Makefile

.PHONY: setup preprocess sql dbt notebook pipeline dashboard test typecheck verify clean

# ============================================================
# E-commerce User Behavior Analytics — Orchestration
# ============================================================

# Absolute paths for dbt so DuckDB / seed references resolve the same way.
export DBT_DUCKDB_PATH := $(CURDIR)/data/processed/analytics.duckdb
export DBT_DATA_PATH := $(CURDIR)/data/processed/user_behavior_cleaned.csv

setup:
	pip install -r requirements.lock
	pip install -e ".[dev]"
	pre-commit install

preprocess:
	python -m shoplytics.preprocess \
		--input data/raw/UserBehavior.csv \
		--output data/processed/

sql:
	python -m shoplytics.run_sql

dbt:
	cd dbt && dbt run && dbt test

notebook:
	jupyter notebook notebooks/

pipeline:
	python -m shoplytics.pipeline

dashboard:
	streamlit run dashboard/app.py

test:
	pytest tests/ -v --cov=shoplytics --cov-report=term-missing --cov-fail-under=20

typecheck:
	mypy src/shoplytics

lint:
	ruff check src/ tests/ dashboard/
	PYTHONUTF8=1 sqlfluff lint sql/

format:
	ruff format src/ tests/ dashboard/

format-check:
	ruff format --check src/ tests/ dashboard/

audit:
	python -m shoplytics.audit_consistency

verify: lint format-check typecheck test audit
	python -m shoplytics.validate_data

# Full workflow (local equivalent of a production DAG)
all: preprocess sql dbt pipeline

clean:
	rm -f data/processed/*.duckdb
	find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true
	find . -type f -name "*.pyc" -delete 2>/dev/null || true
	find . -type d -name ".pytest_cache" -exec rm -rf {} + 2>/dev/null || true
	find . -type d -name ".ruff_cache" -exec rm -rf {} + 2>/dev/null || true