Freedom251 › Statistical Analysis Software

Pingouin

Free plan Linux

What Pingouin is

Pingouin is a free, open-source statistical package written in Python 3 and based mostly on Pandas and NumPy. It includes statistical tests, regression functions, Bayesian analysis, and scripting support, with CSV and XLSX data import through Pandas. Correlation methods include robust, partial, distance, repeated-measures, and pairwise approaches. Modeling functions cover linear and logistic regression, mediation analysis, and multivariate tests. The package also provides effect sizes, power analysis, and parametric or bootstrapped confidence intervals for effect sizes or correlation coefficients. Its plotting functions include Bland–Altman, Q-Q, and paired plots. Several functions, including ANOVA, pairwise tests, correlations, and mediation analysis, can be called as Pandas DataFrame methods. Installation is available through uv, pip, or conda. The documentation says the project is under development, warns that bugs may exist, and advises checking results with other statistical software; it provides no warranty. The GitHub repository identifies the license as GPL-3.0. Questions can go to GitHub Discussions and bug reports to the repository.

Who it suits

Pingouin suits Python users who need statistical tests, modeling, or analysis integrated with Pandas workflows. Users should account for the project’s development warning and verify results with other statistical software.

What it does well

Free and open-source under GPL-3.0.
Offers linear and logistic regression functions.
Provides power analysis and effect sizes.
Some analyses work as Pandas DataFrame methods.
Installable through uv, pip, or conda.

What to know first

Project says it remains under development.
Documentation warns bugs may exist.
The project provides no warranty.

Limits

The package is free, with no paid plans or usage limits stated. The documentation says it is tested for Python 3.11 and later; the project warns that bugs may exist and recommends checking results with other statistical software.

Plans

Plan	Billed and limits	Price
Free and open-source	Python package; no paid plans or usage limits stated	Free

As pingouin-stats.org lists them, read 12 Oct 2026. The maker's own page has the final word.

Getting started

Install Python 3.11 or later.
Install Pingouin with uv, pip, or conda.
Import .csv or .xlsx data through Pandas.
Use Pingouin functions or call supported methods directly on Pandas DataFrames.
Consult GitHub Discussions for questions or the GitHub repository to report bugs.

Verdict

Pingouin offers a broad set of statistical functions within a Python and Pandas-oriented package. Its own development warning makes independent result checking important.

Questions

Is Pingouin free?

Yes. The Free and open-source plan is free, and no paid plans or usage limits are stated.

Is Pingouin open source?

Yes. Its GitHub repository identifies the license as GPL-3.0.

What data formats can it import?

It can work with .csv and .xlsx data through Pandas.

Which Python version does the documentation say it is tested for?

The documentation says Pingouin is tested for Python 3.11 and later.

Who maintains Pingouin?

The documentation says it was created and is maintained by Raphael Vallat, mostly in his spare time.

Where can users ask questions or report bugs?

The documentation directs questions to GitHub Discussions and bug reports to the GitHub repository.

Facts from Pingouin's own pages

Bayesian analysis: Pingouin includes Bayes factors. · pingouin-stats.org, 12 Oct 2026
Correlations: It supports robust, partial, distance, repeated-measures, and pairwise correlations. · pingouin-stats.org, 12 Oct 2026
Data import formats: .csv, .xlsx via Pandas · pingouin-stats.org, 23 Sept 2026
Development status: The project says it is under development, warns that bugs may exist, and advises checking results with other statistical software; it provides no warranty. · pingouin-stats.org, 12 Oct 2026
Effect sizes and power: It provides effect sizes, power analysis, and parametric or bootstrapped confidence intervals for effect sizes or correlation coefficients. · pingouin-stats.org, 12 Oct 2026
Installation: The package can be installed with uv, pip, or conda. · pingouin-stats.org, 12 Oct 2026
License: The project’s GitHub repository identifies its license as GPL-3.0. · github.com, 12 Oct 2026
Maintainer: The documentation says Pingouin was created and is maintained by Raphael Vallat, mostly in his spare time. · pingouin-stats.org, 12 Oct 2026
Modeling: Its listed functions include linear and logistic regression, mediation analysis, and multivariate tests. · pingouin-stats.org, 12 Oct 2026
Pandas integration: Several functions can be called directly as pandas DataFrame methods, including ANOVA, pairwise tests, correlations, and mediation analysis. · pingouin-stats.org, 12 Oct 2026
Purpose: Pingouin is an open-source statistical package written in Python 3 and based mostly on Pandas and NumPy. · pingouin-stats.org, 12 Oct 2026
Regression models: Yes · pingouin-stats.org, 23 Sept 2026
Runtime requirements: The documentation says Pingouin is tested for Python 3.11 and later and lists NumPy, SciPy, Pandas, Statsmodels, Matplotlib, Seaborn, Scikit-learn, and other dependencies. · pingouin-stats.org, 12 Oct 2026
Scripting support: Yes · pingouin-stats.org, 23 Sept 2026
Statistical tests: It includes N-way, repeated-measures, mixed ANOVA and ANCOVA, pairwise tests, and chi-squared tests. · pingouin-stats.org, 12 Oct 2026
Support: The documentation directs questions to GitHub Discussions and bug reports to the GitHub repository. · pingouin-stats.org, 12 Oct 2026
Visualization: Its plotting functions include Bland–Altman, Q-Q, and paired plots. · pingouin-stats.org, 12 Oct 2026

Where Pingouin stands on Freedom251

Statistical Analysis Software#21 of 106