Sprint 3 implementation: - Pydantic schemas for TRREB, CMHC, and dimension data validation - SQLAlchemy models with PostGIS geometry for fact and dimension tables - Parser structure (stubs) for TRREB PDF and CMHC CSV processing Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
70 lines
2.8 KiB
Python
70 lines
2.8 KiB
Python
"""SQLAlchemy models for fact tables."""
|
|
|
|
from sqlalchemy import ForeignKey, Integer, Numeric, String
|
|
from sqlalchemy.orm import Mapped, mapped_column, relationship
|
|
|
|
from .base import Base
|
|
|
|
|
|
class FactPurchases(Base):
|
|
"""Fact table for TRREB purchase/sales data.
|
|
|
|
Grain: One row per district per month.
|
|
"""
|
|
|
|
__tablename__ = "fact_purchases"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
date_key: Mapped[int] = mapped_column(
|
|
Integer, ForeignKey("dim_time.date_key"), nullable=False
|
|
)
|
|
district_key: Mapped[int] = mapped_column(
|
|
Integer, ForeignKey("dim_trreb_district.district_key"), nullable=False
|
|
)
|
|
sales_count: Mapped[int] = mapped_column(Integer, nullable=False)
|
|
dollar_volume: Mapped[float] = mapped_column(Numeric(15, 2), nullable=False)
|
|
avg_price: Mapped[float] = mapped_column(Numeric(12, 2), nullable=False)
|
|
median_price: Mapped[float] = mapped_column(Numeric(12, 2), nullable=False)
|
|
new_listings: Mapped[int] = mapped_column(Integer, nullable=False)
|
|
active_listings: Mapped[int] = mapped_column(Integer, nullable=False)
|
|
avg_dom: Mapped[int] = mapped_column(Integer, nullable=False) # Days on market
|
|
avg_sp_lp: Mapped[float] = mapped_column(
|
|
Numeric(5, 2), nullable=False
|
|
) # Sale/List ratio
|
|
|
|
# Relationships
|
|
time = relationship("DimTime", backref="purchases")
|
|
district = relationship("DimTRREBDistrict", backref="purchases")
|
|
|
|
|
|
class FactRentals(Base):
|
|
"""Fact table for CMHC rental market data.
|
|
|
|
Grain: One row per zone per bedroom type per survey year.
|
|
"""
|
|
|
|
__tablename__ = "fact_rentals"
|
|
|
|
id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
|
|
date_key: Mapped[int] = mapped_column(
|
|
Integer, ForeignKey("dim_time.date_key"), nullable=False
|
|
)
|
|
zone_key: Mapped[int] = mapped_column(
|
|
Integer, ForeignKey("dim_cmhc_zone.zone_key"), nullable=False
|
|
)
|
|
bedroom_type: Mapped[str] = mapped_column(String(20), nullable=False)
|
|
universe: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
|
avg_rent: Mapped[float | None] = mapped_column(Numeric(10, 2), nullable=True)
|
|
median_rent: Mapped[float | None] = mapped_column(Numeric(10, 2), nullable=True)
|
|
vacancy_rate: Mapped[float | None] = mapped_column(Numeric(5, 2), nullable=True)
|
|
availability_rate: Mapped[float | None] = mapped_column(
|
|
Numeric(5, 2), nullable=True
|
|
)
|
|
turnover_rate: Mapped[float | None] = mapped_column(Numeric(5, 2), nullable=True)
|
|
rent_change_pct: Mapped[float | None] = mapped_column(Numeric(5, 2), nullable=True)
|
|
reliability_code: Mapped[str | None] = mapped_column(String(2), nullable=True)
|
|
|
|
# Relationships
|
|
time = relationship("DimTime", backref="rentals")
|
|
zone = relationship("DimCMHCZone", backref="rentals")
|