pyfixest
Fast high dimensional fixed effect estimation following syntax of the fixest R package.
Decision gist · record as of 2026-08-14
Yes, if you work in econometrics or causal inference with panel data or high-dimensional fixed effects. PyFixest is actively maintained, has no known vulnerabilities, and offers a mature feature set (OLS, IV, GLMs, DiD, quantile regression, robust inference) with GPU acceleration available. The MIT license is permissive. Install friction is moderate due to 10 dependencies, but wheels are widely available. Not worth installing if your regression problems are low-dimensional or you don't need the specialized econometric tools.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Optional GPU acceleration requires PyTorch with CUDA support installed separately.
- Medium install friction: 10 runtime dependencies including numpy, pandas, scipy, and specialized libraries like formulaic and narwhals.
License · maintenance · safety
MIT (permissive) — MIT license (permissive) places no restrictions on use, modification, or distribution in commercial or private projects.
last release 2026-06-11 (64 days) · last repo commit 2026-08-12 · 346 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 81,153 downloads/mo, #14,245 on PyPI
Alternatives
Verify before relying
import pyfixest as pf
data = pf.get_data()
result = pf.feols("Y ~ X1 | f1 + f2", data=data)
result.summary()- Whether the torch LSMR backend (GPU acceleration) is production-ready or still experimental beyond the deprecation note.
- Performance characteristics of the default Rust within LSMR backend compared to the MAP backend on typical datasets.
- Whether wildboottest integration is included in the base install or requires a separate optional dependency.
What it is and what it does
PyFixest is a Python implementation of econometric fixed effects regression that closely mirrors the R package fixest's API and defaults. It handles estimation of linear models (OLS, WLS), instrumental variables (IV), generalized linear models (Poisson, logit, probit), and quantile regression in the presence of high-dimensional fixed effects—a common problem in applied econometrics where naive approaches become computationally infeasible. The package offers multiple demeaning backends (MAP, within LSMR on CPU, and torch LSMR on GPU) to trade off speed and memory usage.
Beyond estimation, PyFixest provides a full suite of econometric tools: robust and cluster-robust variance-covariance estimators, wild cluster bootstrap inference, multiple hypothesis corrections, randomization inference, and specialized estimators like the causal cluster variance estimator (CCV). It also supports difference-in-differences designs (TWFE, Did2s, local projections, Sun-Abraham event studies), regression decomposition, and publication-ready table generation via Great Tables or LaTeX. The 10 runtime dependencies (numpy, pandas, scipy, formulaic, joblib, narwhals, seaborn, tabulate, tqdm, maketables) provide the numerical, data manipulation, and visualization infrastructure.
Use it for
- Estimate causal effects in panel data using difference-in-differences or event study designs with multiple fixed effects.
- Perform robust inference on high-dimensional models where standard OLS demeaning is computationally prohibitive.
- Generate publication-ready regression tables with cluster-robust standard errors and multiple hypothesis corrections.
- Run quantile regression with fixed effects to study heterogeneous treatment effects across the outcome distribution.
- Conduct wild cluster bootstrap inference for valid inference under arbitrary cluster correlation structures.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you work in econometrics or causal inference with panel data or high-dimensional fixed effects.
PyFixest is actively maintained, has no known vulnerabilities, and offers a mature feature set (OLS, IV, GLMs, DiD, quantile regression, robust inference) with GPU acceleration available. The MIT license is permissive. Install friction is moderate due to 10 dependencies, but wheels are widely available. Not worth installing if your regression problems are low-dimensional or you don't need the specialized econometric tools.
Install
pyfixest on PyPI
Before you install
Medium install friction: 10 runtime dependencies including numpy, pandas, scipy, and specialized libraries like formulaic and narwhals. Wheels available for Python 3.10–3.14 across Linux, macOS, and Windows. Active maintenance with a release 64 days ago.
Requires Python 3.10 or later. Optional GPU acceleration requires PyTorch with CUDA support installed separately.
License in practice
MIT license (permissive) places no restrictions on use, modification, or distribution in commercial or private projects.
Quickstart
import pyfixest as pf
data = pf.get_data()
result = pf.feols("Y ~ X1 | f1 + f2", data=data)
result.summary()Verify before relying
- Whether the torch LSMR backend (GPU acceleration) is production-ready or still experimental beyond the deprecation note.
- Performance characteristics of the default Rust within LSMR backend compared to the MAP backend on typical datasets.
- Whether wildboottest integration is included in the base install or requires a separate optional dependency.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 10 packagesformulaicjoblibmaketablesnarwhalsnumpypandasscipyseaborntabulatetqdm |
| Maintenance | Actively maintained 64 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 81,153 / month, #14,245 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: Science/ResearchLicense :: OSI Approved :: MIT LicenseOperating System :: MacOS :: MacOS XOperating System :: Microsoft :: WindowsOperating System :: POSIXProgramming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: RustTopic :: Scientific/Engineering :: Mathematics |
Evidence: pyfixest-0.60.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; pyfixest-0.60.0-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl; pyfixest-0.60.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl; pyfixest-0.60.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl; pyfixest-0.60.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl; pyfixest-0.60.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pyfixest-0.60.0-cp310-cp310-musllinux_1_2_aarch64.whl; pyfixest-0.60.0-cp310-cp310-musllinux_1_2_armv7l.whl; pyfixest-0.60.0-cp310-cp310-musllinux_1_2_i686.whl; pyfixest-0.60.0-cp310-cp310-musllinux_1_2_x86_64.whl; pyfixest-0.60.0-cp310-cp310-win_amd64.whl; pyfixest-0.60.0-cp311-cp311-macosx_10_12_x86_64.whl; pyfixest-0.60.0-cp311-cp311-macosx_11_0_arm64.whl; pyfixest-0.60.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl; pyfixest-0.60.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl; pyfixest-0.60.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl; pyfixest-0.60.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl; pyfixest-0.60.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl; pyfixest-0.60.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pyfixest-0.60.0-cp311-cp311-musllinux_1_2_aarch64.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 › “high-dimensional regression demeaning”
- pyfixestPyFixest performs fast high-dimensional fixed effects regression in…
- linearmodelsProvides panel regression, instrumental variable estimators, system…
- quantile-forestQuantile regression forests for estimating conditional quantiles and…
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 linearmodels · pyhdfe · quantile-forest · econml · glum · rdrobust · spglm · polars-ols · spreg · statsmodels