smoteNew: smoteNew is a necessary function that modifies the SMOTE...

In sambia: A Collection of Techniques Correcting for Sample Selection Bias

Description

smoteNewis a necessary function that modifies the SMOTE algorithm in the following ways: (1) correct bug in original smotefamily::SMOTE() function and (2) lets the user specifiy which class to be oversampled.

Usage

smoteNew(data.x, data.y, K, dup_size = 0, class.to.oversample)

Arguments

data.x	A data frame or matrix of numeric-attributed dataset
data.y	A vector of a target class attribute corresponding to a dataset X
K	The number of nearest neighbors during sampling process
dup_size	The number or vector representing the desired times of synthetic minority instances over the original number of majority instances
class.to.oversample	Class to be oversampled

Author(s)

Norbert Krautenbacher, Kevin Strauss, Maximilian Mandl, Christiane Fuchs

Examples

library(smotefamily)
library(sambia)
data.example = sample_generator(10000,ratio = 0.80)
genData = sambia:::smoteNew(data.example[,-3],data.example[,3],K = 5,class.to.oversample = 'p')

sambia documentation built on May 2, 2019, 9:15 a.m.