vaeac_check_mask_gen

Function that checks the specified masking scheme

internal

Complex machine learning models are often hard to interpret. However, in
many situations it is crucial to understand and explain why a model made a specific
prediction. Shapley values is the only method for such prediction explanation framework
with a solid theoretical foundation. Previously known methods for estimating the Shapley
values do, however, assume feature independence. This package implements methods which accounts for any feature
dependence, and thereby produces more accurate estimates of the true Shapley values.
An accompanying 'Python' wrapper ('shaprpy') is available through the GitHub repository.

Martin Jullum

shapr

Prediction Explanation with Dependence-Aware Shapley Values

Lars Henry Berge Olsen

Annabelle Redelmeier

Jon Lachmann

Nikolai Sellereite

Anders Løland

Jens Christian Wahl

Camilla Lingjærde

Norsk Regnesentral 

vaeac_check_mask_gen function

<dl><dt>mask_gen_coalitions</dt>
<dd>Matrix (default is <code>NULL</code>). Matrix containing the coalitions that the
<code>vaeac</code> model will be trained on, see <code>specified_masks_mask_generator()</code>. This parameter is used internally
in <code>shapr</code> when we only consider a subset of coalitions, i.e., when
<code>n_coalitions</code> \(&lt; 2^{n_{\text{features}}}\), and for group Shapley, i.e.,
when <code>group</code> is specified in <code>explain()</code>.</dd>
<dt>mask_gen_coalitions_prob</dt>
<dd>Numeric array (default is <code>NULL</code>). Array of length equal to the height
of <code>mask_gen_coalitions</code> containing the probabilities of sampling the corresponding coalitions in
<code>mask_gen_coalitions</code>.</dd>
<dt>x_train</dt>
<dd>A data.table containing the training data. Categorical data must have class names \(1,2,\dots,K\).</dd></dl>

Arguments

Author

Function that checks the specified masking scheme — vaeac_check_mask_gen

<dl>

<dt>mask_gen_coalitions</dt>
<dd>Matrix (default is <code>NULL</code>). Matrix containing the coalitions that the
<code>vaeac</code> model will be trained on, see <code>specified_masks_mask_generator()</code>. This parameter is used internally
in <code>shapr</code> when we only consider a subset of coalitions, i.e., when
<code>n_coalitions</code> \(&lt; 2^{n_{\text{features}}}\), and for group Shapley, i.e.,
when <code>group</code> is specified in <code>explain()</code>.</dd>


<dt>mask_gen_coalitions_prob</dt>
<dd>Numeric array (default is <code>NULL</code>). Array of length equal to the height
of <code>mask_gen_coalitions</code> containing the probabilities of sampling the corresponding coalitions in
<code>mask_gen_coalitions</code>.</dd>


<dt>x_train</dt>
<dd>A data.table containing the training data. Categorical data must have class names \(1,2,\dots,K\).</dd>

</dl>

Function that checks the specified masking scheme

vaeac_check_mask_gen: Function that checks the specified masking scheme

Description

Usage

Value

Arguments

Author