lme-python

Python bindings for lme-rs: linear, generalized linear, and nonlinear mixed-effects models with lme4-style formulas. Fitting runs in the same Rust engine used by the crate.

Python guide · Examples · Workflow scope

Install

python -m pip install lme-python

Install lme-python, import lme_python. Polars is a package dependency. A compatible binary wheel does not require a Rust toolchain or an R installation.

Check the selected version's PyPI files for your Python interpreter, OS, and architecture. The release workflow builds CPython 3.10 wheels; source-build CI tests Python 3.10–3.13. Those tests do not imply that a wheel is published for each tested interpreter. If pip falls back to a source build, follow the source setup.

Quick start

This example needs no repository files:

import lme_python
import polars as pl

data = pl.DataFrame(
    {
        "y": [10.0, 12.0, 13.0, 15.0, 9.0, 11.0, 14.0, 17.0, 8.0, 10.0, 12.0, 14.0],
        "x": [0.0, 1.0, 2.0, 3.0] * 3,
        "group": ["a"] * 4 + ["b"] * 4 + ["c"] * 4,
    }
)
fit = lme_python.lmer("y ~ x + (1 | group)", data=data, reml=True)
print(fit.summary())
print(fit.predict(data))

The formula estimates a shared intercept and slope plus a random intercept for each group. The small synthetic dataset is an API demonstration. predict returns fixed-effects predictions; use predict_conditional when you want the fitted group effects.

Continue your analysis

The bindings expose lm, lmer, glmer, and nlmer, along with prediction, intervals, simulation, grouped cross-validation, bootstrap refits, ANOVA, contrasts, and LMM estimated marginal means.

Python guide: data requirements, fitting, inference, and structured results.
Type reference: function signatures and result fields.
Supported workflows: model-specific scope and limitations.
Troubleshooting: installation, data, convergence, and prediction problems.
Changelog: release history. Use the matching repository tag for version-specific docs.

Development

See Contributing for the locked development environment and extension build. After building, use uv run --no-sync for examples and tests.

task consumer:smoke builds a wheel, verifies it in isolated environments, and runs portable examples against the installed artifact.

Repeated responses and fit diagnostics

Prepare once when fitting several response vectors against the same design:

prepared = lme_python.prepare_lmer("Reaction ~ Days + (Days | Subject)", data)
control = lme_python.FitControl(max_iterations=2000, require_convergence=True)
fit = prepared.fit(y=data["Reaction"].to_list(), reml=True, control=control)
print(fit.diagnostics)

prepare_lmer(..., weights=...) retains observation precision weights. Responses must contain finite values and match the original row count. Offsets are applied exactly once. prepare_glmer also supports prepared.fit(y=..., control=...). The existing fit_prepared(..., y=..., control=...) and fit_prepared_glmer functions remain available.

FitControl accepts max_iterations, tolerance, max_inner_iterations, starting covariance parameters start, and require_convergence. The iteration limit is per outer search stage. Nonlinear fits use max_inner and max_outer_iters instead. Inspect converged and diagnostics before interpreting a fit; diagnostics report termination, iteration counts, objective value, and requested/effective quadrature.

Conversion serializes columns needed by an explicit formula. Dot formulas retain all columns for expansion. Native fitting releases the interpreter lock; custom Python nonlinear mean callbacks reacquire it while evaluating Python code. Bootstrap generates each response as its worker needs it, retaining only replicate summaries. Thread counts no longer change BLAS/OpenMP process settings. License-File: THIRD_PARTY_NOTICES.md License-File: RELINKING.md License-File: Apache-2.0.txt License-File: BSD-3-Clause-OpenBLAS.txt License-File: GPL-2.0-or-later.txt License-File: LGPL-2.1-only.txt License-File: Intel-Simplified-Software-License.txt

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lme_python-0.2.3.tar.gz (3.6 MB view details)

Uploaded Sep 9, 2026 Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

lme_python-0.2.3-cp310-cp310-win_amd64.whl (21.4 MB view details)

Uploaded Sep 9, 2026 CPython 3.10Windows x86-64

lme_python-0.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (10.0 MB view details)

Uploaded Sep 9, 2026 CPython 3.10manylinux: glibc 2.17+ x86-64

lme_python-0.2.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (6.3 MB view details)

Uploaded Sep 9, 2026 CPython 3.10manylinux: glibc 2.17+ ARM64

lme_python-0.2.3-cp310-cp310-macosx_11_0_arm64.whl (5.3 MB view details)

Uploaded Sep 9, 2026 CPython 3.10macOS 11.0+ ARM64

lme_python-0.2.3-cp310-cp310-macosx_10_12_x86_64.whl (5.5 MB view details)

Uploaded Sep 9, 2026 CPython 3.10macOS 10.12+ x86-64

File details

Details for the file lme_python-0.2.3.tar.gz.

