tuneThreshold

[<code><a rd-options="" href="/link/Prediction?package=mlr&version=2.10" data-mini-rdoc="mlr::Prediction">Prediction</a></code>]
Prediction object.

pred

[<code><a rd-options="" href="/link/Measure?package=mlr&version=2.10" data-mini-rdoc="mlr::Measure">Measure</a></code>]
Performance measure to optimize.
Default is the default measure for the task.

measure

[<code><a rd-options="" href="/link/Task?package=mlr&version=2.10" data-mini-rdoc="mlr::Task">Task</a></code>]
Learning task. Rarely neeeded,
only when required for the performance measure.

task

[<code><a rd-options="" href="/link/WrappedModel?package=mlr&version=2.10" data-mini-rdoc="mlr::WrappedModel">WrappedModel</a></code>]
Fitted model. Rarely neeeded,
only when required for the performance measure.

model

[<code>integer(1)</code>]
Passed to <code><a rd-options="BBmisc" href="/link/optimizeSubInts?package=mlr&version=2.10&to=BBmisc" data-mini-rdoc="BBmisc::optimizeSubInts">optimizeSubInts</a></code> for 2class problems.
Default is 20.

nsub

[<code>list</code>]
Control object for <code><a rd-options="cmaes" href="/link/cma_es?package=mlr&version=2.10&to=cmaes" data-mini-rdoc="cmaes::cma_es">cma_es</a></code> when used.
Default is empty list.

control

Optimizes the threshold of predictions based on probabilities.
Works for classification and multilabel tasks.
Uses <code><a rd-options="BBmisc" href="/link/optimizeSubInts?package=mlr&version=2.10&to=BBmisc" data-mini-rdoc="BBmisc::optimizeSubInts">optimizeSubInts</a></code> for normal binary class problems and <code><a rd-options="cmaes" href="/link/cma_es?package=mlr&version=2.10&to=cmaes" data-mini-rdoc="cmaes::cma_es">cma_es</a></code>
for multiclass and multilabel problems.

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

tuneThreshold function

[<code><a rd-options='' href='Prediction'>Prediction</a></code>]
Prediction object.

[<code><a rd-options='' href='Measure'>Measure</a></code>]
Performance measure to optimize.
Default is the default measure for the task.

[<code><a rd-options='' href='Task'>Task</a></code>]
Learning task. Rarely neeeded,
only when required for the performance measure.

[<code><a rd-options='' href='WrappedModel'>WrappedModel</a></code>]
Fitted model. Rarely neeeded,
only when required for the performance measure.

[<code>integer(1)</code>]
Passed to <code><a rd-options='BBmisc' href='optimizeSubInts'>optimizeSubInts</a></code> for 2class problems.
Default is 20.

[<code>list</code>]
Control object for <code><a rd-options='cmaes' href='cma_es'>cma_es</a></code> when used.
Default is empty list.

Optimizes the threshold of predictions based on probabilities.
Works for classification and multilabel tasks.
Uses <code><a rd-options='BBmisc' href='optimizeSubInts'>optimizeSubInts</a></code> for normal binary class problems and <code><a rd-options='cmaes' href='cma_es'>cma_es</a></code>
for multiclass and multilabel problems.

tuneThreshold: Tune prediction threshold.

Description

Usage

Arguments

Value

See Also