.env.example

@@ -0,0 +1,15 @@
+# Database Configuration
+DATABASE_URL=postgresql://portfolio:portfolio_dev@localhost:5432/portfolio
+POSTGRES_USER=portfolio
+POSTGRES_PASSWORD=portfolio_dev
+POSTGRES_DB=portfolio
+
+# Application Settings
+DASH_DEBUG=true
+SECRET_KEY=change-me-in-production
+
+# Logging
+LOG_LEVEL=INFO
+
+# Optional: dbt profile (defaults to profiles.yml)
+# DBT_PROFILES_DIR=.

.gitignore

@@ -1,4 +1,28 @@
-# ---> Python
+# ====================
+# Project-Specific
+# ====================
+
+# Processed data (generated, not source)
+data/*/processed/
+
+# Reports (generated)
+reports/
+
+# Backups
+backups/
+
+# Notebook exports
+notebooks/*.html
+
+# dbt
+dbt/target/
+dbt/dbt_packages/
+dbt/logs/
+
+# ====================
+# Python
+# ====================
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

.pre-commit-config.yaml

@@ -0,0 +1,32 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+        args: ['--maxkb=1000']
+      - id: check-merge-conflict
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.9
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.8.0
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          - pydantic>=2.0
+          - pandas-stubs
+          - types-requests
+        args: [--ignore-missing-imports]
+        exclude: ^(tests/|dbt/)
+
+ci:
+  autofix_commit_msg: "style: auto-fix by pre-commit hooks"
+  autoupdate_commit_msg: "chore: update pre-commit hooks"