File metadata

Download URL: lme_python-0.2.3.tar.gz
Upload date: Sep 9, 2026
Size: 3.6 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for lme_python-0.2.3.tar.gz
Algorithm	Hash digest
SHA256	`c3a4b5887ba54c8b260de9d352c4c2084ad665f4fb84fcd80635129f901068f1`
MD5	`97198485b6e9b5fc8db539572f138f5f`
BLAKE2b-256	`179c320e34c5f13a819e9c68105e768a7bdf3f72b69387c6dc53877f698d0af5`

See more details on using hashes here.

Provenance

The following attestation bundles were made for lme_python-0.2.3.tar.gz:

Publisher: python-release.yml on x4g4p3x/lme-rs

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: lme_python-0.2.3.tar.gz
- Subject digest: c3a4b5887ba54c8b260de9d352c4c2084ad665f4fb84fcd80635129f901068f1
- Sigstore transparency entry: 2773753236
- Sigstore integration time: Sep 9, 2026
Source repository:
- Permalink: x4g4p3x/lme-rs@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Branch / Tag: refs/heads/master
- Owner: https://github.com/x4g4p3x
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: python-release.yml@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Trigger Event: workflow_dispatch

File details

Details for the file lme_python-0.2.3-cp310-cp310-win_amd64.whl.

File metadata

Download URL: lme_python-0.2.3-cp310-cp310-win_amd64.whl
Upload date: Sep 9, 2026
Size: 21.4 MB
Tags: CPython 3.10, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for lme_python-0.2.3-cp310-cp310-win_amd64.whl
Algorithm	Hash digest
SHA256	`ed0fe08b71f6a3ac553d0d2aa718e7927e3147d954197d4865342ae34b3ec0d2`
MD5	`fa8a3920d0a2e220c2b6f0f77bd1b584`
BLAKE2b-256	`333393870e5316513fd96f1f294943489f4c1b22bf89b1b09bc5e26e2c3c55ff`

See more details on using hashes here.

Provenance

The following attestation bundles were made for lme_python-0.2.3-cp310-cp310-win_amd64.whl:

Publisher: python-release.yml on x4g4p3x/lme-rs

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: lme_python-0.2.3-cp310-cp310-win_amd64.whl
- Subject digest: ed0fe08b71f6a3ac553d0d2aa718e7927e3147d954197d4865342ae34b3ec0d2
- Sigstore transparency entry: 2773753445
- Sigstore integration time: Sep 9, 2026
Source repository:
- Permalink: x4g4p3x/lme-rs@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Branch / Tag: refs/heads/master
- Owner: https://github.com/x4g4p3x
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: python-release.yml@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Trigger Event: workflow_dispatch

File details

Details for the file lme_python-0.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: lme_python-0.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Sep 9, 2026
Size: 10.0 MB
Tags: CPython 3.10, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for lme_python-0.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`08b4db0b3b13b523865785a2a6e05544bf7dbbe2009a9f47d71c8e9d04505805`
MD5	`73c48d6ca87aa57fc26dd39878840acb`
BLAKE2b-256	`9df8aa5477c413e1778ebf8183801cd057c15c43bc4bf75ba8c6ed6116d11d00`

See more details on using hashes here.

