feat(data-analytics-demo): T-03 data generation + T-12 Python CI

.github/dependabot.yml

@@ -54,3 +54,33 @@ updates:
       - github-actions
     commit-message:
       prefix: "chore(ci)"
+
+  - package-ecosystem: pip
+    directory: /packages/data-analytics-demo
+    schedule:
+      interval: weekly
+      day: monday
+      time: "09:00"
+      timezone: Asia/Tokyo
+    open-pull-requests-limit: 5
+    groups:
+      dbt:
+        patterns:
+          - "dbt-*"
+      ml:
+        patterns:
+          - "scikit-learn"
+          - "xgboost"
+          - "shap"
+          - "pandas"
+          - "numpy"
+      duckdb:
+        patterns:
+          - "duckdb"
+      dev:
+        dependency-type: "development"
+    labels:
+      - dependencies
+      - python
+    commit-message:
+      prefix: "chore(deps)"

.github/workflows/python-audit.yml

@@ -0,0 +1,40 @@
+name: python audit (data-analytics-demo)
+
+on:
+  push:
+    branches: [main, master]
+    paths:
+      - "packages/data-analytics-demo/pyproject.toml"
+      - ".github/workflows/python-audit.yml"
+  pull_request:
+    branches: [main, master]
+    paths:
+      - "packages/data-analytics-demo/pyproject.toml"
+      - ".github/workflows/python-audit.yml"
+  schedule:
+    - cron: "0 0 * * 0"
+  workflow_dispatch:
+
+jobs:
+  audit:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    defaults:
+      run:
+        working-directory: packages/data-analytics-demo
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: install pip-audit + package deps
+        run: |
+          python -m pip install --upgrade pip
+          pip install pip-audit
+          pip install -e .
+
+      - name: pip-audit (fail on HIGH or CRITICAL)
+        run: pip-audit --strict --vulnerability-service osv

.github/workflows/python-test.yml

@@ -0,0 +1,43 @@
+name: python test (data-analytics-demo)
+
+on:
+  push:
+    branches: [main, master]
+    paths:
+      - "packages/data-analytics-demo/**"
+      - ".github/workflows/python-test.yml"
+  pull_request:
+    branches: [main, master]
+    paths:
+      - "packages/data-analytics-demo/**"
+      - ".github/workflows/python-test.yml"
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    defaults:
+      run:
+        working-directory: packages/data-analytics-demo
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: install package + dev extras
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e ".[dev]"
+
+      - name: ruff (lint)
+        run: ruff check src tests
+
+      - name: mypy (strict type-check)
+        run: mypy -p data_analytics_demo
+
+      - name: pytest (coverage ≥ 80%)
+        run: pytest

packages/data-analytics-demo/Makefile

@@ -20,10 +20,9 @@ help:
 install:
 	$(PIP) install -e ".[dev]"
 
-# Stage targets — placeholders until T-03 .. T-10 are implemented
+# Stage targets
 data:
-	@echo "[data] TODO T-03: synthetic data generation not yet implemented"
-	@exit 1
+	$(PYTHON) -m data_analytics_demo.data.generate
 
 dbt:
 	@echo "[dbt] TODO T-04/T-05: dbt models not yet implemented"
@@ -53,7 +52,7 @@ test:
 
 lint:
 	$(PYTHON) -m ruff check src tests
-	$(PYTHON) -m mypy src
+	$(PYTHON) -m mypy -p data_analytics_demo
 
 clean:
 	rm -rf warehouse/*.duckdb ml/artifacts/* dashboard/build narrative/output.md

packages/data-analytics-demo/pyproject.toml

@@ -49,6 +49,9 @@ build-backend = "setuptools.build_meta"
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.package-data]
+data_analytics_demo = ["py.typed"]
+
 [tool.ruff]
 line-length = 120
 target-version = "py311"
@@ -65,6 +68,14 @@ strict = true
 python_version = "3.11"
 namespace_packages = true
 explicit_package_bases = true
+mypy_path = "src"
+
+# Third-party libraries without published type stubs. `pandas-stubs` exists
+# but lags behind `pandas` releases; treating these as untyped is the
+# pragmatic choice for a Python 3.11 + pandas 3.x stack.
+[[tool.mypy.overrides]]
+module = ["pandas", "pandas.*", "duckdb", "faker", "shap", "xgboost", "sklearn.*"]
+ignore_missing_imports = true
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

packages/data-analytics-demo/src/data_analytics_demo/cli.py

@@ -26,9 +26,11 @@ def version() -> None:
 
 @app.command()
 def data() -> None:
-    """Generate synthetic SaaS data (T-03, not yet implemented)."""
-    typer.echo("[data] TODO T-03: synthetic data generation not yet implemented", err=True)
-    sys.exit(1)
+    """Generate synthetic SaaS data into warehouse/analytics.duckdb."""
+    from data_analytics_demo.data import generate as gen
+
+    out = gen.main()
+    typer.echo(f"wrote {out}")
 
 
 @app.command()

packages/data-analytics-demo/src/data_analytics_demo/data/__init__.py

@@ -0,0 +1,6 @@
+"""Synthetic SaaS data generation for the customer-analytics demo.
+
+Public surface:
+    generate.main()       Run the full synthesis and persist to DuckDB.
+    schemas.{Customer, Event, Subscription, Invoice}    Pydantic models.
+"""