filterFeatures

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

task

[<code>character(1)</code>]
See <code><a rd-options="" href="/link/listFilterMethods?package=mlr&version=2.10" data-mini-rdoc="mlr::listFilterMethods">listFilterMethods</a></code>.
Default is &#8220;randomForestSRC.rfsrc&#8221;.

method

[<code><a rd-options="" href="/link/FilterValues?package=mlr&version=2.10" data-mini-rdoc="mlr::FilterValues">FilterValues</a></code>]
Result of <code><a rd-options="" href="/link/generateFilterValuesData?package=mlr&version=2.10" data-mini-rdoc="mlr::generateFilterValuesData">generateFilterValuesData</a></code>.
If you pass this, the filter values in the object are used for feature filtering.
<code>method</code> and <code>...</code> are ignored then.
Default is <code>NULL</code> and not used.

fval

[<code>numeric(1)</code>]
If set, select <code>perc</code>*100 top scoring features.
Mutually exclusive with arguments <code>abs</code> and <code>threshold</code>.

perc

[<code>numeric(1)</code>]
If set, select <code>abs</code> top scoring features.
Mutually exclusive with arguments <code>perc</code> and <code>threshold</code>.

[<code>numeric(1)</code>]
If set, select features whose score exceeds <code>threshold</code>.
Mutually exclusive with arguments <code>perc</code> and <code>abs</code>.

threshold

[<code>character</code>]
Mandatory features which are always included regardless of their scores

mandatory.feat

[any]
Passed down to selected filter method.

First, calls <code><a rd-options="" href="/link/generateFilterValuesData?package=mlr&version=2.10" data-mini-rdoc="mlr::generateFilterValuesData">generateFilterValuesData</a></code>.
Features are then selected via <code>select</code> and <code>val</code>.

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

filterFeatures function

[<code><a rd-options='' href='Task'>Task</a></code>]
The task.

[<code>character(1)</code>]
See <code><a rd-options='' href='listFilterMethods'>listFilterMethods</a></code>.
Default is &#8220;randomForestSRC.rfsrc&#8221;.

[<code><a rd-options='' href='FilterValues'>FilterValues</a></code>]
Result of <code><a rd-options='' href='generateFilterValuesData'>generateFilterValuesData</a></code>.
If you pass this, the filter values in the object are used for feature filtering.
<code>method</code> and <code>...</code> are ignored then.
Default is <code>NULL</code> and not used.

First, calls <code><a rd-options='' href='generateFilterValuesData'>generateFilterValuesData</a></code>.
Features are then selected via <code>select</code> and <code>val</code>.

filterFeatures: Filter features by thresholding filter values.

Description

Usage

Arguments

Value

See Also