Update app.py

app.py

@@ -163,34 +163,54 @@ def load_data():
         'West Bengal': (22.9868, 87.8550)
     }
 
-    def get_coords(row):
-        state = row.get('state', 'Delhi')
-        district = str(row.get('district', 'Unknown'))
-        
-        # 1. Get State Base Coordinates
-        base_lat, base_lon = state_centers.get(state, (20.5937, 78.9629)) # Default to India Center
-        
-        # 2. DETERMINISTIC HASHING FOR DISTRICT
-        # This ensures "District A" is ALWAYS in the same spot relative to the State Center
-        # Creates distinct clusters instead of random noise
-        district_hash = hash(state + district)
-        np.random.seed(district_hash % 2**32) 
-        
-        # Offset the district center by up to 1.5 degrees (~150km) from state center
-        dist_lat_offset = np.random.uniform(-1.5, 1.5)
-        dist_lon_offset = np.random.uniform(-1.5, 1.5)
-        
-        # 3. INDIVIDUAL CENTER JITTER
-        # Add tiny random noise (~4km) so points don't stack perfectly
-        # We re-seed with None to get true randomness for the jitter
-        np.random.seed(None) 
-        noise_lat = np.random.normal(0, 0.04) 
-        noise_lon = np.random.normal(0, 0.04)
-        
-        return pd.Series({
-            'lat': base_lat + dist_lat_offset + noise_lat,
-            'lon': base_lon + dist_lon_offset + noise_lon
-        })
+def get_coords(row):
+    state = row.get('state', 'Delhi')
+    district = str(row.get('district', 'Unknown'))
+    
+    # 1. Get State Base Coordinates (Use your updated list)
+    base_lat, base_lon = state_centers.get(state, (20.5937, 78.9629))
+    
+    # 2. DEFINE STATE RADIUS SCALER (In Degrees)
+    # Default is 0.5 (~55km) which is safer than 1.5
+    default_radius = 0.5 
+    
+    # Tighter constraints for small States/UTs
+    radius_map = {
+        'Chandigarh': 0.04,
+        'Delhi': 0.15,
+        'Goa': 0.15,
+        'Puducherry': 0.1,
+        'Lakshadweep': 0.05,
+        'Daman and Diu': 0.05,
+        'Dadra and Nagar Haveli': 0.05,
+        'Kerala': 0.3,      # Narrow state
+        'Haryana': 0.4,
+        'Punjab': 0.4,
+        'Tripura': 0.3,
+        'Sikkim': 0.15,
+        'Andaman and Nicobar Islands': 1.0 # Long archipelago
+    }
+    
+    # Get the specific radius for this state
+    radius = radius_map.get(state, default_radius)
+    
+    # 3. DETERMINISTIC HASHING
+    district_hash = hash(state + district)
+    np.random.seed(district_hash % 2**32) 
+    
+    # Offset using the specific radius
+    dist_lat_offset = np.random.uniform(-radius, radius)
+    dist_lon_offset = np.random.uniform(-radius, radius)
+    
+    # 4. MICRO JITTER (Random noise for individual points)
+    np.random.seed(None) 
+    noise_lat = np.random.normal(0, 0.02 * radius) # Scale noise relative to state size
+    noise_lon = np.random.normal(0, 0.02 * radius)
+    
+    return pd.Series({
+        'lat': base_lat + dist_lat_offset + noise_lat,
+        'lon': base_lon + dist_lon_offset + noise_lon
+    })
     
     # Apply coordinates
     coords = df.apply(get_coords, axis=1)