Installation

purgedcv is on PyPI and requires Python 3.10 or newer.

From PyPI

The base install gets the splitters, metrics, and diagnostics:

pip install purgedcv

Optional extras

Each extra is independent; install only what you need.

ExamplesDevelopmentDocumentation site

To run the eleven worked notebooks in examples/ (Jupyter, Matplotlib, the pricehub OHLC fetcher for the crypto examples):

pip install "purgedcv[examples]"

To run the test suite, the linter, and the type checker the same way CI does:

pip install "purgedcv[dev]"

Then the gates locally are:

ruff check .
black --check src tests tools examples/_lcl_harness.py
mypy src tests
pytest -q

To build this documentation site locally:

pip install "purgedcv[docs]"
mkdocs serve

From source

git clone https://github.com/eslazarev/purged-cross-validation.git
cd purged-cross-validation
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev,docs]"

The build backend is hatchling; no special steps are required.

Verifying the install

python -c "import purgedcv; print(purgedcv.__version__)"

should print the installed version. The full public surface is in purgedcv.__all__.