oversample_smote

Imbalanced training datasets impede many popular classifiers. To balance training data, a combination of oversampling minority classes and undersampling majority classes is useful. This package implements the SCUT (SMOTE and Cluster-based Undersampling Technique) algorithm as described in Agrawal et. al. (2015) <doi:10.5220/0005595502260234>. Their paper uses model-based clustering and synthetic oversampling to balance multiclass training datasets, although other resampling methods are provided in this package.

Keenan Ganz

scutr

Balancing Multiclass Datasets for Classification Tasks

oversample_smote function

<dl><dt>data</dt>
<dd>Dataset to be oversampled.</dd>
<dt>cls</dt>
<dd>Class to be oversampled.</dd>
<dt>cls_col</dt>
<dd>Column containing class information.</dd>
<dt>m</dt>
<dd>Desired number of samples in the oversampled data.</dd>
<dt>k</dt>
<dd>Number of neighbors used in <code>SMOTE()</code> to generate synthetic minority instances. This value must be smaller than the number of minority instances already present for a given class. If <code>NA</code>, <code>min(5, n-1)</code> is chosen, where n is the number of instances of the minority class.</dd></dl>

Arguments

Oversample a dataset by SMOTE. — oversample_smote

<dl>

<dt>data</dt>
<dd>Dataset to be oversampled.</dd>


<dt>cls</dt>
<dd>Class to be oversampled.</dd>


<dt>cls_col</dt>
<dd>Column containing class information.</dd>


<dt>m</dt>
<dd>Desired number of samples in the oversampled data.</dd>


<dt>k</dt>
<dd>Number of neighbors used in <code>SMOTE()</code> to generate synthetic minority instances. This value must be smaller than the number of minority instances already present for a given class. If <code>NA</code>, <code>min(5, n-1)</code> is chosen, where n is the number of instances of the minority class.</dd>

</dl>

oversample_smote: Oversample a dataset by SMOTE.

Description

Usage

Value

Arguments

Examples