bord_noise

Computation of a noisy label based on majority class among k nearest neighbors with different label.

internal

Implementation of models for the controlled introduction of errors in
classification datasets. This package contains the noise models described in
Saez (2022) <doi:10.3390/math10203736> that allow corrupting class labels,
attributes and both simultaneously.

Jos<c3><a9> A. S<c3><a1>ez

noisemodel

Noise Models for Classification Datasets

José A. Sáez

bord_noise function

<dl><dt>x</dt>
<dd>a data frame of input attributes.</dd>
<dt>y</dt>
<dd>a factor vector with the output class of each sample.</dd>
<dt>num_noise</dt>
<dd>an integer with the number of noisy samples.</dd>
<dt>idx_noise</dt>
<dd>an integer vector with the indices of noisy samples.</dd>
<dt>k</dt>
<dd>an integer with the number of nearest neighbors to use.</dd></dl>

Arguments

Mislabeling based on k-nearest neighbors — bord_noise

<dl>

<dt>x</dt>
<dd>a data frame of input attributes.</dd>


<dt>y</dt>
<dd>a factor vector with the output class of each sample.</dd>


<dt>num_noise</dt>
<dd>an integer with the number of noisy samples.</dd>


<dt>idx_noise</dt>
<dd>an integer vector with the indices of noisy samples.</dd>


<dt>k</dt>
<dd>an integer with the number of nearest neighbors to use.</dd>

</dl>

bord_noise: Mislabeling based on k-nearest neighbors

Description

Usage

Value

Arguments