Multi-Label Classification in Python
Scikit-multilearn is a BSD-licensed library for multi-label classification that is built on top of the well-known scikit-learn ecosystem.
pip install scikit-multilearnScikit-multilearn provides many native Python multi-label classifiers classifiers.
Use expert knowledge or infer label relationships from your data to improve your model.
Embedd the label space to improve discriminative ability of your classifier.
Extend your Keras or pytorch neural networks to solve multi-label classification problems.
Scikit-multilearn is faster and takes much less memory than the standard stack of MULAN, MEKA & WEKA.
The licensing model follows scikit's BSD licence, to allow maximum interopability. Some libraries if used for label space division may incur GPL requirements.
Scikit-multilearn is faster and takes much less memory than the standard stack of MULAN, MEKA & WEKA.
Use expert knowledge or infer label relationships from your data to improve your model.
Missing a particular classifier which exists in the Java MEKA and WEKA stack? Now you can use it like a native scikit classifier!
Scikit-multilearn has over 82% test coverage and undergoes continous integration on Windows 10, OS X and Ubuntu.
Scikit-multilearn is compatible with the Scipy and scikit-learn stack. Use our classifiers with scikit, use scikit classifiers with our code.
Need help? Ask a question on Stack Overflow, our community will answer.
News
0.2.0 (released 2018-12-10)
A new feature release:
- first python implementation of multi-label SVM (MLTSVM)
- a general multi-label embedding framework with several embedders supported (LNEMLC, CLEMS)
- balanced k-means clusterer from HOMER implemented
- wrapper for Keras model use in scikit-multilearn
0.1.0 [stable] (released 2018-09-04)
Fix a lot of bugs and generally improve stability, cross-platform functionality standard and unit test coverage. This release has been tested with a large set of unit tests that work across Windows. Also, new features:
- multi-label stratification algorithm and stratification quality measures
- a robust reorganization of label space division, alongside with a working stochastic blockmodel approach and new underlying layer - graph builders that allow using graph models for dividing the label space based not just on label co-occurence but on any kind of network relationships between labels you can come up with
- meka wrapper works fully cross-platform now, including windows 10
- multi-label data set downloading and load/save functionality brought in, like sklearn's dataset
- kNN models support sparse input
- MLARAM models support sparse input
- BSD-compatible label space partitioning via NetworkX
- dependence on GPL libraries made optional
- working predict_proba added for label space partitioning methods
- MLARAM moved to from neurofuzzy to adapt
- test coverage increased to 94%
- Classifier Chains allow specifying the chain order
- lots of documentation updates