Welcome to scikit-multilearn-ng’s documentation!

scikit-multilearn-ng is a Python module capable of performing multi-label learning tasks, building on the legacy of scikit-multilearn. It integrates seamlessly with scientific Python packages like numpy and scipy and follows a familiar API akin to scikit-learn.

PyPI Version License

Features

  • Native Python Implementation: Variety of multi-label classification algorithms implemented natively in Python.

  • Interface to Meka: Provides access to all methods available in MEKA, MULAN, and WEKA via a Meka wrapper class.

  • Integration with numpy and scikit: Use scikit-learn’s base classifiers and benefit from numpy’s computational efficiency.

Installation & Dependencies

To install scikit-multilearn-ng:

$ pip install scikit-multilearn-ng

For the latest development version:

$ git clone https://github.com/scikit-multilearn-ng/scikit-multilearn-ng.git
$ cd scikit-multilearn-ng
$ python setup.py install

Optional dependencies can be installed as follows:

$ pip install scikit-multilearn-ng[gpl,keras,meka]

For installing openNE:

$ pip install 'openne @ git+https://github.com/thunlp/OpenNE.git@master#subdirectory=src'

Note: Installing GPL licensed graphtool is more complex. Please refer to the graphtool install instructions.

Basic Usage

# Import BinaryRelevance from skmultilearn
from skmultilearn.problem_transform import BinaryRelevance
from sklearn.svm import SVC

# Setup the classifier
classifier = BinaryRelevance(classifier=SVC(), require_dense=[False, True])

# Train
classifier.fit(X_train, y_train)

# Predict
predictions = classifier.predict(X_test)

To see more examples, please refer to the example usage page.

More examples and use cases will be added soon.

Contributing

Contributions to scikit-multilearn-ng are welcome! Here are some ways to contribute:

  • Reporting or fixing bugs

  • Requesting features

  • Demonstrating use-cases

  • Updating documentation

Indices and tables

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,
}