Update app.py

app.py

@@ -5,6 +5,8 @@ import plotly.graph_objects as go
 import numpy as np
 import requests
 import time
+import json
+import os
 from datetime import datetime, timedelta
 
 # 1. PAGE CONFIGURATION
@@ -62,16 +64,32 @@ st.markdown("""
     </style>
 """, unsafe_allow_html=True)
 
-# 3. DYNAMIC GEOCODING ENGINE
+# 3. DYNAMIC GEOCODING ENGINE WITH PERSISTENT JSON
 @st.cache_data(show_spinner=False)
 def fetch_coordinates_batch(unique_locations):
     """
     Fetches coordinates from OpenStreetMap Nominatim API.
+    Uses 'district_coords.json' for persistent storage.
     unique_locations: List of tuples (District, State)
     Returns: Dictionary {(District, State): (lat, lon)}
     """
-    # 1. Pre-filled Cache (For speed & redundancy)
-    coords_map = {
+    json_file = 'district_coords.json'
+    coords_map = {}
+
+    # 1. Load from JSON if exists
+    if os.path.exists(json_file):
+        try:
+            with open(json_file, 'r') as f:
+                # Convert string keys "District, State" back to tuple
+                loaded_data = json.load(f)
+                for k, v in loaded_data.items():
+                    dist, state = k.split("|")
+                    coords_map[(dist, state)] = tuple(v)
+        except json.JSONDecodeError:
+            pass # File corrupted, start fresh
+
+    # 2. Add Hardcoded Pre-fills (High Priority Redundancy)
+    hardcoded_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),
@@ -91,18 +109,21 @@ def fetch_coordinates_batch(unique_locations):
         ('Delhi', 'Delhi'): (28.7041, 77.1025),
         ('Shimla', 'Himachal Pradesh'): (31.1048, 77.1734)
     }
+    # Update cache with hardcoded values (overrides JSON if conflict, usually better accuracy)
+    coords_map.update(hardcoded_map)
     
-    # 2. Identify missing locations
+    # 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
 
-    # 3. Dynamic Fetching for missing
+    # 4. 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)'}
+    updated = False
     
     for i, (district, state) in enumerate(missing_locs):
         try:
@@ -119,6 +140,7 @@ def fetch_coordinates_batch(unique_locations):
             if response.status_code == 200 and response.json():
                 data = response.json()[0]
                 coords_map[(district, state)] = (float(data['lat']), float(data['lon']))
+                updated = True
             else:
                 # Fallback if API fails: Keep existing State Centers logic inside main loop later
                 pass
@@ -130,6 +152,14 @@ def fetch_coordinates_batch(unique_locations):
             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
@@ -150,7 +180,7 @@ def load_data():
     # Get Unique Locations
     unique_locs = list(df[['district', 'state']].drop_duplicates().itertuples(index=False, name=None))
     
-    # Fetch Coordinates (Cached)
+    # Fetch Coordinates (Cached + Persistent JSON)
     coords_db = fetch_coordinates_batch(unique_locs)
     
     # Fallback Centers (State Capitals)