Provenance

The following attestation bundles were made for lme_python-0.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: python-release.yml on x4g4p3x/lme-rs

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: lme_python-0.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 08b4db0b3b13b523865785a2a6e05544bf7dbbe2009a9f47d71c8e9d04505805
- Sigstore transparency entry: 2773753403
- Sigstore integration time: Sep 9, 2026
Source repository:
- Permalink: x4g4p3x/lme-rs@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Branch / Tag: refs/heads/master
- Owner: https://github.com/x4g4p3x
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: python-release.yml@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Trigger Event: workflow_dispatch

File details

Details for the file lme_python-0.2.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

Download URL: lme_python-0.2.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Upload date: Sep 9, 2026
Size: 6.3 MB
Tags: CPython 3.10, manylinux: glibc 2.17+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for lme_python-0.2.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm	Hash digest
SHA256	`1bd8e2e669440955f2fdb31b35dacce721f7de138621e278d3e8c85ad6635ff2`
MD5	`d07f432fb2619656fbaa16418fbfa98e`
BLAKE2b-256	`872c78660e981286adcd3b4615713b05cdf9eb5ce38b89b7e6ad42e00040af73`

See more details on using hashes here.

Provenance

The following attestation bundles were made for lme_python-0.2.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl:

Publisher: python-release.yml on x4g4p3x/lme-rs

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: lme_python-0.2.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
- Subject digest: 1bd8e2e669440955f2fdb31b35dacce721f7de138621e278d3e8c85ad6635ff2
- Sigstore transparency entry: 2773753333
- Sigstore integration time: Sep 9, 2026
Source repository:
- Permalink: x4g4p3x/lme-rs@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Branch / Tag: refs/heads/master
- Owner: https://github.com/x4g4p3x
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: python-release.yml@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Trigger Event: workflow_dispatch

File details

Details for the file lme_python-0.2.3-cp310-cp310-macosx_11_0_arm64.whl.

File metadata

Download URL: lme_python-0.2.3-cp310-cp310-macosx_11_0_arm64.whl
Upload date: Sep 9, 2026
Size: 5.3 MB
Tags: CPython 3.10, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for lme_python-0.2.3-cp310-cp310-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`d54639c2b1a7152c7d118b1949aa7f52074150807ecf030c55eeb31f07f9d20a`
MD5	`a7956a570f6d10caf9d54d9b85054993`
BLAKE2b-256	`956088d86720b6106808223d487c63be85e317d9b52021a5b0e9159bf08deb80`

See more details on using hashes here.

Provenance

The following attestation bundles were made for lme_python-0.2.3-cp310-cp310-macosx_11_0_arm64.whl:

Publisher: python-release.yml on x4g4p3x/lme-rs

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: lme_python-0.2.3-cp310-cp310-macosx_11_0_arm64.whl
- Subject digest: d54639c2b1a7152c7d118b1949aa7f52074150807ecf030c55eeb31f07f9d20a
- Sigstore transparency entry: 2773753291
- Sigstore integration time: Sep 9, 2026
Source repository:
- Permalink: x4g4p3x/lme-rs@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Branch / Tag: refs/heads/master
- Owner: https://github.com/x4g4p3x
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: python-release.yml@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Trigger Event: workflow_dispatch

File details

Details for the file lme_python-0.2.3-cp310-cp310-macosx_10_12_x86_64.whl.

File metadata

Download URL: lme_python-0.2.3-cp310-cp310-macosx_10_12_x86_64.whl
Upload date: Sep 9, 2026
Size: 5.5 MB
Tags: CPython 3.10, macOS 10.12+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for lme_python-0.2.3-cp310-cp310-macosx_10_12_x86_64.whl
Algorithm	Hash digest
SHA256	`afc059fdd9eebfffaf14820e3f2085f20ce9f82192960d84aa79befd2c70a353`
MD5	`a14845dbe08cce4d163cae6b31a2de93`
BLAKE2b-256	`f6de4e1c40a0d79232ee3d9ccb4ccab8423972c6b12be42fb6dbb8b834272aff`

See more details on using hashes here.

Provenance

The following attestation bundles were made for lme_python-0.2.3-cp310-cp310-macosx_10_12_x86_64.whl:

Publisher: python-release.yml on x4g4p3x/lme-rs

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: lme_python-0.2.3-cp310-cp310-macosx_10_12_x86_64.whl
- Subject digest: afc059fdd9eebfffaf14820e3f2085f20ce9f82192960d84aa79befd2c70a353
- Sigstore transparency entry: 2773753379
- Sigstore integration time: Sep 9, 2026
Source repository:
- Permalink: x4g4p3x/lme-rs@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Branch / Tag: refs/heads/master
- Owner: https://github.com/x4g4p3x
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: python-release.yml@4b9d52a8b3d29df811135e1486475a68db5d49f7
- Trigger Event: workflow_dispatch