Banana data

A two-dimensional, two-class imbalanced data set with an imbalance ratio of 1:9. The classes cannot be separated linearly but can be separated non-linearly, and both are multimodal. The data set contains class overlap and noise as well, so it shows many of the difficulties of imbalanced classification in a plot. It is used in the examples and the vignette of the package.

Usage

banana

Format

A data frame with 2640 rows and 3 variables:

At1

first feature.

At2

second feature.

Class

factor with levels "negative" (2376 samples) and "positive" (264 samples). The imbalance ratio is 9.

Source

The banana data set of the KEEL data set repository, https://sci2s.ugr.es/keel/datasets.php.

References

Alcalá-Fdez, J., Fernández, A., Luengo, J., Derrac, J., García, S., Sánchez, L., & Herrera, F. (2011). KEEL data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. Journal of Multiple-Valued Logic and Soft Computing, 17(2-3), 255-287.

Examples

table(banana$Class)
#> 
#> negative positive 
#>     2376      264 
plot(banana$At1, banana$At2, col = ifelse(banana$Class == "positive", "red", "grey60"),
     pch = 16, xlab = "At1", ylab = "At2")