Getting started

Requirements

• Python 3.12 or 3.13
• Poetry 2.x

Clone the repository and install all runtime and development dependencies:

git clone git@gitlab.com:DiogoRibeiro7/causal-econometrics.git
cd causal-econometrics
poetry install --with docs

Run the quality gates:

poetry run ruff check .
poetry run ruff format --check .
poetry run mypy src tests
poetry run pytest
poetry run mkdocs build --strict

Run the portfolio case study

poetry run causal-econometrics-case-study \
  --output outputs/retail_pricing_case_study

The command writes a reproducible artifact bundle with tables, figures, diagnostics, a summary, and SHA-256 checksums.

Run a production workflow from files

poetry run causal-econometrics-workflow \
  --input retail_policy.csv \
  --config examples/configs/retail_pricing_policy.json \
  --output outputs/retail_policy

The input is validated before estimation. Invalid schemas or treatment paths fail with a machine-readable validation report.

Build documentation locally

poetry run mkdocs serve

Then open the local address printed by MkDocs.

Suggested reading path

For causal methodology, start with:

1. Estimands and identification
2. Difference-in-Differences
3. Instrumental variables
4. Sensitivity and falsification

For engineering, read:

1. Architecture
2. Reproducibility
3. Production causal workflows