.python-version

@@ -0,0 +1 @@
+3.11

CLAUDE.md

@@ -0,0 +1,258 @@
+# CLAUDE.md
+
+Working context for Claude Code on the Analytics Portfolio project.
+
+---
+
+## Project Status
+
+**Current Sprint**: 1 (Project Bootstrap)
+**Phase**: 1 - Toronto Housing Dashboard
+**Branch**: `development` (feature branches merge here)
+
+---
+
+## Quick Reference
+
+### Run Commands
+
+```bash
+make setup          # Install deps, create .env, init pre-commit
+make docker-up      # Start PostgreSQL + PostGIS
+make docker-down    # Stop containers
+make db-init        # Initialize database schema
+make run            # Start Dash dev server
+make test           # Run pytest
+make lint           # Run ruff linter
+make format         # Run ruff formatter
+make ci             # Run all checks
+```
+
+### Branch Workflow
+
+1. Create feature branch FROM `development`: `git checkout -b feature/{sprint}-{description}`
+2. Work and commit on feature branch
+3. Merge INTO `development` when complete
+4. `development` -> `staging` -> `main` for releases
+
+---
+
+## Code Conventions
+
+### Import Style
+
+| Context | Style | Example |
+|---------|-------|---------|
+| Same directory | Single dot | `from .trreb import TRREBParser` |
+| Sibling directory | Double dot | `from ..schemas.trreb import TRREBRecord` |
+| External packages | Absolute | `import pandas as pd` |
+
+### Module Responsibilities
+
+| Directory | Contains | Purpose |
+|-----------|----------|---------|
+| `schemas/` | Pydantic models | Data validation |
+| `models/` | SQLAlchemy ORM | Database persistence |
+| `parsers/` | PDF/CSV extraction | Raw data ingestion |
+| `loaders/` | Database operations | Data loading |
+| `figures/` | Chart factories | Plotly figure generation |
+| `callbacks/` | Dash callbacks | In `pages/{dashboard}/callbacks/` |
+| `errors/` | Exceptions + handlers | Error handling |
+
+### Type Hints
+
+Use Python 3.10+ style:
+```python
+def process(items: list[str], config: dict[str, int] | None = None) -> bool:
+    ...
+```
+
+### Error Handling
+
+```python
+# errors/exceptions.py
+class PortfolioError(Exception):
+    """Base exception."""
+
+class ParseError(PortfolioError):
+    """PDF/CSV parsing failed."""
+
+class ValidationError(PortfolioError):
+    """Pydantic or business rule validation failed."""
+
+class LoadError(PortfolioError):
+    """Database load operation failed."""
+```
+
+### Code Standards
+
+- Single responsibility functions with verb naming
+- Early returns over deep nesting
+- Google-style docstrings only for non-obvious behavior
+- Module-level constants for magic values
+- Pydantic BaseSettings for runtime config
+
+---
+
+## Application Structure
+
+```
+portfolio_app/
+├── app.py                    # Dash app factory with Pages routing
+├── config.py                 # Pydantic BaseSettings
+├── assets/                   # CSS, images (auto-served)
+├── pages/
+│   ├── home.py              # Bio landing page -> /
+│   └── toronto/
+│       ├── dashboard.py     # Layout only -> /toronto
+│       └── callbacks/       # Interaction logic
+├── components/              # Shared UI (navbar, footer, cards)
+├── figures/                 # Shared chart factories
+├── toronto/                 # Toronto data logic
+│   ├── parsers/
+│   ├── loaders/
+│   ├── schemas/             # Pydantic
+│   └── models/              # SQLAlchemy
+└── errors/
+```
+
+### URL Routing
+
+| URL | Page | Sprint |
+|-----|------|--------|
+| `/` | Bio landing page | 2 |
+| `/toronto` | Toronto Housing Dashboard | 6 |
+
+---
+
+## Tech Stack (Locked)
+
+| Layer | Technology | Version |
+|-------|------------|---------|
+| Database | PostgreSQL + PostGIS | 16.x |
+| Validation | Pydantic | >=2.0 |
+| ORM | SQLAlchemy | >=2.0 (2.0-style API only) |
+| Transformation | dbt-postgres | >=1.7 |
+| Data Processing | Pandas | >=2.1 |
+| Geospatial | GeoPandas + Shapely | >=0.14 |
+| Visualization | Dash + Plotly | >=2.14 |
+| UI Components | dash-mantine-components | Latest stable |
+| Testing | pytest | >=7.0 |
+| Python | 3.11+ | Via pyenv |
+
+**Notes**:
+- SQLAlchemy 2.0 + Pydantic 2.0 only (never mix 1.x APIs)
+- PostGIS extension required in database
+- Docker Compose V2 format (no `version` field)
+
+---
+
+## Data Model Overview
+
+### Geographic Reality (Toronto Housing)
+
+```
+TRREB Districts (~35)     - Purchase data (W01, C01, E01...)
+CMHC Zones (~20)          - Rental data (Census Tract aligned)
+City Neighbourhoods (158) - Enrichment/overlay only
+```
+
+**Critical**: These geographies do NOT align. Display as separate layers—do not force crosswalks.
+
+### Star Schema
+
+| Table | Type | Keys |
+|-------|------|------|
+| `fact_purchases` | Fact | -> dim_time, dim_trreb_district |
+| `fact_rentals` | Fact | -> dim_time, dim_cmhc_zone |
+| `dim_time` | Dimension | date_key (PK) |
+| `dim_trreb_district` | Dimension | district_key (PK), geometry |
+| `dim_cmhc_zone` | Dimension | zone_key (PK), geometry |
+| `dim_neighbourhood` | Dimension | neighbourhood_id (PK), geometry |
+| `dim_policy_event` | Dimension | event_id (PK) |
+
+**V1 Rule**: `dim_neighbourhood` has NO FK to fact tables—reference overlay only.
+
+### dbt Layers
+
+| Layer | Naming | Purpose |
+|-------|--------|---------|
+| Staging | `stg_{source}__{entity}` | 1:1 source, cleaned, typed |
+| Intermediate | `int_{domain}__{transform}` | Business logic |
+| Marts | `mart_{domain}` | Final analytical tables |
+
+---
+
+## DO NOT BUILD (Phase 1)
+
+**Stop and flag if a task seems to require these**:
+
+| Feature | Reason |
+|---------|--------|
+| `bridge_district_neighbourhood` table | Area-weighted aggregation is Phase 4 |
+| Crime data integration | Deferred to Phase 4 |
+| Historical boundary reconciliation (140->158) | 2021+ data only for V1 |
+| ML prediction models | Energy project scope (Phase 3) |
+| Multi-project shared infrastructure | Build first, abstract second (Phase 2) |
+
+---
+
+## Sprint 1 Deliverables
+
+| Category | Tasks |
+|----------|-------|
+| **Bootstrap** | Git init, pyproject.toml, .env.example, Makefile, CLAUDE.md |
+| **Infrastructure** | Docker Compose (PostgreSQL + PostGIS), scripts/ directory |
+| **App Foundation** | portfolio_app/ structure, config.py, error handling |
+| **Tests** | tests/ directory, conftest.py, pytest config |
+| **Data Acquisition** | Download TRREB PDFs, START boundary digitization (HUMAN task) |
+
+### Human Tasks (Cannot Automate)
+
+| Task | Tool | Effort |
+|------|------|--------|
+| Digitize TRREB district boundaries | QGIS | 3-4 hours |
+| Research policy events (10-20) | Manual | 2-3 hours |
+| Replace social link placeholders | Manual | 5 minutes |
+
+---
+
+## Environment Variables
+
+Required in `.env`:
+
+```bash
+DATABASE_URL=postgresql://user:pass@localhost:5432/portfolio
+POSTGRES_USER=portfolio
+POSTGRES_PASSWORD=<secure>
+POSTGRES_DB=portfolio
+DASH_DEBUG=true
+SECRET_KEY=<random>
+LOG_LEVEL=INFO
+```
+
+---
+
+## Script Standards
+
+All scripts in `scripts/`:
+- Include usage comments at top
+- Idempotent where possible
+- Exit codes: 0 = success, 1 = error
+- Use `set -euo pipefail` for bash
+- Log to stdout, errors to stderr
+
+---
+
+## Reference Documents
+
+| Document | Location | Use When |
+|----------|----------|----------|
+| Full specification | `docs/PROJECT_REFERENCE.md` | Architecture decisions |
+| Data schemas | `docs/toronto_housing_spec.md` | Parser/model tasks |
+| WBS details | `docs/wbs.md` | Sprint planning |
+| Bio content | `docs/bio_content.md` | Building home.py |
+
+---
+
+*Last Updated: Sprint 1*

