PredictorParsnip

<p>This task specializes Predictor for <code>parsnip</code> models.
The <code>model</code> is assumed to be a <code>model_fit</code> object.</p>
<p>It is recommended to use <code>makePredictor()</code> for construction of Predictor objects.</p>

Create local, regional, and global explanations for any machine learning model with forward marginal effects. You provide a model and data, and 'fmeffects' computes feature effects. The package is based on the theory in: C. A. Scholbeck, G. Casalicchio, C. Molnar, B. Bischl, and C. Heumann (2022) <doi:10.48550/arXiv.2201.08837>.

Holger Löwe

fmeffects

Model-Agnostic Interpretations with Forward Marginal Effects

Christian Scholbeck

Christian Heumann

Bernd Bischl

Giuseppe Casalicchio

PredictorParsnip function

<p><code>fmeffects::Predictor</code> -&gt; <code>PredictorParsnip</code></p>

Super class


<div class="section" id="public-methods">
<h3>Public methods</h3><p></p><p><ul>
<li><p><a href="/link/PredictorParsnip%24new()?package=fmeffects&version=0.1.3" data-mini-rdoc="fmeffects::PredictorParsnip$new()"><code>PredictorParsnip$new()</code></a></p></li>
<li><p><a href="/link/PredictorParsnip%24predict()?package=fmeffects&version=0.1.3" data-mini-rdoc="fmeffects::PredictorParsnip$predict()"><code>PredictorParsnip$predict()</code></a></p></li>
<li><p><a href="/link/PredictorParsnip%24clone()?package=fmeffects&version=0.1.3" data-mini-rdoc="fmeffects::PredictorParsnip$clone()"><code>PredictorParsnip$clone()</code></a></p></li>
</ul></p><p></p></div><p><hr>
<a id="method-PredictorParsnip-new"></a></p><div class="section" id="method-new-">
<h3>Method <code>new()</code></h3>
<p>Create a new PredictorParsnip object.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>PredictorParsnip$new(model, data)</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="arguments">
<h4>Arguments</h4>
<p><div class="arguments"></div></p><dl>
<dt><code>model</code></dt>
<dd><p><code>model_fit</code> object.</p></dd></dl></div></p><p>
<dt><code>data</code></dt>
<dd><p>The data used for computing FMEs, must be data.frame or data.table.</p></dd></p><p>
</p><p></p>
<p></p><p></p><p><hr>
<a id="method-PredictorParsnip-predict"></a></p><div class="section" id="method-predict-">
<h3>Method <code><a href="/link/predict()?package=fmeffects&version=0.1.3" data-mini-rdoc="fmeffects::predict()">predict()</a></code></h3>
<p>Predicts on an observation <code>"newdata"</code>.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>PredictorParsnip$predict(newdata)</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="arguments">
<h4>Arguments</h4>
<p><div class="arguments"></div></p><dl>
<dt><code>newdata</code></dt>
<dd><p>The feature vector for which the target should be predicted.</p></dd></dl></div></p><p>
</p><p></p>
<p></p><p></p><p><hr>
<a id="method-PredictorParsnip-clone"></a></p><div class="section" id="method-clone-">
<h3>Method <code>clone()</code></h3>
<p>The objects of this class are cloneable with this method.</p><div class="section" id="usage">
<h4>Usage</h4>
<p><div class="r"></div></p><pre><code>PredictorParsnip$clone(deep = FALSE)</code></pre><p></p></div><p></p>
</div><p></p><p><div class="section" id="arguments">
<h4>Arguments</h4>
<p><div class="arguments"></div></p><dl>
<dt><code>deep</code></dt>
<dd><p>Whether to make a deep clone.</p></dd></dl></div></p><p>
</p><p></p>
<p></p><p>
</p>

Methods

PredictorParsnip — PredictorParsnip


<div class='section' id='public-methods'>
<h3>Public methods</h3>

<ul>
<li><p><a href='#method-PredictorParsnip-new'><code>PredictorParsnip$new()</code></a></p></li>
<li><p><a href='#method-PredictorParsnip-predict'><code>PredictorParsnip$predict()</code></a></p></li>
<li><p><a href='#method-PredictorParsnip-clone'><code>PredictorParsnip$clone()</code></a></p></li>
</ul>

</div><p><hr>
<a id="method-PredictorParsnip-new"></a></p><div class='section' id='method-new-'>
<h3>Method <code>new()</code></h3>
<p>Create a new PredictorParsnip object.</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>PredictorParsnip$new(model, data)</code></pre><p></div></p>
</div>

<div class='section' id='arguments'>
<h4>Arguments</h4>
<p><div class="arguments"></p><dl>
<dt><code>model</code></dt>
<dd><p><code>model_fit</code> object.</p></dd>


<dt><code>data</code></dt>
<dd><p>The data used for computing FMEs, must be data.frame or data.table.</p></dd>


</dl><p></div></p>
</div>

</div><p><hr>
<a id="method-PredictorParsnip-predict"></a></p><div class='section' id='method-predict-'>
<h3>Method <code><a href='https://rdrr.io/r/stats/predict.html'>predict()</a></code></h3>
<p>Predicts on an observation <code>"newdata"</code>.</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>PredictorParsnip$predict(newdata)</code></pre><p></div></p>
</div>

<div class='section' id='arguments'>
<h4>Arguments</h4>
<p><div class="arguments"></p><dl>
<dt><code>newdata</code></dt>
<dd><p>The feature vector for which the target should be predicted.</p></dd>


</dl><p></div></p>
</div>

</div><p><hr>
<a id="method-PredictorParsnip-clone"></a></p><div class='section' id='method-clone-'>
<h3>Method <code>clone()</code></h3>
<p>The objects of this class are cloneable with this method.</p><div class='section' id='usage'>
<h4>Usage</h4>
<p><div class="r"></p><pre><code>PredictorParsnip$clone(deep = FALSE)</code></pre><p></div></p>
</div>

<div class='section' id='arguments'>
<h4>Arguments</h4>
<p><div class="arguments"></p><dl>
<dt><code>deep</code></dt>
<dd><p>Whether to make a deep clone.</p></dd>


</dl><p></div></p>
</div>

</div>


PredictorParsnip: PredictorParsnip

Description

Arguments

Super class

Methods

Public methods

Method `new()`

Usage

Arguments

Method `predict()`

Usage

Arguments

Method `clone()`

Usage

Arguments

Description

Arguments

Super class

Methods

Public methods

Method new()

Usage

Arguments

Method predict()

Usage

Arguments

Method clone()

Usage

Arguments

Method `new()`

Method `predict()`

Method `clone()`