Learn R Programming

costsensitive (version 0.1.2.10)

Cost-Sensitive Multi-Class Classification

Description

Reduction-based techniques for cost-sensitive multi-class classification, in which each observation has a different cost for classifying it into one class, and the goal is to predict the class with the minimum expected cost for each new observation. Implements Weighted All-Pairs (Beygelzimer, A., Langford, J., & Zadrozny, B., 2008, ), Weighted One-Vs-Rest (Beygelzimer, A., Dani, V., Hayes, T., Langford, J., & Zadrozny, B., 2005, ) and Regression One-Vs-Rest. Works with arbitrary classifiers taking observation weights, or with regressors. Also implements cost-proportionate rejection sampling for working with classifiers that don't accept observation weights.

Copy Link

Version

Install

install.packages('costsensitive')

Monthly Downloads

176

Version

0.1.2.10

License

BSD_2_clause + file LICENSE

Issues

Pull Requests

Stars

Forks

Maintainer

David Cortes

Last Published

July 28th, 2019

Functions in costsensitive (0.1.2.10)

print.costprop

Get information about Cost-Proportionate classifier object
weighted.one.vs.rest

Weighted One-Vs-Rest
weighted.all.pairs

Weighted All-Pairs
summary.costprop

Get information about Cost-Proportionate classifier object
summary.rovr

Get information about Regression One-Vs-Rest object
summary.wovr

Get information about Weighted One-Vs-Rest object
summary.wap

Get information about Weighted All-Pairs object
predict.wap

Predict method for Weighted All-Pairs
predict.rovr

Predict method for Regression One-Vs-Rest
predict.wovr

Predict method for Weighted One-Vs-Rest
cost.proportionate.classifier

Cost-Proportionate Classifier
predict.costprop

Predict method for Cost-Proportionate Classifier
print.wovr

Get information about Weighted One-Vs-Rest object
regression.one.vs.rest

Regression One-Vs-Rest
print.rovr

Get information about Regression One-Vs-Rest object
print.wap

Get information about Weighted All-Pairs object