Makefile

@@ -0,0 +1,157 @@
+.PHONY: setup docker-up docker-down db-init run test dbt-run dbt-test lint format ci deploy clean help
+
+# Default target
+.DEFAULT_GOAL := help
+
+# Environment
+PYTHON := python3
+PIP := pip
+DOCKER_COMPOSE := docker compose
+
+# Colors for output
+BLUE := \033[0;34m
+GREEN := \033[0;32m
+YELLOW := \033[0;33m
+NC := \033[0m
+
+help: ## Show this help message
+	@echo "Usage: make [target]"
+	@echo ""
+	@echo "Targets:"
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "  $(BLUE)%-15s$(NC) %s\n", $$1, $$2}'
+
+# =============================================================================
+# Setup
+# =============================================================================
+
+setup: ## Install dependencies, create .env, init pre-commit
+	@echo "$(GREEN)Installing dependencies...$(NC)"
+	$(PIP) install -e ".[dev,dbt]"
+	@echo "$(GREEN)Setting up environment...$(NC)"
+	@if [ ! -f .env ]; then cp .env.example .env; echo "$(YELLOW)Created .env from .env.example - please update values$(NC)"; fi
+	@echo "$(GREEN)Installing pre-commit hooks...$(NC)"
+	pre-commit install
+	@echo "$(GREEN)Setup complete!$(NC)"
+
+# =============================================================================
+# Docker
+# =============================================================================
+
+docker-up: ## Start PostgreSQL + PostGIS containers
+	@echo "$(GREEN)Starting database containers...$(NC)"
+	$(DOCKER_COMPOSE) up -d
+	@echo "$(GREEN)Waiting for database to be ready...$(NC)"
+	@sleep 3
+	@echo "$(GREEN)Database containers started!$(NC)"
+
+docker-down: ## Stop containers
+	@echo "$(YELLOW)Stopping containers...$(NC)"
+	$(DOCKER_COMPOSE) down
+
+docker-logs: ## View container logs
+	$(DOCKER_COMPOSE) logs -f
+
+# =============================================================================
+# Database
+# =============================================================================
+
+db-init: ## Initialize database schema
+	@echo "$(GREEN)Initializing database schema...$(NC)"
+	@if [ -f scripts/db/init.sh ]; then \
+		bash scripts/db/init.sh; \
+	else \
+		echo "$(YELLOW)scripts/db/init.sh not found - skipping$(NC)"; \
+	fi
+
+db-reset: ## Drop and recreate database (DESTRUCTIVE)
+	@echo "$(YELLOW)WARNING: This will delete all data!$(NC)"
+	@read -p "Are you sure? [y/N] " confirm && [ "$$confirm" = "y" ] || exit 1
+	$(DOCKER_COMPOSE) down -v
+	$(DOCKER_COMPOSE) up -d
+	@sleep 3
+	$(MAKE) db-init
+
+# =============================================================================
+# Application
+# =============================================================================
+
+run: ## Start Dash development server
+	@echo "$(GREEN)Starting Dash server...$(NC)"
+	$(PYTHON) -m portfolio_app.app
+
+# =============================================================================
+# Testing
+# =============================================================================
+
+test: ## Run pytest
+	@echo "$(GREEN)Running tests...$(NC)"
+	pytest
+
+test-cov: ## Run pytest with coverage
+	@echo "$(GREEN)Running tests with coverage...$(NC)"
+	pytest --cov=portfolio_app --cov-report=html --cov-report=term
+
+# =============================================================================
+# dbt
+# =============================================================================
+
+dbt-run: ## Run dbt models
+	@echo "$(GREEN)Running dbt models...$(NC)"
+	cd dbt && dbt run
+
+dbt-test: ## Run dbt tests
+	@echo "$(GREEN)Running dbt tests...$(NC)"
+	cd dbt && dbt test
+
+dbt-docs: ## Generate dbt documentation
+	@echo "$(GREEN)Generating dbt docs...$(NC)"
+	cd dbt && dbt docs generate && dbt docs serve
+
+# =============================================================================
+# Code Quality
+# =============================================================================
+
+lint: ## Run ruff linter
+	@echo "$(GREEN)Running linter...$(NC)"
+	ruff check .
+
+format: ## Run ruff formatter
+	@echo "$(GREEN)Formatting code...$(NC)"
+	ruff format .
+	ruff check --fix .
+
+typecheck: ## Run mypy type checker
+	@echo "$(GREEN)Running type checker...$(NC)"
+	mypy portfolio_app
+
+ci: ## Run all checks (lint, typecheck, test)
+	@echo "$(GREEN)Running CI checks...$(NC)"
+	$(MAKE) lint
+	$(MAKE) typecheck
+	$(MAKE) test
+	@echo "$(GREEN)All checks passed!$(NC)"
+
+# =============================================================================
+# Deployment
+# =============================================================================
+
+deploy: ## Deploy to production
+	@echo "$(YELLOW)Deployment not yet configured$(NC)"
+	@echo "TODO: Add deployment script"
+
+# =============================================================================
+# Cleanup
+# =============================================================================
+
+clean: ## Remove build artifacts and caches
+	@echo "$(YELLOW)Cleaning up...$(NC)"
+	rm -rf build/
+	rm -rf dist/
+	rm -rf *.egg-info/
+	rm -rf .pytest_cache/
+	rm -rf .ruff_cache/
+	rm -rf .mypy_cache/
+	rm -rf htmlcov/
+	rm -rf .coverage
+	find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true
+	@echo "$(GREEN)Clean complete!$(NC)"

