, Ali Dag [ctb],
Serhat Simsek [ctb], Anton Ivanov [ctb], Asil Oztekin [ths]| Title: | Synthetic Data Generation for Imbalanced Learning in 'R' |
|---|---|
| Description: | Machine learning is widely used in information-systems design. Yet, training algorithms on imbalanced datasets may severely affect performance on unseen data. For example, in some cases in healthcare, financial, or internet-security contexts, certain sub-classes are difficult to learn because they are underrepresented in training data. This 'R' package offers a flexible and efficient solution based on a new synthetic average neighborhood sampling algorithm ('SANSA'), which, in contrast to other solutions, introduces a novel “placement” parameter that can be tuned to adapt to each datasets unique manifestation of the imbalance. More information about the algorithm's parameters can be found at Nasir et al. (2022) <https://murtaza.cc/SANSA/>. |
| Authors: | Murtaza Nasir [aut, cre]
, Ali Dag [ctb],
Serhat Simsek [ctb], Anton Ivanov [ctb], Asil Oztekin [ths] |
| Maintainer: | Murtaza Nasir <[email protected]> |
| License: | GPL (>= 3) |
| Version: | 0.0.1 |
| Built: | 2024-12-12 07:01:24 UTC |
| Source: | CRAN |
Title
sansa(x, y, lambda = 0, ksel = 3)sansa(x, y, lambda = 0, ksel = 3)
x |
Input predictor as a dataframe |
y |
Target variable as factor |
lambda |
Lambda parameter to select distribution of synthetic variables |
ksel |
K parameter to choose how many neighbors are used in calculations |
A list with two elements: x contains predictors with synthetic data, y contains target with synthetic data.
library(sansa) library(ggplot2) minority = data.frame(x1 = rnorm(10, 10, 3), x2 = rnorm(10, 25, 10), target = "true") majority = data.frame(x1 = rnorm(100, 4, 2), x2 = rnorm(100, 30, 10), target = "false") dataset = rbind(minority, majority) ggplot(dataset) + geom_point(aes(x1, x2, color = target)) sansaobject = sansa(x = dataset[,1:2], y = dataset$target, lambda = 1, ksel = 3) balanced <- sansaobject$x balanced$target = sansaobject$y ggplot(balanced) + geom_point(aes(x1, x2, color = target))library(sansa) library(ggplot2) minority = data.frame(x1 = rnorm(10, 10, 3), x2 = rnorm(10, 25, 10), target = "true") majority = data.frame(x1 = rnorm(100, 4, 2), x2 = rnorm(100, 30, 10), target = "false") dataset = rbind(minority, majority) ggplot(dataset) + geom_point(aes(x1, x2, color = target)) sansaobject = sansa(x = dataset[,1:2], y = dataset$target, lambda = 1, ksel = 3) balanced <- sansaobject$x balanced$target = sansaobject$y ggplot(balanced) + geom_point(aes(x1, x2, color = target))