Introducing Postgresql for persistance

backend/app.py

@@ -14,17 +14,27 @@ from typing import Optional
 
 from .config import settings
 from .schemas import METRIC_DEFINITIONS, RANKING_COLUMNS, SCHOOL_COLUMNS
-from .data_loader import load_school_data, clear_cache, geocode_single_postcode, geocode_postcodes_bulk, haversine_distance
+from .data_loader import (
+    load_school_data, clear_cache, geocode_single_postcode, 
+    geocode_postcodes_bulk, haversine_distance, get_data_info as get_db_info
+)
+from .database import init_db
 from .utils import clean_for_json
 
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     """Application lifespan - startup and shutdown events."""
-    # Startup: pre-load data
-    print("Starting up: Loading school data...")
-    load_school_data()
-    print("Data loaded successfully.")
+    # Startup: initialize database and pre-load data
+    print("Starting up: Initializing database...")
+    init_db()  # Ensure tables exist
+    
+    print("Loading school data from database...")
+    df = load_school_data()
+    if df.empty:
+        print("Warning: No data in database. Run the migration script to import data.")
+    else:
+        print("Data loaded successfully.")
     
     yield  # Application runs here
     
@@ -325,13 +335,24 @@ async def get_rankings(
 @app.get("/api/data-info")
 async def get_data_info():
     """Get information about loaded data."""
+    # Get info directly from database
+    db_info = get_db_info()
+    
+    if db_info["total_schools"] == 0:
+        return {
+            "status": "no_data",
+            "message": "No data in database. Run the migration script: python scripts/migrate_csv_to_db.py",
+            "data_source": "PostgreSQL",
+        }
+    
+    # Also get DataFrame-based stats for backwards compatibility
     df = load_school_data()
     
     if df.empty:
         return {
             "status": "no_data",
-            "message": "No data files found in data folder. Please download KS2 data from the government website.",
-            "data_folder": str(settings.data_dir),
+            "message": "No data available",
+            "data_source": "PostgreSQL",
         }
     
     years = [int(y) for y in sorted(df["year"].unique())]
@@ -340,6 +361,7 @@ async def get_data_info():
     
     return {
         "status": "loaded",
+        "data_source": "PostgreSQL",
         "total_records": int(len(df)),
         "unique_schools": int(df["urn"].nunique()),
         "years_available": years,