docker-compose.yml

@@ -0,0 +1,22 @@
+services:
+  db:
+    image: postgis/postgis:16-3.4
+    container_name: portfolio-db
+    restart: unless-stopped
+    ports:
+      - "5432:5432"
+    environment:
+      POSTGRES_USER: ${POSTGRES_USER:-portfolio}
+      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-portfolio_dev}
+      POSTGRES_DB: ${POSTGRES_DB:-portfolio}
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+      - ./scripts/db/init-postgis.sql:/docker-entrypoint-initdb.d/init-postgis.sql:ro
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-portfolio} -d ${POSTGRES_DB:-portfolio}"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+
+volumes:
+  postgres_data:

portfolio_app/__init__.py

@@ -0,0 +1,3 @@
+"""Analytics Portfolio Application."""
+
+__version__ = "0.1.0"

portfolio_app/errors/__init__.py

@@ -0,0 +1,5 @@
+"""Error handling for the portfolio application."""
+
+from .exceptions import LoadError, ParseError, PortfolioError, ValidationError
+
+__all__ = ["PortfolioError", "ParseError", "ValidationError", "LoadError"]

portfolio_app/errors/exceptions.py

@@ -0,0 +1,17 @@
+"""Custom exceptions for the portfolio application."""
+
+
+class PortfolioError(Exception):
+    """Base exception for all portfolio errors."""
+
+
+class ParseError(PortfolioError):
+    """PDF/CSV parsing failed."""
+
+
+class ValidationError(PortfolioError):
+    """Pydantic or business rule validation failed."""
+
+
+class LoadError(PortfolioError):
+    """Database load operation failed."""

portfolio_app/pages/__init__.py

@@ -0,0 +1 @@
+"""Dash pages."""

portfolio_app/pages/toronto/__init__.py

@@ -0,0 +1 @@
+"""Toronto Housing Dashboard page."""

portfolio_app/pages/toronto/callbacks/__init__.py

@@ -0,0 +1 @@
+"""Toronto dashboard callbacks."""

portfolio_app/toronto/__init__.py

@@ -0,0 +1 @@
+"""Toronto housing data logic."""

