Skip to content

AnchorBlues/GroupLasso

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

GroupLasso

Group Lasso package for Python.

Installation Guide

Using pip

The easiest way to install GroupLasso is using pip

pip install GroupLasso

Building from source

Run the following commands:

git clone https://github.com/AnchorBlues/GroupLasso.git
cd GroupLasso
python setup.py install

Getting started

Here is the GroupLassoRegressor model:

from grouplasso import GroupLassoRegressor

Create sample dataset:

import numpy as np
np.random.seed(0)
X = np.random.randn(10, 3)
# target variable is strongly correlated with 0th feature.
y = X[:, 0] + np.random.randn(10) * 0.1

Set group_ids, which specify group membership:

# 0th feature and 1st feature are the same group.
group_ids = np.array([0, 0, 1])

You can now train Group Lasso:

model = GroupLassoRegressor(group_ids=group_ids, random_state=42, verbose=False, alpha=1e-1)
model.fit(X, y)

Note that all the members of a particular group are either selected(coef_ != 0) or not selected(coef_ == 0).

model.coef_
# array([ 0.84795715, -0.01193528, -0.        ])

About

Group Lasso package for Python.

Resources

License

Stars

Watchers

Forks

Packages

No packages published