pilotr 0.2.0

Simulate experimental and behavioural data from a portable design specification (cross-language with the R package of the same name).

pilotr (Python)

Python implementation of pilotr. It simulates experimental and behavioural data from a portable JSON design specification, producing output that is bit-identical to the R package of the same name. See the project README for the full toolkit (the no-code app, the R package and the specification format).

Install

pip install pilotr             # core engine (pure Python, dependency-free)
pip install "pilotr[power]"    # + scipy, for the simulation-based power demo

Requires Python 3.9 or later; the generative core has no dependencies.

For development, install from a checkout of the repository instead: clone https://github.com/pablobernabeu/pilotr and run pip install . (or pip install ".[dev]") from the python directory.

Quick start

from pilotr import simulate

spec = {
    "name": "two_group", "seed": 2024,
    "units": {"subject": {"n": 64}},
    "factors": [{"name": "group", "levels": ["control", "treatment"],
                 "contrasts": {"effect": [-0.5, 0.5]}, "between": "subject"}],
    "fixed": {"intercept": 100, "coefficients": {"effect": 5}},
    "response": {"family": "gaussian", "name": "score", "sigma": 10},
}

data = simulate(spec)               # 64 rows

Given the same specification and seed, this reproduces the data generated by the R package to full floating-point precision.

Try it without installing

A serverless build runs entirely in your browser, with no installation required and no data uploaded. It is available as a no-code app.

Learn more

The Python documentation site walks through the quick start, the response families, power and design analysis, the specification format and the API reference. The full repository, including the R package and the no-code app, is at https://github.com/pablobernabeu/pilotr.