https://github.com/awojna/Rseslib
Tip revision: cc3dc25724b6c4f0947f9111ff2e68a6fc054791 authored by awojna on 19 April 2025, 18:15:06 UTC
AttrDescriptorSet extracted from AQ15OneRuleGenerator
AttrDescriptorSet extracted from AQ15OneRuleGenerator
Tip revision: cc3dc25
Description.props
# Description file of Rseslib package for Weka
#
#
# Package name (required)
PackageName=Rseslib
# Version (required)
Version=3.6.0-SNAPSHOT
#Date
Date=2025-04-14
# Title (required)
Title=Rough Sets, Rule Induction, Neural Net and Analogy-Based Reasoning
Category=Classification
# Author (required)
Author=Arkadiusz Wojna,Grzegorz Gora,Wiktor Gromniak,Marcin Jalmuzna,Michal Kurzydlowski,Rafal Latkowski,Marcin Piliszczuk,Jakub Sakowicz,Cezary Tkaczyk,Beata Zielosko
# Maintainer (required)
Maintainer=Arkadiusz Wojna <wojna@mimuw.edu.pl>
# License (required)
License=GPL 3.0
# Description (required)
Description=The package provides 6 classifiers: RseslibKNN, LocalKNN, RseslibNN, AQ15, RoughSet and RIONIDA. \
The k nearest neighbors classifier RseslibKNN provides variety of distance measures that can work also for data with both numeric and nominal attributes and has built-in k optimization. \
It implements a fast neighbors searching algorithm making the classifier work for very large data sets. The classifier has also the mode to work as RIONA algorithm. \
The LocalKNN classifier is the extension of the k nearest neighbors method that induces a local metric for each classified object. \
It is dedicated rather to large data sets (2000+ training instances) and improves accuracy particularly in case of data containing nominal attributes. \
RseslibNN is a neural network selecting the network structure according to data and using the classical back-propagation algorithm with sigmoid activation function for all neurons. \
The AQ15 classifier uses the set of rules generated by the AQ15 covering algorithm. \
The rule classifier RoughSet uses the concepts of discernibility matrix, reducts and rules generated from reducts. \
It provides variety of algorithms generating reducts including giving more general rules local reducts and has modes to work with incomplete data and inconsistent data. \
The RIONIDA classifier dedicated to imbalanced data with two decision classes combines instance-based learning with rule induction. It enables to differentiate the importance of the decisions \
and to control the impact of rules on the decision selection process and applies multi-dimensional optimization of classification measures relevant for imbalanced data.
# Package URL for obtaining the package archive (required)
PackageURL=https://github.com/awojna/Rseslib/releases/download/v3.5.0/rseslib-3.5.0-weka.zip
# URL for further information
URL=http://rseslib.mimuw.edu.pl
# Dependencies
Depends=weka (>=3.8.0)