fix: Repair data pipeline with StatCan CMHC rental data

- Add StatCan CMHC parser to fetch rental data from Statistics Canada API
- Create year spine (2014-2025) as time dimension driver instead of census
- Add CMA-level rental and income intermediate models
- Update mart_neighbourhood_overview to use rental years as base
- Fix neighbourhood_service queries to match dbt schema
- Add CMHC data loading to pipeline script

Data now flows correctly: 158 neighbourhoods × 12 years = 1,896 records
Rent data available 2019-2025, crime data 2014-2024

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

scripts/data/load_toronto_data.py

@@ -38,12 +38,16 @@ from portfolio_app.toronto.loaders import (  # noqa: E402
     load_census_data,
     load_crime_data,
     load_neighbourhoods,
+    load_statcan_cmhc_data,
     load_time_dimension,
 )
 from portfolio_app.toronto.parsers import (  # noqa: E402
     TorontoOpenDataParser,
     TorontoPoliceParser,
 )
+from portfolio_app.toronto.parsers.statcan_cmhc import (  # noqa: E402
+    fetch_toronto_rental_data,
+)
 from portfolio_app.toronto.schemas import Neighbourhood  # noqa: E402
 
 # Configure logging
@@ -91,6 +95,9 @@ class DataPipeline:
                 # 5. Load amenities
                 self._load_amenities(session)
 
+                # 6. Load CMHC rental data from StatCan
+                self._load_rentals(session)
+
                 session.commit()
                 logger.info("All data committed to database")
 
@@ -241,6 +248,32 @@ class DataPipeline:
 
         self.stats["amenities"] = total_count
 
+    def _load_rentals(self, session: Any) -> None:
+        """Fetch and load CMHC rental data from StatCan."""
+        logger.info("Fetching CMHC rental data from Statistics Canada...")
+
+        if self.dry_run:
+            logger.info("  [DRY RUN] Would fetch and load CMHC rental data")
+            return
+
+        try:
+            # Fetch rental data (2014-present)
+            rental_records = fetch_toronto_rental_data(start_year=2014)
+
+            if not rental_records:
+                logger.warning("  No rental records fetched")
+                return
+
+            count = load_statcan_cmhc_data(rental_records, session)
+            self.stats["rentals"] = count
+            logger.info(f"  Loaded {count} CMHC rental records")
+        except Exception as e:
+            logger.warning(f"  Failed to load CMHC rental data: {e}")
+            if self.verbose:
+                import traceback
+
+                traceback.print_exc()
+
     def run_dbt(self) -> bool:
         """Run dbt to transform data.
 

scripts/db/init_schema.py

@@ -25,8 +25,10 @@ def main() -> int:
         engine = get_engine()
 
         # Test connection
+        from sqlalchemy import text
+
         with engine.connect() as conn:
-            result = conn.execute("SELECT 1")
+            result = conn.execute(text("SELECT 1"))
             result.fetchone()
         print("Database connection successful")