Large-scale sparse linear classification, regression and ranking in Python
lightning is a library for large-scale linear classification, regression and ranking in Python.
- follows the scikit-learn API conventions
- supports natively both dense and sparse data representations
- computationally demanding parts implemented in Cython
- primal coordinate descent
- dual coordinate descent (SDCA, Prox-SDCA)
- SGD, AdaGrad, SAG, SAGA, SVRG
Example that shows how to learn a multiclass classifier with group lasso penalty on the News20 dataset (c.f., Blondel et al. 2013):
from sklearn.datasets import fetch_20newsgroups_vectorized from lightning.classification import CDClassifier # Load News20 dataset from scikit-learn. bunch = fetch_20newsgroups_vectorized(subset="all") X = bunch.data y = bunch.target # Set classifier options. clf = CDClassifier(penalty="l1/l2", loss="squared_hinge", multiclass=True, max_iter=20, alpha=1e-4, C=1.0 / X.shape, tol=1e-3) # Train the model. clf.fit(X, y) # Accuracy print(clf.score(X, y)) # Percentage of selected features print(clf.n_nonzero(percentage=True))
lightning requires Python >= 2.7, setuptools, Numpy >= 1.3, SciPy >= 0.7 and scikit-learn >= 0.15. Building from source also requires Cython and a working C/C++ compiler. To run the tests you will also need nose >= 0.10.
Precompiled binaries for the stable version of lightning are available for the main platforms and can be installed using pip:
pip install sklearn-contrib-lightning
conda install -c conda-forge sklearn-contrib-lightning
The development version of lightning can be installed from its git repository. In this case it is assumed that you have the git version control system, a working C++ compiler, Cython and the numpy development libraries. In order to install the development version, type:
git clone https://github.com/scikit-learn-contrib/lightning.git cd lightning python setup.py build sudo python setup.py install