shapley_weights

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 

shapley_weights function

<dl><dt>m</dt>
<dd>Positive integer.
Total number of features/groups.</dd>
<dt>N</dt>
<dd>Positive integer. The number of unique coalitions when sampling <code>n_components</code> features/feature
groups, without replacement, from a sample space consisting of <code>m</code> different features/feature groups.</dd>
<dt>n_components</dt>
<dd>Positive integer. Represents the number of features/feature groups you want to sample from
a feature space consisting of <code>m</code> unique features/feature groups. Note that <code> 0 &lt; = n_components &lt;= m</code>.</dd>
<dt>weight_zero_m</dt>
<dd>Numeric.
The value to use as a replacement for infinite coalition weights when doing numerical operations.</dd></dl>

Arguments

Author

Calculate Shapley weight — shapley_weights

<dl>

<dt>m</dt>
<dd>Positive integer.
Total number of features/groups.</dd>


<dt>N</dt>
<dd>Positive integer. The number of unique coalitions when sampling <code>n_components</code> features/feature
groups, without replacement, from a sample space consisting of <code>m</code> different features/feature groups.</dd>


<dt>n_components</dt>
<dd>Positive integer. Represents the number of features/feature groups you want to sample from
a feature space consisting of <code>m</code> unique features/feature groups. Note that <code> 0 &lt; = n_components &lt;= m</code>.</dd>


<dt>weight_zero_m</dt>
<dd>Numeric.
The value to use as a replacement for infinite coalition weights when doing numerical operations.</dd>

</dl>

Calculate Shapley weight

shapley_weights: Calculate Shapley weight

Description

Usage

Value

Arguments

Author