portfolio_app/toronto/loaders/__init__.py

@@ -0,0 +1 @@
+"""Database loaders for Toronto housing data."""

portfolio_app/toronto/models/__init__.py

@@ -0,0 +1 @@
+"""SQLAlchemy models for Toronto housing data."""

portfolio_app/toronto/parsers/__init__.py

@@ -0,0 +1 @@
+"""Data parsers for Toronto housing data sources."""

portfolio_app/toronto/schemas/__init__.py

@@ -0,0 +1 @@
+"""Pydantic schemas for Toronto housing data validation."""

pyproject.toml

@@ -0,0 +1,148 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "portfolio"
+version = "0.1.0"
+description = "Analytics Portfolio - Data engineering and visualization showcase"
+readme = "README.md"
+license = {text = "MIT"}
+requires-python = ">=3.11"
+authors = [
+    {name = "Leo Miranda"}
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+dependencies = [
+    # Database
+    "sqlalchemy>=2.0",
+    "psycopg2-binary>=2.9",
+    "geoalchemy2>=0.14",
+
+    # Validation
+    "pydantic>=2.0",
+    "pydantic-settings>=2.0",
+
+    # Data Processing
+    "pandas>=2.1",
+    "geopandas>=0.14",
+    "shapely>=2.0",
+
+    # Visualization
+    "dash>=2.14",
+    "plotly>=5.18",
+    "dash-mantine-components>=0.14",
+
+    # PDF Parsing
+    "pdfplumber>=0.10",
+    "tabula-py>=2.9",
+
+    # Utilities
+    "python-dotenv>=1.0",
+    "httpx>=0.25",
+]
+
+[project.optional-dependencies]
+dev = [
+    # Testing
+    "pytest>=7.0",
+    "pytest-cov>=4.0",
+    "pytest-asyncio>=0.21",
+
+    # Linting & Formatting
+    "ruff>=0.1",
+    "mypy>=1.7",
+
+    # Pre-commit
+    "pre-commit>=3.5",
+
+    # Type stubs
+    "pandas-stubs",
+    "types-requests",
+]
+dbt = [
+    "dbt-postgres>=1.7",
+]
+
+[project.scripts]
+portfolio = "portfolio_app.app:main"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["portfolio_app*"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = ["test_*.py"]
+python_functions = ["test_*"]
+addopts = [
+    "-v",
+    "--tb=short",
+    "--strict-markers",
+]
+markers = [
+    "slow: marks tests as slow (deselect with '-m \"not slow\"')",
+    "integration: marks tests as integration tests",
+]
+
+[tool.ruff]
+target-version = "py311"
+line-length = 88
+exclude = [
+    ".git",
+    ".venv",
+    "__pycache__",
+    "build",
+    "dist",
+    ".ruff_cache",
+    "dbt/target",
+]
+
+[tool.ruff.lint]
+select = [
+    "E",    # pycodestyle errors
+    "W",    # pycodestyle warnings
+    "F",    # pyflakes
+    "I",    # isort
+    "B",    # flake8-bugbear
+    "C4",   # flake8-comprehensions
+    "UP",   # pyupgrade
+    "SIM",  # flake8-simplify
+]
+ignore = [
+    "E501",  # line too long (handled by formatter)
+]
+
+[tool.ruff.lint.isort]
+known-first-party = ["portfolio_app"]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+
+[tool.mypy]
+python_version = "3.11"
+strict = true
+warn_return_any = true
+warn_unused_ignores = true
+disallow_untyped_defs = true
+plugins = ["pydantic.mypy"]
+
+[[tool.mypy.overrides]]
+module = [
+    "dash.*",
+    "plotly.*",
+    "geopandas.*",
+    "shapely.*",
+    "pdfplumber.*",
+    "tabula.*",
+]
+ignore_missing_imports = true

scripts/db/init-postgis.sql

@@ -0,0 +1,8 @@
+-- Initialize PostGIS extension
+-- This script runs automatically on first container start
+
+-- Enable PostGIS extension
+CREATE EXTENSION IF NOT EXISTS postgis;
+
+-- Verify installation
+SELECT PostGIS_Version();

tests/__init__.py

@@ -0,0 +1 @@
+"""Test suite for analytics portfolio."""

tests/conftest.py

@@ -0,0 +1,9 @@
+"""Pytest configuration and fixtures."""
+
+import pytest
+
+
+@pytest.fixture
+def sample_fixture():
+    """Example fixture - replace with actual fixtures as needed."""
+    return {}