explain_dalex

Creates a DALEX explainer and computes permutation based variable importance,
partial dependence (model profiles) and Shapley values.

Provides a guarded resampling workflow for training and evaluating machine‑learning models.
When the guarded resampling path is used, preprocessing and model fitting are re‑estimated within
each resampling split to reduce leakage risk. Supports multiple resampling schemes, integrates
with established engines in the 'tidymodels' ecosystem, and aims to improve evaluation reliability by
coordinating preprocessing, fitting, and evaluation within supported workflows. Offers a lightweight
AutoML‑style workflow by automating model training, resampling, and tuning across multiple algorithms,
while keeping evaluation design explicit and user‑controlled.

Selcuk Korkmaz

fastml

Guarded Resampling Workflows for Safe and Automated Machine
Learning in R

Dincer Goksuluk

Eda Karaismailoglu

explain_dalex function

<dl><dt>object</dt>
<dd>A <code>fastml</code> object.</dd>
<dt>features</dt>
<dd>Character vector of feature names for partial dependence (model profiles). Default NULL.</dd>
<dt>grid_size</dt>
<dd>Number of grid points for partial dependence. Default 20.</dd>
<dt>shap_sample</dt>
<dd>Integer number of observations from processed training data to compute SHAP values for. Default 5.</dd>
<dt>vi_iterations</dt>
<dd>Integer. Number of permutations for variable importance (B). Default 10.</dd>
<dt>seed</dt>
<dd>Integer. A value specifying the random seed.</dd>
<dt>loss_function</dt>
<dd>Function. The loss function for <code>model_parts</code>.<ul>
<li>If <code>NULL</code> and task = 'classification', defaults to <code>DALEX::loss_cross_entropy</code>.</li>
<li>If <code>NULL</code> and task = 'regression', defaults to <code>DALEX::loss_root_mean_square</code>.</li>
</ul></dd></dl>

Arguments

Generate DALEX explanations for a fastml model — explain_dalex

<dl>

<dt>object</dt>
<dd>A <code>fastml</code> object.</dd>


<dt>features</dt>
<dd>Character vector of feature names for partial dependence (model profiles). Default NULL.</dd>


<dt>grid_size</dt>
<dd>Number of grid points for partial dependence. Default 20.</dd>


<dt>shap_sample</dt>
<dd>Integer number of observations from processed training data to compute SHAP values for. Default 5.</dd>


<dt>vi_iterations</dt>
<dd>Integer. Number of permutations for variable importance (B). Default 10.</dd>


<dt>seed</dt>
<dd>Integer. A value specifying the random seed.</dd>


<dt>loss_function</dt>
<dd>Function. The loss function for <code>model_parts</code>.<ul>
<li>If <code>NULL</code> and task = 'classification', defaults to <code>DALEX::loss_cross_entropy</code>.</li>
<li>If <code>NULL</code> and task = 'regression', defaults to <code>DALEX::loss_root_mean_square</code>.</li>
</ul></dd>

</dl>

explain_dalex: Generate DALEX explanations for a fastml model

Description

Usage

Value

Arguments