lmiranda
053acf6436
Add schemas, parsers, loaders, and models for Toronto neighbourhood-centric data including census profiles, crime statistics, and amenities. Schemas: - NeighbourhoodRecord, CensusRecord, CrimeRecord, CrimeType - AmenityType, AmenityRecord, AmenityCount Models: - BridgeCMHCNeighbourhood (zone-to-neighbourhood mapping with weights) - FactCensus, FactCrime, FactAmenities Parsers: - TorontoOpenDataParser (CKAN API for neighbourhoods, census, amenities) - TorontoPoliceParser (crime rates, MCI data) Loaders: - load_census_data, load_crime_data, load_amenities - build_cmhc_neighbourhood_crosswalk (PostGIS area weights) Also updates CLAUDE.md with projman plugin workflow documentation. Closes #53, #54, #55, #56, #57, #58, #59 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
46 lines
1.2 KiB
Python
46 lines
1.2 KiB
Python
"""Loader for crime data to fact_crime table."""
|
|
|
|
from sqlalchemy.orm import Session
|
|
|
|
from portfolio_app.toronto.models import FactCrime
|
|
from portfolio_app.toronto.schemas import CrimeRecord
|
|
|
|
from .base import get_session, upsert_by_key
|
|
|
|
|
|
def load_crime_data(
|
|
records: list[CrimeRecord],
|
|
session: Session | None = None,
|
|
) -> int:
|
|
"""Load crime records to fact_crime table.
|
|
|
|
Args:
|
|
records: List of validated CrimeRecord schemas.
|
|
session: Optional existing session.
|
|
|
|
Returns:
|
|
Number of records loaded (inserted + updated).
|
|
"""
|
|
|
|
def _load(sess: Session) -> int:
|
|
models = []
|
|
for r in records:
|
|
model = FactCrime(
|
|
neighbourhood_id=r.neighbourhood_id,
|
|
year=r.year,
|
|
crime_type=r.crime_type.value,
|
|
count=r.count,
|
|
rate_per_100k=float(r.rate_per_100k) if r.rate_per_100k else None,
|
|
)
|
|
models.append(model)
|
|
|
|
inserted, updated = upsert_by_key(
|
|
sess, FactCrime, models, ["neighbourhood_id", "year", "crime_type"]
|
|
)
|
|
return inserted + updated
|
|
|
|
if session:
|
|
return _load(session)
|
|
with get_session() as sess:
|
|
return _load(sess)
|