TuneResult

Container for results of hyperparameter tuning.
Contains the obtained point in search space, its performance values
and the optimization path which lead there.
Object members:<dl class="dl-horizontal">
<dt>learner (<a rd-options="" href="/link/Learner?package=mlr&version=2.13" data-mini-rdoc="mlr::Learner">Learner</a>)</dt><dd>Learner that was optimized.</dd>
<dt>control (<a rd-options="" href="/link/TuneControl?package=mlr&version=2.13" data-mini-rdoc="mlr::TuneControl">TuneControl</a>)</dt><dd>Control object from tuning.</dd>
<dt>x (<a rd-options="" href="/link/list?package=mlr&version=2.13" data-mini-rdoc="mlr::list">list</a>)</dt><dd>Named list of hyperparameter values identified as optimal.
Note that when you have trafos on some of your params, <code>x</code> will always be
on the TRANSFORMED scale so you directly use it.</dd>
<dt>y (<a rd-options="" href="/link/numeric?package=mlr&version=2.13" data-mini-rdoc="mlr::numeric">numeric</a>)</dt><dd>Performance values for optimal <code>x</code>.</dd>
<dt>threshold (<a rd-options="" href="/link/numeric?package=mlr&version=2.13" data-mini-rdoc="mlr::numeric">numeric</a>)</dt><dd>Vector of finally found and used thresholds
if <code>tune.threshold</code> was enabled in <a rd-options="" href="/link/TuneControl?package=mlr&version=2.13" data-mini-rdoc="mlr::TuneControl">TuneControl</a>, otherwise not present and
hence <code>NULL</code>.</dd>
<dt>opt.path (<a rd-options="ParamHelpers:OptPath" href="/link/ParamHelpers%3A%3AOptPath?package=mlr&version=2.13&to=ParamHelpers%3AOptPath" data-mini-rdoc="ParamHelpers:OptPath::ParamHelpers::OptPath">ParamHelpers::OptPath</a>)</dt><dd>Optimization path which lead to <code>x</code>.
Note that when you have trafos on some of your params, the opt.path always contains the
UNTRANSFORMED values on the original scale. You can simply call <code>trafoOptPath(opt.path)</code> to
transform them, or, <code>as.data.frame{trafoOptPath(opt.path)}</code>.
If mlr option <code>on.error.dump</code> is <code>TRUE</code>, <code>OptPath</code> will have a <code>.dump</code> object
in its <code>extra</code> column which contains error dump traces from failed optimization evaluations.
It can be accessed by <code>getOptPathEl(opt.path)$extra$.dump</code>.</dd>
</dl>

Interface to a large number of classification and regression
techniques, including machine-readable parameter descriptions. There is
also an experimental extension for survival analysis, clustering and
general, example-specific cost-sensitive learning. Generic resampling,
including cross-validation, bootstrapping and subsampling. Hyperparameter
tuning with modern optimization techniques, for single- and multi-objective
problems. Filter and wrapper methods for feature selection. Extension of
basic learners with additional operations common in machine learning, also
allowing for easy nested resampling. Most operations can be parallelized.

Bernd Bischl

Machine Learning in R

Michel Lang

Lars Kotthoff

Julia Schiffner

Jakob Richter

Zachary Jones

Giuseppe Casalicchio

Mason Gallo

Patrick Schratz

Jakob Bossek

Erich Studerus

Leonard Judt

Tobias Kuehn

Pascal Kerschke

Florian Fendt

Philipp Probst

Xudong Sun

Janek Thomas

Bruno Vieira

Laura Beggel

Quay Au

Martin Binder

Florian Pfisterer

Stefan Coors

Steve Bronder

Alexander Engelhardt

Christoph Molnar

TuneResult function

Container for results of hyperparameter tuning.
Contains the obtained point in search space, its performance values
and the optimization path which lead there.
Object members:<dl class='dl-horizontal'>
<dt>learner (<a rd-options='' href='Learner'>Learner</a>)</dt><dd>Learner that was optimized.</dd>
<dt>control (<a rd-options='' href='TuneControl'>TuneControl</a>)</dt><dd>Control object from tuning.</dd>
<dt>x (<a rd-options='' href='list'>list</a>)</dt><dd>Named list of hyperparameter values identified as optimal.
Note that when you have trafos on some of your params, <code>x</code> will always be
on the TRANSFORMED scale so you directly use it.</dd>
<dt>y (<a rd-options='' href='numeric'>numeric</a>)</dt><dd>Performance values for optimal <code>x</code>.</dd>
<dt>threshold (<a rd-options='' href='numeric'>numeric</a>)</dt><dd>Vector of finally found and used thresholds
if <code>tune.threshold</code> was enabled in <a rd-options='' href='TuneControl'>TuneControl</a>, otherwise not present and
hence <code>NULL</code>.</dd>
<dt>opt.path (<a rd-options='ParamHelpers:OptPath' href='ParamHelpers::OptPath'>ParamHelpers::OptPath</a>)</dt><dd>Optimization path which lead to <code>x</code>.
Note that when you have trafos on some of your params, the opt.path always contains the
UNTRANSFORMED values on the original scale. You can simply call <code>trafoOptPath(opt.path)</code> to
transform them, or, <code>as.data.frame{trafoOptPath(opt.path)}</code>.
If mlr option <code>on.error.dump</code> is <code>TRUE</code>, <code>OptPath</code> will have a <code>.dump</code> object
in its <code>extra</code> column which contains error dump traces from failed optimization evaluations.
It can be accessed by <code>getOptPathEl(opt.path)$extra$.dump</code>.</dd>
</dl>

Result of tuning. — TuneResult

Result of tuning.

TuneResult: Result of tuning.

Description

Arguments