Welcome to scikit-multilearn’s documentation!

Scikit-multilearn is a BSD-licensed library for multi-label classification that is built on top of the well-known scikit-learn ecosystem.

How do I start?

If you are new to multi-label classification alltogether, start with the Concepts chapter which goes through the concepts and shows where different methods fit.

If you’ve already performed multi-label classification or you’ve used scikit-learn before, you should:

  1. read about The data format for multi-label classification in scikit-multilearn
  2. learn about Loading and generating multi-label datasets
  3. start the fun with classification by Selecting a multi-label classifier
  4. see how you can improve your results by Estimating parameters

If you came here to use the wrapper around the well known meka library, there’s an example of how to do this in: Using the meka wrapper.

If you are a developer and want to join scikit-multilearn, here you can find out how to:

Some candidates for implementation are listed in the Junior Jobs section of the website if you’d like to help.

Indices and tables