License

Scikit-multilearn-ng follows the widely employed copyleft licensing of the scikit community and is licensed BSD 2-Clause “Simplified” License. You can:

• Use, copy and distribute the unmodified source or binary forms of the licensed program

• Use, copy and distribute modified source or binary forms of the licensed program, provided that all distributed copies are accompanied by the license

Learn mode

GPL library dependency

Some of the sub-functionalities of the library uses and depends on GPL-licensed libraries:

• skmultilearn.cluster.graphtool depends on GPL licensed python-graphtool module for Stochastic Blockmodel functionality

• skmultilearn.cluster.igraph depends on GPL licensed python-igraph module for community detection methods

Using any of these modules incurs GPL on your codebase, thus for commercial purposes for network-based label space division you should be using the skmultilearn.cluster.networkx module which is depends on the well known BSD-licensed liibrary NetworkX.

Note that none of these libraries are installed by default.

---

Cite us

If you use scikit-multilearn-ng in your research and publish it, please consider citing scikit-multilearn:

@ARTICLE{2017arXiv170201460S,
    author = {{Szyma{'n}ski}, P. and {Kajdanowicz}, T.},
    title = "{A scikit-based Python environment for performing multi-label classification}",
    journal = {ArXiv e-prints},
    archivePrefix = "arXiv",
    eprint = {1702.01460},
    primaryClass = "cs.LG",
    keywords = {Computer Science - Learning, Computer Science - Mathematical Software},
    year = 2017,
    month = feb,
}