gitlab-mbq.r-universe.dev

[mbq] Boruta 10.0.0

m@mbq.me (Miron Bartosz Kursa) — Sat, 22 Aug 2026 17:17:55 GMT

An all relevant feature selection wrapper algorithm. It finds relevant features by comparing original attributes' importance with importance achievable at random, estimated using their permuted copies (shadows).

[mbq] fru 1.0.0

m@mbq.me (Miron Bartosz Kursa) — Wed, 19 Aug 2026 22:54:05 GMT

Yet another implementation of the Random Forest method by Breiman (2001) , written in Rust and tailored towards stability, correctness, efficiency and scalability on modern multi-core machines. Handles both classification and regression, as well as provides permutation feature importance via a novel, highly optimised algorithm.

[mbq] praznik 13.0.0

m@mbq.me (Miron B. Kursa) — Wed, 19 Aug 2026 22:51:20 GMT

A toolbox of fast, native and parallel implementations of various information-based importance criteria estimators and feature selection filters based on them, inspired by the overview by Brown, Pocock, Zhao and Lujan (2012) . Contains, among other, minimum redundancy maximal relevancy ('mRMR') method by Peng, Long and Ding (2005) ; joint mutual information ('JMI') method by Yang and Moody (1999) ; double input symmetrical relevance ('DISR') method by Meyer and Bontempi (2006) as well as joint mutual information maximisation ('JMIM') method by Bennasar, Hicks and Setchi (2015) .

[mbq] rethinker 2.0.0

m@mbq.me (Miron B. Kursa) — Thu, 23 Apr 2026 13:12:54 GMT

A full-featured 'RethinkDB' client for R; allows users to store JSON-serialised data in a robust, distributed no-SQL system, use rich queries and react to data changes in real-time.

[mbq] rFerns 6.0.0

m@mbq.me (Miron Bartosz Kursa) — Thu, 23 Apr 2026 09:31:58 GMT

Provides the random ferns classifier by Ozuysal, Calonder, Lepetit and Fua (2009) , modified for generic and multi-label classification and featuring OOB error approximation and importance measure as introduced in Kursa (2014) .

[mbq] vistla 2.1.2

m@mbq.me (Miron B. Kursa) — Thu, 13 Nov 2025 23:18:39 GMT

Traces information spread through interactions between features, utilising information theory measures and a higher-order generalisation of the concept of widest paths in graphs. In particular, 'vistla' can be used to better understand the results of high-throughput biomedical experiments, by organising the effects of the investigated intervention in a tree-like hierarchy from direct to indirect ones, following the plausible information relay circuits. Due to its higher-order nature, 'vistla' can handle multi-modality and assign multiple roles to a single feature.

[mbq] toporanga 1.0.0

m@mbq.me (Miron B. Kursa) — Sun, 13 Jul 2025 17:58:20 GMT

Deciphering hierarchy of agents exhibiting observable dominance events is a crucial problem in several disciplines, in particular in behavioural analysis of social animals, but also in social sciences and game theory. This package implements an inference approach based on graph theory, namely to extract the optimal acyclic subset of a weighted graph of dominance; this allows for hierarchy estimation through topological sorting. The package also contains infrastructure to investigate partially defined hierarchies and hierarchy dynamics.