafc !important; /* White Text */
+            color: #f8fafc !important; 
         }
 
-        /* EXCEPTION: Inputs inside Sidebar (Selectbox, DateInput) */
-        /* These usually have white backgrounds, so we need Dark Text inside them */
+        /* EXCEPTION: Inputs inside Sidebar */
         section[data-testid="stSidebar"] input, 
         section[data-testid="stSidebar"] textarea, 
         section[data-testid="stSidebar"] div[data-baseweb="select"] div {
-            color: #0f172a !important; /* Dark Text for Inputs */
+            color: #0f172a !important; 
             -webkit-text-fill-color: #0f172a !important;
         }
         
@@ -98,7 +107,6 @@ st.markdown("""
             margin-bottom: 12px; 
             box-shadow: 0 2px 4px rgba(0,0,0,0.05); 
         }
-        /* Since Hotspot Cards are in Main Area, text inherits Dark, which is good. */
         
         /* Status Badges */
         .status-badge { 
@@ -111,82 +119,93 @@ st.markdown("""
     </style>
 """, unsafe_allow_html=True)
 
-# 3. DYNAMIC GEOCODING ENGINE WITH PERSISTENT JSON
+# ==========================================
+# 3. GEOCODING ENGINE (MASTER DB)
+# ==========================================
 @st.cache_data(show_spinner=False)
-def fetch_coordinates_batch(unique_locations):
-    json_file = 'district_coords.json'
-    coords_map = {}
+def get_seed_data():
+    # Pre-loaded cache of critical pincodes from user data + major cities
+    # Ensures instant loading for known high-priority targets
+    return {
+        "783348": [26.13, 90.12], "785601": [26.51, 93.97], "783384": [26.48, 90.56],
+        "782124": [26.33, 92.75], "793150": [25.55, 92.38], "494444": [18.80, 80.82],
+        "201301": [28.58, 77.31], "424306": [20.90, 74.77], "793119": [25.56, 91.29],
+        "784115": [26.44, 92.00], "781123": [26.15, 91.22], "784505": [26.77, 92.70],
+        "493770": [20.71, 81.55], "576101": [13.34, 74.75], "854338": [26.29, 86.82],
+        "201305": [28.39, 77.65], "723146": [23.25, 86.50], "110001": [28.61, 77.21],
+        "560001": [12.97, 77.59], "400001": [18.93, 72.83], "700001": [22.57, 88.36],
+        "600001": [13.08, 80.27], "500001": [17.38, 78.48]
+    }
+
+@st.cache_data(show_spinner=False)
+def fetch_coordinates(unique_pincodes):
+    json_file = "india_pincode_master.json"
+    coords_map = get_seed_data() # Initialize with Seed Data
 
+    # 1. Load Master DB if exists
     if os.path.exists(json_file):
         try:
-            with open(json_file, 'r') as f:
-                loaded_data = json.load(f)
-                for k, v in loaded_data.items():
-                    if "|" in k:
-                        d, s = k.split("|")
-                        coords_map[(d, s)] = tuple(v)
-        except json.JSONDecodeError:
+            with open(json_file, "r") as f:
+                saved_map = json.load(f)
+                coords_map.update(saved_map) # Merge saved with seed
+        except:
             pass
 
-    prefills = {
-        ('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)
-    }
-    for k, v in prefills.items():
-        if k not in coords_map:
-            coords_map[k] = v
+    # 2. Identify Missing Pincodes
+    # Convert to string to ensure consistent keys
+    missing = [str(p) for p in unique_pincodes if str(p) not in coords_map]
 
-    missing_locs = [loc for loc in unique_locations if loc not in coords_map]
-    if not missing_locs:
+    if not missing:
         return coords_map
 
-    progress_text = "📡 New locations found. Fetching coordinates..."
-    my_bar = st.progress(0, text=progress_text)
-    headers = {'User-Agent': 'StarkDashboard/1.0 (Government Research Project)'}
-    updated = False
+    # 3. Fetch Missing from API
+    headers = {"User-Agent": "UIDAI-Sentinel-Dashboard/2.0 (Govt Hackathon)"}
+    
+    # Placeholder for progress
+    progress_placeholder = st.empty()
+    my_bar = progress_placeholder.progress(0, text=f"📡 Updating Master DB: 0/{len(missing)} pincodes...")
 
