orsf_control_custom

Fit, interpret, and compute predictions with oblique random
forests. Includes support for partial dependence, variable importance,
passing customized functions for variable importance and identification
of linear combinations of features. Methods for the oblique random
survival forest are described in Jaeger et al., (2023)
<DOI:10.1080/10618600.2023.2231048>.

Byron Jaeger

aorsf

Accelerated Oblique Random Forests

Nicholas Pajewski

Sawyer Welden

Christopher Jackson

Marvin Wright

Lukas Burk

orsf_control_custom function

<dl><dt>beta_fun</dt>
<dd>(function) a function to define coefficients used
in linear combinations of predictor variables. <code>beta_fun</code> must accept
three inputs named <code>x_node</code>, <code>y_node</code> and <code>w_node</code>, and should expect
the following types and dimensions:<ul>
<li><code>x_node</code> (matrix; <code>n</code> rows, <code>p</code> columns)</li>
<li><code>y_node</code> (matrix; <code>n</code> rows, <code>2</code> columns)</li>
<li><code>w_node</code> (matrix; <code>n</code> rows, <code>1</code> column)</li>
</ul></dd>In addition, <code>beta_fun</code> must return a matrix with p rows and 1 column. If
any of these conditions are not met, <code>orsf_control_custom()</code> will let
you know.
<dt>...</dt>
<dd>Further arguments passed to or from other methods (not currently used).</dd></dl>

Arguments

Custom ORSF control — orsf_control_custom

<dl>

<dt>beta_fun</dt>
<dd>(function) a function to define coefficients used
in linear combinations of predictor variables. <code>beta_fun</code> must accept
three inputs named <code>x_node</code>, <code>y_node</code> and <code>w_node</code>, and should expect
the following types and dimensions:<ul>
<li><code>x_node</code> (matrix; <code>n</code> rows, <code>p</code> columns)</li>
<li><code>y_node</code> (matrix; <code>n</code> rows, <code>2</code> columns)</li>
<li><code>w_node</code> (matrix; <code>n</code> rows, <code>1</code> column)</li>
</ul>

In addition, <code>beta_fun</code> must return a matrix with p rows and 1 column. If
any of these conditions are not met, <code>orsf_control_custom()</code> will let
you know.</dd>


<dt>...</dt>
<dd>Further arguments passed to or from other methods (not currently used).</dd>

</dl>

orsf_control_custom: Custom ORSF control

Description

Usage

Value

Arguments

See Also