Package: UBL 0.0.7

UBL: An Implementation of Re-Sampling Approaches to Utility-Based Learning for Both Classification and Regression Tasks

Provides a set of functions that can be used to obtain better predictive performance on cost-sensitive and cost/benefits tasks (for both regression and classification). This includes re-sampling approaches that modify the original data set biasing it towards the user preferences.

Authors:Paula Branco [aut, cre], Rita Ribeiro [aut, ctb], Luis Torgo [aut, ctb]

UBL_0.0.7.tar.gz
UBL_0.0.7.zip(r-4.5)UBL_0.0.7.zip(r-4.4)UBL_0.0.7.zip(r-4.3)
UBL_0.0.7.tgz(r-4.5-x86_64)UBL_0.0.7.tgz(r-4.5-arm64)UBL_0.0.7.tgz(r-4.4-x86_64)UBL_0.0.7.tgz(r-4.4-arm64)UBL_0.0.7.tgz(r-4.3-x86_64)UBL_0.0.7.tgz(r-4.3-arm64)
UBL_0.0.7.tar.gz(r-4.5-noble)UBL_0.0.7.tar.gz(r-4.4-noble)
UBL_0.0.7.tgz(r-4.4-emscripten)UBL_0.0.7.tgz(r-4.3-emscripten)
UBL.pdf |UBL.html✨
UBL/json (API)

# Install 'UBL' in R:
install.packages('UBL', repos = c('https://paobranco.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/paobranco/ubl/issues

Datasets:
  • ImbC - Synthetic Imbalanced Data Set for a Multi-class Task
  • ImbR - Synthetic Regression Data Set

On CRAN:

Conda-Forge:

fortran

6.39 score 33 stars 1 packages 165 scripts 577 downloads 3 mentions 32 exports 55 dependencies

Last updated 3 months agofrom:9ad43783ad. Checks:4 OK, 7 WARNING. Indexed: yes.

TargetResultLatest binary
Doc / VignettesOKFeb 08 2025
R-4.5-win-x86_64WARNINGFeb 08 2025
R-4.5-mac-x86_64WARNINGFeb 08 2025
R-4.5-mac-aarch64WARNINGFeb 08 2025
R-4.5-linux-x86_64WARNINGFeb 08 2025
R-4.4-win-x86_64WARNINGFeb 08 2025
R-4.4-mac-x86_64WARNINGFeb 08 2025
R-4.4-mac-aarch64WARNINGFeb 08 2025
R-4.3-win-x86_64OKFeb 08 2025
R-4.3-mac-x86_64OKFeb 08 2025
R-4.3-mac-aarch64OKFeb 08 2025

Exports:AdasynClassifBaggingRegressBagModelCNNClassifdistancesENNClassifEvalClassifMetricsEvalRegressMetricsGaussNoiseClassifGaussNoiseRegressNCLClassifneighboursOSSClassifphiphi.controlpredictRandOverClassifRandOverRegressRandUnderClassifRandUnderRegressReBaggRegressshowSMOGNClassifSMOGNRegressSmoteClassifSmoteRegressTomekClassifUtilInterpolUtilOptimClassifUtilOptimRegressWERCSClassifWERCSRegress

Dependencies:abindautomapBHclassclassIntclicolorspaceDBIe1071fansifarverFNNggplot2gluegstatgtableintervalsisobandKernSmoothlabelinglatticelifecyclemagrittrMASSMatrixMBAmgcvmunsellnlmepillarpkgconfigplyrproxyR6randomForestRColorBrewerRcppreshaperlangs2scalessfsftimespspacetimestarstibbleunitsutf8vctrsviridisLitewithrwkxtszoo

Readme and manuals

Help Manual

Help pageTopics
UBL: Utility-Based LearningUBL-package
ADASYN algorithm for unbalanced classification problems, both binary and multi-class.AdasynClassif
Standard Bagging ensemble for regression problems.BaggingRegress
Class "BagModel"BagModel BagModel-class show,BagModel-method
Condensed Nearest Neighbors strategy for multiclass imbalanced problemsCNNClassif
Distance matrix between all data set examples according to a selected distance metric.distances
Edited Nearest Neighbor for multiclass imbalanced problemsENNClassif
Utility metrics for assessing the performance of utility-based classification tasks.EvalClassifMetrics
Utility metrics for assessing the performance of utility-based regression tasks.EvalRegressMetrics
Introduction of Gaussian Noise for the generation of synthetic examples to handle imbalanced multiclass problems.GaussNoiseClassif
Introduction of Gaussian Noise for the generation of synthetic examples to handle imbalanced regression problemsGaussNoiseRegress
Synthetic Imbalanced Data Set for a Multi-class TaskImbC
Synthetic Regression Data SetImbR
Neighborhood Cleaning Rule (NCL) algorithm for multiclass imbalanced problemsNCLClassif
Computation of nearest neighbours using a selected distance function.neighbours
One-sided selection strategy for handling multiclass imbalanced problems.OSSClassif
Relevance function.phi
Estimation of parameters used for obtaining the relevance function.phi.control
Predicting on new data with a *BagModel* modelpredict,BagModel-method
Random over-sampling for imbalanced classification problemsRandOverClassif
Random over-sampling for imbalanced regression problemsRandOverRegress
Random under-sampling for imbalanced classification problemsRandUnderClassif
Random under-sampling for imbalanced regression problemsRandUnderRegress
REBaggRegress: RE(sampled) BAG(ging), an ensemble method for dealing with imbalanced regression problems.ReBaggRegress
SMOGN algorithm for imbalanced classification problemsSMOGNClassif
SMOGN algorithm for imbalanced regression problemsSMOGNRegress
SMOTE algorithm for unbalanced classification problemsSmoteClassif
SMOTE algorithm for imbalanced regression problemsSmoteRegress
Tomek links for imbalanced classification problemsTomekClassif
Utility surface obtained through methods for spatial interpolation of points.UtilInterpol
Optimization of predictions utility, cost or benefit for classification problems.UtilOptimClassif
Optimization of predictions utility, cost or benefit for regression problems.UtilOptimRegress
WEighted Relevance-based Combination Strategy (WERCS) algorithm for imbalanced classification problemsWERCSClassif
WEighted Relevance-based Combination Strategy (WERCS) algorithm for imbalanced regression problemsWERCSRegress