MKLpy is a framework for Multiple Kernel Learning (MKL) inspired by the scikit-learn project.
This package contains:
- the implementation of some MKL algorithms, such as EasyMKL;
- tools to operate on kernels, such as normalization, centering, summation, average...;
- metrics, such as kernel_alignment, radius of Minimum Enclosing Ball, margin between classes, spectral ratio...;
- kernel functions, including boolean kernels (disjunctive, conjunctive, DNF, CNF) and string kernels (spectrum, fixed length and all subsequences).
The 'examples' folder contains useful snippets of code.
MKLpy is also available on PyPI:
pip install MKLpy
To work properly, MKLpy requires:
resource | website |
---|---|
numpy | https://www.numpy.org/ |
scikit-learn | https://scikit-learn.org/stable/ |
cvxopt | https://cvxopt.org/ |
The folder examples contains several scripts and snippets of codes to show the potentialities of MKLpy. The examples show how to train a classifier, how to process data, and how to use kernel functions. Currently, we ware working for a complete documentation.
MKLpy is under development! We are working to integrate several features, including:
- further MKL algorithms, such as GRAM, MEMO, and SimpleMKL;
- more kernels for structured data;
- incremental generators of kernels;
- tensorflow as backend !