Kerpy Save

python code for kernel methods

Project README


python code framework for kernel methods in hypothesis testing. some code on kernel computation was adapted from

To set up as a package run in terminal:

python develop


Code for HSIC-based large-scale independence tests. The methods are described in:

Q. Zhang, S. Filippi, A. Gretton, and D. Sejdinovic, Large-Scale Kernel Methods for Independence Testing, Statistics and Computing, to appear, 2017. url

For an example use of the code, demonstrating how to run an HSIC-based large-scale independence test on either simulated data or data loaded from a file, see

To reproduce results from the paper, see,,


Code for feature-to-feature regression for a two-step conditional independence tests (i.e. testing for weak conditional independence). The methods are described in:

Q. Zhang, S. Filippi, S. Flaxman, and D. Sejdinovic, Feature-to-Feature Regression for a Two-Step Conditional Independence Test, UAI, 2017.

To reproduce results from the paper, see,, (the nodes names correspond to the varibales in Synthetic_DAGexample.csv file, to run it for Boston Housing Data (BH_prewhiten.csv) or Ozone Data (Ozone_prewhiten.csv) simply change the label names in the script.)

Open Source Agenda is not affiliated with "Kerpy" Project. README Source: oxcsml/kerpy
Open Issues
Last Commit
4 years ago

Open Source Agenda Badge

Open Source Agenda Rating