mahalanobis_distance_cpp

Used to get the Euclidean distance as well by setting <code>mcov</code> = <code>diag(m)</code>.

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 the method
described in Aas, Jullum and Løland (2019) <arXiv:1903.10464>, which accounts for any feature
dependence, and thereby produces more accurate estimates of the true Shapley values.

Martin Jullum

shapr

Prediction Explanation with Dependence-Aware Shapley Values

Nikolai Sellereite

Annabelle Redelmeier

Anders Løland

Jens Christian Wahl

Camilla Lingjærde

Norsk Regnesentral 

mahalanobis_distance_cpp function

<dl><dt>featureList</dt>
<dd>List of vectors indicating all factor combinations that should be included in the computations. Assumes that the first one is empty.</dd>
<dt>Xtrain_mat</dt>
<dd>Matrix</dd>
<dt>Xtest_mat</dt>
<dd>Matrix</dd>
<dt>mcov</dt>
<dd>Matrix. The Sigma-matrix in the Mahalanobis distance formula (<code>stats::cov(Xtrain_mat)</code>) gives Mahalanobis distance,
<code>diag(m)</code> gives the Euclidean distance.</dd>
<dt>S_scale_dist</dt>
<dd>Logical indicating</dd></dl>

Arguments

Author

(Generalized) Mahalanobis distance — mahalanobis_distance_cpp

<dl>

<dt>featureList</dt>
<dd>List of vectors indicating all factor combinations that should be included in the computations. Assumes that the first one is empty.</dd>


<dt>Xtrain_mat</dt>
<dd>Matrix</dd>


<dt>Xtest_mat</dt>
<dd>Matrix</dd>


<dt>mcov</dt>
<dd>Matrix. The Sigma-matrix in the Mahalanobis distance formula (<code>stats::cov(Xtrain_mat)</code>) gives Mahalanobis distance,
<code>diag(m)</code> gives the Euclidean distance.</dd>


<dt>S_scale_dist</dt>
<dd>Logical indicating</dd>

</dl>

(Generalized) Mahalanobis distance

mahalanobis_distance_cpp: (Generalized) Mahalanobis distance

Description

Usage

Value

Arguments

Author