Projects / Milk


Milk is a machine learning toolkit in Python. Its focus is on supervised classification with several classifiers available: SVMs (based on libsvm), k-NN, random forests, and decision trees. It also performs feature selection. These classifiers can be combined in many ways to form different classification systems. For unsupervised learning, milk supports k-means clustering and affinity propagation.

Operating Systems

RSS Recent releases

  •  19 Jun 2013 17:48

Release Notes: This release adds fixes compilation on a few older compilers and adds some new functionality on Multidimensional scaling.

  •  17 Jan 2013 22:08

Release Notes: The most important change is the inclusion of eigen in the source distribution, which makes milk easier to compile. In addition, this release adds subspace projection k-nearest neighbours and mds_dists functionality.

  •  08 Nov 2012 02:44

Release Notes: This release adds coordinate descent-based LASSO and makes SVM classification much faster (a 2.5x speedup on the yeast UCI dataset).

  •  22 Sep 2012 22:33

Release Notes: This release fixes a bug in adaboost and adds a few extra small functions such as zscoring on multiple axes, Euclidean multi-dimensional scaling, and tree-based multi-class learning.

  •  16 Jan 2012 20:45

Release Notes: Interfaces are more consistent (learners ignore arguments they cannot use and the default model supports the apply_many method). There are many improvements and bugfixes.


Project Spotlight


A pure Java Git solution.


Project Spotlight


A collection of tools for dumping and mastering PlayStation 1 CD-ROM images.