Zoning Intelligence Engine

A lightweight Python prototype for parcel-level zoning analysis, site study generation, and early-stage feasibility workflows.

Motivation

This project models zoning rules explicitly and builds a simple pipeline:

parcel → zoning rules → site study → feasibility → underwriting

Features

• Structured zoning model
  Represents parcels, zoning districts, and overlays with explicit constraints (uses, height, units, lot size, parking)

• Knowledge graph representation
  Encodes relationships like:

  • Parcel → has_zoning → RMU
  • RMU → allows_use → multi_family

• Site study generation
  Recommends a feasible development type based on zoning rules

• Feasibility checks
  Validates use, lot size, unit count, and parking requirements

• Lightweight underwriting
  Estimates revenue and profit for a proposed project

Example Workflow

For a parcel:

• Address: 123 Main St
• Zoning: RMU
• Overlay: TOD
• Lot size: 3200 sqft

The engine will:

1. Build zoning relationships (knowledge graph)
2. Recommend a development type (e.g., multifamily)
3. Check feasibility against constraints
4. Estimate basic financial outcomes

Run

python zoning_engine.py

Example Output

=== KNOWLEDGE GRAPH ===
('123 Main St', 'has_zoning', 'RMU')
('123 Main St', 'has_overlay', 'TOD')
('RMU', 'max_height_ft', 70)
('RMU', 'max_units', 12)
('RMU', 'min_lot_sqft', 2500)
('RMU', 'parking_per_unit', 1.0)
('RMU', 'allows_use', 'single_family')
('RMU', 'allows_use', 'multi_family')
('RMU', 'allows_use', 'mixed_use')
('RMU', 'allows_use', 'live_work')

=== SITE STUDY ===
{'recommended_use': 'mixed_use', 'max_units': 12, 'max_height_ft': 70}

=== FEASIBILITY TEST ===
{'use_allowed': True, 'lot_size_ok': True, 'number_of_units_ok': True, 'parking_required': 12.0}

=== UNDERWRITING ===
{'revenue': 3600000, 'profit': 1200000}