binary_params

internal

Implements multiple performance measures for
supervised learning.  Includes over 40 measures for regression and
classification. Additionally, meta information about the performance
measures can be queried, e.g. what the best and worst possible
performances scores are.

Michel Lang

mlr3measures

Performance Measures for 'mlr3'

Martin Binder

binary_params function

<dl><dt>truth</dt>
<dd>(<code><a href="/link/factor()?package=mlr3measures&version=0.5.0" data-mini-rdoc="mlr3measures::factor()">factor()</a></code>) 
True (observed) labels.
Must have the exactly same two levels and the same length as <code>response</code>.</dd>
<dt>response</dt>
<dd>(<code><a href="/link/factor()?package=mlr3measures&version=0.5.0" data-mini-rdoc="mlr3measures::factor()">factor()</a></code>) 
Predicted response labels.
Must have the exactly same two levels and the same length as <code>truth</code>.</dd>
<dt>prob</dt>
<dd>(<code><a href="/link/numeric()?package=mlr3measures&version=0.5.0" data-mini-rdoc="mlr3measures::numeric()">numeric()</a></code>) 
Predicted probability for positive class.
Must have exactly same length as <code>truth</code>.</dd>
<dt>positive</dt>
<dd>(<code>character(1))</code> 
Name of the positive class.</dd>
<dt>sample_weights</dt>
<dd>(<code><a href="/link/numeric()?package=mlr3measures&version=0.5.0" data-mini-rdoc="mlr3measures::numeric()">numeric()</a></code>) 
Vector of non-negative and finite sample weights.
Must have the same length as <code>truth</code>.
The vector gets automatically normalized to sum to one.
Defaults to equal sample weights.</dd>
<dt>na_value</dt>
<dd>(<code>numeric(1)</code>) 
Value that should be returned if the measure is not defined for the input
(as described in the note). Default is <code>NaN</code>.</dd>
<dt>...</dt>
<dd>(<code>any</code>) 
Additional arguments. Currently ignored.</dd></dl>

Arguments

Binary Classification Parameters — binary_params

<dl>

<dt>truth</dt>
<dd>(<code><a href='https://rdrr.io/r/base/factor.html'>factor()</a></code>) 
True (observed) labels.
Must have the exactly same two levels and the same length as <code>response</code>.</dd>


<dt>response</dt>
<dd>(<code><a href='https://rdrr.io/r/base/factor.html'>factor()</a></code>) 
Predicted response labels.
Must have the exactly same two levels and the same length as <code>truth</code>.</dd>


<dt>prob</dt>
<dd>(<code><a href='https://rdrr.io/r/base/numeric.html'>numeric()</a></code>) 
Predicted probability for positive class.
Must have exactly same length as <code>truth</code>.</dd>


<dt>positive</dt>
<dd>(<code>character(1))</code> 
Name of the positive class.</dd>


<dt>sample_weights</dt>
<dd>(<code><a href='https://rdrr.io/r/base/numeric.html'>numeric()</a></code>) 
Vector of non-negative and finite sample weights.
Must have the same length as <code>truth</code>.
The vector gets automatically normalized to sum to one.
Defaults to equal sample weights.</dd>


<dt>na_value</dt>
<dd>(<code>numeric(1)</code>) 
Value that should be returned if the measure is not defined for the input
(as described in the note). Default is <code>NaN</code>.</dd>


<dt>...</dt>
<dd>(<code>any</code>) 
Additional arguments. Currently ignored.</dd>

</dl>

binary_params: Binary Classification Parameters

Description

Arguments