-    for i, (district, state) in enumerate(missing_locs):
+    updated = False
+    for i, pin in enumerate(missing):
         try:
-            my_bar.progress((i + 1) / len(missing_locs), text=f"📍 Locating: {district}, {state}")
-            query = f"{district}, {state}, India"
+            # Query format: "110001 India"
+            q = f"{pin} 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']))
+            params = {"q": q, "format": "json", "limit": 1}
+            
+            r = requests.get(url, params=params, headers=headers, timeout=5)
+
+            if r.status_code == 200 and r.json():
+                data = r.json()[0]
+                lat = float(data["lat"])
+                lon = float(data["lon"])
+                coords_map[str(pin)] = [lat, lon]
                 updated = True
-            time.sleep(1.1)
+            else:
+                # Fallback: India Centroid if not found
+                coords_map[str(pin)] = [20.5937, 78.9629]
+            
+            # Respect API Rate Limits (Important for Free Tier)
+            time.sleep(1.0)
+            
         except Exception:
-            continue
+            coords_map[str(pin)] = [20.5937, 78.9629]
+
+        my_bar.progress((i + 1) / len(missing), text=f"📡 Updating Master DB: {i+1}/{len(missing)}...")
 
     my_bar.empty()
+    progress_placeholder.empty()
 
+    # 4. Save Updates to Master DB
     if updated:
-        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)
+        with open(json_file, "w") as f:
+            json.dump(coords_map, f)
 
     return coords_map
 
+# ==========================================
 # 4. MAIN DATA LOADER
+# ==========================================
 @st.cache_data(ttl=300)
 def load_data():
     try:
@@ -200,6 +219,11 @@ def load_data():
     df['district'] = df['district'].astype(str).str.strip()
     df['state'] = df['state'].astype(str).str.strip()
 
+    # FIX 3: PINCODE TYPE NORMALIZATION
+    # Ensures all pincodes are clean strings, removing junk/letters
+    df["pincode"] = df["pincode"].astype(str).str.extract(r"(\d{6})")[0]
+    
+    # Normalize State Names
     state_mapping = {
         'Jammu & Kashmir': 'Jammu and Kashmir',
         'J&K': 'Jammu and Kashmir',
@@ -217,31 +241,37 @@ def load_data():
     }
     df['state'] = df['state'].replace(state_mapping)
 
-    unique_locs = list(df[['district', 'state']].drop_duplicates().itertuples(index=False, name=None))
-    coords_db = fetch_coordinates_batch(unique_locs)
-    state_centers = {
-        'Delhi': (28.7041, 77.1025), 'Maharashtra': (19.7515, 75.7139), 'Karnataka': (15.3173, 75.7139)
-    }
+    # --- GEOCODING INTEGRATION START ---
+    unique_pincodes = df["pincode"].dropna().unique().tolist()
+    coords_db = fetch_coordinates(unique_pincodes)
 
     def get_lat_lon(row):
-        key = (row['district'], row['state'])
-        if key in coords_db:
-            lat, lon = coords_db[key]
-            return pd.Series({'lat': lat + np.random.normal(0, 0.002), 'lon': lon + np.random.normal(0, 0.002)})
-        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), 'lon': center[1] + np.random.uniform(-0.5, 0.5)})
+        pin = str(row["pincode"])
+        # Default to India Centroid if somehow missing
+        lat, lon = coords_db.get(pin, [20.5937, 78.9629])
+        
+        # FIX 2: SCALED JITTER (90m separation)
+        # Prevents overlap without distorting district view
+        jitter_lat = np.random.uniform(-0.0008, 0.0008)
+        jitter_lon = np.random.uniform(-0.0008, 0.0008)
+        
+        return pd.Series({'lat': lat + jitter_lat, 'lon': lon + jitter_lon})
 
     coords = df.apply(get_lat_lon, axis=1)
     df['lat'] = coords['lat']
     df['lon'] = coords['lon']
+    # --- GEOCODING INTEGRATION END ---
+
+    # Categorize Risk
     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.A.T.A.R.K AI...'):
     df = load_data()
 
+# ==========================================
 # 5. SIDEBAR & FILTERS
+# ==========================================
 with st.sidebar:
     st.markdown("### 🛡️ S.A.T.A.R.K AI Control")
     st.markdown("---")
@@ -273,7 +303,9 @@ 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')}")
 
+# ==========================================
 # 6. HEADER & METRICS
+# ==========================================
 col1, col2 = st.columns([3, 1])
 with col1:
     st.title("🛡️ S.A.T.A.R.K AI Dashboard")
@@ -299,7 +331,9 @@ else:
 
 st.markdown("##")
 
+# ==========================================
 # 7. TABS
+# ==========================================
 tab_map, tab_list, tab_charts, tab_insights = st.tabs(["🗺️ Geographic Risk", "📋 Priority List", "📊 Patterns", "🔍 AI Insights"])
 
 with tab_map:
@@ -307,6 +341,7 @@ with tab_map:
     with c_map:
         if not filtered_df.empty:
             zoom_lvl = 10 if sel_dist != 'All' else (6 if sel_state != 'All' else 3.8)
+            # Use Lat/Lon for plotting
             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()},