SamplerHierarchical

Hierarchical sampling for arbitrary param sets with dependencies, where the user specifies 1D samplers per param.
Dependencies are topologically sorted, parameters are then sampled in topological order,
and if dependencies do not hold, values are set to <code>NA</code> in the resulting <code>data.table</code>.

datasets

Define parameter spaces, constraints and
dependencies for arbitrary algorithms, to program on such spaces. Also
includes statistical designs and random samplers. Objects are implemented
as 'R6' classes.

Michel Lang

paradox

Define and Work with Parameter Spaces for Complex Algorithms

Bernd Bischl

Jakob Richter

Xudong Sun

Martin Binder

SamplerHierarchical function

<a rd-options="R6:R6Class" href="/link/R6%3A%3AR6Class?package=paradox&version=0.1.0&to=R6%3AR6Class" data-mini-rdoc="R6:R6Class::R6::R6Class">R6::R6Class</a> inheriting from <a rd-options="" href="/link/Sampler?package=paradox&version=0.1.0" data-mini-rdoc="paradox::Sampler">Sampler</a>.

Format

<pre>smpl = SamplerHierarchical$new(param_set, samplers)
</pre>
<ul>
<li><code>param_set</code> :: <a rd-options="" href="/link/ParamSet?package=paradox&version=0.1.0" data-mini-rdoc="paradox::ParamSet">ParamSet</a>
Domain / support of the distribution we want to sample from.</li>
<li><code>samplers</code> :: <code>list()</code>
List of <a rd-options="" href="/link/Sampler1D?package=paradox&version=0.1.0" data-mini-rdoc="paradox::Sampler1D">Sampler1D</a> objects that gives a Sampler for each <a rd-options="" href="/link/Param?package=paradox&version=0.1.0" data-mini-rdoc="paradox::Param">Param</a> in the <code>param_set</code>.</li>
</ul>

Construction

See <a rd-options="" href="/link/Sampler?package=paradox&version=0.1.0" data-mini-rdoc="paradox::Sampler">Sampler</a>.
Additionally, the class provides:<ul>
<li><code>samplers</code> :: <code>list()</code>
List of <a rd-options="" href="/link/Sampler1D?package=paradox&version=0.1.0" data-mini-rdoc="paradox::Sampler1D">Sampler1D</a> objects that gives a Sampler for each <a rd-options="" href="/link/Param?package=paradox&version=0.1.0" data-mini-rdoc="paradox::Param">Param</a> in the <code>param_set</code>.</li>
</ul>

Fields

See <a rd-options="" href="/link/Sampler?package=paradox&version=0.1.0" data-mini-rdoc="paradox::Sampler">Sampler</a>.

Methods

SamplerHierarchical Class — SamplerHierarchical

<a rd-options='R6:R6Class' href='R6::R6Class'>R6::R6Class</a> inheriting from <a rd-options='' href='Sampler'>Sampler</a>.

<pre>smpl = SamplerHierarchical$new(param_set, samplers)
</pre>
<ul>
<li><code>param_set</code> :: <a rd-options='' href='ParamSet'>ParamSet</a>
Domain / support of the distribution we want to sample from.</li>
<li><code>samplers</code> :: <code>list()</code>
List of <a rd-options='' href='Sampler1D'>Sampler1D</a> objects that gives a Sampler for each <a rd-options='' href='Param'>Param</a> in the <code>param_set</code>.</li>
</ul>

SamplerHierarchical: SamplerHierarchical Class

Description

Arguments

Format

Construction

Fields

Methods

See Also