Skip to main content
Warning: You are using the test version of PyPI. This is a pre-production deployment of Warehouse. Changes made here affect the production instance of TestPyPI (
Help us improve Python packaging - Donate today!

Elastic-net regularized generalized linear models.

Project Description

A python implementation of elastic-net regularized generalized linear models

|License| |Travis| |Codecov| |Gitter|

`Generalized linear
models <>`__ are
well-established tools for regression and classification and are widely
applied across the sciences, economics, business, and finance. They are
uniquely identifiable due to their convex loss and easy to interpret due
to their point-wise non-linearities and well-defined noise models.

In the era of exploratory data analyses with a large number of predictor
variables, it is important to regularize. Regularization prevents
overfitting by penalizing the negative log likelihood and can be used to
articulate prior knowledge about the parameters in a structured form.

Despite the attractiveness of regularized GLMs, the available tools in
the Python data science eco-system are highly fragmented. More

- `statsmodels <>`__
provides a wide range of link functions but no regularization.
- `scikit-learn <>`__
provides elastic net regularization but only for linear models.
- `lightning <>`__
provides elastic net and group lasso regularization, but only for
linear and logistic regression.

**Pyglmnet** is a response to this fragmentation. Here are some

- Pyglmnet provides a wide range of noise models (and paired canonical
link functions): ``'gaussian'``, ``'binomial'``, ``'multinomial'``,
'``poisson``', and ``'softplus'``.

- It supports a wide range of regularizers: ridge, lasso, elastic net,
lasso <>`__,
and `Tikhonov
regularization <>`__.

- Pyglmnet's API is designed to be compatible with scikit-learn, so you
can deploy ``Pipeline`` tools such as ``GridSearchCV()`` and

- We follow the same approach and notations as in `Friedman, J.,
Hastie, T., & Tibshirani, R.
(2010) <>`__ and the
accompanying widely popular `R
package <>`__.

- We have implemented a cyclical coordinate descent optimizer with
Newton update, active sets, update caching, and warm restarts. This
optimization approach is identical to the one used in R package.

- A number of Python wrappers exist for the R glmnet package (e.g.
`here <>`__ and
`here <>`__) but in contrast to
these, Pyglmnet is a pure python implementation. Therefore, it is
easy to modify and introduce additional noise models and regularizers
in the future.


Here is table comparing ``pyglmnet`` against ``scikit-learn``'s
``linear_model``, ``statsmodels``, and ``R``.

The numbers below are run time (in milliseconds) to fit a :math:`1000`
samples x :math:`100` predictors sparse matrix (density :math:`0.05`).
This was done on a c. 2011 Macbook Pro, so your numbers may vary.

| distr | pyglmnet | scikit-learn | statsmodels | R |
| gaussian | 6.8 | 1.2 | 29.8 | 10.3 |
| binomial | 16.3 | 4.5 | 89.3 | -- |
| poisson | 5.8 | -- | 117.2 | 156.1 |

We provide a function called ``BenchMarkGLM()`` in ``pyglmnet.datasets``
if you would like to run these benchmarks yourself, but you need to take
care of the dependencies: ``scikit-learn``, ``Rpy2``, and
``statsmodels`` yourself.


Now ``pip`` installable!

.. code:: bash

$ pip install pyglmnet

Manual installation instructions below:

Clone the repository.

.. code:: bash

$ git clone

Install ``pyglmnet`` using ```` as follows

.. code:: bash

$ python develop install

Getting Started

Here is an example on how to use the ``GLM`` estimator.

.. code:: python

import numpy as np
import scipy.sparse as sps
from sklearn.preprocessing import StandardScaler
from pyglmnet import GLM

# create an instance of the GLM class
glm = GLM(distr='poisson')

n_samples, n_features = 10000, 100

# sample random coefficients
beta0 = np.random.normal(0.0, 1.0, 1)
beta = sps.rand(n_features, 1, 0.1)
beta = np.array(beta.todense())

# simulate training data
X_train = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_train = glm.simulate(beta0, beta, X_train)

# simulate testing data
X_test = np.random.normal(0.0, 1.0, [n_samples, n_features])
y_test = glm.simulate(beta0, beta, X_test)

# fit the model on the training data
scaler = StandardScaler().fit(X_train), y_train)

# predict using fitted model on the test data
yhat_test = glm.predict(scaler.transform(X_test))

# score the model
deviance = glm.score(X_test, y_test)

`More pyglmnet examples and use
cases <>`__.


Here is an `extensive
tutorial <>`__ on GLMs,
optimization and pseudo-code.

Here are
`slides <>`__ from a
recent talk at `PyData Chicago
2016 <>`__,
corresponding `tutorial
notebooks <>`__ and a
`video <>`__.

How to contribute?

We welcome pull requests. Please see our `developer documentation
page <>`__ for more


- `Pavan Ramkumar <http:/>`__


- `Mainak Jas <http:/>`__
- `Titipat Achakulvisut <http:/>`__
- `Aid Idrizović <http:/>`__
- `Vinicius Marques <http:/>`__
- `Daniel Acuna <http:/>`__
- `Hugo Fernandes <http:/>`__
- `Eva Dyer <http:/>`__
- `Matt Antalek <>`__


- `Konrad Kording <>`__ for funding and support
- `Sara
Solla <>`__
for masterful GLM lectures


MIT License Copyright (c) 2016 Pavan Ramkumar

.. |License| image::
.. |Travis| image::
.. |Codecov| image::
.. |Gitter| image::
Release History

Release History

This version
History Node


Download Files

Download Files

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

File Name & Checksum SHA256 Checksum Help Version File Type Upload Date
pyglmnet-1.0.3.tar.gz (21.5 kB) Copy SHA256 Checksum SHA256 Source Nov 19, 2016

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting