recommimb: Recommendation of Techniques for Imbalanced Datasets

In victorhb/recommimb: What the Package Does (One Line, Title Case)

Description

This is a recommender system of techniques for imbalanced datasets. It recommeds pre-processing and algorithmic-level techniques. The recommendation is based on a meta-learning approach using traditional meta-features and meta-features designed specifically for imbalanced datasets.

Usage

recommimb(...)

## Default S3 method:
recommimb(x, y, top.list = 7, ...)

## S3 method for class 'formula'
recommimb(formula, data, top.list = 7, ...)

Arguments

...	Further arguments passed to the summarization functions.
x	A data.frame contained only the input attributes.
y	A factor response vector with one label for each row/component of x.
top.list	Number of recommended techniques. Default is 7 due to experimental evaluations.
formula	A formula to define the class column.
data	A data.frame dataset contained the input attributes and class. The details section describes the valid values for this group.

Value

A list of recommendations to be tested by the user

Examples

## Recommend techniques using formula
data(arsenic_female_bladder)
recommimb(class ~ ., arsenic_female_bladder)

victorhb/recommimb documentation built on Dec. 23, 2021, 3:10 p.m.