pydoe

What it is and what it does

PyDOE is a comprehensive experimental design library that generates structured point sets for planning and analyzing scientific experiments. It implements classical DOE methods (full and fractional factorial, Plackett-Burman, Latin hypercube, Box-Behnken, central composite, Taguchi, and many others) plus advanced techniques like space-filling designs, low-discrepancy sequences, and optimal design algorithms. The package depends on numpy and scipy for numerical computation and is built on a stable, long-running codebase (first released in 2013) that supports modern Python versions.

Typical users are experimentalists who need to choose factor levels and run counts before conducting expensive tests—whether in manufacturing, materials science, simulation, or parameter optimization. Rather than running all possible combinations or guessing, PyDOE lets you construct designs that balance coverage, efficiency, and statistical properties, then analyze results to identify important factors or fit response models.

Use it for:

• Plan a manufacturing experiment with multiple process parameters using fractional factorial to reduce runs while detecting main effects.
• Generate space-filling sample points for computer simulation or surrogate model training using Latin hypercube or Sobol sequences.
• Construct a response-surface design (Box-Behnken or central composite) to fit a polynomial model and optimize a process output.
• Screen many factors quickly with Plackett-Burman or Morris sensitivity analysis to identify which ones matter most.
• Design a mixture experiment (e.g., recipe formulation) using simplex-lattice or simplex-centroid designs.
• Apply Taguchi robust design methods to find factor settings that minimize variation under noise conditions.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

PyDOE constructs experimental designs for scientists and engineers, providing factorial, mixture, response-surface, space-filling, and optimal design methods to plan efficient experiments.

Yes. PyDOE is a mature, actively maintained library with no security vulnerabilities, low install friction, and permissive licensing. Install it if you need to design experiments systematically—it covers classical and modern DOE methods and integrates cleanly with numpy and scipy workflows. Skip it only if your experiment is too simple to benefit from structured design or if you prefer a different framework.

Install

pydoe on PyPI

pip install pydoe

uv add pydoe

poetry add pydoe

Installing pydoe

Before you install

Low friction: pure Python wheel with only numpy and scipy as runtime dependencies. Actively maintained with a recent release (9 days ago) and no known vulnerabilities.

License in practice

BSD-3-Clause is permissive; you can use, modify, and distribute this package freely in commercial and open-source projects with minimal restrictions.

Quickstart

pip install pydoe

import pydoe
design = pydoe.fullfact([2, 3, 4])  # Full factorial with 2, 3, 4 levels

Requires Python 3.10 or later.

Verify before relying

• Whether the package's large API surface (many design methods) is actively maintained or if some functions are legacy/deprecated.
• Performance characteristics for large-scale designs (e.g., how many factors or runs the methods can handle efficiently).

Package facts

Evidence: pydoe-1.4.0-py3-none-any.whl

Keywords: DOE, design of experiments, experimental design, optimal design, optimization, python, sparse grids, statistics, taguchi design

Tags

More Software Development packages