pingouin
Pingouin: statistical package for Python
Decision gist · record as of 2026-08-14
Yes. Pingouin is well-maintained, actively developed, has no security vulnerabilities, and fills a genuine gap: it wraps SciPy and Statsmodels with sensible defaults and comprehensive output. The GPL-3.0 license is standard for academic software and poses no barrier to research use. Install it if you do statistical testing in Python and want richer output than SciPy alone provides.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Nine runtime dependencies (NumPy, SciPy, Pandas, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Pandas-flavor, Tabulate) must be installed; pip handles this automatically.
- Low friction installation with a pure-Python wheel distribution.
License · maintenance · safety
GPL-3.0 (copyleft) — GPL-3.0 copyleft license means any derivative work or modification must also be released under GPL-3.0. This is permissive for research and internal use but restricts commercial redistribution without source disclosure.
last release 2026-03-28 (139 days) · last repo commit 2026-04-05 · 1,929 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 524,957 downloads/mo, #6,187 on PyPI
Alternatives
Verify before relying
pip install pingouin
import pingouin as pg
import numpy as np
np.random.seed(123)
x = np.random.normal(0, 1, 30)
y = np.random.normal(0, 1, 30)
result = pg.ttest(x, y)
print(result)- Whether all statistical functions work equally well with missing data or require preprocessing
- Performance characteristics on large datasets (memory usage, computation time)
- Availability and completeness of circular statistics functions mentioned in description
What it is and what it does
Pingouin is a statistical package built on NumPy, SciPy, and Pandas that provides a high-level interface to common statistical tests and analyses. Unlike lower-level libraries, it returns comprehensive results by default—a t-test includes not just the t-value and p-value but also degrees of freedom, Cohen's d effect size, 95% confidence intervals, statistical power, and Bayes factors. It covers parametric and non-parametric tests, ANOVAs (one-way, repeated measures, mixed, ANCOVA), pairwise post-hoc tests, multiple correlation methods (Pearson, Spearman, robust, partial, distance, repeated measures), linear and logistic regression, mediation analysis, multivariate tests, reliability measures, and circular statistics.
The package is designed for researchers and data analysts who want exhaustive statistical output without writing custom code. It integrates with Pandas DataFrames, supports grouped and long-format data, and includes plotting functions (Bland-Altman, Q-Q, paired plots). Dependencies are all standard scientific Python libraries, making it straightforward to install. The codebase is actively maintained, tested on Python 3.10 through 3.14, and has no known security vulnerabilities.
Use it for
- Run a t-test and immediately get effect size, confidence intervals, power, and Bayes factor for publication-ready reporting
- Perform repeated-measures ANOVA with post-hoc pairwise comparisons on grouped experimental data in a DataFrame
- Compare correlation robustness by testing Pearson, Spearman, and biweight midcorrelation on the same data to handle outliers
- Test multivariate normality and homogeneity assumptions before choosing parametric or non-parametric tests
- Compute power analysis and effect sizes for study design planning before data collection
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Pingouin is well-maintained, actively developed, has no security vulnerabilities, and fills a genuine gap: it wraps SciPy and Statsmodels with sensible defaults and comprehensive output. The GPL-3.0 license is standard for academic software and poses no barrier to research use. Install it if you do statistical testing in Python and want richer output than SciPy alone provides.
Install
pingouin on PyPI
Before you install
Low friction installation with a pure-Python wheel distribution. Active maintenance with a recent release (139 days ago) and steady community engagement. Requires modern Python (3.10+) and depends on established scientific libraries (NumPy, SciPy, Pandas, Statsmodels, Scikit-learn).
Requires Python 3.10 or later. Nine runtime dependencies (NumPy, SciPy, Pandas, Statsmodels, Scikit-learn, Matplotlib, Seaborn, Pandas-flavor, Tabulate) must be installed; pip handles this automatically.
License in practice
GPL-3.0 copyleft license means any derivative work or modification must also be released under GPL-3.0. This is permissive for research and internal use but restricts commercial redistribution without source disclosure.
Quickstart
pip install pingouin
import pingouin as pg
import numpy as np
np.random.seed(123)
x = np.random.normal(0, 1, 30)
y = np.random.normal(0, 1, 30)
result = pg.ttest(x, y)
print(result)Verify before relying
- Whether all statistical functions work equally well with missing data or require preprocessing
- Performance characteristics on large datasets (memory usage, computation time)
- Availability and completeness of circular statistics functions mentioned in description
Package facts
| License | GPL-3.0 copyleft |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 9 packagesmatplotlibnumpypandaspandas_flavorscikit-learnscipyseabornstatsmodelstabulate |
| Maintenance | Actively maintained 139 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 524,957 / month, #6,187 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: Science/ResearchOperating System :: MacOSOperating System :: POSIXOperating System :: UnixProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/Engineering :: Mathematics |
Evidence: pingouin-0.6.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “t-test anova correlation”
- pingouinPingouin provides a comprehensive statistical analysis toolkit for…
- anova-wifiCommunicate with Anova precision cookers over WiFi to read device…
- scikit-posthocsProvides post hoc statistical tests for pairwise multiple comparisons…
Give your agent the search over MCP, or paste the wish link into any chat.
More Mathematics packages
NetworkX provides data structures and algorithms for creating, analyzing, and manipulating graphs and networks, supporting everything from simple undirected graphs to complex directed and weighted networks.
kiwisolver is a Python binding to a fast C++ implementation of the Cassowary constraint solver, enabling you to solve systems of linear constraints and inequalities.
Install it if you need to solve constraint systems; skip it if you only need simple linear algebra.
SymPy is a Python library for symbolic mathematics, performing algebraic manipulation, calculus, equation solving, and mathematical expression simplification without numerical approximation.
ContourPy calculates contours of 2D quadrilateral grids using C++11 algorithms wrapped in Python, offering serial and multithreaded implementations without requiring Matplotlib as a dependency.
PyTorch provides GPU-accelerated tensor computation and automatic differentiation for building and training deep neural networks in Python.
onnxruntime loads and executes Open Neural Network Exchange (ONNX) models with a focus on inference performance across CPUs and accelerators.
Install it if you have ONNX models to run in production or development.
See also allpairspy · hyppo · scikit-posthocs · phik · bootstrapped · statsmodels · quantile-forest · forestci · diptest · psmpy