Package containing functions to manage Error Distribution Rules

Projeto Final de Aprendizado Descritivo @ DCC/UFMG

Subgroup-selective knockoff filter

Subgroup discovery method is applied to random forest in order to select subgroups of entities in the dataset, which seems to be able to approximate with a single random tree. This provides us with the interpretable subgroups of dataset, which makes the random forest model less black-box than usual.

This repository reproduces the experiments of the paper "Discovering outstanding subgroup lists for numeric targets using MDL" published at ECML-PKDD.

Code for the paper "Using Constraints to Discover Sparse and Alternative Subgroup Descriptions".

Redescriptional model mining in python

A heavily modified Exceptional Preferences Mining version of the Python Exceptional Model Mining implemenation by MathynS supporting both an Apriori as well as a Best First algorithm for mining subgroups featuring exceptional preferences.

R code for the discovery of COVID-19 subgroups by symptoms and comorbidities.

A machine learning python package for learning ensembles of subgroups for predictive tasks.

subgroups is a python library which contains a collection of subgroup discovery algorithms and other data analysis utilities.