CorrMapper is finally finished

danielhomola Blog 1 Comment

After 2.5 half years of work, CorrMapper is finished. In the past 6 months, I weeded out a lot of bugs and improved both network explorer with lots of features. The paper is in preparation and should be submitted in the coming weeks. I’ll make the source code available as soon as the paper is out. Until then, give it …

danielhomolaCorrMapper is finally finished

CorrMapper (main project of my phd) is ready(ish)

danielhomola Blog Leave a Comment

My PhD is entitled: Integration and visualisation of clinical-metabolic datasets for medical-decision making. So after several initial projects, in the past 1.5 years I’ve been working on a general system for the integration, exploration and visualisation of complex biological datasets. The problem with such an ambitious and broad PhD title is that it can fragment your attention and you can quickly …

danielhomolaCorrMapper (main project of my phd) is ready(ish)

MIFS – parallelized Mutual Information based Feature Selection module

danielhomola Blog Leave a Comment

TL,DR: I wrapped up three mutual information based feature selection methods in a scikit-learn like module. You can find it on my GitHub. It is very easy to use, you can run the example.py or import it into your project and apply it to your data like any other scikit-learn method.

Mutual information based filter methods The following bit is adopted …

danielhomolaMIFS – parallelized Mutual Information based Feature Selection module

BorutaPy – an all relevant feature selection method

danielhomola Blog 8 Comments

TL,DR: There’s a pretty clever all-relevant feature selection method, which was conceived by Witold R. Rudnicki and developed by Miron B. Kursa at the ICM UW. Here is its website. While working on my PhD project I read their paper, really liked the method, but didn’t quite like how slow it was. It’s based on R’s Random Forest implementation which runs …

danielhomolaBorutaPy – an all relevant feature selection method